interfaces: create a new folder for interfaces and move repository.py in it

I was trying to understand current interfaces and write new ones and I realized
we need to improve how current interfaces are organised. This creates a
dedicated folder for defining interfaces and move `repository.py` which defines
all the current interfaces inside it.

Differential Revision: https://phab.mercurial-scm.org/D6741

contrib/import-checker.py

@@ -1,748 +1,749
 #!/usr/bin/env python
 
 from __future__ import absolute_import, print_function
 
 import ast
 import collections
 import os
 import sys
 
 # Import a minimal set of stdlib modules needed for list_stdlib_modules()
 # to work when run from a virtualenv.  The modules were chosen empirically
 # so that the return value matches the return value without virtualenv.
 if True: # disable lexical sorting checks
     try:
         import BaseHTTPServer as basehttpserver
     except ImportError:
         basehttpserver = None
     import zlib
 
 import testparseutil
 
 # Whitelist of modules that symbols can be directly imported from.
 allowsymbolimports = (
     '__future__',
     'bzrlib',
     'hgclient',
     'mercurial',
     'mercurial.hgweb.common',
     'mercurial.hgweb.request',
     'mercurial.i18n',
+    'mercurial.interfaces',
     'mercurial.node',
     # for revlog to re-export constant to extensions
     'mercurial.revlogutils.constants',
     'mercurial.revlogutils.flagutil',
     # for cffi modules to re-export pure functions
     'mercurial.pure.base85',
     'mercurial.pure.bdiff',
     'mercurial.pure.mpatch',
     'mercurial.pure.osutil',
     'mercurial.pure.parsers',
     # third-party imports should be directly imported
     'mercurial.thirdparty',
     'mercurial.thirdparty.attr',
     'mercurial.thirdparty.zope',
     'mercurial.thirdparty.zope.interface',
 )
 
 # Whitelist of symbols that can be directly imported.
 directsymbols = (
     'demandimport',
 )
 
 # Modules that must be aliased because they are commonly confused with
 # common variables and can create aliasing and readability issues.
 requirealias = {
     'ui': 'uimod',
 }
 
 def usingabsolute(root):
     """Whether absolute imports are being used."""
     if sys.version_info[0] >= 3:
         return True
 
     for node in ast.walk(root):
         if isinstance(node, ast.ImportFrom):
             if node.module == '__future__':
                 for n in node.names:
                     if n.name == 'absolute_import':
                         return True
 
     return False
 
 def walklocal(root):
     """Recursively yield all descendant nodes but not in a different scope"""
     todo = collections.deque(ast.iter_child_nodes(root))
     yield root, False
     while todo:
         node = todo.popleft()
         newscope = isinstance(node, ast.FunctionDef)
         if not newscope:
             todo.extend(ast.iter_child_nodes(node))
         yield node, newscope
 
 def dotted_name_of_path(path):
     """Given a relative path to a source file, return its dotted module name.
 
     >>> dotted_name_of_path('mercurial/error.py')
     'mercurial.error'
     >>> dotted_name_of_path('zlibmodule.so')
     'zlib'
     """
     parts = path.replace(os.sep, '/').split('/')
     parts[-1] = parts[-1].split('.', 1)[0] # remove .py and .so and .ARCH.so
     if parts[-1].endswith('module'):
         parts[-1] = parts[-1][:-6]
     return '.'.join(parts)
 
 def fromlocalfunc(modulename, localmods):
     """Get a function to examine which locally defined module the
     target source imports via a specified name.
 
     `modulename` is an `dotted_name_of_path()`-ed source file path,
     which may have `.__init__` at the end of it, of the target source.
 
     `localmods` is a set of absolute `dotted_name_of_path()`-ed source file
     paths of locally defined (= Mercurial specific) modules.
 
     This function assumes that module names not existing in
     `localmods` are from the Python standard library.
 
     This function returns the function, which takes `name` argument,
     and returns `(absname, dottedpath, hassubmod)` tuple if `name`
     matches against locally defined module. Otherwise, it returns
     False.
 
     It is assumed that `name` doesn't have `.__init__`.
 
     `absname` is an absolute module name of specified `name`
     (e.g. "hgext.convert"). This can be used to compose prefix for sub
     modules or so.
 
     `dottedpath` is a `dotted_name_of_path()`-ed source file path
     (e.g. "hgext.convert.__init__") of `name`. This is used to look
     module up in `localmods` again.
 
     `hassubmod` is whether it may have sub modules under it (for
     convenient, even though this is also equivalent to "absname !=
     dottednpath")
 
     >>> localmods = {'foo.__init__', 'foo.foo1',
     ...              'foo.bar.__init__', 'foo.bar.bar1',
     ...              'baz.__init__', 'baz.baz1'}
     >>> fromlocal = fromlocalfunc('foo.xxx', localmods)
     >>> # relative
     >>> fromlocal('foo1')
     ('foo.foo1', 'foo.foo1', False)
     >>> fromlocal('bar')
     ('foo.bar', 'foo.bar.__init__', True)
     >>> fromlocal('bar.bar1')
     ('foo.bar.bar1', 'foo.bar.bar1', False)
     >>> # absolute
     >>> fromlocal('baz')
     ('baz', 'baz.__init__', True)
     >>> fromlocal('baz.baz1')
     ('baz.baz1', 'baz.baz1', False)
     >>> # unknown = maybe standard library
     >>> fromlocal('os')
     False
     >>> fromlocal(None, 1)
     ('foo', 'foo.__init__', True)
     >>> fromlocal('foo1', 1)
     ('foo.foo1', 'foo.foo1', False)
     >>> fromlocal2 = fromlocalfunc('foo.xxx.yyy', localmods)
     >>> fromlocal2(None, 2)
     ('foo', 'foo.__init__', True)
     >>> fromlocal2('bar2', 1)
     False
     >>> fromlocal2('bar', 2)
     ('foo.bar', 'foo.bar.__init__', True)
     """
     if not isinstance(modulename, str):
         modulename = modulename.decode('ascii')
     prefix = '.'.join(modulename.split('.')[:-1])
     if prefix:
         prefix += '.'
     def fromlocal(name, level=0):
         # name is false value when relative imports are used.
         if not name:
             # If relative imports are used, level must not be absolute.
             assert level > 0
             candidates = ['.'.join(modulename.split('.')[:-level])]
         else:
             if not level:
                 # Check relative name first.
                 candidates = [prefix + name, name]
             else:
                 candidates = ['.'.join(modulename.split('.')[:-level]) +
                               '.' + name]
 
         for n in candidates:
             if n in localmods:
                 return (n, n, False)
             dottedpath = n + '.__init__'
             if dottedpath in localmods:
                 return (n, dottedpath, True)
         return False
     return fromlocal
 
 def populateextmods(localmods):
     """Populate C extension modules based on pure modules"""
     newlocalmods = set(localmods)
     for n in localmods:
         if n.startswith('mercurial.pure.'):
             m = n[len('mercurial.pure.'):]
             newlocalmods.add('mercurial.cext.' + m)
             newlocalmods.add('mercurial.cffi._' + m)
     return newlocalmods
 
 def list_stdlib_modules():
     """List the modules present in the stdlib.
 
     >>> py3 = sys.version_info[0] >= 3
     >>> mods = set(list_stdlib_modules())
     >>> 'BaseHTTPServer' in mods or py3
     True
 
     os.path isn't really a module, so it's missing:
 
     >>> 'os.path' in mods
     False
 
     sys requires special treatment, because it's baked into the
     interpreter, but it should still appear:
 
     >>> 'sys' in mods
     True
 
     >>> 'collections' in mods
     True
 
     >>> 'cStringIO' in mods or py3
     True
 
     >>> 'cffi' in mods
     True
     """
     for m in sys.builtin_module_names:
         yield m
     # These modules only exist on windows, but we should always
     # consider them stdlib.
     for m in ['msvcrt', '_winreg']:
         yield m
     yield '__builtin__'
     yield 'builtins' # python3 only
     yield 'importlib.abc' # python3 only
     yield 'importlib.machinery' # python3 only
     yield 'importlib.util' # python3 only
     for m in 'fcntl', 'grp', 'pwd', 'termios':  # Unix only
         yield m
     for m in 'cPickle', 'datetime': # in Python (not C) on PyPy
         yield m
     for m in ['cffi']:
         yield m
     stdlib_prefixes = {sys.prefix, sys.exec_prefix}
     # We need to supplement the list of prefixes for the search to work
     # when run from within a virtualenv.
     for mod in (basehttpserver, zlib):
         if mod is None:
             continue
         try:
             # Not all module objects have a __file__ attribute.
             filename = mod.__file__
         except AttributeError:
             continue
         dirname = os.path.dirname(filename)
         for prefix in stdlib_prefixes:
             if dirname.startswith(prefix):
                 # Then this directory is redundant.
                 break
         else:
             stdlib_prefixes.add(dirname)
     sourceroot = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
     for libpath in sys.path:
         # We want to walk everything in sys.path that starts with something in
         # stdlib_prefixes, but not directories from the hg sources.
         if (os.path.abspath(libpath).startswith(sourceroot)
             or not any(libpath.startswith(p) for p in stdlib_prefixes)):
             continue
         for top, dirs, files in os.walk(libpath):
             for i, d in reversed(list(enumerate(dirs))):
                 if (not os.path.exists(os.path.join(top, d, '__init__.py'))
                     or top == libpath and d in ('hgdemandimport', 'hgext',
                                                 'mercurial')):
                     del dirs[i]
             for name in files:
                 if not name.endswith(('.py', '.so', '.pyc', '.pyo', '.pyd')):
                     continue
                 if name.startswith('__init__.py'):
                     full_path = top
                 else:
                     full_path = os.path.join(top, name)
                 rel_path = full_path[len(libpath) + 1:]
                 mod = dotted_name_of_path(rel_path)
                 yield mod
 
 stdlib_modules = set(list_stdlib_modules())
 
 def imported_modules(source, modulename, f, localmods, ignore_nested=False):
     """Given the source of a file as a string, yield the names
     imported by that file.
 
     Args:
       source: The python source to examine as a string.
       modulename: of specified python source (may have `__init__`)
       localmods: set of locally defined module names (may have `__init__`)
       ignore_nested: If true, import statements that do not start in
                      column zero will be ignored.
 
     Returns:
       A list of absolute module names imported by the given source.
 
     >>> f = 'foo/xxx.py'
     >>> modulename = 'foo.xxx'
     >>> localmods = {'foo.__init__': True,
     ...              'foo.foo1': True, 'foo.foo2': True,
     ...              'foo.bar.__init__': True, 'foo.bar.bar1': True,
     ...              'baz.__init__': True, 'baz.baz1': True }
     >>> # standard library (= not locally defined ones)
     >>> sorted(imported_modules(
     ...        'from stdlib1 import foo, bar; import stdlib2',
     ...        modulename, f, localmods))
     []
     >>> # relative importing
     >>> sorted(imported_modules(
     ...        'import foo1; from bar import bar1',
     ...        modulename, f, localmods))
     ['foo.bar.bar1', 'foo.foo1']
     >>> sorted(imported_modules(
     ...        'from bar.bar1 import name1, name2, name3',
     ...        modulename, f, localmods))
     ['foo.bar.bar1']
     >>> # absolute importing
     >>> sorted(imported_modules(
     ...        'from baz import baz1, name1',
     ...        modulename, f, localmods))
     ['baz.__init__', 'baz.baz1']
     >>> # mixed importing, even though it shouldn't be recommended
     >>> sorted(imported_modules(
     ...        'import stdlib, foo1, baz',
     ...        modulename, f, localmods))
     ['baz.__init__', 'foo.foo1']
     >>> # ignore_nested
     >>> sorted(imported_modules(
     ... '''import foo
     ... def wat():
     ...     import bar
     ... ''', modulename, f, localmods))
     ['foo.__init__', 'foo.bar.__init__']
     >>> sorted(imported_modules(
     ... '''import foo
     ... def wat():
     ...     import bar
     ... ''', modulename, f, localmods, ignore_nested=True))
     ['foo.__init__']
     """
     fromlocal = fromlocalfunc(modulename, localmods)
     for node in ast.walk(ast.parse(source, f)):
         if ignore_nested and getattr(node, 'col_offset', 0) > 0:
             continue
         if isinstance(node, ast.Import):
             for n in node.names:
                 found = fromlocal(n.name)
                 if not found:
                     # this should import standard library
                     continue
                 yield found[1]
         elif isinstance(node, ast.ImportFrom):
             found = fromlocal(node.module, node.level)
             if not found:
                 # this should import standard library
                 continue
 
             absname, dottedpath, hassubmod = found
             if not hassubmod:
                 # "dottedpath" is not a package; must be imported
                 yield dottedpath
                 # examination of "node.names" should be redundant
                 # e.g.: from mercurial.node import nullid, nullrev
                 continue
 
             modnotfound = False
             prefix = absname + '.'
             for n in node.names:
                 found = fromlocal(prefix + n.name)
                 if not found:
                     # this should be a function or a property of "node.module"
                     modnotfound = True
                     continue
                 yield found[1]
             if modnotfound:
                 # "dottedpath" is a package, but imported because of non-module
                 # lookup
                 yield dottedpath
 
 def verify_import_convention(module, source, localmods):
     """Verify imports match our established coding convention.
 
     We have 2 conventions: legacy and modern. The modern convention is in
     effect when using absolute imports.
 
     The legacy convention only looks for mixed imports. The modern convention
     is much more thorough.
     """
     root = ast.parse(source)
     absolute = usingabsolute(root)
 
     if absolute:
         return verify_modern_convention(module, root, localmods)
     else:
         return verify_stdlib_on_own_line(root)
 
 def verify_modern_convention(module, root, localmods, root_col_offset=0):
     """Verify a file conforms to the modern import convention rules.
 
     The rules of the modern convention are:
 
     * Ordering is stdlib followed by local imports. Each group is lexically
       sorted.
     * Importing multiple modules via "import X, Y" is not allowed: use
       separate import statements.
     * Importing multiple modules via "from X import ..." is allowed if using
       parenthesis and one entry per line.
     * Only 1 relative import statement per import level ("from .", "from ..")
       is allowed.
     * Relative imports from higher levels must occur before lower levels. e.g.
       "from .." must be before "from .".
     * Imports from peer packages should use relative import (e.g. do not
       "import mercurial.foo" from a "mercurial.*" module).
     * Symbols can only be imported from specific modules (see
       `allowsymbolimports`). For other modules, first import the module then
       assign the symbol to a module-level variable. In addition, these imports
       must be performed before other local imports. This rule only
       applies to import statements outside of any blocks.
     * Relative imports from the standard library are not allowed, unless that
       library is also a local module.
     * Certain modules must be aliased to alternate names to avoid aliasing
       and readability problems. See `requirealias`.
     """
     if not isinstance(module, str):
         module = module.decode('ascii')
     topmodule = module.split('.')[0]
     fromlocal = fromlocalfunc(module, localmods)
 
     # Whether a local/non-stdlib import has been performed.
     seenlocal = None
     # Whether a local/non-stdlib, non-symbol import has been seen.
     seennonsymbollocal = False
     # The last name to be imported (for sorting).
     lastname = None
     laststdlib = None
     # Relative import levels encountered so far.
     seenlevels = set()
 
     for node, newscope in walklocal(root):
         def msg(fmt, *args):
             return (fmt % args, node.lineno)
         if newscope:
             # Check for local imports in function
             for r in verify_modern_convention(module, node, localmods,
                                               node.col_offset + 4):
                 yield r
         elif isinstance(node, ast.Import):
             # Disallow "import foo, bar" and require separate imports
             # for each module.
             if len(node.names) > 1:
                 yield msg('multiple imported names: %s',
                           ', '.join(n.name for n in node.names))
 
             name = node.names[0].name
             asname = node.names[0].asname
 
             stdlib = name in stdlib_modules
 
             # Ignore sorting rules on imports inside blocks.
             if node.col_offset == root_col_offset:
                 if lastname and name < lastname and laststdlib == stdlib:
                     yield msg('imports not lexically sorted: %s < %s',
                               name, lastname)
 
             lastname = name
             laststdlib = stdlib
 
             # stdlib imports should be before local imports.
             if stdlib and seenlocal and node.col_offset == root_col_offset:
                 yield msg('stdlib import "%s" follows local import: %s',
                           name, seenlocal)
 
             if not stdlib:
                 seenlocal = name
 
             # Import of sibling modules should use relative imports.
             topname = name.split('.')[0]
             if topname == topmodule:
                 yield msg('import should be relative: %s', name)
 
             if name in requirealias and asname != requirealias[name]:
                 yield msg('%s module must be "as" aliased to %s',
                           name, requirealias[name])
 
         elif isinstance(node, ast.ImportFrom):
             # Resolve the full imported module name.
             if node.level > 0:
                 fullname = '.'.join(module.split('.')[:-node.level])
                 if node.module:
                     fullname += '.%s' % node.module
             else:
                 assert node.module
                 fullname = node.module
 
                 topname = fullname.split('.')[0]
                 if topname == topmodule:
                     yield msg('import should be relative: %s', fullname)
 
             # __future__ is special since it needs to come first and use
             # symbol import.
             if fullname != '__future__':
                 if not fullname or (
                     fullname in stdlib_modules
                     and fullname not in localmods
                     and fullname + '.__init__' not in localmods):
                     yield msg('relative import of stdlib module')
                 else:
                     seenlocal = fullname
 
             # Direct symbol import is only allowed from certain modules and
             # must occur before non-symbol imports.
             found = fromlocal(node.module, node.level)
             if found and found[2]:  # node.module is a package
                 prefix = found[0] + '.'
                 symbols = (n.name for n in node.names
                            if not fromlocal(prefix + n.name))
             else:
                 symbols = (n.name for n in node.names)
             symbols = [sym for sym in symbols if sym not in directsymbols]
             if node.module and node.col_offset == root_col_offset:
                 if symbols and fullname not in allowsymbolimports:
                     yield msg('direct symbol import %s from %s',
                               ', '.join(symbols), fullname)
 
                 if symbols and seennonsymbollocal:
                     yield msg('symbol import follows non-symbol import: %s',
                               fullname)
             if not symbols and fullname not in stdlib_modules:
                 seennonsymbollocal = True
 
             if not node.module:
                 assert node.level
 
                 # Only allow 1 group per level.
                 if (node.level in seenlevels
                     and node.col_offset == root_col_offset):
                     yield msg('multiple "from %s import" statements',
                               '.' * node.level)
 
                 # Higher-level groups come before lower-level groups.
                 if any(node.level > l for l in seenlevels):
                     yield msg('higher-level import should come first: %s',
                               fullname)
 
                 seenlevels.add(node.level)
 
             # Entries in "from .X import ( ... )" lists must be lexically
             # sorted.
             lastentryname = None
 
             for n in node.names:
                 if lastentryname and n.name < lastentryname:
                     yield msg('imports from %s not lexically sorted: %s < %s',
                               fullname, n.name, lastentryname)
 
                 lastentryname = n.name
 
                 if n.name in requirealias and n.asname != requirealias[n.name]:
                     yield msg('%s from %s must be "as" aliased to %s',
                               n.name, fullname, requirealias[n.name])
 
 def verify_stdlib_on_own_line(root):
     """Given some python source, verify that stdlib imports are done
     in separate statements from relative local module imports.
 
     >>> list(verify_stdlib_on_own_line(ast.parse('import sys, foo')))
     [('mixed imports\\n   stdlib:    sys\\n   relative:  foo', 1)]
     >>> list(verify_stdlib_on_own_line(ast.parse('import sys, os')))
     []
     >>> list(verify_stdlib_on_own_line(ast.parse('import foo, bar')))
     []
     """
     for node in ast.walk(root):
         if isinstance(node, ast.Import):
             from_stdlib = {False: [], True: []}
             for n in node.names:
                 from_stdlib[n.name in stdlib_modules].append(n.name)
             if from_stdlib[True] and from_stdlib[False]:
                 yield ('mixed imports\n   stdlib:    %s\n   relative:  %s' %
                        (', '.join(sorted(from_stdlib[True])),
                         ', '.join(sorted(from_stdlib[False]))), node.lineno)
 
 class CircularImport(Exception):
     pass
 
 def checkmod(mod, imports):
     shortest = {}
     visit = [[mod]]
     while visit:
         path = visit.pop(0)
         for i in sorted(imports.get(path[-1], [])):
             if len(path) < shortest.get(i, 1000):
                 shortest[i] = len(path)
                 if i in path:
                     if i == path[0]:
                         raise CircularImport(path)
                     continue
                 visit.append(path + [i])
 
 def rotatecycle(cycle):
     """arrange a cycle so that the lexicographically first module listed first
 
     >>> rotatecycle(['foo', 'bar'])
     ['bar', 'foo', 'bar']
     """
     lowest = min(cycle)
     idx = cycle.index(lowest)
     return cycle[idx:] + cycle[:idx] + [lowest]
 
 def find_cycles(imports):
     """Find cycles in an already-loaded import graph.
 
     All module names recorded in `imports` should be absolute one.
 
     >>> from __future__ import print_function
     >>> imports = {'top.foo': ['top.bar', 'os.path', 'top.qux'],
     ...            'top.bar': ['top.baz', 'sys'],
     ...            'top.baz': ['top.foo'],
     ...            'top.qux': ['top.foo']}
     >>> print('\\n'.join(sorted(find_cycles(imports))))
     top.bar -> top.baz -> top.foo -> top.bar
     top.foo -> top.qux -> top.foo
     """
     cycles = set()
     for mod in sorted(imports.keys()):
         try:
             checkmod(mod, imports)
         except CircularImport as e:
             cycle = e.args[0]
             cycles.add(" -> ".join(rotatecycle(cycle)))
     return cycles
 
 def _cycle_sortkey(c):
     return len(c), c
 
 def embedded(f, modname, src):
     """Extract embedded python code
 
     >>> def _forcestr(thing):
     ...     if not isinstance(thing, str):
     ...         return thing.decode('ascii')
     ...     return thing
     >>> def test(fn, lines):
     ...     for s, m, f, l in embedded(fn, b"example", lines):
     ...         print("%s %s %d" % (_forcestr(m), _forcestr(f), l))
     ...         print(repr(_forcestr(s)))
     >>> lines = [
     ...   'comment',
     ...   '  >>> from __future__ import print_function',
     ...   "  >>> ' multiline",
     ...   "  ... string'",
     ...   '  ',
     ...   'comment',
     ...   '  $ cat > foo.py <<EOF',
     ...   '  > from __future__ import print_function',
     ...   '  > EOF',
     ... ]
     >>> test(b"example.t", lines)
     example[2] doctest.py 1
     "from __future__ import print_function\\n' multiline\\nstring'\\n\\n"
     example[8] foo.py 7
     'from __future__ import print_function\\n'
     """
     errors = []
     for name, starts, ends, code in testparseutil.pyembedded(f, src, errors):
         if not name:
             # use 'doctest.py', in order to make already existing
             # doctest above pass instantly
             name = 'doctest.py'
         # "starts" is "line number" (1-origin), but embedded() is
         # expected to return "line offset" (0-origin). Therefore, this
         # yields "starts - 1".
         if not isinstance(modname, str):
             modname = modname.decode('utf8')
         yield code, "%s[%d]" % (modname, starts), name, starts - 1
 
 def sources(f, modname):
     """Yields possibly multiple sources from a filepath
 
     input: filepath, modulename
     yields:  script(string), modulename, filepath, linenumber
 
     For embedded scripts, the modulename and filepath will be different
     from the function arguments. linenumber is an offset relative to
     the input file.
     """
     py = False
     if not f.endswith('.t'):
         with open(f, 'rb') as src:
             yield src.read(), modname, f, 0
             py = True
     if py or f.endswith('.t'):
         with open(f, 'r') as src:
             for script, modname, t, line in embedded(f, modname, src):
                 yield script, modname.encode('utf8'), t, line
 
 def main(argv):
     if len(argv) < 2 or (argv[1] == '-' and len(argv) > 2):
         print('Usage: %s {-|file [file] [file] ...}')
         return 1
     if argv[1] == '-':
         argv = argv[:1]
         argv.extend(l.rstrip() for l in sys.stdin.readlines())
     localmodpaths = {}
     used_imports = {}
     any_errors = False
     for source_path in argv[1:]:
         modname = dotted_name_of_path(source_path)
         localmodpaths[modname] = source_path
     localmods = populateextmods(localmodpaths)
     for localmodname, source_path in sorted(localmodpaths.items()):
         if not isinstance(localmodname, bytes):
             # This is only safe because all hg's files are ascii
             localmodname = localmodname.encode('ascii')
         for src, modname, name, line in sources(source_path, localmodname):
             try:
                 used_imports[modname] = sorted(
                     imported_modules(src, modname, name, localmods,
                                      ignore_nested=True))
                 for error, lineno in verify_import_convention(modname, src,
                                                               localmods):
                     any_errors = True
                     print('%s:%d: %s' % (source_path, lineno + line, error))
             except SyntaxError as e:
                 print('%s:%d: SyntaxError: %s' %
                       (source_path, e.lineno + line, e))
     cycles = find_cycles(used_imports)
     if cycles:
         firstmods = set()
         for c in sorted(cycles, key=_cycle_sortkey):
             first = c.split()[0]
             # As a rough cut, ignore any cycle that starts with the
             # same module as some other cycle. Otherwise we see lots
             # of cycles that are effectively duplicates.
             if first in firstmods:
                 continue
             print('Import cycle:', c)
             firstmods.add(first)
         any_errors = True
     return any_errors != 0
 
 if __name__ == '__main__':
     sys.exit(int(main(sys.argv)))

hgext/lfs/__init__.py

@@ -1,383 +1,386
 # lfs - hash-preserving large file support using Git-LFS protocol
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """lfs - large file support (EXPERIMENTAL)
 
 This extension allows large files to be tracked outside of the normal
 repository storage and stored on a centralized server, similar to the
 ``largefiles`` extension.  The ``git-lfs`` protocol is used when
 communicating with the server, so existing git infrastructure can be
 harnessed.  Even though the files are stored outside of the repository,
 they are still integrity checked in the same manner as normal files.
 
 The files stored outside of the repository are downloaded on demand,
 which reduces the time to clone, and possibly the local disk usage.
 This changes fundamental workflows in a DVCS, so careful thought
 should be given before deploying it.  :hg:`convert` can be used to
 convert LFS repositories to normal repositories that no longer
 require this extension, and do so without changing the commit hashes.
 This allows the extension to be disabled if the centralized workflow
 becomes burdensome.  However, the pre and post convert clones will
 not be able to communicate with each other unless the extension is
 enabled on both.
 
 To start a new repository, or to add LFS files to an existing one, just
 create an ``.hglfs`` file as described below in the root directory of
 the repository.  Typically, this file should be put under version
 control, so that the settings will propagate to other repositories with
 push and pull.  During any commit, Mercurial will consult this file to
 determine if an added or modified file should be stored externally.  The
 type of storage depends on the characteristics of the file at each
 commit.  A file that is near a size threshold may switch back and forth
 between LFS and normal storage, as needed.
 
 Alternately, both normal repositories and largefile controlled
 repositories can be converted to LFS by using :hg:`convert` and the
 ``lfs.track`` config option described below.  The ``.hglfs`` file
 should then be created and added, to control subsequent LFS selection.
 The hashes are also unchanged in this case.  The LFS and non-LFS
 repositories can be distinguished because the LFS repository will
 abort any command if this extension is disabled.
 
 Committed LFS files are held locally, until the repository is pushed.
 Prior to pushing the normal repository data, the LFS files that are
 tracked by the outgoing commits are automatically uploaded to the
 configured central server.  No LFS files are transferred on
 :hg:`pull` or :hg:`clone`.  Instead, the files are downloaded on
 demand as they need to be read, if a cached copy cannot be found
 locally.  Both committing and downloading an LFS file will link the
 file to a usercache, to speed up future access.  See the `usercache`
 config setting described below.
 
 .hglfs::
 
     The extension reads its configuration from a versioned ``.hglfs``
     configuration file found in the root of the working directory. The
     ``.hglfs`` file uses the same syntax as all other Mercurial
     configuration files. It uses a single section, ``[track]``.
 
     The ``[track]`` section specifies which files are stored as LFS (or
     not). Each line is keyed by a file pattern, with a predicate value.
     The first file pattern match is used, so put more specific patterns
     first.  The available predicates are ``all()``, ``none()``, and
     ``size()``. See "hg help filesets.size" for the latter.
 
     Example versioned ``.hglfs`` file::
 
       [track]
       # No Makefile or python file, anywhere, will be LFS
       **Makefile = none()
       **.py = none()
 
       **.zip = all()
       **.exe = size(">1MB")
 
       # Catchall for everything not matched above
       ** = size(">10MB")
 
 Configs::
 
     [lfs]
     # Remote endpoint. Multiple protocols are supported:
     # - http(s)://user:[e-mail]/path
     #   git-lfs endpoint
     # - file:///tmp/path
     #   local filesystem, usually for testing
     # if unset, lfs will assume the remote repository also handles blob storage
     # for http(s) URLs.  Otherwise, lfs will prompt to set this when it must
     # use this value.
     # (default: unset)
     url = https://example.com/repo.git/info/lfs
 
     # Which files to track in LFS.  Path tests are "**.extname" for file
     # extensions, and "path:under/some/directory" for path prefix.  Both
     # are relative to the repository root.
     # File size can be tested with the "size()" fileset, and tests can be
     # joined with fileset operators.  (See "hg help filesets.operators".)
     #
     # Some examples:
     # - all()                       # everything
     # - none()                      # nothing
     # - size(">20MB")               # larger than 20MB
     # - !**.txt                     # anything not a *.txt file
     # - **.zip | **.tar.gz | **.7z  # some types of compressed files
     # - path:bin                    # files under "bin" in the project root
     # - (**.php & size(">2MB")) | (**.js & size(">5MB")) | **.tar.gz
     #     | (path:bin & !path:/bin/README) | size(">1GB")
     # (default: none())
     #
     # This is ignored if there is a tracked '.hglfs' file, and this setting
     # will eventually be deprecated and removed.
     track = size(">10M")
 
     # how many times to retry before giving up on transferring an object
     retry = 5
 
     # the local directory to store lfs files for sharing across local clones.
     # If not set, the cache is located in an OS specific cache location.
     usercache = /path/to/global/cache
 """
 
 from __future__ import absolute_import
 
 import sys
 
 from mercurial.i18n import _
 
 from mercurial import (
     config,
     context,
     error,
     exchange,
     extensions,
     exthelper,
     filelog,
     filesetlang,
     localrepo,
     minifileset,
     node,
     pycompat,
-    repository,
     revlog,
     scmutil,
     templateutil,
     util,
 )
 
+from mercurial.interfaces import (
+    repository,
+)
+
 from . import (
     blobstore,
     wireprotolfsserver,
     wrapper,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 eh = exthelper.exthelper()
 eh.merge(wrapper.eh)
 eh.merge(wireprotolfsserver.eh)
 
 cmdtable = eh.cmdtable
 configtable = eh.configtable
 extsetup = eh.finalextsetup
 uisetup = eh.finaluisetup
 filesetpredicate = eh.filesetpredicate
 reposetup = eh.finalreposetup
 templatekeyword = eh.templatekeyword
 
 eh.configitem('experimental', 'lfs.serve',
     default=True,
 )
 eh.configitem('experimental', 'lfs.user-agent',
     default=None,
 )
 eh.configitem('experimental', 'lfs.disableusercache',
     default=False,
 )
 eh.configitem('experimental', 'lfs.worker-enable',
     default=False,
 )
 
 eh.configitem('lfs', 'url',
     default=None,
 )
 eh.configitem('lfs', 'usercache',
     default=None,
 )
 # Deprecated
 eh.configitem('lfs', 'threshold',
     default=None,
 )
 eh.configitem('lfs', 'track',
     default='none()',
 )
 eh.configitem('lfs', 'retry',
     default=5,
 )
 
 lfsprocessor = (
     wrapper.readfromstore,
     wrapper.writetostore,
     wrapper.bypasscheckhash,
 )
 
 def featuresetup(ui, supported):
     # don't die on seeing a repo with the lfs requirement
     supported |= {'lfs'}
 
 @eh.uisetup
 def _uisetup(ui):
     localrepo.featuresetupfuncs.add(featuresetup)
 
 @eh.reposetup
 def _reposetup(ui, repo):
     # Nothing to do with a remote repo
     if not repo.local():
         return
 
     repo.svfs.lfslocalblobstore = blobstore.local(repo)
     repo.svfs.lfsremoteblobstore = blobstore.remote(repo)
 
     class lfsrepo(repo.__class__):
         @localrepo.unfilteredmethod
         def commitctx(self, ctx, error=False, origctx=None):
             repo.svfs.options['lfstrack'] = _trackedmatcher(self)
             return super(lfsrepo, self).commitctx(ctx, error, origctx=origctx)
 
     repo.__class__ = lfsrepo
 
     if 'lfs' not in repo.requirements:
         def checkrequireslfs(ui, repo, **kwargs):
             if 'lfs' in repo.requirements:
                 return 0
 
             last = kwargs.get(r'node_last')
             _bin = node.bin
             if last:
                 s = repo.set('%n:%n', _bin(kwargs[r'node']), _bin(last))
             else:
                 s = repo.set('%n', _bin(kwargs[r'node']))
             match = repo._storenarrowmatch
             for ctx in s:
                 # TODO: is there a way to just walk the files in the commit?
                 if any(ctx[f].islfs() for f in ctx.files()
                        if f in ctx and match(f)):
                     repo.requirements.add('lfs')
                     repo.features.add(repository.REPO_FEATURE_LFS)
                     repo._writerequirements()
                     repo.prepushoutgoinghooks.add('lfs', wrapper.prepush)
                     break
 
         ui.setconfig('hooks', 'commit.lfs', checkrequireslfs, 'lfs')
         ui.setconfig('hooks', 'pretxnchangegroup.lfs', checkrequireslfs, 'lfs')
     else:
         repo.prepushoutgoinghooks.add('lfs', wrapper.prepush)
 
 def _trackedmatcher(repo):
     """Return a function (path, size) -> bool indicating whether or not to
     track a given file with lfs."""
     if not repo.wvfs.exists('.hglfs'):
         # No '.hglfs' in wdir.  Fallback to config for now.
         trackspec = repo.ui.config('lfs', 'track')
 
         # deprecated config: lfs.threshold
         threshold = repo.ui.configbytes('lfs', 'threshold')
         if threshold:
             filesetlang.parse(trackspec)  # make sure syntax errors are confined
             trackspec = "(%s) | size('>%d')" % (trackspec, threshold)
 
         return minifileset.compile(trackspec)
 
     data = repo.wvfs.tryread('.hglfs')
     if not data:
         return lambda p, s: False
 
     # Parse errors here will abort with a message that points to the .hglfs file
     # and line number.
     cfg = config.config()
     cfg.parse('.hglfs', data)
 
     try:
         rules = [(minifileset.compile(pattern), minifileset.compile(rule))
                  for pattern, rule in cfg.items('track')]
     except error.ParseError as e:
         # The original exception gives no indicator that the error is in the
         # .hglfs file, so add that.
 
         # TODO: See if the line number of the file can be made available.
         raise error.Abort(_('parse error in .hglfs: %s') % e)
 
     def _match(path, size):
         for pat, rule in rules:
             if pat(path, size):
                 return rule(path, size)
 
         return False
 
     return _match
 
 # Called by remotefilelog
 def wrapfilelog(filelog):
     wrapfunction = extensions.wrapfunction
 
     wrapfunction(filelog, 'addrevision', wrapper.filelogaddrevision)
     wrapfunction(filelog, 'renamed', wrapper.filelogrenamed)
     wrapfunction(filelog, 'size', wrapper.filelogsize)
 
 @eh.wrapfunction(localrepo, 'resolverevlogstorevfsoptions')
 def _resolverevlogstorevfsoptions(orig, ui, requirements, features):
     opts = orig(ui, requirements, features)
     for name, module in extensions.extensions(ui):
         if module is sys.modules[__name__]:
             if revlog.REVIDX_EXTSTORED in opts[b'flagprocessors']:
                 msg = (_(b"cannot register multiple processors on flag '%#x'.")
                        % revlog.REVIDX_EXTSTORED)
                 raise error.Abort(msg)
 
             opts[b'flagprocessors'][revlog.REVIDX_EXTSTORED] = lfsprocessor
             break
 
     return opts
 
 @eh.extsetup
 def _extsetup(ui):
     wrapfilelog(filelog.filelog)
 
     context.basefilectx.islfs = wrapper.filectxislfs
 
     scmutil.fileprefetchhooks.add('lfs', wrapper._prefetchfiles)
 
     # Make bundle choose changegroup3 instead of changegroup2. This affects
     # "hg bundle" command. Note: it does not cover all bundle formats like
     # "packed1". Using "packed1" with lfs will likely cause trouble.
     exchange._bundlespeccontentopts["v2"]["cg.version"] = "03"
 
 @eh.filesetpredicate('lfs()')
 def lfsfileset(mctx, x):
     """File that uses LFS storage."""
     # i18n: "lfs" is a keyword
     filesetlang.getargs(x, 0, 0, _("lfs takes no arguments"))
     ctx = mctx.ctx
     def lfsfilep(f):
         return wrapper.pointerfromctx(ctx, f, removed=True) is not None
     return mctx.predicate(lfsfilep, predrepr='<lfs>')
 
 @eh.templatekeyword('lfs_files', requires={'ctx'})
 def lfsfiles(context, mapping):
     """List of strings. All files modified, added, or removed by this
     changeset."""
     ctx = context.resource(mapping, 'ctx')
 
     pointers = wrapper.pointersfromctx(ctx, removed=True) # {path: pointer}
     files = sorted(pointers.keys())
 
     def pointer(v):
         # In the file spec, version is first and the other keys are sorted.
         sortkeyfunc = lambda x: (x[0] != 'version', x)
         items = sorted(pointers[v].iteritems(), key=sortkeyfunc)
         return util.sortdict(items)
 
     makemap = lambda v: {
         'file': v,
         'lfsoid': pointers[v].oid() if pointers[v] else None,
         'lfspointer': templateutil.hybriddict(pointer(v)),
     }
 
     # TODO: make the separator ', '?
     f = templateutil._showcompatlist(context, mapping, 'lfs_file', files)
     return templateutil.hybrid(f, files, makemap, pycompat.identity)
 
 @eh.command('debuglfsupload',
             [('r', 'rev', [], _('upload large files introduced by REV'))])
 def debuglfsupload(ui, repo, **opts):
     """upload lfs blobs added by the working copy parent or given revisions"""
     revs = opts.get(r'rev', [])
     pointers = wrapper.extractpointers(repo, scmutil.revrange(repo, revs))
     wrapper.uploadblobs(repo, pointers)

hgext/lfs/wrapper.py

@@ -1,446 +1,449
 # wrapper.py - methods wrapping core mercurial logic
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid, short
 
 from mercurial import (
     bundle2,
     changegroup,
     cmdutil,
     context,
     error,
     exchange,
     exthelper,
     localrepo,
-    repository,
     revlog,
     scmutil,
     upgrade,
     util,
     vfs as vfsmod,
     wireprotov1server,
 )
 
+from mercurial.interfaces import (
+    repository,
+)
+
 from mercurial.utils import (
     storageutil,
     stringutil,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
 eh = exthelper.exthelper()
 
 @eh.wrapfunction(localrepo, 'makefilestorage')
 def localrepomakefilestorage(orig, requirements, features, **kwargs):
     if b'lfs' in requirements:
         features.add(repository.REPO_FEATURE_LFS)
 
     return orig(requirements=requirements, features=features, **kwargs)
 
 @eh.wrapfunction(changegroup, 'allsupportedversions')
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add('03')
     return versions
 
 @eh.wrapfunction(wireprotov1server, '_capabilities')
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     if util.safehasattr(repo.svfs, 'lfslocalblobstore'):
         # Advertise a slightly different capability when lfs is *required*, so
         # that the client knows it MUST load the extension.  If lfs is not
         # required on the server, there's no reason to autoload the extension
         # on the client.
         if b'lfs' in repo.requirements:
             caps.append('lfs-serve')
 
         caps.append('lfs')
     return caps
 
 def bypasscheckhash(self, text):
     return False
 
 def readfromstore(self, text):
     """Read filelog content from local blobstore transform for flagprocessor.
 
     Default tranform for flagprocessor, returning contents from blobstore.
     Returns a 2-typle (text, validatehash) where validatehash is True as the
     contents of the blobstore should be checked using checkhash.
     """
     p = pointer.deserialize(text)
     oid = p.oid()
     store = self.opener.lfslocalblobstore
     if not store.has(oid):
         p.filename = self.filename
         self.opener.lfsremoteblobstore.readbatch([p], store)
 
     # The caller will validate the content
     text = store.read(oid, verify=False)
 
     # pack hg filelog metadata
     hgmeta = {}
     for k in p.keys():
         if k.startswith('x-hg-'):
             name = k[len('x-hg-'):]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith('\1\n'):
         text = storageutil.packmeta(hgmeta, text)
 
     return (text, True)
 
 def writetostore(self, text):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = storageutil.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
 
     # git-lfs only supports sha256
     oid = hex(hashlib.sha256(text).digest())
     self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = 'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size='%d' % len(text))
 
     # by default, we expect the content to be binary. however, LFS could also
     # be used for non-binary content. add a special entry for non-binary data.
     # this will be used by filectx.isbinary().
     if not stringutil.binary(text):
         # not hg filelog metadata (affecting commit hash), no "x-hg-" prefix
         metadata['x-is-binary'] = '0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         for k, v in hgmeta.iteritems():
             metadata['x-hg-%s' % k] = v
 
     rawtext = metadata.serialize()
     return (rawtext, False)
 
 def _islfs(rlog, node=None, rev=None):
     if rev is None:
         if node is None:
             # both None - likely working copy content where node is not ready
             return False
         rev = rlog._revlog.rev(node)
     else:
         node = rlog._revlog.node(rev)
     if node == nullid:
         return False
     flags = rlog._revlog.flags(rev)
     return bool(flags & revlog.REVIDX_EXTSTORED)
 
 # Wrapping may also be applied by remotefilelog
 def filelogaddrevision(orig, self, text, transaction, link, p1, p2,
                        cachedelta=None, node=None,
                        flags=revlog.REVIDX_DEFAULT_FLAGS, **kwds):
     # The matcher isn't available if reposetup() wasn't called.
     lfstrack = self._revlog.opener.options.get('lfstrack')
 
     if lfstrack:
         textlen = len(text)
         # exclude hg rename meta from file size
         meta, offset = storageutil.parsemeta(text)
         if offset:
             textlen -= offset
 
         if lfstrack(self._revlog.filename, textlen):
             flags |= revlog.REVIDX_EXTSTORED
 
     return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
                 node=node, flags=flags, **kwds)
 
 # Wrapping may also be applied by remotefilelog
 def filelogrenamed(orig, self, node):
     if _islfs(self, node):
         rawtext = self._revlog.rawdata(node)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if 'x-hg-copy' in metadata and 'x-hg-copyrev' in metadata:
             return metadata['x-hg-copy'], bin(metadata['x-hg-copyrev'])
         else:
             return False
     return orig(self, node)
 
 # Wrapping may also be applied by remotefilelog
 def filelogsize(orig, self, rev):
     if _islfs(self, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self._revlog.rawdata(rev)
         metadata = pointer.deserialize(rawtext)
         return int(metadata['size'])
     return orig(self, rev)
 
 @eh.wrapfunction(context.basefilectx, 'cmp')
 def filectxcmp(orig, self, fctx):
     """returns True if text is different than fctx"""
     # some fctx (ex. hg-git) is not based on basefilectx and do not have islfs
     if self.islfs() and getattr(fctx, 'islfs', lambda: False)():
         # fast path: check LFS oid
         p1 = pointer.deserialize(self.rawdata())
         p2 = pointer.deserialize(fctx.rawdata())
         return p1.oid() != p2.oid()
     return orig(self, fctx)
 
 @eh.wrapfunction(context.basefilectx, 'isbinary')
 def filectxisbinary(orig, self):
     if self.islfs():
         # fast path: use lfs metadata to answer isbinary
         metadata = pointer.deserialize(self.rawdata())
         # if lfs metadata says nothing, assume it's binary by default
         return bool(int(metadata.get('x-is-binary', 1)))
     return orig(self)
 
 def filectxislfs(self):
     return _islfs(self.filelog(), self.filenode())
 
 @eh.wrapfunction(cmdutil, '_updatecatformatter')
 def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
     orig(fm, ctx, matcher, path, decode)
     fm.data(rawdata=ctx[path].rawdata())
 
 @eh.wrapfunction(scmutil, 'wrapconvertsink')
 def convertsink(orig, sink):
     sink = orig(sink)
     if sink.repotype == 'hg':
         class lfssink(sink.__class__):
             def putcommit(self, files, copies, parents, commit, source, revmap,
                           full, cleanp2):
                 pc = super(lfssink, self).putcommit
                 node = pc(files, copies, parents, commit, source, revmap, full,
                           cleanp2)
 
                 if 'lfs' not in self.repo.requirements:
                     ctx = self.repo[node]
 
                     # The file list may contain removed files, so check for
                     # membership before assuming it is in the context.
                     if any(f in ctx and ctx[f].islfs() for f, n in files):
                         self.repo.requirements.add('lfs')
                         self.repo._writerequirements()
 
                 return node
 
         sink.__class__ = lfssink
 
     return sink
 
 # bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
 # options and blob stores are passed from othervfs to the new readonlyvfs.
 @eh.wrapfunction(vfsmod.readonlyvfs, '__init__')
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith('lfs'):
             self.options[k] = v
     # also copy lfs blobstores. note: this can run before reposetup, so lfs
     # blobstore attributes are not always ready at this time.
     for name in ['lfslocalblobstore', 'lfsremoteblobstore']:
         if util.safehasattr(othervfs, name):
             setattr(self, name, getattr(othervfs, name))
 
 def _prefetchfiles(repo, revs, match):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     if not util.safehasattr(repo.svfs, 'lfslocalblobstore'):
         return
 
     pointers = []
     oids = set()
     localstore = repo.svfs.lfslocalblobstore
 
     for rev in revs:
         ctx = repo[rev]
         for f in ctx.walk(match):
             p = pointerfromctx(ctx, f)
             if p and p.oid() not in oids and not localstore.has(p.oid()):
                 p.filename = f
                 pointers.append(p)
                 oids.add(p.oid())
 
     if pointers:
         # Recalculating the repo store here allows 'paths.default' that is set
         # on the repo by a clone command to be used for the update.
         blobstore.remote(repo).readbatch(pointers, localstore)
 
 def _canskipupload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
         return True
 
     # if remotestore is a null store, upload is a no-op and can be skipped
     return isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 def candownload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, 'lfsremoteblobstore'):
         return False
 
     # if remotestore is a null store, downloads will lead to nothing
     return not isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 def uploadblobsfromrevs(repo, revs):
     '''upload lfs blobs introduced by revs
 
     Note: also used by other extensions e. g. infinitepush. avoid renaming.
     '''
     if _canskipupload(repo):
         return
     pointers = extractpointers(repo, revs)
     uploadblobs(repo, pointers)
 
 def prepush(pushop):
     """Prepush hook.
 
     Read through the revisions to push, looking for filelog entries that can be
     deserialized into metadata so that we can block the push on their upload to
     the remote blobstore.
     """
     return uploadblobsfromrevs(pushop.repo, pushop.outgoing.missing)
 
 @eh.wrapfunction(exchange, 'push')
 def push(orig, repo, remote, *args, **kwargs):
     """bail on push if the extension isn't enabled on remote when needed, and
     update the remote store based on the destination path."""
     if 'lfs' in repo.requirements:
         # If the remote peer is for a local repo, the requirement tests in the
         # base class method enforce lfs support.  Otherwise, some revisions in
         # this repo use lfs, and the remote repo needs the extension loaded.
         if not remote.local() and not remote.capable('lfs'):
             # This is a copy of the message in exchange.push() when requirements
             # are missing between local repos.
             m = _("required features are not supported in the destination: %s")
             raise error.Abort(m % 'lfs',
                               hint=_('enable the lfs extension on the server'))
 
         # Repositories where this extension is disabled won't have the field.
         # But if there's a requirement, then the extension must be loaded AND
         # there may be blobs to push.
         remotestore = repo.svfs.lfsremoteblobstore
         try:
             repo.svfs.lfsremoteblobstore = blobstore.remote(repo, remote.url())
             return orig(repo, remote, *args, **kwargs)
         finally:
             repo.svfs.lfsremoteblobstore = remotestore
     else:
         return orig(repo, remote, *args, **kwargs)
 
 # when writing a bundle via "hg bundle" command, upload related LFS blobs
 @eh.wrapfunction(bundle2, 'writenewbundle')
 def writenewbundle(orig, ui, repo, source, filename, bundletype, outgoing,
                    *args, **kwargs):
     """upload LFS blobs added by outgoing revisions on 'hg bundle'"""
     uploadblobsfromrevs(repo, outgoing.missing)
     return orig(ui, repo, source, filename, bundletype, outgoing, *args,
                 **kwargs)
 
 def extractpointers(repo, revs):
     """return a list of lfs pointers added by given revs"""
     repo.ui.debug('lfs: computing set of blobs to upload\n')
     pointers = {}
 
     makeprogress = repo.ui.makeprogress
     with makeprogress(_('lfs search'), _('changesets'), len(revs)) as progress:
         for r in revs:
             ctx = repo[r]
             for p in pointersfromctx(ctx).values():
                 pointers[p.oid()] = p
             progress.increment()
         return sorted(pointers.values(), key=lambda p: p.oid())
 
 def pointerfromctx(ctx, f, removed=False):
     """return a pointer for the named file from the given changectx, or None if
     the file isn't LFS.
 
     Optionally, the pointer for a file deleted from the context can be returned.
     Since no such pointer is actually stored, and to distinguish from a non LFS
     file, this pointer is represented by an empty dict.
     """
     _ctx = ctx
     if f not in ctx:
         if not removed:
             return None
         if f in ctx.p1():
             _ctx = ctx.p1()
         elif f in ctx.p2():
             _ctx = ctx.p2()
         else:
             return None
     fctx = _ctx[f]
     if not _islfs(fctx.filelog(), fctx.filenode()):
         return None
     try:
         p = pointer.deserialize(fctx.rawdata())
         if ctx == _ctx:
             return p
         return {}
     except pointer.InvalidPointer as ex:
         raise error.Abort(_('lfs: corrupted pointer (%s@%s): %s\n')
                           % (f, short(_ctx.node()), ex))
 
 def pointersfromctx(ctx, removed=False):
     """return a dict {path: pointer} for given single changectx.
 
     If ``removed`` == True and the LFS file was removed from ``ctx``, the value
     stored for the path is an empty dict.
     """
     result = {}
     m = ctx.repo().narrowmatch()
 
     # TODO: consider manifest.fastread() instead
     for f in ctx.files():
         if not m(f):
             continue
         p = pointerfromctx(ctx, f, removed=removed)
         if p is not None:
             result[f] = p
     return result
 
 def uploadblobs(repo, pointers):
     """upload given pointers from local blobstore"""
     if not pointers:
         return
 
     remoteblob = repo.svfs.lfsremoteblobstore
     remoteblob.writebatch(pointers, repo.svfs.lfslocalblobstore)
 
 @eh.wrapfunction(upgrade, '_finishdatamigration')
 def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
     orig(ui, srcrepo, dstrepo, requirements)
 
     # Skip if this hasn't been passed to reposetup()
     if (util.safehasattr(srcrepo.svfs, 'lfslocalblobstore') and
         util.safehasattr(dstrepo.svfs, 'lfslocalblobstore')):
         srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
         dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs
 
         for dirpath, dirs, files in srclfsvfs.walk():
             for oid in files:
                 ui.write(_('copying lfs blob %s\n') % oid)
                 lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 @eh.wrapfunction(upgrade, 'preservedrequirements')
 @eh.wrapfunction(upgrade, 'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if 'lfs' in repo.requirements:
         reqs.add('lfs')
     return reqs

hgext/narrow/__init__.py

@@ -1,71 +1,74
 # __init__.py - narrowhg extension
 #
 # Copyright 2017 Google, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 '''create clones which fetch history data for subset of files (EXPERIMENTAL)'''
 
 from __future__ import absolute_import
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 from mercurial import (
     localrepo,
     registrar,
+)
+
+from mercurial.interfaces import (
     repository,
 )
 
 from . import (
     narrowbundle2,
     narrowcommands,
     narrowrepo,
     narrowtemplates,
     narrowwirepeer,
 )
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 # Narrowhg *has* support for serving ellipsis nodes (which are used at
 # least by Google's internal server), but that support is pretty
 # fragile and has a lot of problems on real-world repositories that
 # have complex graph topologies. This could probably be corrected, but
 # absent someone needing the full support for ellipsis nodes in
 # repositories with merges, it's unlikely this work will get done. As
 # of this writining in late 2017, all repositories large enough for
 # ellipsis nodes to be a hard requirement also enforce strictly linear
 # history for other scaling reasons.
 configitem('experimental', 'narrowservebrokenellipses',
            default=False,
            alias=[('narrow', 'serveellipses')],
 )
 
 # Export the commands table for Mercurial to see.
 cmdtable = narrowcommands.table
 
 def featuresetup(ui, features):
     features.add(repository.NARROW_REQUIREMENT)
 
 def uisetup(ui):
     """Wraps user-facing mercurial commands with narrow-aware versions."""
     localrepo.featuresetupfuncs.add(featuresetup)
     narrowbundle2.setup()
     narrowcommands.setup()
     narrowwirepeer.uisetup()
 
 def reposetup(ui, repo):
     """Wraps local repositories with narrow repo support."""
     if not repo.local():
         return
 
     repo.ui.setconfig('experimental', 'narrow', True, 'narrow-ext')
     if repository.NARROW_REQUIREMENT in repo.requirements:
         narrowrepo.wraprepo(repo)
         narrowwirepeer.reposetup(repo)
 
 templatekeyword = narrowtemplates.templatekeyword
 revsetpredicate = narrowtemplates.revsetpredicate

hgext/narrow/narrowbundle2.py

@@ -1,301 +1,303
 # narrowbundle2.py - bundle2 extensions for narrow repository support
 #
 # Copyright 2017 Google, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import struct
 
 from mercurial.i18n import _
 from mercurial.node import (
     bin,
     nullid,
 )
 from mercurial import (
     bundle2,
     changegroup,
     error,
     exchange,
     localrepo,
     narrowspec,
     repair,
-    repository,
     util,
     wireprototypes,
 )
+from mercurial.interfaces import (
+    repository,
+)
 from mercurial.utils import (
     stringutil,
 )
 
 _NARROWACL_SECTION = 'narrowacl'
 _CHANGESPECPART = 'narrow:changespec'
 _RESSPECS = 'narrow:responsespec'
 _SPECPART = 'narrow:spec'
 _SPECPART_INCLUDE = 'include'
 _SPECPART_EXCLUDE = 'exclude'
 _KILLNODESIGNAL = 'KILL'
 _DONESIGNAL = 'DONE'
 _ELIDEDCSHEADER = '>20s20s20sl' # cset id, p1, p2, len(text)
 _ELIDEDMFHEADER = '>20s20s20s20sl' # manifest id, p1, p2, link id, len(text)
 _CSHEADERSIZE = struct.calcsize(_ELIDEDCSHEADER)
 _MFHEADERSIZE = struct.calcsize(_ELIDEDMFHEADER)
 
 # Serve a changegroup for a client with a narrow clone.
 def getbundlechangegrouppart_narrow(bundler, repo, source,
                                     bundlecaps=None, b2caps=None, heads=None,
                                     common=None, **kwargs):
     assert repo.ui.configbool('experimental', 'narrowservebrokenellipses')
 
     cgversions = b2caps.get('changegroup')
     cgversions = [v for v in cgversions
                   if v in changegroup.supportedoutgoingversions(repo)]
     if not cgversions:
         raise ValueError(_('no common changegroup version'))
     version = max(cgversions)
 
     oldinclude = sorted(filter(bool, kwargs.get(r'oldincludepats', [])))
     oldexclude = sorted(filter(bool, kwargs.get(r'oldexcludepats', [])))
     newinclude = sorted(filter(bool, kwargs.get(r'includepats', [])))
     newexclude = sorted(filter(bool, kwargs.get(r'excludepats', [])))
     known = {bin(n) for n in kwargs.get(r'known', [])}
     generateellipsesbundle2(bundler, repo, oldinclude, oldexclude, newinclude,
                             newexclude, version, common, heads, known,
                             kwargs.get(r'depth', None))
 
 def generateellipsesbundle2(bundler, repo, oldinclude, oldexclude, newinclude,
                             newexclude, version, common, heads, known, depth):
     newmatch = narrowspec.match(repo.root, include=newinclude,
                                 exclude=newexclude)
     if depth is not None:
         depth = int(depth)
         if depth < 1:
             raise error.Abort(_('depth must be positive, got %d') % depth)
 
     heads = set(heads or repo.heads())
     common = set(common or [nullid])
     if known and (oldinclude != newinclude or oldexclude != newexclude):
         # Steps:
         # 1. Send kill for "$known & ::common"
         #
         # 2. Send changegroup for ::common
         #
         # 3. Proceed.
         #
         # In the future, we can send kills for only the specific
         # nodes we know should go away or change shape, and then
         # send a data stream that tells the client something like this:
         #
         # a) apply this changegroup
         # b) apply nodes XXX, YYY, ZZZ that you already have
         # c) goto a
         #
         # until they've built up the full new state.
         # Convert to revnums and intersect with "common". The client should
         # have made it a subset of "common" already, but let's be safe.
         known = set(repo.revs("%ln & ::%ln", known, common))
         # TODO: we could send only roots() of this set, and the
         # list of nodes in common, and the client could work out
         # what to strip, instead of us explicitly sending every
         # single node.
         deadrevs = known
         def genkills():
             for r in deadrevs:
                 yield _KILLNODESIGNAL
                 yield repo.changelog.node(r)
             yield _DONESIGNAL
         bundler.newpart(_CHANGESPECPART, data=genkills())
         newvisit, newfull, newellipsis = exchange._computeellipsis(
             repo, set(), common, known, newmatch)
         if newvisit:
             packer = changegroup.getbundler(version, repo,
                                             matcher=newmatch,
                                             ellipses=True,
                                             shallow=depth is not None,
                                             ellipsisroots=newellipsis,
                                             fullnodes=newfull)
             cgdata = packer.generate(common, newvisit, False, 'narrow_widen')
 
             part = bundler.newpart('changegroup', data=cgdata)
             part.addparam('version', version)
             if 'treemanifest' in repo.requirements:
                 part.addparam('treemanifest', '1')
 
     visitnodes, relevant_nodes, ellipsisroots = exchange._computeellipsis(
         repo, common, heads, set(), newmatch, depth=depth)
 
     repo.ui.debug('Found %d relevant revs\n' % len(relevant_nodes))
     if visitnodes:
         packer = changegroup.getbundler(version, repo,
                                         matcher=newmatch,
                                         ellipses=True,
                                         shallow=depth is not None,
                                         ellipsisroots=ellipsisroots,
                                         fullnodes=relevant_nodes)
         cgdata = packer.generate(common, visitnodes, False, 'narrow_widen')
 
         part = bundler.newpart('changegroup', data=cgdata)
         part.addparam('version', version)
         if 'treemanifest' in repo.requirements:
             part.addparam('treemanifest', '1')
 
 @bundle2.parthandler(_SPECPART, (_SPECPART_INCLUDE, _SPECPART_EXCLUDE))
 def _handlechangespec_2(op, inpart):
     # XXX: This bundle2 handling is buggy and should be removed after hg5.2 is
     # released. New servers will send a mandatory bundle2 part named
     # 'Narrowspec' and will send specs as data instead of params.
     # Refer to issue5952 and 6019
     includepats = set(inpart.params.get(_SPECPART_INCLUDE, '').splitlines())
     excludepats = set(inpart.params.get(_SPECPART_EXCLUDE, '').splitlines())
     narrowspec.validatepatterns(includepats)
     narrowspec.validatepatterns(excludepats)
 
     if not repository.NARROW_REQUIREMENT in op.repo.requirements:
         op.repo.requirements.add(repository.NARROW_REQUIREMENT)
         op.repo._writerequirements()
     op.repo.setnarrowpats(includepats, excludepats)
     narrowspec.copytoworkingcopy(op.repo)
 
 @bundle2.parthandler(_RESSPECS)
 def _handlenarrowspecs(op, inpart):
     data = inpart.read()
     inc, exc = data.split('\0')
     includepats = set(inc.splitlines())
     excludepats = set(exc.splitlines())
     narrowspec.validatepatterns(includepats)
     narrowspec.validatepatterns(excludepats)
 
     if repository.NARROW_REQUIREMENT not in op.repo.requirements:
         op.repo.requirements.add(repository.NARROW_REQUIREMENT)
         op.repo._writerequirements()
     op.repo.setnarrowpats(includepats, excludepats)
     narrowspec.copytoworkingcopy(op.repo)
 
 @bundle2.parthandler(_CHANGESPECPART)
 def _handlechangespec(op, inpart):
     repo = op.repo
     cl = repo.changelog
 
     # changesets which need to be stripped entirely. either they're no longer
     # needed in the new narrow spec, or the server is sending a replacement
     # in the changegroup part.
     clkills = set()
 
     # A changespec part contains all the updates to ellipsis nodes
     # that will happen as a result of widening or narrowing a
     # repo. All the changes that this block encounters are ellipsis
     # nodes or flags to kill an existing ellipsis.
     chunksignal = changegroup.readexactly(inpart, 4)
     while chunksignal != _DONESIGNAL:
         if chunksignal == _KILLNODESIGNAL:
             # a node used to be an ellipsis but isn't anymore
             ck = changegroup.readexactly(inpart, 20)
             if cl.hasnode(ck):
                 clkills.add(ck)
         else:
             raise error.Abort(
                 _('unexpected changespec node chunk type: %s') % chunksignal)
         chunksignal = changegroup.readexactly(inpart, 4)
 
     if clkills:
         # preserve bookmarks that repair.strip() would otherwise strip
         op._bookmarksbackup = repo._bookmarks
         class dummybmstore(dict):
             def applychanges(self, repo, tr, changes):
                 pass
         localrepo.localrepository._bookmarks.set(repo, dummybmstore())
         chgrpfile = repair.strip(op.ui, repo, list(clkills), backup=True,
                                  topic='widen')
         if chgrpfile:
             op._widen_uninterr = repo.ui.uninterruptible()
             op._widen_uninterr.__enter__()
             # presence of _widen_bundle attribute activates widen handler later
             op._widen_bundle = chgrpfile
     # Set the new narrowspec if we're widening. The setnewnarrowpats() method
     # will currently always be there when using the core+narrowhg server, but
     # other servers may include a changespec part even when not widening (e.g.
     # because we're deepening a shallow repo).
     if util.safehasattr(repo, 'setnewnarrowpats'):
         repo.setnewnarrowpats()
 
 def handlechangegroup_widen(op, inpart):
     """Changegroup exchange handler which restores temporarily-stripped nodes"""
     # We saved a bundle with stripped node data we must now restore.
     # This approach is based on mercurial/repair.py@6ee26a53c111.
     repo = op.repo
     ui = op.ui
 
     chgrpfile = op._widen_bundle
     del op._widen_bundle
     vfs = repo.vfs
 
     ui.note(_("adding branch\n"))
     f = vfs.open(chgrpfile, "rb")
     try:
         gen = exchange.readbundle(ui, f, chgrpfile, vfs)
         if not ui.verbose:
             # silence internal shuffling chatter
             ui.pushbuffer()
         if isinstance(gen, bundle2.unbundle20):
             with repo.transaction('strip') as tr:
                 bundle2.processbundle(repo, gen, lambda: tr)
         else:
             gen.apply(repo, 'strip', 'bundle:' + vfs.join(chgrpfile), True)
         if not ui.verbose:
             ui.popbuffer()
     finally:
         f.close()
 
     # remove undo files
     for undovfs, undofile in repo.undofiles():
         try:
             undovfs.unlink(undofile)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 ui.warn(_('error removing %s: %s\n') %
                         (undovfs.join(undofile), stringutil.forcebytestr(e)))
 
     # Remove partial backup only if there were no exceptions
     op._widen_uninterr.__exit__(None, None, None)
     vfs.unlink(chgrpfile)
 
 def setup():
     """Enable narrow repo support in bundle2-related extension points."""
     getbundleargs = wireprototypes.GETBUNDLE_ARGUMENTS
 
     getbundleargs['narrow'] = 'boolean'
     getbundleargs['depth'] = 'plain'
     getbundleargs['oldincludepats'] = 'csv'
     getbundleargs['oldexcludepats'] = 'csv'
     getbundleargs['known'] = 'csv'
 
     # Extend changegroup serving to handle requests from narrow clients.
     origcgfn = exchange.getbundle2partsmapping['changegroup']
     def wrappedcgfn(*args, **kwargs):
         repo = args[1]
         if repo.ui.has_section(_NARROWACL_SECTION):
             kwargs = exchange.applynarrowacl(repo, kwargs)
 
         if (kwargs.get(r'narrow', False) and
             repo.ui.configbool('experimental', 'narrowservebrokenellipses')):
             getbundlechangegrouppart_narrow(*args, **kwargs)
         else:
             origcgfn(*args, **kwargs)
     exchange.getbundle2partsmapping['changegroup'] = wrappedcgfn
 
     # Extend changegroup receiver so client can fixup after widen requests.
     origcghandler = bundle2.parthandlermapping['changegroup']
     def wrappedcghandler(op, inpart):
         origcghandler(op, inpart)
         if util.safehasattr(op, '_widen_bundle'):
             handlechangegroup_widen(op, inpart)
         if util.safehasattr(op, '_bookmarksbackup'):
             localrepo.localrepository._bookmarks.set(op.repo,
                                                      op._bookmarksbackup)
             del op._bookmarksbackup
 
     wrappedcghandler.params = origcghandler.params
     bundle2.parthandlermapping['changegroup'] = wrappedcghandler

hgext/narrow/narrowcommands.py

@@ -1,478 +1,480
 # narrowcommands.py - command modifications for narrowhg extension
 #
 # Copyright 2017 Google, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import itertools
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     bundle2,
     cmdutil,
     commands,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     hg,
     narrowspec,
     node,
     pycompat,
     registrar,
     repair,
-    repository,
     repoview,
     sparse,
     util,
     wireprototypes,
 )
+from mercurial.interfaces import (
+    repository,
+)
 
 table = {}
 command = registrar.command(table)
 
 def setup():
     """Wraps user-facing mercurial commands with narrow-aware versions."""
 
     entry = extensions.wrapcommand(commands.table, 'clone', clonenarrowcmd)
     entry[1].append(('', 'narrow', None,
                      _("create a narrow clone of select files")))
     entry[1].append(('', 'depth', '',
                      _("limit the history fetched by distance from heads")))
     entry[1].append(('', 'narrowspec', '',
                      _("read narrowspecs from file")))
     # TODO(durin42): unify sparse/narrow --include/--exclude logic a bit
     if 'sparse' not in extensions.enabled():
         entry[1].append(('', 'include', [],
                          _("specifically fetch this file/directory")))
         entry[1].append(
             ('', 'exclude', [],
              _("do not fetch this file/directory, even if included")))
 
     entry = extensions.wrapcommand(commands.table, 'pull', pullnarrowcmd)
     entry[1].append(('', 'depth', '',
                      _("limit the history fetched by distance from heads")))
 
     extensions.wrapcommand(commands.table, 'archive', archivenarrowcmd)
 
 def clonenarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps clone command, so 'hg clone' first wraps localrepo.clone()."""
     opts = pycompat.byteskwargs(opts)
     wrappedextraprepare = util.nullcontextmanager()
     narrowspecfile = opts['narrowspec']
 
     if narrowspecfile:
         filepath = os.path.join(encoding.getcwd(), narrowspecfile)
         ui.status(_("reading narrowspec from '%s'\n") % filepath)
         try:
             fdata = util.readfile(filepath)
         except IOError as inst:
             raise error.Abort(_("cannot read narrowspecs from '%s': %s") %
                               (filepath, encoding.strtolocal(inst.strerror)))
 
         includes, excludes, profiles = sparse.parseconfig(ui, fdata, 'narrow')
         if profiles:
             raise error.Abort(_("cannot specify other files using '%include' in"
                                 " narrowspec"))
 
         narrowspec.validatepatterns(includes)
         narrowspec.validatepatterns(excludes)
 
         # narrowspec is passed so we should assume that user wants narrow clone
         opts['narrow'] = True
         opts['include'].extend(includes)
         opts['exclude'].extend(excludes)
 
     if opts['narrow']:
         def pullbundle2extraprepare_widen(orig, pullop, kwargs):
             orig(pullop, kwargs)
 
             if opts.get('depth'):
                 kwargs['depth'] = opts['depth']
         wrappedextraprepare = extensions.wrappedfunction(exchange,
             '_pullbundle2extraprepare', pullbundle2extraprepare_widen)
 
     with wrappedextraprepare:
         return orig(ui, repo, *args, **pycompat.strkwargs(opts))
 
 def pullnarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps pull command to allow modifying narrow spec."""
     wrappedextraprepare = util.nullcontextmanager()
     if repository.NARROW_REQUIREMENT in repo.requirements:
 
         def pullbundle2extraprepare_widen(orig, pullop, kwargs):
             orig(pullop, kwargs)
             if opts.get(r'depth'):
                 kwargs['depth'] = opts[r'depth']
         wrappedextraprepare = extensions.wrappedfunction(exchange,
             '_pullbundle2extraprepare', pullbundle2extraprepare_widen)
 
     with wrappedextraprepare:
         return orig(ui, repo, *args, **opts)
 
 def archivenarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps archive command to narrow the default includes."""
     if repository.NARROW_REQUIREMENT in repo.requirements:
         repo_includes, repo_excludes = repo.narrowpats
         includes = set(opts.get(r'include', []))
         excludes = set(opts.get(r'exclude', []))
         includes, excludes, unused_invalid = narrowspec.restrictpatterns(
             includes, excludes, repo_includes, repo_excludes)
         if includes:
             opts[r'include'] = includes
         if excludes:
             opts[r'exclude'] = excludes
     return orig(ui, repo, *args, **opts)
 
 def pullbundle2extraprepare(orig, pullop, kwargs):
     repo = pullop.repo
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return orig(pullop, kwargs)
 
     if wireprototypes.NARROWCAP not in pullop.remote.capabilities():
         raise error.Abort(_("server does not support narrow clones"))
     orig(pullop, kwargs)
     kwargs['narrow'] = True
     include, exclude = repo.narrowpats
     kwargs['oldincludepats'] = include
     kwargs['oldexcludepats'] = exclude
     if include:
         kwargs['includepats'] = include
     if exclude:
         kwargs['excludepats'] = exclude
     # calculate known nodes only in ellipses cases because in non-ellipses cases
     # we have all the nodes
     if wireprototypes.ELLIPSESCAP1 in pullop.remote.capabilities():
         kwargs['known'] = [node.hex(ctx.node()) for ctx in
                            repo.set('::%ln', pullop.common)
                            if ctx.node() != node.nullid]
         if not kwargs['known']:
             # Mercurial serializes an empty list as '' and deserializes it as
             # [''], so delete it instead to avoid handling the empty string on
             # the server.
             del kwargs['known']
 
 extensions.wrapfunction(exchange,'_pullbundle2extraprepare',
                         pullbundle2extraprepare)
 
 def _narrow(ui, repo, remote, commoninc, oldincludes, oldexcludes,
             newincludes, newexcludes, force):
     oldmatch = narrowspec.match(repo.root, oldincludes, oldexcludes)
     newmatch = narrowspec.match(repo.root, newincludes, newexcludes)
 
     # This is essentially doing "hg outgoing" to find all local-only
     # commits. We will then check that the local-only commits don't
     # have any changes to files that will be untracked.
     unfi = repo.unfiltered()
     outgoing = discovery.findcommonoutgoing(unfi, remote,
                                             commoninc=commoninc)
     ui.status(_('looking for local changes to affected paths\n'))
     localnodes = []
     for n in itertools.chain(outgoing.missing, outgoing.excluded):
         if any(oldmatch(f) and not newmatch(f) for f in unfi[n].files()):
             localnodes.append(n)
     revstostrip = unfi.revs('descendants(%ln)', localnodes)
     hiddenrevs = repoview.filterrevs(repo, 'visible')
     visibletostrip = list(repo.changelog.node(r)
                           for r in (revstostrip - hiddenrevs))
     if visibletostrip:
         ui.status(_('The following changeset(s) or their ancestors have '
                     'local changes not on the remote:\n'))
         maxnodes = 10
         if ui.verbose or len(visibletostrip) <= maxnodes:
             for n in visibletostrip:
                 ui.status('%s\n' % node.short(n))
         else:
             for n in visibletostrip[:maxnodes]:
                 ui.status('%s\n' % node.short(n))
             ui.status(_('...and %d more, use --verbose to list all\n') %
                       (len(visibletostrip) - maxnodes))
         if not force:
             raise error.Abort(_('local changes found'),
                               hint=_('use --force-delete-local-changes to '
                                      'ignore'))
 
     with ui.uninterruptible():
         if revstostrip:
             tostrip = [unfi.changelog.node(r) for r in revstostrip]
             if repo['.'].node() in tostrip:
                 # stripping working copy, so move to a different commit first
                 urev = max(repo.revs('(::%n) - %ln + null',
                                      repo['.'].node(), visibletostrip))
                 hg.clean(repo, urev)
             overrides = {('devel', 'strip-obsmarkers'): False}
             with ui.configoverride(overrides, 'narrow'):
                 repair.strip(ui, unfi, tostrip, topic='narrow')
 
         todelete = []
         for f, f2, size in repo.store.datafiles():
             if f.startswith('data/'):
                 file = f[5:-2]
                 if not newmatch(file):
                     todelete.append(f)
             elif f.startswith('meta/'):
                 dir = f[5:-13]
                 dirs = sorted(util.dirs({dir})) + [dir]
                 include = True
                 for d in dirs:
                     visit = newmatch.visitdir(d)
                     if not visit:
                         include = False
                         break
                     if visit == 'all':
                         break
                 if not include:
                     todelete.append(f)
 
         repo.destroying()
 
         with repo.transaction('narrowing'):
             # Update narrowspec before removing revlogs, so repo won't be
             # corrupt in case of crash
             repo.setnarrowpats(newincludes, newexcludes)
 
             for f in todelete:
                 ui.status(_('deleting %s\n') % f)
                 util.unlinkpath(repo.svfs.join(f))
                 repo.store.markremoved(f)
 
             narrowspec.updateworkingcopy(repo, assumeclean=True)
             narrowspec.copytoworkingcopy(repo)
 
         repo.destroyed()
 
 def _widen(ui, repo, remote, commoninc, oldincludes, oldexcludes,
            newincludes, newexcludes):
     # for now we assume that if a server has ellipses enabled, we will be
     # exchanging ellipses nodes. In future we should add ellipses as a client
     # side requirement (maybe) to distinguish a client is shallow or not and
     # then send that information to server whether we want ellipses or not.
     # Theoretically a non-ellipses repo should be able to use narrow
     # functionality from an ellipses enabled server
     remotecap = remote.capabilities()
     ellipsesremote = any(cap in remotecap
                          for cap in wireprototypes.SUPPORTED_ELLIPSESCAP)
 
     # check whether we are talking to a server which supports old version of
     # ellipses capabilities
     isoldellipses = (ellipsesremote and wireprototypes.ELLIPSESCAP1 in
                      remotecap and wireprototypes.ELLIPSESCAP not in remotecap)
 
     def pullbundle2extraprepare_widen(orig, pullop, kwargs):
         orig(pullop, kwargs)
         # The old{in,ex}cludepats have already been set by orig()
         kwargs['includepats'] = newincludes
         kwargs['excludepats'] = newexcludes
     wrappedextraprepare = extensions.wrappedfunction(exchange,
         '_pullbundle2extraprepare', pullbundle2extraprepare_widen)
 
     # define a function that narrowbundle2 can call after creating the
     # backup bundle, but before applying the bundle from the server
     def setnewnarrowpats():
         repo.setnarrowpats(newincludes, newexcludes)
     repo.setnewnarrowpats = setnewnarrowpats
     # silence the devel-warning of applying an empty changegroup
     overrides = {('devel', 'all-warnings'): False}
 
     common = commoninc[0]
     with ui.uninterruptible():
         if ellipsesremote:
             ds = repo.dirstate
             p1, p2 = ds.p1(), ds.p2()
             with ds.parentchange():
                 ds.setparents(node.nullid, node.nullid)
         if isoldellipses:
             with wrappedextraprepare:
                 exchange.pull(repo, remote, heads=common)
         else:
             known = []
             if ellipsesremote:
                 known = [node.hex(ctx.node()) for ctx in
                          repo.set('::%ln', common)
                          if ctx.node() != node.nullid]
             with remote.commandexecutor() as e:
                 bundle = e.callcommand('narrow_widen', {
                     'oldincludes': oldincludes,
                     'oldexcludes': oldexcludes,
                     'newincludes': newincludes,
                     'newexcludes': newexcludes,
                     'cgversion': '03',
                     'commonheads': common,
                     'known': known,
                     'ellipses': ellipsesremote,
                 }).result()
 
             trmanager = exchange.transactionmanager(repo, 'widen', remote.url())
             with trmanager, repo.ui.configoverride(overrides, 'widen'):
                 op = bundle2.bundleoperation(repo, trmanager.transaction,
                                              source='widen')
                 # TODO: we should catch error.Abort here
                 bundle2.processbundle(repo, bundle, op=op)
 
         if ellipsesremote:
             with ds.parentchange():
                 ds.setparents(p1, p2)
 
         with repo.transaction('widening'):
             repo.setnewnarrowpats()
             narrowspec.updateworkingcopy(repo)
             narrowspec.copytoworkingcopy(repo)
 
 # TODO(rdamazio): Make new matcher format and update description
 @command('tracked',
     [('', 'addinclude', [], _('new paths to include')),
      ('', 'removeinclude', [], _('old paths to no longer include')),
      ('', 'addexclude', [], _('new paths to exclude')),
      ('', 'import-rules', '', _('import narrowspecs from a file')),
      ('', 'removeexclude', [], _('old paths to no longer exclude')),
      ('', 'clear', False, _('whether to replace the existing narrowspec')),
      ('', 'force-delete-local-changes', False,
        _('forces deletion of local changes when narrowing')),
      ('', 'update-working-copy', False,
       _('update working copy when the store has changed')),
     ] + commands.remoteopts,
     _('[OPTIONS]... [REMOTE]'),
     inferrepo=True)
 def trackedcmd(ui, repo, remotepath=None, *pats, **opts):
     """show or change the current narrowspec
 
     With no argument, shows the current narrowspec entries, one per line. Each
     line will be prefixed with 'I' or 'X' for included or excluded patterns,
     respectively.
 
     The narrowspec is comprised of expressions to match remote files and/or
     directories that should be pulled into your client.
     The narrowspec has *include* and *exclude* expressions, with excludes always
     trumping includes: that is, if a file matches an exclude expression, it will
     be excluded even if it also matches an include expression.
     Excluding files that were never included has no effect.
 
     Each included or excluded entry is in the format described by
     'hg help patterns'.
 
     The options allow you to add or remove included and excluded expressions.
 
     If --clear is specified, then all previous includes and excludes are DROPPED
     and replaced by the new ones specified to --addinclude and --addexclude.
     If --clear is specified without any further options, the narrowspec will be
     empty and will not match any files.
 
     --import-rules accepts a path to a file containing rules, allowing you to
     add --addinclude, --addexclude rules in bulk. Like the other include and
     exclude switches, the changes are applied immediately.
     """
     opts = pycompat.byteskwargs(opts)
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         raise error.Abort(_('the tracked command is only supported on '
                             'repositories cloned with --narrow'))
 
     # Before supporting, decide whether it "hg tracked --clear" should mean
     # tracking no paths or all paths.
     if opts['clear']:
         raise error.Abort(_('the --clear option is not yet supported'))
 
     # import rules from a file
     newrules = opts.get('import_rules')
     if newrules:
         try:
             filepath = os.path.join(encoding.getcwd(), newrules)
             fdata = util.readfile(filepath)
         except IOError as inst:
             raise error.Abort(_("cannot read narrowspecs from '%s': %s") %
                               (filepath, encoding.strtolocal(inst.strerror)))
         includepats, excludepats, profiles = sparse.parseconfig(ui, fdata,
                                                                 'narrow')
         if profiles:
             raise error.Abort(_("including other spec files using '%include' "
                                 "is not supported in narrowspec"))
         opts['addinclude'].extend(includepats)
         opts['addexclude'].extend(excludepats)
 
     addedincludes = narrowspec.parsepatterns(opts['addinclude'])
     removedincludes = narrowspec.parsepatterns(opts['removeinclude'])
     addedexcludes = narrowspec.parsepatterns(opts['addexclude'])
     removedexcludes = narrowspec.parsepatterns(opts['removeexclude'])
 
     update_working_copy = opts['update_working_copy']
     only_show = not (addedincludes or removedincludes or addedexcludes or
                      removedexcludes or newrules or update_working_copy)
 
     oldincludes, oldexcludes = repo.narrowpats
 
     # filter the user passed additions and deletions into actual additions and
     # deletions of excludes and includes
     addedincludes -= oldincludes
     removedincludes &= oldincludes
     addedexcludes -= oldexcludes
     removedexcludes &= oldexcludes
 
     widening = addedincludes or removedexcludes
     narrowing = removedincludes or addedexcludes
 
     # Only print the current narrowspec.
     if only_show:
         ui.pager('tracked')
         fm = ui.formatter('narrow', opts)
         for i in sorted(oldincludes):
             fm.startitem()
             fm.write('status', '%s ', 'I', label='narrow.included')
             fm.write('pat', '%s\n', i, label='narrow.included')
         for i in sorted(oldexcludes):
             fm.startitem()
             fm.write('status', '%s ', 'X', label='narrow.excluded')
             fm.write('pat', '%s\n', i, label='narrow.excluded')
         fm.end()
         return 0
 
     if update_working_copy:
         with repo.wlock(), repo.lock(), repo.transaction('narrow-wc'):
             narrowspec.updateworkingcopy(repo)
             narrowspec.copytoworkingcopy(repo)
         return 0
 
     if not widening and not narrowing:
         ui.status(_("nothing to widen or narrow\n"))
         return 0
 
     with repo.wlock(), repo.lock():
         cmdutil.bailifchanged(repo)
 
         # Find the revisions we have in common with the remote. These will
         # be used for finding local-only changes for narrowing. They will
         # also define the set of revisions to update for widening.
         remotepath = ui.expandpath(remotepath or 'default')
         url, branches = hg.parseurl(remotepath)
         ui.status(_('comparing with %s\n') % util.hidepassword(url))
         remote = hg.peer(repo, opts, url)
 
         # check narrow support before doing anything if widening needs to be
         # performed. In future we should also abort if client is ellipses and
         # server does not support ellipses
         if widening and wireprototypes.NARROWCAP not in remote.capabilities():
             raise error.Abort(_("server does not support narrow clones"))
 
         commoninc = discovery.findcommonincoming(repo, remote)
 
         if narrowing:
             newincludes = oldincludes - removedincludes
             newexcludes = oldexcludes | addedexcludes
             _narrow(ui, repo, remote, commoninc, oldincludes, oldexcludes,
                     newincludes, newexcludes,
                     opts['force_delete_local_changes'])
             # _narrow() updated the narrowspec and _widen() below needs to
             # use the updated values as its base (otherwise removed includes
             # and addedexcludes will be lost in the resulting narrowspec)
             oldincludes = newincludes
             oldexcludes = newexcludes
 
         if widening:
             newincludes = oldincludes | addedincludes
             newexcludes = oldexcludes - removedexcludes
             _widen(ui, repo, remote, commoninc, oldincludes, oldexcludes,
                     newincludes, newexcludes)
 
     return 0

hgext/sqlitestore.py

@@ -1,1174 +1,1176
 # sqlitestore.py - Storage backend that uses SQLite
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """store repository data in SQLite (EXPERIMENTAL)
 
 The sqlitestore extension enables the storage of repository data in SQLite.
 
 This extension is HIGHLY EXPERIMENTAL. There are NO BACKWARDS COMPATIBILITY
 GUARANTEES. This means that repositories created with this extension may
 only be usable with the exact version of this extension/Mercurial that was
 used. The extension attempts to enforce this in order to prevent repository
 corruption.
 
 In addition, several features are not yet supported or have known bugs:
 
 * Only some data is stored in SQLite. Changeset, manifest, and other repository
   data is not yet stored in SQLite.
 * Transactions are not robust. If the process is aborted at the right time
   during transaction close/rollback, the repository could be in an inconsistent
   state. This problem will diminish once all repository data is tracked by
   SQLite.
 * Bundle repositories do not work (the ability to use e.g.
   `hg -R <bundle-file> log` to automatically overlay a bundle on top of the
   existing repository).
 * Various other features don't work.
 
 This extension should work for basic clone/pull, update, and commit workflows.
 Some history rewriting operations may fail due to lack of support for bundle
 repositories.
 
 To use, activate the extension and set the ``storage.new-repo-backend`` config
 option to ``sqlite`` to enable new repositories to use SQLite for storage.
 """
 
 # To run the test suite with repos using SQLite by default, execute the
 # following:
 #
 # HGREPOFEATURES="sqlitestore" run-tests.py \
 #     --extra-config-opt extensions.sqlitestore= \
 #     --extra-config-opt storage.new-repo-backend=sqlite
 
 from __future__ import absolute_import
 
 import hashlib
 import sqlite3
 import struct
 import threading
 import zlib
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     nullrev,
     short,
 )
 from mercurial.thirdparty import (
     attr,
 )
 from mercurial import (
     ancestor,
     dagop,
     encoding,
     error,
     extensions,
     localrepo,
     mdiff,
     pycompat,
     registrar,
-    repository,
     util,
     verify,
 )
+from mercurial.interfaces import (
+    repository,
+)
 from mercurial.utils import (
     interfaceutil,
     storageutil,
 )
 
 try:
     from mercurial import zstd
     zstd.__version__
 except ImportError:
     zstd = None
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 # experimental config: storage.sqlite.compression
 configitem('storage', 'sqlite.compression',
            default='zstd' if zstd else 'zlib',
            experimental=True)
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 REQUIREMENT = b'exp-sqlite-001'
 REQUIREMENT_ZSTD = b'exp-sqlite-comp-001=zstd'
 REQUIREMENT_ZLIB = b'exp-sqlite-comp-001=zlib'
 REQUIREMENT_NONE = b'exp-sqlite-comp-001=none'
 REQUIREMENT_SHALLOW_FILES = b'exp-sqlite-shallow-files'
 
 CURRENT_SCHEMA_VERSION = 1
 
 COMPRESSION_NONE = 1
 COMPRESSION_ZSTD = 2
 COMPRESSION_ZLIB = 3
 
 FLAG_CENSORED = 1
 FLAG_MISSING_P1 = 2
 FLAG_MISSING_P2 = 4
 
 CREATE_SCHEMA = [
     # Deltas are stored as content-indexed blobs.
     # compression column holds COMPRESSION_* constant for how the
     # delta is encoded.
 
     r'CREATE TABLE delta ('
     r'    id INTEGER PRIMARY KEY, '
     r'    compression INTEGER NOT NULL, '
     r'    hash BLOB UNIQUE ON CONFLICT ABORT, '
     r'    delta BLOB NOT NULL '
     r')',
 
     # Tracked paths are denormalized to integers to avoid redundant
     # storage of the path name.
     r'CREATE TABLE filepath ('
     r'    id INTEGER PRIMARY KEY, '
     r'    path BLOB NOT NULL '
     r')',
 
     r'CREATE UNIQUE INDEX filepath_path '
     r'    ON filepath (path)',
 
     # We have a single table for all file revision data.
     # Each file revision is uniquely described by a (path, rev) and
     # (path, node).
     #
     # Revision data is stored as a pointer to the delta producing this
     # revision and the file revision whose delta should be applied before
     # that one. One can reconstruct the delta chain by recursively following
     # the delta base revision pointers until one encounters NULL.
     #
     # flags column holds bitwise integer flags controlling storage options.
     # These flags are defined by the FLAG_* constants.
     r'CREATE TABLE fileindex ('
     r'    id INTEGER PRIMARY KEY, '
     r'    pathid INTEGER REFERENCES filepath(id), '
     r'    revnum INTEGER NOT NULL, '
     r'    p1rev INTEGER NOT NULL, '
     r'    p2rev INTEGER NOT NULL, '
     r'    linkrev INTEGER NOT NULL, '
     r'    flags INTEGER NOT NULL, '
     r'    deltaid INTEGER REFERENCES delta(id), '
     r'    deltabaseid INTEGER REFERENCES fileindex(id), '
     r'    node BLOB NOT NULL '
     r')',
 
     r'CREATE UNIQUE INDEX fileindex_pathrevnum '
     r'    ON fileindex (pathid, revnum)',
 
     r'CREATE UNIQUE INDEX fileindex_pathnode '
     r'    ON fileindex (pathid, node)',
 
     # Provide a view over all file data for convenience.
     r'CREATE VIEW filedata AS '
     r'SELECT '
     r'    fileindex.id AS id, '
     r'    filepath.id AS pathid, '
     r'    filepath.path AS path, '
     r'    fileindex.revnum AS revnum, '
     r'    fileindex.node AS node, '
     r'    fileindex.p1rev AS p1rev, '
     r'    fileindex.p2rev AS p2rev, '
     r'    fileindex.linkrev AS linkrev, '
     r'    fileindex.flags AS flags, '
     r'    fileindex.deltaid AS deltaid, '
     r'    fileindex.deltabaseid AS deltabaseid '
     r'FROM filepath, fileindex '
     r'WHERE fileindex.pathid=filepath.id',
 
     r'PRAGMA user_version=%d' % CURRENT_SCHEMA_VERSION,
 ]
 
 def resolvedeltachain(db, pathid, node, revisioncache,
                       stoprids, zstddctx=None):
     """Resolve a delta chain for a file node."""
 
     # TODO the "not in ({stops})" here is possibly slowing down the query
     # because it needs to perform the lookup on every recursive invocation.
     # This could possibly be faster if we created a temporary query with
     # baseid "poisoned" to null and limited the recursive filter to
     # "is not null".
     res = db.execute(
         r'WITH RECURSIVE '
         r'    deltachain(deltaid, baseid) AS ('
         r'        SELECT deltaid, deltabaseid FROM fileindex '
         r'            WHERE pathid=? AND node=? '
         r'        UNION ALL '
         r'        SELECT fileindex.deltaid, deltabaseid '
         r'            FROM fileindex, deltachain '
         r'            WHERE '
         r'                fileindex.id=deltachain.baseid '
         r'                AND deltachain.baseid IS NOT NULL '
         r'                AND fileindex.id NOT IN ({stops}) '
         r'    ) '
         r'SELECT deltachain.baseid, compression, delta '
         r'FROM deltachain, delta '
         r'WHERE delta.id=deltachain.deltaid'.format(
             stops=r','.join([r'?'] * len(stoprids))),
         tuple([pathid, node] + list(stoprids.keys())))
 
     deltas = []
     lastdeltabaseid = None
 
     for deltabaseid, compression, delta in res:
         lastdeltabaseid = deltabaseid
 
         if compression == COMPRESSION_ZSTD:
             delta = zstddctx.decompress(delta)
         elif compression == COMPRESSION_NONE:
             delta = delta
         elif compression == COMPRESSION_ZLIB:
             delta = zlib.decompress(delta)
         else:
             raise SQLiteStoreError('unhandled compression type: %d' %
                                    compression)
 
         deltas.append(delta)
 
     if lastdeltabaseid in stoprids:
         basetext = revisioncache[stoprids[lastdeltabaseid]]
     else:
         basetext = deltas.pop()
 
     deltas.reverse()
     fulltext = mdiff.patches(basetext, deltas)
 
     # SQLite returns buffer instances for blob columns on Python 2. This
     # type can propagate through the delta application layer. Because
     # downstream callers assume revisions are bytes, cast as needed.
     if not isinstance(fulltext, bytes):
         fulltext = bytes(delta)
 
     return fulltext
 
 def insertdelta(db, compression, hash, delta):
     try:
         return db.execute(
             r'INSERT INTO delta (compression, hash, delta) '
             r'VALUES (?, ?, ?)',
             (compression, hash, delta)).lastrowid
     except sqlite3.IntegrityError:
         return db.execute(
             r'SELECT id FROM delta WHERE hash=?',
             (hash,)).fetchone()[0]
 
 class SQLiteStoreError(error.StorageError):
     pass
 
 @attr.s
 class revisionentry(object):
     rid = attr.ib()
     rev = attr.ib()
     node = attr.ib()
     p1rev = attr.ib()
     p2rev = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     linkrev = attr.ib()
     flags = attr.ib()
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class sqliterevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     linknode = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class sqliteproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.ifilestorage)
 class sqlitefilestore(object):
     """Implements storage for an individual tracked path."""
 
     def __init__(self, db, path, compression):
         self._db = db
         self._path = path
 
         self._pathid = None
 
         # revnum -> node
         self._revtonode = {}
         # node -> revnum
         self._nodetorev = {}
         # node -> data structure
         self._revisions = {}
 
         self._revisioncache = util.lrucachedict(10)
 
         self._compengine = compression
 
         if compression == 'zstd':
             self._cctx = zstd.ZstdCompressor(level=3)
             self._dctx = zstd.ZstdDecompressor()
         else:
             self._cctx = None
             self._dctx = None
 
         self._refreshindex()
 
     def _refreshindex(self):
         self._revtonode = {}
         self._nodetorev = {}
         self._revisions = {}
 
         res = list(self._db.execute(
             r'SELECT id FROM filepath WHERE path=?', (self._path,)))
 
         if not res:
             self._pathid = None
             return
 
         self._pathid = res[0][0]
 
         res = self._db.execute(
             r'SELECT id, revnum, node, p1rev, p2rev, linkrev, flags '
             r'FROM fileindex '
             r'WHERE pathid=? '
             r'ORDER BY revnum ASC',
             (self._pathid,))
 
         for i, row in enumerate(res):
             rid, rev, node, p1rev, p2rev, linkrev, flags = row
 
             if i != rev:
                 raise SQLiteStoreError(_('sqlite database has inconsistent '
                                          'revision numbers'))
 
             if p1rev == nullrev:
                 p1node = nullid
             else:
                 p1node = self._revtonode[p1rev]
 
             if p2rev == nullrev:
                 p2node = nullid
             else:
                 p2node = self._revtonode[p2rev]
 
             entry = revisionentry(
                 rid=rid,
                 rev=rev,
                 node=node,
                 p1rev=p1rev,
                 p2rev=p2rev,
                 p1node=p1node,
                 p2node=p2node,
                 linkrev=linkrev,
                 flags=flags)
 
             self._revtonode[rev] = node
             self._nodetorev[node] = rev
             self._revisions[node] = entry
 
     # Start of ifileindex interface.
 
     def __len__(self):
         return len(self._revisions)
 
     def __iter__(self):
         return iter(pycompat.xrange(len(self._revisions)))
 
     def hasnode(self, node):
         if node == nullid:
             return False
 
         return node in self._nodetorev
 
     def revs(self, start=0, stop=None):
         return storageutil.iterrevs(len(self._revisions), start=start,
                                     stop=stop)
 
     def parents(self, node):
         if node == nullid:
             return nullid, nullid
 
         if node not in self._revisions:
             raise error.LookupError(node, self._path, _('no node'))
 
         entry = self._revisions[node]
         return entry.p1node, entry.p2node
 
     def parentrevs(self, rev):
         if rev == nullrev:
             return nullrev, nullrev
 
         if rev not in self._revtonode:
             raise IndexError(rev)
 
         entry = self._revisions[self._revtonode[rev]]
         return entry.p1rev, entry.p2rev
 
     def rev(self, node):
         if node == nullid:
             return nullrev
 
         if node not in self._nodetorev:
             raise error.LookupError(node, self._path, _('no node'))
 
         return self._nodetorev[node]
 
     def node(self, rev):
         if rev == nullrev:
             return nullid
 
         if rev not in self._revtonode:
             raise IndexError(rev)
 
         return self._revtonode[rev]
 
     def lookup(self, node):
         return storageutil.fileidlookup(self, node, self._path)
 
     def linkrev(self, rev):
         if rev == nullrev:
             return nullrev
 
         if rev not in self._revtonode:
             raise IndexError(rev)
 
         entry = self._revisions[self._revtonode[rev]]
         return entry.linkrev
 
     def iscensored(self, rev):
         if rev == nullrev:
             return False
 
         if rev not in self._revtonode:
             raise IndexError(rev)
 
         return self._revisions[self._revtonode[rev]].flags & FLAG_CENSORED
 
     def commonancestorsheads(self, node1, node2):
         rev1 = self.rev(node1)
         rev2 = self.rev(node2)
 
         ancestors = ancestor.commonancestorsheads(self.parentrevs, rev1, rev2)
         return pycompat.maplist(self.node, ancestors)
 
     def descendants(self, revs):
         # TODO we could implement this using a recursive SQL query, which
         # might be faster.
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def heads(self, start=None, stop=None):
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
 
         startrev = self.rev(start) if start is not None else nullrev
         stoprevs = {self.rev(n) for n in stop or []}
 
         revs = dagop.headrevssubset(self.revs, self.parentrevs,
                                     startrev=startrev, stoprevs=stoprevs)
 
         return [self.node(rev) for rev in revs]
 
     def children(self, node):
         rev = self.rev(node)
 
         res = self._db.execute(
             r'SELECT'
             r'  node '
             r'  FROM filedata '
             r'  WHERE path=? AND (p1rev=? OR p2rev=?) '
             r'  ORDER BY revnum ASC',
             (self._path, rev, rev))
 
         return [row[0] for row in res]
 
     # End of ifileindex interface.
 
     # Start of ifiledata interface.
 
     def size(self, rev):
         if rev == nullrev:
             return 0
 
         if rev not in self._revtonode:
             raise IndexError(rev)
 
         node = self._revtonode[rev]
 
         if self.renamed(node):
             return len(self.read(node))
 
         return len(self.revision(node))
 
     def revision(self, node, raw=False, _verifyhash=True):
         if node in (nullid, nullrev):
             return b''
 
         if isinstance(node, int):
             node = self.node(node)
 
         if node not in self._nodetorev:
             raise error.LookupError(node, self._path, _('no node'))
 
         if node in self._revisioncache:
             return self._revisioncache[node]
 
         # Because we have a fulltext revision cache, we are able to
         # short-circuit delta chain traversal and decompression as soon as
         # we encounter a revision in the cache.
 
         stoprids = {self._revisions[n].rid: n
                     for n in self._revisioncache}
 
         if not stoprids:
             stoprids[-1] = None
 
         fulltext = resolvedeltachain(self._db, self._pathid, node,
                                      self._revisioncache, stoprids,
                                      zstddctx=self._dctx)
 
         # Don't verify hashes if parent nodes were rewritten, as the hash
         # wouldn't verify.
         if self._revisions[node].flags & (FLAG_MISSING_P1 | FLAG_MISSING_P2):
             _verifyhash = False
 
         if _verifyhash:
             self._checkhash(fulltext, node)
             self._revisioncache[node] = fulltext
 
         return fulltext
 
     def rawdata(self, *args, **kwargs):
         return self.revision(*args, **kwargs)
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     def cmp(self, node, fulltext):
         return not storageutil.filedataequivalent(self, node, fulltext)
 
     def emitrevisions(self, nodes, nodesorder=None, revisiondata=False,
                       assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         if nodesorder not in ('nodes', 'storage', 'linear', None):
             raise error.ProgrammingError('unhandled value for nodesorder: %s' %
                                          nodesorder)
 
         nodes = [n for n in nodes if n != nullid]
 
         if not nodes:
             return
 
         # TODO perform in a single query.
         res = self._db.execute(
             r'SELECT revnum, deltaid FROM fileindex '
             r'WHERE pathid=? '
             r'    AND node in (%s)' % (r','.join([r'?'] * len(nodes))),
             tuple([self._pathid] + nodes))
 
         deltabases = {}
 
         for rev, deltaid in res:
             res = self._db.execute(
                 r'SELECT revnum from fileindex WHERE pathid=? AND deltaid=?',
                 (self._pathid, deltaid))
             deltabases[rev] = res.fetchone()[0]
 
         # TODO define revdifffn so we can use delta from storage.
         for delta in storageutil.emitrevisions(
             self, nodes, nodesorder, sqliterevisiondelta,
             deltaparentfn=deltabases.__getitem__,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode):
 
             yield delta
 
     # End of ifiledata interface.
 
     # Start of ifilemutation interface.
 
     def add(self, filedata, meta, transaction, linkrev, p1, p2):
         if meta or filedata.startswith(b'\x01\n'):
             filedata = storageutil.packmeta(meta, filedata)
 
         return self.addrevision(filedata, transaction, linkrev, p1, p2)
 
     def addrevision(self, revisiondata, transaction, linkrev, p1, p2, node=None,
                     flags=0, cachedelta=None):
         if flags:
             raise SQLiteStoreError(_('flags not supported on revisions'))
 
         validatehash = node is not None
         node = node or storageutil.hashrevisionsha1(revisiondata, p1, p2)
 
         if validatehash:
             self._checkhash(revisiondata, node, p1, p2)
 
         if node in self._nodetorev:
             return node
 
         node = self._addrawrevision(node, revisiondata, transaction, linkrev,
                                     p1, p2)
 
         self._revisioncache[node] = revisiondata
         return node
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None,
                  maybemissingparents=False):
         nodes = []
 
         for node, p1, p2, linknode, deltabase, delta, wireflags in deltas:
             storeflags = 0
 
             if wireflags & repository.REVISION_FLAG_CENSORED:
                 storeflags |= FLAG_CENSORED
 
             if wireflags & ~repository.REVISION_FLAG_CENSORED:
                 raise SQLiteStoreError('unhandled revision flag')
 
             if maybemissingparents:
                 if p1 != nullid and not self.hasnode(p1):
                     p1 = nullid
                     storeflags |= FLAG_MISSING_P1
 
                 if p2 != nullid and not self.hasnode(p2):
                     p2 = nullid
                     storeflags |= FLAG_MISSING_P2
 
             baserev = self.rev(deltabase)
 
             # If base is censored, delta must be full replacement in a single
             # patch operation.
             if baserev != nullrev and self.iscensored(baserev):
                 hlen = struct.calcsize('>lll')
                 oldlen = len(self.rawdata(deltabase, _verifyhash=False))
                 newlen = len(delta) - hlen
 
                 if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                     raise error.CensoredBaseError(self._path,
                                                   deltabase)
 
             if (not (storeflags & FLAG_CENSORED)
                 and storageutil.deltaiscensored(
                     delta, baserev, lambda x: len(self.rawdata(x)))):
                 storeflags |= FLAG_CENSORED
 
             linkrev = linkmapper(linknode)
 
             nodes.append(node)
 
             if node in self._revisions:
                 # Possibly reset parents to make them proper.
                 entry = self._revisions[node]
 
                 if entry.flags & FLAG_MISSING_P1 and p1 != nullid:
                     entry.p1node = p1
                     entry.p1rev = self._nodetorev[p1]
                     entry.flags &= ~FLAG_MISSING_P1
 
                     self._db.execute(
                         r'UPDATE fileindex SET p1rev=?, flags=? '
                         r'WHERE id=?',
                         (self._nodetorev[p1], entry.flags, entry.rid))
 
                 if entry.flags & FLAG_MISSING_P2 and p2 != nullid:
                     entry.p2node = p2
                     entry.p2rev = self._nodetorev[p2]
                     entry.flags &= ~FLAG_MISSING_P2
 
                     self._db.execute(
                         r'UPDATE fileindex SET p2rev=?, flags=? '
                         r'WHERE id=?',
                         (self._nodetorev[p1], entry.flags, entry.rid))
 
                 continue
 
             if deltabase == nullid:
                 text = mdiff.patch(b'', delta)
                 storedelta = None
             else:
                 text = None
                 storedelta = (deltabase, delta)
 
             self._addrawrevision(node, text, transaction, linkrev, p1, p2,
                                  storedelta=storedelta, flags=storeflags)
 
             if addrevisioncb:
                 addrevisioncb(self, node)
 
         return nodes
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         # This restriction is cargo culted from revlogs and makes no sense for
         # SQLite, since columns can be resized at will.
         if len(tombstone) > len(self.rawdata(censornode)):
             raise error.Abort(_('censor tombstone must be no longer than '
                                 'censored data'))
 
         # We need to replace the censored revision's data with the tombstone.
         # But replacing that data will have implications for delta chains that
         # reference it.
         #
         # While "better," more complex strategies are possible, we do something
         # simple: we find delta chain children of the censored revision and we
         # replace those incremental deltas with fulltexts of their corresponding
         # revision. Then we delete the now-unreferenced delta and original
         # revision and insert a replacement.
 
         # Find the delta to be censored.
         censoreddeltaid = self._db.execute(
             r'SELECT deltaid FROM fileindex WHERE id=?',
             (self._revisions[censornode].rid,)).fetchone()[0]
 
         # Find all its delta chain children.
         # TODO once we support storing deltas for !files, we'll need to look
         # for those delta chains too.
         rows = list(self._db.execute(
             r'SELECT id, pathid, node FROM fileindex '
             r'WHERE deltabaseid=? OR deltaid=?',
             (censoreddeltaid, censoreddeltaid)))
 
         for row in rows:
             rid, pathid, node = row
 
             fulltext = resolvedeltachain(self._db, pathid, node, {}, {-1: None},
                                          zstddctx=self._dctx)
 
             deltahash = hashlib.sha1(fulltext).digest()
 
             if self._compengine == 'zstd':
                 deltablob = self._cctx.compress(fulltext)
                 compression = COMPRESSION_ZSTD
             elif self._compengine == 'zlib':
                 deltablob = zlib.compress(fulltext)
                 compression = COMPRESSION_ZLIB
             elif self._compengine == 'none':
                 deltablob = fulltext
                 compression = COMPRESSION_NONE
             else:
                 raise error.ProgrammingError('unhandled compression engine: %s'
                                              % self._compengine)
 
             if len(deltablob) >= len(fulltext):
                 deltablob = fulltext
                 compression = COMPRESSION_NONE
 
             deltaid = insertdelta(self._db, compression, deltahash, deltablob)
 
             self._db.execute(
                 r'UPDATE fileindex SET deltaid=?, deltabaseid=NULL '
                 r'WHERE id=?', (deltaid, rid))
 
         # Now create the tombstone delta and replace the delta on the censored
         # node.
         deltahash = hashlib.sha1(tombstone).digest()
         tombstonedeltaid = insertdelta(self._db, COMPRESSION_NONE,
                                        deltahash, tombstone)
 
         flags = self._revisions[censornode].flags
         flags |= FLAG_CENSORED
 
         self._db.execute(
             r'UPDATE fileindex SET flags=?, deltaid=?, deltabaseid=NULL '
             r'WHERE pathid=? AND node=?',
             (flags, tombstonedeltaid, self._pathid, censornode))
 
         self._db.execute(
             r'DELETE FROM delta WHERE id=?', (censoreddeltaid,))
 
         self._refreshindex()
         self._revisioncache.clear()
 
     def getstrippoint(self, minlink):
         return storageutil.resolvestripinfo(minlink, len(self) - 1,
                                             [self.rev(n) for n in self.heads()],
                                             self.linkrev,
                                             self.parentrevs)
 
     def strip(self, minlink, transaction):
         if not len(self):
             return
 
         rev, _ignored = self.getstrippoint(minlink)
 
         if rev == len(self):
             return
 
         for rev in self.revs(rev):
             self._db.execute(
                 r'DELETE FROM fileindex WHERE pathid=? AND node=?',
                 (self._pathid, self.node(rev)))
 
         # TODO how should we garbage collect data in delta table?
 
         self._refreshindex()
 
     # End of ifilemutation interface.
 
     # Start of ifilestorage interface.
 
     def files(self):
         return []
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         d = {}
 
         if exclusivefiles:
             d['exclusivefiles'] = []
 
         if sharedfiles:
             # TODO list sqlite file(s) here.
             d['sharedfiles'] = []
 
         if revisionscount:
             d['revisionscount'] = len(self)
 
         if trackedsize:
             d['trackedsize'] = sum(len(self.revision(node))
                                        for node in self._nodetorev)
 
         if storedsize:
             # TODO implement this?
             d['storedsize'] = None
 
         return d
 
     def verifyintegrity(self, state):
         state['skipread'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             try:
                 self.revision(node)
             except Exception as e:
                 yield sqliteproblem(
                     error=_('unpacking %s: %s') % (short(node), e),
                     node=node)
 
                 state['skipread'].add(node)
 
     # End of ifilestorage interface.
 
     def _checkhash(self, fulltext, node, p1=None, p2=None):
         if p1 is None and p2 is None:
             p1, p2 = self.parents(node)
 
         if node == storageutil.hashrevisionsha1(fulltext, p1, p2):
             return
 
         try:
             del self._revisioncache[node]
         except KeyError:
             pass
 
         if storageutil.iscensoredtext(fulltext):
             raise error.CensoredNodeError(self._path, node, fulltext)
 
         raise SQLiteStoreError(_('integrity check failed on %s') %
                                self._path)
 
     def _addrawrevision(self, node, revisiondata, transaction, linkrev,
                         p1, p2, storedelta=None, flags=0):
         if self._pathid is None:
             res = self._db.execute(
                 r'INSERT INTO filepath (path) VALUES (?)', (self._path,))
             self._pathid = res.lastrowid
 
         # For simplicity, always store a delta against p1.
         # TODO we need a lot more logic here to make behavior reasonable.
 
         if storedelta:
             deltabase, delta = storedelta
 
             if isinstance(deltabase, int):
                 deltabase = self.node(deltabase)
 
         else:
             assert revisiondata is not None
             deltabase = p1
 
             if deltabase == nullid:
                 delta = revisiondata
             else:
                 delta = mdiff.textdiff(self.revision(self.rev(deltabase)),
                                        revisiondata)
 
         # File index stores a pointer to its delta and the parent delta.
         # The parent delta is stored via a pointer to the fileindex PK.
         if deltabase == nullid:
             baseid = None
         else:
             baseid = self._revisions[deltabase].rid
 
         # Deltas are stored with a hash of their content. This allows
         # us to de-duplicate. The table is configured to ignore conflicts
         # and it is faster to just insert and silently noop than to look
         # first.
         deltahash = hashlib.sha1(delta).digest()
 
         if self._compengine == 'zstd':
             deltablob = self._cctx.compress(delta)
             compression = COMPRESSION_ZSTD
         elif self._compengine == 'zlib':
             deltablob = zlib.compress(delta)
             compression = COMPRESSION_ZLIB
         elif self._compengine == 'none':
             deltablob = delta
             compression = COMPRESSION_NONE
         else:
             raise error.ProgrammingError('unhandled compression engine: %s' %
                                          self._compengine)
 
         # Don't store compressed data if it isn't practical.
         if len(deltablob) >= len(delta):
             deltablob = delta
             compression = COMPRESSION_NONE
 
         deltaid = insertdelta(self._db, compression, deltahash, deltablob)
 
         rev = len(self)
 
         if p1 == nullid:
             p1rev = nullrev
         else:
             p1rev = self._nodetorev[p1]
 
         if p2 == nullid:
             p2rev = nullrev
         else:
             p2rev = self._nodetorev[p2]
 
         rid = self._db.execute(
             r'INSERT INTO fileindex ('
             r'    pathid, revnum, node, p1rev, p2rev, linkrev, flags, '
             r'    deltaid, deltabaseid) '
             r'    VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)',
             (self._pathid, rev, node, p1rev, p2rev, linkrev, flags,
              deltaid, baseid)
         ).lastrowid
 
         entry = revisionentry(
             rid=rid,
             rev=rev,
             node=node,
             p1rev=p1rev,
             p2rev=p2rev,
             p1node=p1,
             p2node=p2,
             linkrev=linkrev,
             flags=flags)
 
         self._nodetorev[node] = rev
         self._revtonode[rev] = node
         self._revisions[node] = entry
 
         return node
 
 class sqliterepository(localrepo.localrepository):
     def cancopy(self):
         return False
 
     def transaction(self, *args, **kwargs):
         current = self.currenttransaction()
 
         tr = super(sqliterepository, self).transaction(*args, **kwargs)
 
         if current:
             return tr
 
         self._dbconn.execute(r'BEGIN TRANSACTION')
 
         def committransaction(_):
             self._dbconn.commit()
 
         tr.addfinalize('sqlitestore', committransaction)
 
         return tr
 
     @property
     def _dbconn(self):
         # SQLite connections can only be used on the thread that created
         # them. In most cases, this "just works." However, hgweb uses
         # multiple threads.
         tid = threading.current_thread().ident
 
         if self._db:
             if self._db[0] == tid:
                 return self._db[1]
 
         db = makedb(self.svfs.join('db.sqlite'))
         self._db = (tid, db)
 
         return db
 
 def makedb(path):
     """Construct a database handle for a database at path."""
 
     db = sqlite3.connect(encoding.strfromlocal(path))
     db.text_factory = bytes
 
     res = db.execute(r'PRAGMA user_version').fetchone()[0]
 
     # New database.
     if res == 0:
         for statement in CREATE_SCHEMA:
             db.execute(statement)
 
         db.commit()
 
     elif res == CURRENT_SCHEMA_VERSION:
         pass
 
     else:
         raise error.Abort(_('sqlite database has unrecognized version'))
 
     db.execute(r'PRAGMA journal_mode=WAL')
 
     return db
 
 def featuresetup(ui, supported):
     supported.add(REQUIREMENT)
 
     if zstd:
         supported.add(REQUIREMENT_ZSTD)
 
     supported.add(REQUIREMENT_ZLIB)
     supported.add(REQUIREMENT_NONE)
     supported.add(REQUIREMENT_SHALLOW_FILES)
     supported.add(repository.NARROW_REQUIREMENT)
 
 def newreporequirements(orig, ui, createopts):
     if createopts['backend'] != 'sqlite':
         return orig(ui, createopts)
 
     # This restriction can be lifted once we have more confidence.
     if 'sharedrepo' in createopts:
         raise error.Abort(_('shared repositories not supported with SQLite '
                             'store'))
 
     # This filtering is out of an abundance of caution: we want to ensure
     # we honor creation options and we do that by annotating exactly the
     # creation options we recognize.
     known = {
         'narrowfiles',
         'backend',
         'shallowfilestore',
     }
 
     unsupported = set(createopts) - known
     if unsupported:
         raise error.Abort(_('SQLite store does not support repo creation '
                             'option: %s') % ', '.join(sorted(unsupported)))
 
     # Since we're a hybrid store that still relies on revlogs, we fall back
     # to using the revlogv1 backend's storage requirements then adding our
     # own requirement.
     createopts['backend'] = 'revlogv1'
     requirements = orig(ui, createopts)
     requirements.add(REQUIREMENT)
 
     compression = ui.config('storage', 'sqlite.compression')
 
     if compression == 'zstd' and not zstd:
         raise error.Abort(_('storage.sqlite.compression set to "zstd" but '
                             'zstandard compression not available to this '
                             'Mercurial install'))
 
     if compression == 'zstd':
         requirements.add(REQUIREMENT_ZSTD)
     elif compression == 'zlib':
         requirements.add(REQUIREMENT_ZLIB)
     elif compression == 'none':
         requirements.add(REQUIREMENT_NONE)
     else:
         raise error.Abort(_('unknown compression engine defined in '
                             'storage.sqlite.compression: %s') % compression)
 
     if createopts.get('shallowfilestore'):
         requirements.add(REQUIREMENT_SHALLOW_FILES)
 
     return requirements
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class sqlitefilestorage(object):
     """Repository file storage backed by SQLite."""
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         if REQUIREMENT_ZSTD in self.requirements:
             compression = 'zstd'
         elif REQUIREMENT_ZLIB in self.requirements:
             compression = 'zlib'
         elif REQUIREMENT_NONE in self.requirements:
             compression = 'none'
         else:
             raise error.Abort(_('unable to determine what compression engine '
                                 'to use for SQLite storage'))
 
         return sqlitefilestore(self._dbconn, path, compression)
 
 def makefilestorage(orig, requirements, features, **kwargs):
     """Produce a type conforming to ``ilocalrepositoryfilestorage``."""
     if REQUIREMENT in requirements:
         if REQUIREMENT_SHALLOW_FILES in requirements:
             features.add(repository.REPO_FEATURE_SHALLOW_FILE_STORAGE)
 
         return sqlitefilestorage
     else:
         return orig(requirements=requirements, features=features, **kwargs)
 
 def makemain(orig, ui, requirements, **kwargs):
     if REQUIREMENT in requirements:
         if REQUIREMENT_ZSTD in requirements and not zstd:
             raise error.Abort(_('repository uses zstandard compression, which '
                                 'is not available to this Mercurial install'))
 
         return sqliterepository
 
     return orig(requirements=requirements, **kwargs)
 
 def verifierinit(orig, self, *args, **kwargs):
     orig(self, *args, **kwargs)
 
     # We don't care that files in the store don't align with what is
     # advertised. So suppress these warnings.
     self.warnorphanstorefiles = False
 
 def extsetup(ui):
     localrepo.featuresetupfuncs.add(featuresetup)
     extensions.wrapfunction(localrepo, 'newreporequirements',
                             newreporequirements)
     extensions.wrapfunction(localrepo, 'makefilestorage',
                             makefilestorage)
     extensions.wrapfunction(localrepo, 'makemain',
                             makemain)
     extensions.wrapfunction(verify.verifier, '__init__',
                             verifierinit)
 
 def reposetup(ui, repo):
     if isinstance(repo, sqliterepository):
         repo._db = None
 
     # TODO check for bundlerepository?

mercurial/changegroup.py

@@ -1,1423 +1,1426
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import struct
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     nullrev,
     short,
 )
 
 from . import (
     error,
     match as matchmod,
     mdiff,
     phases,
     pycompat,
+    util,
+)
+
+from .interfaces import (
     repository,
-    util,
 )
 
 _CHANGEGROUPV1_DELTA_HEADER = struct.Struct("20s20s20s20s")
 _CHANGEGROUPV2_DELTA_HEADER = struct.Struct("20s20s20s20s20s")
 _CHANGEGROUPV3_DELTA_HEADER = struct.Struct(">20s20s20s20s20sH")
 
 LFS_REQUIREMENT = 'lfs'
 
 readexactly = util.readexactly
 
 def getchunk(stream):
     """return the next chunk from stream as a string"""
     d = readexactly(stream, 4)
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         if l:
             raise error.Abort(_("invalid chunk length %d") % l)
         return ""
     return readexactly(stream, l - 4)
 
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 def _fileheader(path):
     """Obtain a changegroup chunk header for a named path."""
     return chunkheader(len(path)) + path
 
 def writechunks(ui, chunks, filename, vfs=None):
     """Write chunks to a file and return its filename.
 
     The stream is assumed to be a bundle file.
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     """
     fh = None
     cleanup = None
     try:
         if filename:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 # Increase default buffer size because default is usually
                 # small (4k is common on Linux).
                 fh = open(filename, "wb", 131072)
         else:
             fd, filename = pycompat.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, r"wb")
         cleanup = filename
         for c in chunks:
             fh.write(c)
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 class cg1unpacker(object):
     """Unpacker for cg1 changegroup streams.
 
     A changegroup unpacker handles the framing of the revision data in
     the wire format. Most consumers will want to use the apply()
     method to add the changes from the changegroup to a repository.
 
     If you're forwarding a changegroup unmodified to another consumer,
     use getchunks(), which returns an iterator of changegroup
     chunks. This is mostly useful for cases where you need to know the
     data stream has ended by observing the end of the changegroup.
 
     deltachunk() is useful only if you're applying delta data. Most
     consumers should prefer apply() instead.
 
     A few other public methods exist. Those are used only for
     bundlerepo and some debug commands - their use is discouraged.
     """
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '01'
     _grouplistcount = 1 # One list of files after the manifests
 
     def __init__(self, fh, alg, extras=None):
         if alg is None:
             alg = 'UN'
         if alg not in util.compengines.supportedbundletypes:
             raise error.Abort(_('unknown stream compression type: %s')
                              % alg)
         if alg == 'BZ':
             alg = '_truncatedBZ'
 
         compengine = util.compengines.forbundletype(alg)
         self._stream = compengine.decompressorreader(fh)
         self._type = alg
         self.extras = extras or {}
         self.callback = None
 
     # These methods (compressed, read, seek, tell) all appear to only
     # be used by bundlerepo, but it's a little hard to tell.
     def compressed(self):
         return self._type is not None and self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
     def close(self):
         return self._stream.close()
 
     def _chunklength(self):
         d = readexactly(self._stream, 4)
         l = struct.unpack(">l", d)[0]
         if l <= 4:
             if l:
                 raise error.Abort(_("invalid chunk length %d") % l)
             return 0
         if self.callback:
             self.callback()
         return l - 4
 
     def changelogheader(self):
         """v10 does not have a changelog header chunk"""
         return {}
 
     def manifestheader(self):
         """v10 does not have a manifest header chunk"""
         return {}
 
     def filelogheader(self):
         """return the header of the filelogs chunk, v10 only has the filename"""
         l = self._chunklength()
         if not l:
             return {}
         fname = readexactly(self._stream, l)
         return {'filename': fname}
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
     def deltachunk(self, prevnode):
         l = self._chunklength()
         if not l:
             return {}
         headerdata = readexactly(self._stream, self.deltaheadersize)
         header = self.deltaheader.unpack(headerdata)
         delta = readexactly(self._stream, l - self.deltaheadersize)
         node, p1, p2, deltabase, cs, flags = self._deltaheader(header, prevnode)
         return (node, p1, p2, cs, deltabase, delta, flags)
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # For changegroup 1 and 2, we expect 3 parts: changelog, manifestlog,
         # and a list of filelogs. For changegroup 3, we expect 4 parts:
         # changelog, manifestlog, a list of tree manifestlogs, and a list of
         # filelogs.
         #
         # Changelog and manifestlog parts are terminated with empty chunks. The
         # tree and file parts are a list of entry sections. Each entry section
         # is a series of chunks terminating in an empty chunk. The list of these
         # entry sections is terminated in yet another empty chunk, so we know
         # we've reached the end of the tree/file list when we reach an empty
         # chunk that was proceeded by no non-empty chunks.
 
         parts = 0
         while parts < 2 + self._grouplistcount:
             noentries = True
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     # The first two empty chunks represent the end of the
                     # changelog and the manifestlog portions. The remaining
                     # empty chunks represent either A) the end of individual
                     # tree or file entries in the file list, or B) the end of
                     # the entire list. It's the end of the entire list if there
                     # were no entries (i.e. noentries is True).
                     if parts < 2:
                         parts += 1
                     elif noentries:
                         parts += 1
                     break
                 noentries = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
     def _unpackmanifests(self, repo, revmap, trp, prog):
         self.callback = prog.increment
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         self.manifestheader()
         deltas = self.deltaiter()
         repo.manifestlog.getstorage(b'').addgroup(deltas, revmap, trp)
         prog.complete()
         self.callback = None
 
     def apply(self, repo, tr, srctype, url, targetphase=phases.draft,
               expectedtotal=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         repo = repo.unfiltered()
         def csmap(x):
             repo.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         changesets = files = revisions = 0
 
         try:
             # The transaction may already carry source information. In this
             # case we use the top level data. We overwrite the argument
             # because we need to use the top level value (if they exist)
             # in this function.
             srctype = tr.hookargs.setdefault('source', srctype)
             tr.hookargs.setdefault('url', url)
             repo.hook('prechangegroup',
                       throw=True, **pycompat.strkwargs(tr.hookargs))
 
             # write changelog data to temp files so concurrent readers
             # will not see an inconsistent view
             cl = repo.changelog
             cl.delayupdate(tr)
             oldheads = set(cl.heads())
 
             trp = weakref.proxy(tr)
             # pull off the changeset group
             repo.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             progress = repo.ui.makeprogress(_('changesets'), unit=_('chunks'),
                                             total=expectedtotal)
             self.callback = progress.increment
 
             efiles = set()
             def onchangelog(cl, node):
                 efiles.update(cl.readfiles(node))
 
             self.changelogheader()
             deltas = self.deltaiter()
             cgnodes = cl.addgroup(deltas, csmap, trp, addrevisioncb=onchangelog)
             efiles = len(efiles)
 
             if not cgnodes:
                 repo.ui.develwarn('applied empty changelog from changegroup',
                                   config='warn-empty-changegroup')
             clend = len(cl)
             changesets = clend - clstart
             progress.complete()
             self.callback = None
 
             # pull off the manifest group
             repo.ui.status(_("adding manifests\n"))
             # We know that we'll never have more manifests than we had
             # changesets.
             progress = repo.ui.makeprogress(_('manifests'), unit=_('chunks'),
                                             total=changesets)
             self._unpackmanifests(repo, revmap, trp, progress)
 
             needfiles = {}
             if repo.ui.configbool('server', 'validate'):
                 cl = repo.changelog
                 ml = repo.manifestlog
                 # validate incoming csets have their manifests
                 for cset in pycompat.xrange(clstart, clend):
                     mfnode = cl.changelogrevision(cset).manifest
                     mfest = ml[mfnode].readdelta()
                     # store file cgnodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             repo.ui.status(_("adding file changes\n"))
             newrevs, newfiles = _addchangegroupfiles(
                 repo, self, revmap, trp, efiles, needfiles)
             revisions += newrevs
             files += newfiles
 
             deltaheads = 0
             if oldheads:
                 heads = cl.heads()
                 deltaheads = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and repo[h].closesbranch():
                         deltaheads -= 1
             htext = ""
             if deltaheads:
                 htext = _(" (%+d heads)") % deltaheads
 
             repo.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
             repo.invalidatevolatilesets()
 
             if changesets > 0:
                 if 'node' not in tr.hookargs:
                     tr.hookargs['node'] = hex(cl.node(clstart))
                     tr.hookargs['node_last'] = hex(cl.node(clend - 1))
                     hookargs = dict(tr.hookargs)
                 else:
                     hookargs = dict(tr.hookargs)
                     hookargs['node'] = hex(cl.node(clstart))
                     hookargs['node_last'] = hex(cl.node(clend - 1))
                 repo.hook('pretxnchangegroup',
                           throw=True, **pycompat.strkwargs(hookargs))
 
             added = [cl.node(r) for r in pycompat.xrange(clstart, clend)]
             phaseall = None
             if srctype in ('push', 'serve'):
                 # Old servers can not push the boundary themselves.
                 # New servers won't push the boundary if changeset already
                 # exists locally as secret
                 #
                 # We should not use added here but the list of all change in
                 # the bundle
                 if repo.publishing():
                     targetphase = phaseall = phases.public
                 else:
                     # closer target phase computation
 
                     # Those changesets have been pushed from the
                     # outside, their phases are going to be pushed
                     # alongside. Therefor `targetphase` is
                     # ignored.
                     targetphase = phaseall = phases.draft
             if added:
                 phases.registernew(repo, tr, targetphase, added)
             if phaseall is not None:
                 phases.advanceboundary(repo, tr, phaseall, cgnodes)
 
             if changesets > 0:
 
                 def runhooks():
                     # These hooks run when the lock releases, not when the
                     # transaction closes. So it's possible for the changelog
                     # to have changed since we last saw it.
                     if clstart >= len(repo):
                         return
 
                     repo.hook("changegroup", **pycompat.strkwargs(hookargs))
 
                     for n in added:
                         args = hookargs.copy()
                         args['node'] = hex(n)
                         del args['node_last']
                         repo.hook("incoming", **pycompat.strkwargs(args))
 
                     newheads = [h for h in repo.heads()
                                 if h not in oldheads]
                     repo.ui.log("incoming",
                                 "%d incoming changes - new heads: %s\n",
                                 len(added),
                                 ', '.join([hex(c[:6]) for c in newheads]))
 
                 tr.addpostclose('changegroup-runhooks-%020i' % clstart,
                                 lambda tr: repo._afterlock(runhooks))
         finally:
             repo.ui.flush()
         # never return 0 here:
         if deltaheads < 0:
             ret = deltaheads - 1
         else:
             ret = deltaheads + 1
         return ret
 
     def deltaiter(self):
         """
         returns an iterator of the deltas in this changegroup
 
         Useful for passing to the underlying storage system to be stored.
         """
         chain = None
         for chunkdata in iter(lambda: self.deltachunk(chain), {}):
             # Chunkdata: (node, p1, p2, cs, deltabase, delta, flags)
             yield chunkdata
             chain = chunkdata[0]
 
 class cg2unpacker(cg1unpacker):
     """Unpacker for cg2 streams.
 
     cg2 streams add support for generaldelta, so the delta header
     format is slightly different. All other features about the data
     remain the same.
     """
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '02'
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs = headertuple
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
 class cg3unpacker(cg2unpacker):
     """Unpacker for cg3 streams.
 
     cg3 streams add support for exchanging treemanifests and revlog
     flags. It adds the revlog flags to the delta header and an empty chunk
     separating manifests and files.
     """
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
     deltaheadersize = deltaheader.size
     version = '03'
     _grouplistcount = 2 # One list of manifests and one list of files
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs, flags = headertuple
         return node, p1, p2, deltabase, cs, flags
 
     def _unpackmanifests(self, repo, revmap, trp, prog):
         super(cg3unpacker, self)._unpackmanifests(repo, revmap, trp, prog)
         for chunkdata in iter(self.filelogheader, {}):
             # If we get here, there are directory manifests in the changegroup
             d = chunkdata["filename"]
             repo.ui.debug("adding %s revisions\n" % d)
             deltas = self.deltaiter()
             if not repo.manifestlog.getstorage(d).addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received dir revlog group is empty"))
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 def _revisiondeltatochunks(delta, headerfn):
     """Serialize a revisiondelta to changegroup chunks."""
 
     # The captured revision delta may be encoded as a delta against
     # a base revision or as a full revision. The changegroup format
     # requires that everything on the wire be deltas. So for full
     # revisions, we need to invent a header that says to rewrite
     # data.
 
     if delta.delta is not None:
         prefix, data = b'', delta.delta
     elif delta.basenode == nullid:
         data = delta.revision
         prefix = mdiff.trivialdiffheader(len(data))
     else:
         data = delta.revision
         prefix = mdiff.replacediffheader(delta.baserevisionsize,
                                          len(data))
 
     meta = headerfn(delta)
 
     yield chunkheader(len(meta) + len(prefix) + len(data))
     yield meta
     if prefix:
         yield prefix
     yield data
 
 def _sortnodesellipsis(store, nodes, cl, lookup):
     """Sort nodes for changegroup generation."""
     # Ellipses serving mode.
     #
     # In a perfect world, we'd generate better ellipsis-ified graphs
     # for non-changelog revlogs. In practice, we haven't started doing
     # that yet, so the resulting DAGs for the manifestlog and filelogs
     # are actually full of bogus parentage on all the ellipsis
     # nodes. This has the side effect that, while the contents are
     # correct, the individual DAGs might be completely out of whack in
     # a case like 882681bc3166 and its ancestors (back about 10
     # revisions or so) in the main hg repo.
     #
     # The one invariant we *know* holds is that the new (potentially
     # bogus) DAG shape will be valid if we order the nodes in the
     # order that they're introduced in dramatis personae by the
     # changelog, so what we do is we sort the non-changelog histories
     # by the order in which they are used by the changelog.
     key = lambda n: cl.rev(lookup(n))
     return sorted(nodes, key=key)
 
 def _resolvenarrowrevisioninfo(cl, store, ischangelog, rev, linkrev,
                                linknode, clrevtolocalrev, fullclnodes,
                                precomputedellipsis):
     linkparents = precomputedellipsis[linkrev]
     def local(clrev):
         """Turn a changelog revnum into a local revnum.
 
         The ellipsis dag is stored as revnums on the changelog,
         but when we're producing ellipsis entries for
         non-changelog revlogs, we need to turn those numbers into
         something local. This does that for us, and during the
         changelog sending phase will also expand the stored
         mappings as needed.
         """
         if clrev == nullrev:
             return nullrev
 
         if ischangelog:
             return clrev
 
         # Walk the ellipsis-ized changelog breadth-first looking for a
         # change that has been linked from the current revlog.
         #
         # For a flat manifest revlog only a single step should be necessary
         # as all relevant changelog entries are relevant to the flat
         # manifest.
         #
         # For a filelog or tree manifest dirlog however not every changelog
         # entry will have been relevant, so we need to skip some changelog
         # nodes even after ellipsis-izing.
         walk = [clrev]
         while walk:
             p = walk[0]
             walk = walk[1:]
             if p in clrevtolocalrev:
                 return clrevtolocalrev[p]
             elif p in fullclnodes:
                 walk.extend([pp for pp in cl.parentrevs(p)
                                 if pp != nullrev])
             elif p in precomputedellipsis:
                 walk.extend([pp for pp in precomputedellipsis[p]
                                 if pp != nullrev])
             else:
                 # In this case, we've got an ellipsis with parents
                 # outside the current bundle (likely an
                 # incremental pull). We "know" that we can use the
                 # value of this same revlog at whatever revision
                 # is pointed to by linknode. "Know" is in scare
                 # quotes because I haven't done enough examination
                 # of edge cases to convince myself this is really
                 # a fact - it works for all the (admittedly
                 # thorough) cases in our testsuite, but I would be
                 # somewhat unsurprised to find a case in the wild
                 # where this breaks down a bit. That said, I don't
                 # know if it would hurt anything.
                 for i in pycompat.xrange(rev, 0, -1):
                     if store.linkrev(i) == clrev:
                         return i
                 # We failed to resolve a parent for this node, so
                 # we crash the changegroup construction.
                 raise error.Abort(
                     'unable to resolve parent while packing %r %r'
                     ' for changeset %r' % (store.indexfile, rev, clrev))
 
         return nullrev
 
     if not linkparents or (
         store.parentrevs(rev) == (nullrev, nullrev)):
         p1, p2 = nullrev, nullrev
     elif len(linkparents) == 1:
         p1, = sorted(local(p) for p in linkparents)
         p2 = nullrev
     else:
         p1, p2 = sorted(local(p) for p in linkparents)
 
     p1node, p2node = store.node(p1), store.node(p2)
 
     return p1node, p2node, linknode
 
 def deltagroup(repo, store, nodes, ischangelog, lookup, forcedeltaparentprev,
                topic=None,
                ellipses=False, clrevtolocalrev=None, fullclnodes=None,
                precomputedellipsis=None):
     """Calculate deltas for a set of revisions.
 
     Is a generator of ``revisiondelta`` instances.
 
     If topic is not None, progress detail will be generated using this
     topic name (e.g. changesets, manifests, etc).
     """
     if not nodes:
         return
 
     cl = repo.changelog
 
     if ischangelog:
         # `hg log` shows changesets in storage order. To preserve order
         # across clones, send out changesets in storage order.
         nodesorder = 'storage'
     elif ellipses:
         nodes = _sortnodesellipsis(store, nodes, cl, lookup)
         nodesorder = 'nodes'
     else:
         nodesorder = None
 
     # Perform ellipses filtering and revision massaging. We do this before
     # emitrevisions() because a) filtering out revisions creates less work
     # for emitrevisions() b) dropping revisions would break emitrevisions()'s
     # assumptions about delta choices and we would possibly send a delta
     # referencing a missing base revision.
     #
     # Also, calling lookup() has side-effects with regards to populating
     # data structures. If we don't call lookup() for each node or if we call
     # lookup() after the first pass through each node, things can break -
     # possibly intermittently depending on the python hash seed! For that
     # reason, we store a mapping of all linknodes during the initial node
     # pass rather than use lookup() on the output side.
     if ellipses:
         filtered = []
         adjustedparents = {}
         linknodes = {}
 
         for node in nodes:
             rev = store.rev(node)
             linknode = lookup(node)
             linkrev = cl.rev(linknode)
             clrevtolocalrev[linkrev] = rev
 
             # If linknode is in fullclnodes, it means the corresponding
             # changeset was a full changeset and is being sent unaltered.
             if linknode in fullclnodes:
                 linknodes[node] = linknode
 
             # If the corresponding changeset wasn't in the set computed
             # as relevant to us, it should be dropped outright.
             elif linkrev not in precomputedellipsis:
                 continue
 
             else:
                 # We could probably do this later and avoid the dict
                 # holding state. But it likely doesn't matter.
                 p1node, p2node, linknode = _resolvenarrowrevisioninfo(
                     cl, store, ischangelog, rev, linkrev, linknode,
                     clrevtolocalrev, fullclnodes, precomputedellipsis)
 
                 adjustedparents[node] = (p1node, p2node)
                 linknodes[node] = linknode
 
             filtered.append(node)
 
         nodes = filtered
 
     # We expect the first pass to be fast, so we only engage the progress
     # meter for constructing the revision deltas.
     progress = None
     if topic is not None:
         progress = repo.ui.makeprogress(topic, unit=_('chunks'),
                                         total=len(nodes))
 
     configtarget = repo.ui.config('devel', 'bundle.delta')
     if configtarget not in ('', 'p1', 'full'):
         msg = _("""config "devel.bundle.delta" as unknown value: %s""")
         repo.ui.warn(msg % configtarget)
 
     deltamode = repository.CG_DELTAMODE_STD
     if forcedeltaparentprev:
         deltamode = repository.CG_DELTAMODE_PREV
     elif configtarget == 'p1':
         deltamode = repository.CG_DELTAMODE_P1
     elif configtarget == 'full':
         deltamode = repository.CG_DELTAMODE_FULL
 
     revisions = store.emitrevisions(
         nodes,
         nodesorder=nodesorder,
         revisiondata=True,
         assumehaveparentrevisions=not ellipses,
         deltamode=deltamode)
 
     for i, revision in enumerate(revisions):
         if progress:
             progress.update(i + 1)
 
         if ellipses:
             linknode = linknodes[revision.node]
 
             if revision.node in adjustedparents:
                 p1node, p2node = adjustedparents[revision.node]
                 revision.p1node = p1node
                 revision.p2node = p2node
                 revision.flags |= repository.REVISION_FLAG_ELLIPSIS
 
         else:
             linknode = lookup(revision.node)
 
         revision.linknode = linknode
         yield revision
 
     if progress:
         progress.complete()
 
 class cgpacker(object):
     def __init__(self, repo, oldmatcher, matcher, version,
                  builddeltaheader, manifestsend,
                  forcedeltaparentprev=False,
                  bundlecaps=None, ellipses=False,
                  shallow=False, ellipsisroots=None, fullnodes=None):
         """Given a source repo, construct a bundler.
 
         oldmatcher is a matcher that matches on files the client already has.
         These will not be included in the changegroup.
 
         matcher is a matcher that matches on files to include in the
         changegroup. Used to facilitate sparse changegroups.
 
         forcedeltaparentprev indicates whether delta parents must be against
         the previous revision in a delta group. This should only be used for
         compatibility with changegroup version 1.
 
         builddeltaheader is a callable that constructs the header for a group
         delta.
 
         manifestsend is a chunk to send after manifests have been fully emitted.
 
         ellipses indicates whether ellipsis serving mode is enabled.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle. While bundlecaps is
         unused in core Mercurial, extensions rely on this feature to communicate
         capabilities to customize the changegroup packer.
 
         shallow indicates whether shallow data might be sent. The packer may
         need to pack file contents not introduced by the changes being packed.
 
         fullnodes is the set of changelog nodes which should not be ellipsis
         nodes. We store this rather than the set of nodes that should be
         ellipsis because for very large histories we expect this to be
         significantly smaller.
         """
         assert oldmatcher
         assert matcher
         self._oldmatcher = oldmatcher
         self._matcher = matcher
 
         self.version = version
         self._forcedeltaparentprev = forcedeltaparentprev
         self._builddeltaheader = builddeltaheader
         self._manifestsend = manifestsend
         self._ellipses = ellipses
 
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         self._isshallow = shallow
         self._fullclnodes = fullnodes
 
         # Maps ellipsis revs to their roots at the changelog level.
         self._precomputedellipsis = ellipsisroots
 
         self._repo = repo
 
         if self._repo.ui.verbose and not self._repo.ui.debugflag:
             self._verbosenote = self._repo.ui.note
         else:
             self._verbosenote = lambda s: None
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source,
                  changelog=True):
         """Yield a sequence of changegroup byte chunks.
         If changelog is False, changelog data won't be added to changegroup
         """
 
         repo = self._repo
         cl = repo.changelog
 
         self._verbosenote(_('uncompressed size of bundle content:\n'))
         size = 0
 
         clstate, deltas = self._generatechangelog(cl, clnodes,
                                                   generate=changelog)
         for delta in deltas:
             for chunk in _revisiondeltatochunks(delta,
                                                 self._builddeltaheader):
                 size += len(chunk)
                 yield chunk
 
         close = closechunk()
         size += len(close)
         yield closechunk()
 
         self._verbosenote(_('%8.i (changelog)\n') % size)
 
         clrevorder = clstate['clrevorder']
         manifests = clstate['manifests']
         changedfiles = clstate['changedfiles']
 
         # We need to make sure that the linkrev in the changegroup refers to
         # the first changeset that introduced the manifest or file revision.
         # The fastpath is usually safer than the slowpath, because the filelogs
         # are walked in revlog order.
         #
         # When taking the slowpath when the manifest revlog uses generaldelta,
         # the manifest may be walked in the "wrong" order. Without 'clrevorder',
         # we would get an incorrect linkrev (see fix in cc0ff93d0c0c).
         #
         # When taking the fastpath, we are only vulnerable to reordering
         # of the changelog itself. The changelog never uses generaldelta and is
         # never reordered. To handle this case, we simply take the slowpath,
         # which already has the 'clrevorder' logic. This was also fixed in
         # cc0ff93d0c0c.
 
         # Treemanifests don't work correctly with fastpathlinkrev
         # either, because we don't discover which directory nodes to
         # send along with files. This could probably be fixed.
         fastpathlinkrev = fastpathlinkrev and (
             'treemanifest' not in repo.requirements)
 
         fnodes = {}  # needed file nodes
 
         size = 0
         it = self.generatemanifests(
             commonrevs, clrevorder, fastpathlinkrev, manifests, fnodes, source,
             clstate['clrevtomanifestrev'])
 
         for tree, deltas in it:
             if tree:
                 assert self.version == b'03'
                 chunk = _fileheader(tree)
                 size += len(chunk)
                 yield chunk
 
             for delta in deltas:
                 chunks = _revisiondeltatochunks(delta, self._builddeltaheader)
                 for chunk in chunks:
                     size += len(chunk)
                     yield chunk
 
             close = closechunk()
             size += len(close)
             yield close
 
         self._verbosenote(_('%8.i (manifests)\n') % size)
         yield self._manifestsend
 
         mfdicts = None
         if self._ellipses and self._isshallow:
             mfdicts = [(self._repo.manifestlog[n].read(), lr)
                        for (n, lr) in manifests.iteritems()]
 
         manifests.clear()
         clrevs = set(cl.rev(x) for x in clnodes)
 
         it = self.generatefiles(changedfiles, commonrevs,
                                 source, mfdicts, fastpathlinkrev,
                                 fnodes, clrevs)
 
         for path, deltas in it:
             h = _fileheader(path)
             size = len(h)
             yield h
 
             for delta in deltas:
                 chunks = _revisiondeltatochunks(delta, self._builddeltaheader)
                 for chunk in chunks:
                     size += len(chunk)
                     yield chunk
 
             close = closechunk()
             size += len(close)
             yield close
 
             self._verbosenote(_('%8.i  %s\n') % (size, path))
 
         yield closechunk()
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def _generatechangelog(self, cl, nodes, generate=True):
         """Generate data for changelog chunks.
 
         Returns a 2-tuple of a dict containing state and an iterable of
         byte chunks. The state will not be fully populated until the
         chunk stream has been fully consumed.
 
         if generate is False, the state will be fully populated and no chunk
         stream will be yielded
         """
         clrevorder = {}
         manifests = {}
         mfl = self._repo.manifestlog
         changedfiles = set()
         clrevtomanifestrev = {}
 
         state = {
             'clrevorder': clrevorder,
             'manifests': manifests,
             'changedfiles': changedfiles,
             'clrevtomanifestrev': clrevtomanifestrev,
         }
 
         if not (generate or self._ellipses):
             # sort the nodes in storage order
             nodes = sorted(nodes, key=cl.rev)
             for node in nodes:
                 c = cl.changelogrevision(node)
                 clrevorder[node] = len(clrevorder)
                 # record the first changeset introducing this manifest version
                 manifests.setdefault(c.manifest, node)
                 # Record a complete list of potentially-changed files in
                 # this manifest.
                 changedfiles.update(c.files)
 
             return state, ()
 
         # Callback for the changelog, used to collect changed files and
         # manifest nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.changelogrevision(x)
             clrevorder[x] = len(clrevorder)
 
             if self._ellipses:
                 # Only update manifests if x is going to be sent. Otherwise we
                 # end up with bogus linkrevs specified for manifests and
                 # we skip some manifest nodes that we should otherwise
                 # have sent.
                 if (x in self._fullclnodes
                     or cl.rev(x) in self._precomputedellipsis):
 
                     manifestnode = c.manifest
                     # Record the first changeset introducing this manifest
                     # version.
                     manifests.setdefault(manifestnode, x)
                     # Set this narrow-specific dict so we have the lowest
                     # manifest revnum to look up for this cl revnum. (Part of
                     # mapping changelog ellipsis parents to manifest ellipsis
                     # parents)
                     clrevtomanifestrev.setdefault(
                         cl.rev(x), mfl.rev(manifestnode))
                 # We can't trust the changed files list in the changeset if the
                 # client requested a shallow clone.
                 if self._isshallow:
                     changedfiles.update(mfl[c.manifest].read().keys())
                 else:
                     changedfiles.update(c.files)
             else:
                 # record the first changeset introducing this manifest version
                 manifests.setdefault(c.manifest, x)
                 # Record a complete list of potentially-changed files in
                 # this manifest.
                 changedfiles.update(c.files)
 
             return x
 
         gen = deltagroup(
             self._repo, cl, nodes, True, lookupcl,
             self._forcedeltaparentprev,
             ellipses=self._ellipses,
             topic=_('changesets'),
             clrevtolocalrev={},
             fullclnodes=self._fullclnodes,
             precomputedellipsis=self._precomputedellipsis)
 
         return state, gen
 
     def generatemanifests(self, commonrevs, clrevorder, fastpathlinkrev,
                           manifests, fnodes, source, clrevtolocalrev):
         """Returns an iterator of changegroup chunks containing manifests.
 
         `source` is unused here, but is used by extensions like remotefilelog to
         change what is sent based in pulls vs pushes, etc.
         """
         repo = self._repo
         mfl = repo.manifestlog
         tmfnodes = {'': manifests}
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def makelookupmflinknode(tree, nodes):
             if fastpathlinkrev:
                 assert not tree
                 return manifests.__getitem__
 
             def lookupmflinknode(x):
                 """Callback for looking up the linknode for manifests.
 
                 Returns the linkrev node for the specified manifest.
 
                 SIDE EFFECT:
 
                 1) fclnodes gets populated with the list of relevant
                    file nodes if we're not using fastpathlinkrev
                 2) When treemanifests are in use, collects treemanifest nodes
                    to send
 
                 Note that this means manifests must be completely sent to
                 the client before you can trust the list of files and
                 treemanifests to send.
                 """
                 clnode = nodes[x]
                 mdata = mfl.get(tree, x).readfast(shallow=True)
                 for p, n, fl in mdata.iterentries():
                     if fl == 't': # subdirectory manifest
                         subtree = tree + p + '/'
                         tmfclnodes = tmfnodes.setdefault(subtree, {})
                         tmfclnode = tmfclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[tmfclnode]:
                             tmfclnodes[n] = clnode
                     else:
                         f = tree + p
                         fclnodes = fnodes.setdefault(f, {})
                         fclnode = fclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[fclnode]:
                             fclnodes[n] = clnode
                 return clnode
             return lookupmflinknode
 
         while tmfnodes:
             tree, nodes = tmfnodes.popitem()
 
             should_visit = self._matcher.visitdir(tree[:-1])
             if tree and not should_visit:
                 continue
 
             store = mfl.getstorage(tree)
 
             if not should_visit:
                 # No nodes to send because this directory is out of
                 # the client's view of the repository (probably
                 # because of narrow clones). Do this even for the root
                 # directory (tree=='')
                 prunednodes = []
             else:
                 # Avoid sending any manifest nodes we can prove the
                 # client already has by checking linkrevs. See the
                 # related comment in generatefiles().
                 prunednodes = self._prunemanifests(store, nodes, commonrevs)
 
             if tree and not prunednodes:
                 continue
 
             lookupfn = makelookupmflinknode(tree, nodes)
 
             deltas = deltagroup(
                 self._repo, store, prunednodes, False, lookupfn,
                 self._forcedeltaparentprev,
                 ellipses=self._ellipses,
                 topic=_('manifests'),
                 clrevtolocalrev=clrevtolocalrev,
                 fullclnodes=self._fullclnodes,
                 precomputedellipsis=self._precomputedellipsis)
 
             if not self._oldmatcher.visitdir(store.tree[:-1]):
                 yield tree, deltas
             else:
                 # 'deltas' is a generator and we need to consume it even if
                 # we are not going to send it because a side-effect is that
                 # it updates tmdnodes (via lookupfn)
                 for d in deltas:
                     pass
                 if not tree:
                     yield tree, []
 
     def _prunemanifests(self, store, nodes, commonrevs):
         if not self._ellipses:
             # In non-ellipses case and large repositories, it is better to
             # prevent calling of store.rev and store.linkrev on a lot of
             # nodes as compared to sending some extra data
             return nodes.copy()
         # This is split out as a separate method to allow filtering
         # commonrevs in extension code.
         #
         # TODO(augie): this shouldn't be required, instead we should
         # make filtering of revisions to send delegated to the store
         # layer.
         frev, flr = store.rev, store.linkrev
         return [n for n in nodes if flr(frev(n)) not in commonrevs]
 
     # The 'source' parameter is useful for extensions
     def generatefiles(self, changedfiles, commonrevs, source,
                       mfdicts, fastpathlinkrev, fnodes, clrevs):
         changedfiles = [f for f in changedfiles
                         if self._matcher(f) and not self._oldmatcher(f)]
 
         if not fastpathlinkrev:
             def normallinknodes(unused, fname):
                 return fnodes.get(fname, {})
         else:
             cln = self._repo.changelog.node
 
             def normallinknodes(store, fname):
                 flinkrev = store.linkrev
                 fnode = store.node
                 revs = ((r, flinkrev(r)) for r in store)
                 return dict((fnode(r), cln(lr))
                             for r, lr in revs if lr in clrevs)
 
         clrevtolocalrev = {}
 
         if self._isshallow:
             # In a shallow clone, the linknodes callback needs to also include
             # those file nodes that are in the manifests we sent but weren't
             # introduced by those manifests.
             commonctxs = [self._repo[c] for c in commonrevs]
             clrev = self._repo.changelog.rev
 
             def linknodes(flog, fname):
                 for c in commonctxs:
                     try:
                         fnode = c.filenode(fname)
                         clrevtolocalrev[c.rev()] = flog.rev(fnode)
                     except error.ManifestLookupError:
                         pass
                 links = normallinknodes(flog, fname)
                 if len(links) != len(mfdicts):
                     for mf, lr in mfdicts:
                         fnode = mf.get(fname, None)
                         if fnode in links:
                             links[fnode] = min(links[fnode], lr, key=clrev)
                         elif fnode:
                             links[fnode] = lr
                 return links
         else:
             linknodes = normallinknodes
 
         repo = self._repo
         progress = repo.ui.makeprogress(_('files'), unit=_('files'),
                                         total=len(changedfiles))
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise error.Abort(_("empty or missing file data for %s") %
                                   fname)
 
             clrevtolocalrev.clear()
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             frev, flr = filerevlog.rev, filerevlog.linkrev
             # Skip sending any filenode we know the client already
             # has. This avoids over-sending files relatively
             # inexpensively, so it's not a problem if we under-filter
             # here.
             filenodes = [n for n in linkrevnodes
                          if flr(frev(n)) not in commonrevs]
 
             if not filenodes:
                 continue
 
             progress.update(i + 1, item=fname)
 
             deltas = deltagroup(
                 self._repo, filerevlog, filenodes, False, lookupfilelog,
                 self._forcedeltaparentprev,
                 ellipses=self._ellipses,
                 clrevtolocalrev=clrevtolocalrev,
                 fullclnodes=self._fullclnodes,
                 precomputedellipsis=self._precomputedellipsis)
 
             yield fname, deltas
 
         progress.complete()
 
 def _makecg1packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV1_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.linknode)
 
     return cgpacker(repo, oldmatcher, matcher, b'01',
                     builddeltaheader=builddeltaheader,
                     manifestsend=b'',
                     forcedeltaparentprev=True,
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 def _makecg2packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV2_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.basenode, d.linknode)
 
     return cgpacker(repo, oldmatcher, matcher, b'02',
                     builddeltaheader=builddeltaheader,
                     manifestsend=b'',
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 def _makecg3packer(repo, oldmatcher, matcher, bundlecaps,
                    ellipses=False, shallow=False, ellipsisroots=None,
                    fullnodes=None):
     builddeltaheader = lambda d: _CHANGEGROUPV3_DELTA_HEADER.pack(
         d.node, d.p1node, d.p2node, d.basenode, d.linknode, d.flags)
 
     return cgpacker(repo, oldmatcher, matcher, b'03',
                     builddeltaheader=builddeltaheader,
                     manifestsend=closechunk(),
                     bundlecaps=bundlecaps,
                     ellipses=ellipses,
                     shallow=shallow,
                     ellipsisroots=ellipsisroots,
                     fullnodes=fullnodes)
 
 _packermap = {'01': (_makecg1packer, cg1unpacker),
              # cg2 adds support for exchanging generaldelta
              '02': (_makecg2packer, cg2unpacker),
              # cg3 adds support for exchanging revlog flags and treemanifests
              '03': (_makecg3packer, cg3unpacker),
 }
 
 def allsupportedversions(repo):
     versions = set(_packermap.keys())
     if not (repo.ui.configbool('experimental', 'changegroup3') or
             repo.ui.configbool('experimental', 'treemanifest') or
             'treemanifest' in repo.requirements):
         versions.discard('03')
     return versions
 
 # Changegroup versions that can be applied to the repo
 def supportedincomingversions(repo):
     return allsupportedversions(repo)
 
 # Changegroup versions that can be created from the repo
 def supportedoutgoingversions(repo):
     versions = allsupportedversions(repo)
     if 'treemanifest' in repo.requirements:
         # Versions 01 and 02 support only flat manifests and it's just too
         # expensive to convert between the flat manifest and tree manifest on
         # the fly. Since tree manifests are hashed differently, all of history
         # would have to be converted. Instead, we simply don't even pretend to
         # support versions 01 and 02.
         versions.discard('01')
         versions.discard('02')
     if repository.NARROW_REQUIREMENT in repo.requirements:
         # Versions 01 and 02 don't support revlog flags, and we need to
         # support that for stripping and unbundling to work.
         versions.discard('01')
         versions.discard('02')
     if LFS_REQUIREMENT in repo.requirements:
         # Versions 01 and 02 don't support revlog flags, and we need to
         # mark LFS entries with REVIDX_EXTSTORED.
         versions.discard('01')
         versions.discard('02')
 
     return versions
 
 def localversion(repo):
     # Finds the best version to use for bundles that are meant to be used
     # locally, such as those from strip and shelve, and temporary bundles.
     return max(supportedoutgoingversions(repo))
 
 def safeversion(repo):
     # Finds the smallest version that it's safe to assume clients of the repo
     # will support. For example, all hg versions that support generaldelta also
     # support changegroup 02.
     versions = supportedoutgoingversions(repo)
     if 'generaldelta' in repo.requirements:
         versions.discard('01')
     assert versions
     return min(versions)
 
 def getbundler(version, repo, bundlecaps=None, oldmatcher=None,
                matcher=None, ellipses=False, shallow=False,
                ellipsisroots=None, fullnodes=None):
     assert version in supportedoutgoingversions(repo)
 
     if matcher is None:
         matcher = matchmod.always()
     if oldmatcher is None:
         oldmatcher = matchmod.never()
 
     if version == '01' and not matcher.always():
         raise error.ProgrammingError('version 01 changegroups do not support '
                                      'sparse file matchers')
 
     if ellipses and version in (b'01', b'02'):
         raise error.Abort(
             _('ellipsis nodes require at least cg3 on client and server, '
               'but negotiated version %s') % version)
 
     # Requested files could include files not in the local store. So
     # filter those out.
     matcher = repo.narrowmatch(matcher)
 
     fn = _packermap[version][0]
     return fn(repo, oldmatcher, matcher, bundlecaps, ellipses=ellipses,
               shallow=shallow, ellipsisroots=ellipsisroots,
               fullnodes=fullnodes)
 
 def getunbundler(version, fh, alg, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def makechangegroup(repo, outgoing, version, source, fastpath=False,
                     bundlecaps=None):
     cgstream = makestream(repo, outgoing, version, source,
                           fastpath=fastpath, bundlecaps=bundlecaps)
     return getunbundler(version, util.chunkbuffer(cgstream), None,
                         {'clcount': len(outgoing.missing) })
 
 def makestream(repo, outgoing, version, source, fastpath=False,
                bundlecaps=None, matcher=None):
     bundler = getbundler(version, repo, bundlecaps=bundlecaps,
                          matcher=matcher)
 
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
     return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
 
 def _addchangegroupfiles(repo, source, revmap, trp, expectedfiles, needfiles):
     revisions = 0
     files = 0
     progress = repo.ui.makeprogress(_('files'), unit=_('files'),
                                     total=expectedfiles)
     for chunkdata in iter(source.filelogheader, {}):
         files += 1
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         progress.increment()
         fl = repo.file(f)
         o = len(fl)
         try:
             deltas = source.deltaiter()
             if not fl.addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received file revlog group is empty"))
         except error.CensoredBaseError as e:
             raise error.Abort(_("received delta base is censored: %s") % e)
         revisions += len(fl) - o
         if f in needfiles:
             needs = needfiles[f]
             for new in pycompat.xrange(o, len(fl)):
                 n = fl.node(new)
                 if n in needs:
                     needs.remove(n)
                 else:
                     raise error.Abort(
                         _("received spurious file revlog entry"))
             if not needs:
                 del needfiles[f]
     progress.complete()
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise error.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files

mercurial/exchange.py

@@ -1,2701 +1,2703
 # exchange.py - utility to exchange data between repos.
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import hashlib
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from .thirdparty import (
     attr,
 )
 from . import (
     bookmarks as bookmod,
     bundle2,
     changegroup,
     discovery,
     error,
     exchangev2,
     lock as lockmod,
     logexchange,
     narrowspec,
     obsolete,
     phases,
     pushkey,
     pycompat,
-    repository,
     scmutil,
     sslutil,
     streamclone,
     url as urlmod,
     util,
     wireprototypes,
 )
+from .interfaces import (
+    repository,
+)
 from .utils import (
     stringutil,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _NARROWACL_SECTION = 'narrowacl'
 
 # Maps bundle version human names to changegroup versions.
 _bundlespeccgversions = {'v1': '01',
                          'v2': '02',
                          'packed1': 's1',
                          'bundle2': '02', #legacy
                         }
 
 # Maps bundle version with content opts to choose which part to bundle
 _bundlespeccontentopts = {
     'v1': {
         'changegroup': True,
         'cg.version': '01',
         'obsolescence': False,
         'phases': False,
         'tagsfnodescache': False,
         'revbranchcache': False
     },
     'v2': {
         'changegroup': True,
         'cg.version': '02',
         'obsolescence': False,
         'phases': False,
         'tagsfnodescache': True,
         'revbranchcache': True
     },
     'packed1' : {
         'cg.version': 's1'
     }
 }
 _bundlespeccontentopts['bundle2'] = _bundlespeccontentopts['v2']
 
 _bundlespecvariants = {"streamv2": {"changegroup": False, "streamv2": True,
                                     "tagsfnodescache": False,
                                     "revbranchcache": False}}
 
 # Compression engines allowed in version 1. THIS SHOULD NEVER CHANGE.
 _bundlespecv1compengines = {'gzip', 'bzip2', 'none'}
 
 @attr.s
 class bundlespec(object):
     compression = attr.ib()
     wirecompression = attr.ib()
     version = attr.ib()
     wireversion = attr.ib()
     params = attr.ib()
     contentopts = attr.ib()
 
 def parsebundlespec(repo, spec, strict=True):
     """Parse a bundle string specification into parts.
 
     Bundle specifications denote a well-defined bundle/exchange format.
     The content of a given specification should not change over time in
     order to ensure that bundles produced by a newer version of Mercurial are
     readable from an older version.
 
     The string currently has the form:
 
        <compression>-<type>[;<parameter0>[;<parameter1>]]
 
     Where <compression> is one of the supported compression formats
     and <type> is (currently) a version string. A ";" can follow the type and
     all text afterwards is interpreted as URI encoded, ";" delimited key=value
     pairs.
 
     If ``strict`` is True (the default) <compression> is required. Otherwise,
     it is optional.
 
     Returns a bundlespec object of (compression, version, parameters).
     Compression will be ``None`` if not in strict mode and a compression isn't
     defined.
 
     An ``InvalidBundleSpecification`` is raised when the specification is
     not syntactically well formed.
 
     An ``UnsupportedBundleSpecification`` is raised when the compression or
     bundle type/version is not recognized.
 
     Note: this function will likely eventually return a more complex data
     structure, including bundle2 part information.
     """
     def parseparams(s):
         if ';' not in s:
             return s, {}
 
         params = {}
         version, paramstr = s.split(';', 1)
 
         for p in paramstr.split(';'):
             if '=' not in p:
                 raise error.InvalidBundleSpecification(
                     _('invalid bundle specification: '
                       'missing "=" in parameter: %s') % p)
 
             key, value = p.split('=', 1)
             key = urlreq.unquote(key)
             value = urlreq.unquote(value)
             params[key] = value
 
         return version, params
 
 
     if strict and '-' not in spec:
         raise error.InvalidBundleSpecification(
                 _('invalid bundle specification; '
                   'must be prefixed with compression: %s') % spec)
 
     if '-' in spec:
         compression, version = spec.split('-', 1)
 
         if compression not in util.compengines.supportedbundlenames:
             raise error.UnsupportedBundleSpecification(
                     _('%s compression is not supported') % compression)
 
         version, params = parseparams(version)
 
         if version not in _bundlespeccgversions:
             raise error.UnsupportedBundleSpecification(
                     _('%s is not a recognized bundle version') % version)
     else:
         # Value could be just the compression or just the version, in which
         # case some defaults are assumed (but only when not in strict mode).
         assert not strict
 
         spec, params = parseparams(spec)
 
         if spec in util.compengines.supportedbundlenames:
             compression = spec
             version = 'v1'
             # Generaldelta repos require v2.
             if 'generaldelta' in repo.requirements:
                 version = 'v2'
             # Modern compression engines require v2.
             if compression not in _bundlespecv1compengines:
                 version = 'v2'
         elif spec in _bundlespeccgversions:
             if spec == 'packed1':
                 compression = 'none'
             else:
                 compression = 'bzip2'
             version = spec
         else:
             raise error.UnsupportedBundleSpecification(
                     _('%s is not a recognized bundle specification') % spec)
 
     # Bundle version 1 only supports a known set of compression engines.
     if version == 'v1' and compression not in _bundlespecv1compengines:
         raise error.UnsupportedBundleSpecification(
             _('compression engine %s is not supported on v1 bundles') %
             compression)
 
     # The specification for packed1 can optionally declare the data formats
     # required to apply it. If we see this metadata, compare against what the
     # repo supports and error if the bundle isn't compatible.
     if version == 'packed1' and 'requirements' in params:
         requirements = set(params['requirements'].split(','))
         missingreqs = requirements - repo.supportedformats
         if missingreqs:
             raise error.UnsupportedBundleSpecification(
                     _('missing support for repository features: %s') %
                       ', '.join(sorted(missingreqs)))
 
     # Compute contentopts based on the version
     contentopts = _bundlespeccontentopts.get(version, {}).copy()
 
     # Process the variants
     if "stream" in params and params["stream"] == "v2":
         variant = _bundlespecvariants["streamv2"]
         contentopts.update(variant)
 
     engine = util.compengines.forbundlename(compression)
     compression, wirecompression = engine.bundletype()
     wireversion = _bundlespeccgversions[version]
 
     return bundlespec(compression, wirecompression, version, wireversion,
                       params, contentopts)
 
 def readbundle(ui, fh, fname, vfs=None):
     header = changegroup.readexactly(fh, 4)
 
     alg = None
     if not fname:
         fname = "stream"
         if not header.startswith('HG') and header.startswith('\0'):
             fh = changegroup.headerlessfixup(fh, header)
             header = "HG10"
             alg = 'UN'
     elif vfs:
         fname = vfs.join(fname)
 
     magic, version = header[0:2], header[2:4]
 
     if magic != 'HG':
         raise error.Abort(_('%s: not a Mercurial bundle') % fname)
     if version == '10':
         if alg is None:
             alg = changegroup.readexactly(fh, 2)
         return changegroup.cg1unpacker(fh, alg)
     elif version.startswith('2'):
         return bundle2.getunbundler(ui, fh, magicstring=magic + version)
     elif version == 'S1':
         return streamclone.streamcloneapplier(fh)
     else:
         raise error.Abort(_('%s: unknown bundle version %s') % (fname, version))
 
 def getbundlespec(ui, fh):
     """Infer the bundlespec from a bundle file handle.
 
     The input file handle is seeked and the original seek position is not
     restored.
     """
     def speccompression(alg):
         try:
             return util.compengines.forbundletype(alg).bundletype()[0]
         except KeyError:
             return None
 
     b = readbundle(ui, fh, None)
     if isinstance(b, changegroup.cg1unpacker):
         alg = b._type
         if alg == '_truncatedBZ':
             alg = 'BZ'
         comp = speccompression(alg)
         if not comp:
             raise error.Abort(_('unknown compression algorithm: %s') % alg)
         return '%s-v1' % comp
     elif isinstance(b, bundle2.unbundle20):
         if 'Compression' in b.params:
             comp = speccompression(b.params['Compression'])
             if not comp:
                 raise error.Abort(_('unknown compression algorithm: %s') % comp)
         else:
             comp = 'none'
 
         version = None
         for part in b.iterparts():
             if part.type == 'changegroup':
                 version = part.params['version']
                 if version in ('01', '02'):
                     version = 'v2'
                 else:
                     raise error.Abort(_('changegroup version %s does not have '
                                         'a known bundlespec') % version,
                                       hint=_('try upgrading your Mercurial '
                                               'client'))
             elif part.type == 'stream2' and version is None:
                 # A stream2 part requires to be part of a v2 bundle
                 requirements = urlreq.unquote(part.params['requirements'])
                 splitted = requirements.split()
                 params = bundle2._formatrequirementsparams(splitted)
                 return 'none-v2;stream=v2;%s' % params
 
         if not version:
             raise error.Abort(_('could not identify changegroup version in '
                                 'bundle'))
 
         return '%s-%s' % (comp, version)
     elif isinstance(b, streamclone.streamcloneapplier):
         requirements = streamclone.readbundle1header(fh)[2]
         formatted = bundle2._formatrequirementsparams(requirements)
         return 'none-packed1;%s' % formatted
     else:
         raise error.Abort(_('unknown bundle type: %s') % b)
 
 def _computeoutgoing(repo, heads, common):
     """Computes which revs are outgoing given a set of common
     and a set of heads.
 
     This is a separate function so extensions can have access to
     the logic.
 
     Returns a discovery.outgoing object.
     """
     cl = repo.changelog
     if common:
         hasnode = cl.hasnode
         common = [n for n in common if hasnode(n)]
     else:
         common = [nullid]
     if not heads:
         heads = cl.heads()
     return discovery.outgoing(repo, common, heads)
 
 def _checkpublish(pushop):
     repo = pushop.repo
     ui = repo.ui
     behavior = ui.config('experimental', 'auto-publish')
     if pushop.publish or behavior not in ('warn', 'confirm', 'abort'):
         return
     remotephases = listkeys(pushop.remote, 'phases')
     if not remotephases.get('publishing', False):
         return
 
     if pushop.revs is None:
         published = repo.filtered('served').revs('not public()')
     else:
         published = repo.revs('::%ln - public()', pushop.revs)
     if published:
         if behavior == 'warn':
             ui.warn(_('%i changesets about to be published\n')
                     % len(published))
         elif behavior == 'confirm':
             if ui.promptchoice(_('push and publish %i changesets (yn)?'
                                  '$$ &Yes $$ &No') % len(published)):
                 raise error.Abort(_('user quit'))
         elif behavior == 'abort':
             msg = _('push would publish %i changesets') % len(published)
             hint = _("use --publish or adjust 'experimental.auto-publish'"
                      " config")
             raise error.Abort(msg, hint=hint)
 
 def _forcebundle1(op):
     """return true if a pull/push must use bundle1
 
     This function is used to allow testing of the older bundle version"""
     ui = op.repo.ui
     # The goal is this config is to allow developer to choose the bundle
     # version used during exchanged. This is especially handy during test.
     # Value is a list of bundle version to be picked from, highest version
     # should be used.
     #
     # developer config: devel.legacy.exchange
     exchange = ui.configlist('devel', 'legacy.exchange')
     forcebundle1 = 'bundle2' not in exchange and 'bundle1' in exchange
     return forcebundle1 or not op.remote.capable('bundle2')
 
 class pushoperation(object):
     """A object that represent a single push operation
 
     Its purpose is to carry push related state and very common operations.
 
     A new pushoperation should be created at the beginning of each push and
     discarded afterward.
     """
 
     def __init__(self, repo, remote, force=False, revs=None, newbranch=False,
                  bookmarks=(), publish=False, pushvars=None):
         # repo we push from
         self.repo = repo
         self.ui = repo.ui
         # repo we push to
         self.remote = remote
         # force option provided
         self.force = force
         # revs to be pushed (None is "all")
         self.revs = revs
         # bookmark explicitly pushed
         self.bookmarks = bookmarks
         # allow push of new branch
         self.newbranch = newbranch
         # step already performed
         # (used to check what steps have been already performed through bundle2)
         self.stepsdone = set()
         # Integer version of the changegroup push result
         # - None means nothing to push
         # - 0 means HTTP error
         # - 1 means we pushed and remote head count is unchanged *or*
         #   we have outgoing changesets but refused to push
         # - other values as described by addchangegroup()
         self.cgresult = None
         # Boolean value for the bookmark push
         self.bkresult = None
         # discover.outgoing object (contains common and outgoing data)
         self.outgoing = None
         # all remote topological heads before the push
         self.remoteheads = None
         # Details of the remote branch pre and post push
         #
         # mapping: {'branch': ([remoteheads],
         #                      [newheads],
         #                      [unsyncedheads],
         #                      [discardedheads])}
         # - branch: the branch name
         # - remoteheads: the list of remote heads known locally
         #                None if the branch is new
         # - newheads: the new remote heads (known locally) with outgoing pushed
         # - unsyncedheads: the list of remote heads unknown locally.
         # - discardedheads: the list of remote heads made obsolete by the push
         self.pushbranchmap = None
         # testable as a boolean indicating if any nodes are missing locally.
         self.incoming = None
         # summary of the remote phase situation
         self.remotephases = None
         # phases changes that must be pushed along side the changesets
         self.outdatedphases = None
         # phases changes that must be pushed if changeset push fails
         self.fallbackoutdatedphases = None
         # outgoing obsmarkers
         self.outobsmarkers = set()
         # outgoing bookmarks
         self.outbookmarks = []
         # transaction manager
         self.trmanager = None
         # map { pushkey partid -> callback handling failure}
         # used to handle exception from mandatory pushkey part failure
         self.pkfailcb = {}
         # an iterable of pushvars or None
         self.pushvars = pushvars
         # publish pushed changesets
         self.publish = publish
 
     @util.propertycache
     def futureheads(self):
         """future remote heads if the changeset push succeeds"""
         return self.outgoing.missingheads
 
     @util.propertycache
     def fallbackheads(self):
         """future remote heads if the changeset push fails"""
         if self.revs is None:
             # not target to push, all common are relevant
             return self.outgoing.commonheads
         unfi = self.repo.unfiltered()
         # I want cheads = heads(::missingheads and ::commonheads)
         # (missingheads is revs with secret changeset filtered out)
         #
         # This can be expressed as:
         #     cheads = ( (missingheads and ::commonheads)
         #              + (commonheads and ::missingheads))"
         #              )
         #
         # while trying to push we already computed the following:
         #     common = (::commonheads)
         #     missing = ((commonheads::missingheads) - commonheads)
         #
         # We can pick:
         # * missingheads part of common (::commonheads)
         common = self.outgoing.common
         nm = self.repo.changelog.nodemap
         cheads = [node for node in self.revs if nm[node] in common]
         # and
         # * commonheads parents on missing
         revset = unfi.set('%ln and parents(roots(%ln))',
                          self.outgoing.commonheads,
                          self.outgoing.missing)
         cheads.extend(c.node() for c in revset)
         return cheads
 
     @property
     def commonheads(self):
         """set of all common heads after changeset bundle push"""
         if self.cgresult:
             return self.futureheads
         else:
             return self.fallbackheads
 
 # mapping of message used when pushing bookmark
 bookmsgmap = {'update': (_("updating bookmark %s\n"),
                          _('updating bookmark %s failed!\n')),
               'export': (_("exporting bookmark %s\n"),
                          _('exporting bookmark %s failed!\n')),
               'delete': (_("deleting remote bookmark %s\n"),
                          _('deleting remote bookmark %s failed!\n')),
               }
 
 
 def push(repo, remote, force=False, revs=None, newbranch=False, bookmarks=(),
          publish=False, opargs=None):
     '''Push outgoing changesets (limited by revs) from a local
     repository to remote. Return an integer:
       - None means nothing to push
       - 0 means HTTP error
       - 1 means we pushed and remote head count is unchanged *or*
         we have outgoing changesets but refused to push
       - other values as described by addchangegroup()
     '''
     if opargs is None:
         opargs = {}
     pushop = pushoperation(repo, remote, force, revs, newbranch, bookmarks,
                            publish, **pycompat.strkwargs(opargs))
     if pushop.remote.local():
         missing = (set(pushop.repo.requirements)
                    - pushop.remote.local().supported)
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise error.Abort(msg)
 
     if not pushop.remote.canpush():
         raise error.Abort(_("destination does not support push"))
 
     if not pushop.remote.capable('unbundle'):
         raise error.Abort(_('cannot push: destination does not support the '
                             'unbundle wire protocol command'))
 
     # get lock as we might write phase data
     wlock = lock = None
     try:
         # bundle2 push may receive a reply bundle touching bookmarks
         # requiring the wlock. Take it now to ensure proper ordering.
         maypushback = pushop.ui.configbool('experimental', 'bundle2.pushback')
         if ((not _forcebundle1(pushop)) and
             maypushback and
             not bookmod.bookmarksinstore(repo)):
             wlock = pushop.repo.wlock()
         lock = pushop.repo.lock()
         pushop.trmanager = transactionmanager(pushop.repo,
                                               'push-response',
                                               pushop.remote.url())
     except error.LockUnavailable as err:
         # source repo cannot be locked.
         # We do not abort the push, but just disable the local phase
         # synchronisation.
         msg = ('cannot lock source repository: %s\n'
                % stringutil.forcebytestr(err))
         pushop.ui.debug(msg)
 
     with wlock or util.nullcontextmanager():
         with lock or util.nullcontextmanager():
             with pushop.trmanager or util.nullcontextmanager():
                 pushop.repo.checkpush(pushop)
                 _checkpublish(pushop)
                 _pushdiscovery(pushop)
                 if not _forcebundle1(pushop):
                     _pushbundle2(pushop)
                 _pushchangeset(pushop)
                 _pushsyncphase(pushop)
                 _pushobsolete(pushop)
                 _pushbookmark(pushop)
 
     if repo.ui.configbool('experimental', 'remotenames'):
         logexchange.pullremotenames(repo, remote)
 
     return pushop
 
 # list of steps to perform discovery before push
 pushdiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pushdiscoverymapping = {}
 
 def pushdiscovery(stepname):
     """decorator for function performing discovery before push
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pushdiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pushdiscoverymapping
         pushdiscoverymapping[stepname] = func
         pushdiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pushdiscovery(pushop):
     """Run all discovery steps"""
     for stepname in pushdiscoveryorder:
         step = pushdiscoverymapping[stepname]
         step(pushop)
 
 @pushdiscovery('changeset')
 def _pushdiscoverychangeset(pushop):
     """discover the changeset that need to be pushed"""
     fci = discovery.findcommonincoming
     if pushop.revs:
         commoninc = fci(pushop.repo, pushop.remote, force=pushop.force,
                         ancestorsof=pushop.revs)
     else:
         commoninc = fci(pushop.repo, pushop.remote, force=pushop.force)
     common, inc, remoteheads = commoninc
     fco = discovery.findcommonoutgoing
     outgoing = fco(pushop.repo, pushop.remote, onlyheads=pushop.revs,
                    commoninc=commoninc, force=pushop.force)
     pushop.outgoing = outgoing
     pushop.remoteheads = remoteheads
     pushop.incoming = inc
 
 @pushdiscovery('phase')
 def _pushdiscoveryphase(pushop):
     """discover the phase that needs to be pushed
 
     (computed for both success and failure case for changesets push)"""
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     remotephases = listkeys(pushop.remote, 'phases')
 
     if (pushop.ui.configbool('ui', '_usedassubrepo')
         and remotephases    # server supports phases
         and not pushop.outgoing.missing # no changesets to be pushed
         and remotephases.get('publishing', False)):
         # When:
         # - this is a subrepo push
         # - and remote support phase
         # - and no changeset are to be pushed
         # - and remote is publishing
         # We may be in issue 3781 case!
         # We drop the possible phase synchronisation done by
         # courtesy to publish changesets possibly locally draft
         # on the remote.
         pushop.outdatedphases = []
         pushop.fallbackoutdatedphases = []
         return
 
     pushop.remotephases = phases.remotephasessummary(pushop.repo,
                                                      pushop.fallbackheads,
                                                      remotephases)
     droots = pushop.remotephases.draftroots
 
     extracond = ''
     if not pushop.remotephases.publishing:
         extracond = ' and public()'
     revset = 'heads((%%ln::%%ln) %s)' % extracond
     # Get the list of all revs draft on remote by public here.
     # XXX Beware that revset break if droots is not strictly
     # XXX root we may want to ensure it is but it is costly
     fallback = list(unfi.set(revset, droots, pushop.fallbackheads))
     if not pushop.remotephases.publishing and pushop.publish:
         future = list(unfi.set('%ln and (not public() or %ln::)',
                                pushop.futureheads, droots))
     elif not outgoing.missing:
         future = fallback
     else:
         # adds changeset we are going to push as draft
         #
         # should not be necessary for publishing server, but because of an
         # issue fixed in xxxxx we have to do it anyway.
         fdroots = list(unfi.set('roots(%ln  + %ln::)',
                        outgoing.missing, droots))
         fdroots = [f.node() for f in fdroots]
         future = list(unfi.set(revset, fdroots, pushop.futureheads))
     pushop.outdatedphases = future
     pushop.fallbackoutdatedphases = fallback
 
 @pushdiscovery('obsmarker')
 def _pushdiscoveryobsmarkers(pushop):
     if not obsolete.isenabled(pushop.repo, obsolete.exchangeopt):
         return
 
     if not pushop.repo.obsstore:
         return
 
     if 'obsolete' not in listkeys(pushop.remote, 'namespaces'):
         return
 
     repo = pushop.repo
     # very naive computation, that can be quite expensive on big repo.
     # However: evolution is currently slow on them anyway.
     nodes = (c.node() for c in repo.set('::%ln', pushop.futureheads))
     pushop.outobsmarkers = pushop.repo.obsstore.relevantmarkers(nodes)
 
 @pushdiscovery('bookmarks')
 def _pushdiscoverybookmarks(pushop):
     ui = pushop.ui
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     ui.debug("checking for updated bookmarks\n")
     ancestors = ()
     if pushop.revs:
         revnums = pycompat.maplist(repo.changelog.rev, pushop.revs)
         ancestors = repo.changelog.ancestors(revnums, inclusive=True)
 
     remotebookmark = listkeys(remote, 'bookmarks')
 
     explicit = {repo._bookmarks.expandname(bookmark)
                 for bookmark in pushop.bookmarks}
 
     remotebookmark = bookmod.unhexlifybookmarks(remotebookmark)
     comp = bookmod.comparebookmarks(repo, repo._bookmarks, remotebookmark)
 
     def safehex(x):
         if x is None:
             return x
         return hex(x)
 
     def hexifycompbookmarks(bookmarks):
         return [(b, safehex(scid), safehex(dcid))
                 for (b, scid, dcid) in bookmarks]
 
     comp = [hexifycompbookmarks(marks) for marks in comp]
     return _processcompared(pushop, ancestors, explicit, remotebookmark, comp)
 
 def _processcompared(pushop, pushed, explicit, remotebms, comp):
     """take decision on bookmark to pull from the remote bookmark
 
     Exist to help extensions who want to alter this behavior.
     """
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = comp
 
     repo = pushop.repo
 
     for b, scid, dcid in advsrc:
         if b in explicit:
             explicit.remove(b)
         if not pushed or repo[scid].rev() in pushed:
             pushop.outbookmarks.append((b, dcid, scid))
     # search added bookmark
     for b, scid, dcid in addsrc:
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, '', scid))
     # search for overwritten bookmark
     for b, scid, dcid in list(advdst) + list(diverge) + list(differ):
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, dcid, scid))
     # search for bookmark to delete
     for b, scid, dcid in adddst:
         if b in explicit:
             explicit.remove(b)
             # treat as "deleted locally"
             pushop.outbookmarks.append((b, dcid, ''))
     # identical bookmarks shouldn't get reported
     for b, scid, dcid in same:
         if b in explicit:
             explicit.remove(b)
 
     if explicit:
         explicit = sorted(explicit)
         # we should probably list all of them
         pushop.ui.warn(_('bookmark %s does not exist on the local '
                          'or remote repository!\n') % explicit[0])
         pushop.bkresult = 2
 
     pushop.outbookmarks.sort()
 
 def _pushcheckoutgoing(pushop):
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     if not outgoing.missing:
         # nothing to push
         scmutil.nochangesfound(unfi.ui, unfi, outgoing.excluded)
         return False
     # something to push
     if not pushop.force:
         # if repo.obsstore == False --> no obsolete
         # then, save the iteration
         if unfi.obsstore:
             # this message are here for 80 char limit reason
             mso = _("push includes obsolete changeset: %s!")
             mspd = _("push includes phase-divergent changeset: %s!")
             mscd = _("push includes content-divergent changeset: %s!")
             mst = {"orphan": _("push includes orphan changeset: %s!"),
                    "phase-divergent": mspd,
                    "content-divergent": mscd}
             # If we are to push if there is at least one
             # obsolete or unstable changeset in missing, at
             # least one of the missinghead will be obsolete or
             # unstable. So checking heads only is ok
             for node in outgoing.missingheads:
                 ctx = unfi[node]
                 if ctx.obsolete():
                     raise error.Abort(mso % ctx)
                 elif ctx.isunstable():
                     # TODO print more than one instability in the abort
                     # message
                     raise error.Abort(mst[ctx.instabilities()[0]] % ctx)
 
         discovery.checkheads(pushop)
     return True
 
 # List of names of steps to perform for an outgoing bundle2, order matters.
 b2partsgenorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 b2partsgenmapping = {}
 
 def b2partsgenerator(stepname, idx=None):
     """decorator for function generating bundle2 part
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the b2partsgenmapping dictionary directly."""
     def dec(func):
         assert stepname not in b2partsgenmapping
         b2partsgenmapping[stepname] = func
         if idx is None:
             b2partsgenorder.append(stepname)
         else:
             b2partsgenorder.insert(idx, stepname)
         return func
     return dec
 
 def _pushb2ctxcheckheads(pushop, bundler):
     """Generate race condition checking parts
 
     Exists as an independent function to aid extensions
     """
     # * 'force' do not check for push race,
     # * if we don't push anything, there are nothing to check.
     if not pushop.force and pushop.outgoing.missingheads:
         allowunrelated = 'related' in bundler.capabilities.get('checkheads', ())
         emptyremote = pushop.pushbranchmap is None
         if not allowunrelated or emptyremote:
             bundler.newpart('check:heads', data=iter(pushop.remoteheads))
         else:
             affected = set()
             for branch, heads in pushop.pushbranchmap.iteritems():
                 remoteheads, newheads, unsyncedheads, discardedheads = heads
                 if remoteheads is not None:
                     remote = set(remoteheads)
                     affected |= set(discardedheads) & remote
                     affected |= remote - set(newheads)
             if affected:
                 data = iter(sorted(affected))
                 bundler.newpart('check:updated-heads', data=data)
 
 def _pushing(pushop):
     """return True if we are pushing anything"""
     return bool(pushop.outgoing.missing
                 or pushop.outdatedphases
                 or pushop.outobsmarkers
                 or pushop.outbookmarks)
 
 @b2partsgenerator('check-bookmarks')
 def _pushb2checkbookmarks(pushop, bundler):
     """insert bookmark move checking"""
     if not _pushing(pushop) or pushop.force:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     hasbookmarkcheck = 'bookmarks' in b2caps
     if not (pushop.outbookmarks and hasbookmarkcheck):
         return
     data = []
     for book, old, new in pushop.outbookmarks:
         old = bin(old)
         data.append((book, old))
     checkdata = bookmod.binaryencode(data)
     bundler.newpart('check:bookmarks', data=checkdata)
 
 @b2partsgenerator('check-phases')
 def _pushb2checkphases(pushop, bundler):
     """insert phase move checking"""
     if not _pushing(pushop) or pushop.force:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     hasphaseheads = 'heads' in b2caps.get('phases', ())
     if pushop.remotephases is not None and hasphaseheads:
         # check that the remote phase has not changed
         checks = [[] for p in phases.allphases]
         checks[phases.public].extend(pushop.remotephases.publicheads)
         checks[phases.draft].extend(pushop.remotephases.draftroots)
         if any(checks):
             for nodes in checks:
                 nodes.sort()
             checkdata = phases.binaryencode(checks)
             bundler.newpart('check:phases', data=checkdata)
 
 @b2partsgenerator('changeset')
 def _pushb2ctx(pushop, bundler):
     """handle changegroup push through bundle2
 
     addchangegroup result is stored in the ``pushop.cgresult`` attribute.
     """
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     # Send known heads to the server for race detection.
     if not _pushcheckoutgoing(pushop):
         return
     pushop.repo.prepushoutgoinghooks(pushop)
 
     _pushb2ctxcheckheads(pushop, bundler)
 
     b2caps = bundle2.bundle2caps(pushop.remote)
     version = '01'
     cgversions = b2caps.get('changegroup')
     if cgversions:  # 3.1 and 3.2 ship with an empty value
         cgversions = [v for v in cgversions
                       if v in changegroup.supportedoutgoingversions(
                           pushop.repo)]
         if not cgversions:
             raise error.Abort(_('no common changegroup version'))
         version = max(cgversions)
     cgstream = changegroup.makestream(pushop.repo, pushop.outgoing, version,
                                       'push')
     cgpart = bundler.newpart('changegroup', data=cgstream)
     if cgversions:
         cgpart.addparam('version', version)
     if 'treemanifest' in pushop.repo.requirements:
         cgpart.addparam('treemanifest', '1')
     def handlereply(op):
         """extract addchangegroup returns from server reply"""
         cgreplies = op.records.getreplies(cgpart.id)
         assert len(cgreplies['changegroup']) == 1
         pushop.cgresult = cgreplies['changegroup'][0]['return']
     return handlereply
 
 @b2partsgenerator('phase')
 def _pushb2phases(pushop, bundler):
     """handle phase push through bundle2"""
     if 'phases' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     ui = pushop.repo.ui
 
     legacyphase = 'phases' in ui.configlist('devel', 'legacy.exchange')
     haspushkey = 'pushkey' in b2caps
     hasphaseheads = 'heads' in b2caps.get('phases', ())
 
     if hasphaseheads and not legacyphase:
         return _pushb2phaseheads(pushop, bundler)
     elif haspushkey:
         return _pushb2phasespushkey(pushop, bundler)
 
 def _pushb2phaseheads(pushop, bundler):
     """push phase information through a bundle2 - binary part"""
     pushop.stepsdone.add('phases')
     if pushop.outdatedphases:
         updates = [[] for p in phases.allphases]
         updates[0].extend(h.node() for h in pushop.outdatedphases)
         phasedata = phases.binaryencode(updates)
         bundler.newpart('phase-heads', data=phasedata)
 
 def _pushb2phasespushkey(pushop, bundler):
     """push phase information through a bundle2 - pushkey part"""
     pushop.stepsdone.add('phases')
     part2node = []
 
     def handlefailure(pushop, exc):
         targetid = int(exc.partid)
         for partid, node in part2node:
             if partid == targetid:
                 raise error.Abort(_('updating %s to public failed') % node)
 
     enc = pushkey.encode
     for newremotehead in pushop.outdatedphases:
         part = bundler.newpart('pushkey')
         part.addparam('namespace', enc('phases'))
         part.addparam('key', enc(newremotehead.hex()))
         part.addparam('old', enc('%d' % phases.draft))
         part.addparam('new', enc('%d' % phases.public))
         part2node.append((part.id, newremotehead))
         pushop.pkfailcb[part.id] = handlefailure
 
     def handlereply(op):
         for partid, node in part2node:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             msg = None
             if not results:
                 msg = _('server ignored update of %s to public!\n') % node
             elif not int(results[0]['return']):
                 msg = _('updating %s to public failed!\n') % node
             if msg is not None:
                 pushop.ui.warn(msg)
     return handlereply
 
 @b2partsgenerator('obsmarkers')
 def _pushb2obsmarkers(pushop, bundler):
     if 'obsmarkers' in pushop.stepsdone:
         return
     remoteversions = bundle2.obsmarkersversion(bundler.capabilities)
     if obsolete.commonversion(remoteversions) is None:
         return
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         markers = sorted(pushop.outobsmarkers)
         bundle2.buildobsmarkerspart(bundler, markers)
 
 @b2partsgenerator('bookmarks')
 def _pushb2bookmarks(pushop, bundler):
     """handle bookmark push through bundle2"""
     if 'bookmarks' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
 
     legacy = pushop.repo.ui.configlist('devel', 'legacy.exchange')
     legacybooks = 'bookmarks' in legacy
 
     if not legacybooks and 'bookmarks' in b2caps:
         return _pushb2bookmarkspart(pushop, bundler)
     elif 'pushkey' in b2caps:
         return _pushb2bookmarkspushkey(pushop, bundler)
 
 def _bmaction(old, new):
     """small utility for bookmark pushing"""
     if not old:
         return 'export'
     elif not new:
         return 'delete'
     return 'update'
 
 def _pushb2bookmarkspart(pushop, bundler):
     pushop.stepsdone.add('bookmarks')
     if not pushop.outbookmarks:
         return
 
     allactions = []
     data = []
     for book, old, new in pushop.outbookmarks:
         new = bin(new)
         data.append((book, new))
         allactions.append((book, _bmaction(old, new)))
     checkdata = bookmod.binaryencode(data)
     bundler.newpart('bookmarks', data=checkdata)
 
     def handlereply(op):
         ui = pushop.ui
         # if success
         for book, action in allactions:
             ui.status(bookmsgmap[action][0] % book)
 
     return handlereply
 
 def _pushb2bookmarkspushkey(pushop, bundler):
     pushop.stepsdone.add('bookmarks')
     part2book = []
     enc = pushkey.encode
 
     def handlefailure(pushop, exc):
         targetid = int(exc.partid)
         for partid, book, action in part2book:
             if partid == targetid:
                 raise error.Abort(bookmsgmap[action][1].rstrip() % book)
         # we should not be called for part we did not generated
         assert False
 
     for book, old, new in pushop.outbookmarks:
         part = bundler.newpart('pushkey')
         part.addparam('namespace', enc('bookmarks'))
         part.addparam('key', enc(book))
         part.addparam('old', enc(old))
         part.addparam('new', enc(new))
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
         part2book.append((part.id, book, action))
         pushop.pkfailcb[part.id] = handlefailure
 
     def handlereply(op):
         ui = pushop.ui
         for partid, book, action in part2book:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             if not results:
                 pushop.ui.warn(_('server ignored bookmark %s update\n') % book)
             else:
                 ret = int(results[0]['return'])
                 if ret:
                     ui.status(bookmsgmap[action][0] % book)
                 else:
                     ui.warn(bookmsgmap[action][1] % book)
                     if pushop.bkresult is not None:
                         pushop.bkresult = 1
     return handlereply
 
 @b2partsgenerator('pushvars', idx=0)
 def _getbundlesendvars(pushop, bundler):
     '''send shellvars via bundle2'''
     pushvars = pushop.pushvars
     if pushvars:
         shellvars = {}
         for raw in pushvars:
             if '=' not in raw:
                 msg = ("unable to parse variable '%s', should follow "
                         "'KEY=VALUE' or 'KEY=' format")
                 raise error.Abort(msg % raw)
             k, v = raw.split('=', 1)
             shellvars[k] = v
 
         part = bundler.newpart('pushvars')
 
         for key, value in shellvars.iteritems():
             part.addparam(key, value, mandatory=False)
 
 def _pushbundle2(pushop):
     """push data to the remote using bundle2
 
     The only currently supported type of data is changegroup but this will
     evolve in the future."""
     bundler = bundle2.bundle20(pushop.ui, bundle2.bundle2caps(pushop.remote))
     pushback = (pushop.trmanager
                 and pushop.ui.configbool('experimental', 'bundle2.pushback'))
 
     # create reply capability
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(pushop.repo,
                                                       allowpushback=pushback,
                                                       role='client'))
     bundler.newpart('replycaps', data=capsblob)
     replyhandlers = []
     for partgenname in b2partsgenorder:
         partgen = b2partsgenmapping[partgenname]
         ret = partgen(pushop, bundler)
         if callable(ret):
             replyhandlers.append(ret)
     # do not push if nothing to push
     if bundler.nbparts <= 1:
         return
     stream = util.chunkbuffer(bundler.getchunks())
     try:
         try:
             with pushop.remote.commandexecutor() as e:
                 reply = e.callcommand('unbundle', {
                     'bundle': stream,
                     'heads': ['force'],
                     'url': pushop.remote.url(),
                 }).result()
         except error.BundleValueError as exc:
             raise error.Abort(_('missing support for %s') % exc)
         try:
             trgetter = None
             if pushback:
                 trgetter = pushop.trmanager.transaction
             op = bundle2.processbundle(pushop.repo, reply, trgetter)
         except error.BundleValueError as exc:
             raise error.Abort(_('missing support for %s') % exc)
         except bundle2.AbortFromPart as exc:
             pushop.ui.status(_('remote: %s\n') % exc)
             if exc.hint is not None:
                 pushop.ui.status(_('remote: %s\n') % ('(%s)' % exc.hint))
             raise error.Abort(_('push failed on remote'))
     except error.PushkeyFailed as exc:
         partid = int(exc.partid)
         if partid not in pushop.pkfailcb:
             raise
         pushop.pkfailcb[partid](pushop, exc)
     for rephand in replyhandlers:
         rephand(op)
 
 def _pushchangeset(pushop):
     """Make the actual push of changeset bundle to remote repo"""
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     if not _pushcheckoutgoing(pushop):
         return
 
     # Should have verified this in push().
     assert pushop.remote.capable('unbundle')
 
     pushop.repo.prepushoutgoinghooks(pushop)
     outgoing = pushop.outgoing
     # TODO: get bundlecaps from remote
     bundlecaps = None
     # create a changegroup from local
     if pushop.revs is None and not (outgoing.excluded
                             or pushop.repo.changelog.filteredrevs):
         # push everything,
         # use the fast path, no race possible on push
         cg = changegroup.makechangegroup(pushop.repo, outgoing, '01', 'push',
                 fastpath=True, bundlecaps=bundlecaps)
     else:
         cg = changegroup.makechangegroup(pushop.repo, outgoing, '01',
                                         'push', bundlecaps=bundlecaps)
 
     # apply changegroup to remote
     # local repo finds heads on server, finds out what
     # revs it must push. once revs transferred, if server
     # finds it has different heads (someone else won
     # commit/push race), server aborts.
     if pushop.force:
         remoteheads = ['force']
     else:
         remoteheads = pushop.remoteheads
     # ssh: return remote's addchangegroup()
     # http: return remote's addchangegroup() or 0 for error
     pushop.cgresult = pushop.remote.unbundle(cg, remoteheads,
                                         pushop.repo.url())
 
 def _pushsyncphase(pushop):
     """synchronise phase information locally and remotely"""
     cheads = pushop.commonheads
     # even when we don't push, exchanging phase data is useful
     remotephases = listkeys(pushop.remote, 'phases')
     if (pushop.ui.configbool('ui', '_usedassubrepo')
         and remotephases    # server supports phases
         and pushop.cgresult is None # nothing was pushed
         and remotephases.get('publishing', False)):
         # When:
         # - this is a subrepo push
         # - and remote support phase
         # - and no changeset was pushed
         # - and remote is publishing
         # We may be in issue 3871 case!
         # We drop the possible phase synchronisation done by
         # courtesy to publish changesets possibly locally draft
         # on the remote.
         remotephases = {'publishing': 'True'}
     if not remotephases: # old server or public only reply from non-publishing
         _localphasemove(pushop, cheads)
         # don't push any phase data as there is nothing to push
     else:
         ana = phases.analyzeremotephases(pushop.repo, cheads,
                                          remotephases)
         pheads, droots = ana
         ### Apply remote phase on local
         if remotephases.get('publishing', False):
             _localphasemove(pushop, cheads)
         else: # publish = False
             _localphasemove(pushop, pheads)
             _localphasemove(pushop, cheads, phases.draft)
         ### Apply local phase on remote
 
         if pushop.cgresult:
             if 'phases' in pushop.stepsdone:
                 # phases already pushed though bundle2
                 return
             outdated = pushop.outdatedphases
         else:
             outdated = pushop.fallbackoutdatedphases
 
         pushop.stepsdone.add('phases')
 
         # filter heads already turned public by the push
         outdated = [c for c in outdated if c.node() not in pheads]
         # fallback to independent pushkey command
         for newremotehead in outdated:
             with pushop.remote.commandexecutor() as e:
                 r = e.callcommand('pushkey', {
                     'namespace': 'phases',
                     'key': newremotehead.hex(),
                     'old': '%d' % phases.draft,
                     'new': '%d' % phases.public
                 }).result()
 
             if not r:
                 pushop.ui.warn(_('updating %s to public failed!\n')
                                % newremotehead)
 
 def _localphasemove(pushop, nodes, phase=phases.public):
     """move <nodes> to <phase> in the local source repo"""
     if pushop.trmanager:
         phases.advanceboundary(pushop.repo,
                                pushop.trmanager.transaction(),
                                phase,
                                nodes)
     else:
         # repo is not locked, do not change any phases!
         # Informs the user that phases should have been moved when
         # applicable.
         actualmoves = [n for n in nodes if phase < pushop.repo[n].phase()]
         phasestr = phases.phasenames[phase]
         if actualmoves:
             pushop.ui.status(_('cannot lock source repo, skipping '
                                'local %s phase update\n') % phasestr)
 
 def _pushobsolete(pushop):
     """utility function to push obsolete markers to a remote"""
     if 'obsmarkers' in pushop.stepsdone:
         return
     repo = pushop.repo
     remote = pushop.remote
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         pushop.ui.debug('try to push obsolete markers to remote\n')
         rslts = []
         remotedata = obsolete._pushkeyescape(sorted(pushop.outobsmarkers))
         for key in sorted(remotedata, reverse=True):
             # reverse sort to ensure we end with dump0
             data = remotedata[key]
             rslts.append(remote.pushkey('obsolete', key, '', data))
         if [r for r in rslts if not r]:
             msg = _('failed to push some obsolete markers!\n')
             repo.ui.warn(msg)
 
 def _pushbookmark(pushop):
     """Update bookmark position on remote"""
     if pushop.cgresult == 0 or 'bookmarks' in pushop.stepsdone:
         return
     pushop.stepsdone.add('bookmarks')
     ui = pushop.ui
     remote = pushop.remote
 
     for b, old, new in pushop.outbookmarks:
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
 
         with remote.commandexecutor() as e:
             r = e.callcommand('pushkey', {
                 'namespace': 'bookmarks',
                 'key': b,
                 'old': old,
                 'new': new,
             }).result()
 
         if r:
             ui.status(bookmsgmap[action][0] % b)
         else:
             ui.warn(bookmsgmap[action][1] % b)
             # discovery can have set the value form invalid entry
             if pushop.bkresult is not None:
                 pushop.bkresult = 1
 
 class pulloperation(object):
     """A object that represent a single pull operation
 
     It purpose is to carry pull related state and very common operation.
 
     A new should be created at the beginning of each pull and discarded
     afterward.
     """
 
     def __init__(self, repo, remote, heads=None, force=False, bookmarks=(),
                  remotebookmarks=None, streamclonerequested=None,
                  includepats=None, excludepats=None, depth=None):
         # repo we pull into
         self.repo = repo
         # repo we pull from
         self.remote = remote
         # revision we try to pull (None is "all")
         self.heads = heads
         # bookmark pulled explicitly
         self.explicitbookmarks = [repo._bookmarks.expandname(bookmark)
                                   for bookmark in bookmarks]
         # do we force pull?
         self.force = force
         # whether a streaming clone was requested
         self.streamclonerequested = streamclonerequested
         # transaction manager
         self.trmanager = None
         # set of common changeset between local and remote before pull
         self.common = None
         # set of pulled head
         self.rheads = None
         # list of missing changeset to fetch remotely
         self.fetch = None
         # remote bookmarks data
         self.remotebookmarks = remotebookmarks
         # result of changegroup pulling (used as return code by pull)
         self.cgresult = None
         # list of step already done
         self.stepsdone = set()
         # Whether we attempted a clone from pre-generated bundles.
         self.clonebundleattempted = False
         # Set of file patterns to include.
         self.includepats = includepats
         # Set of file patterns to exclude.
         self.excludepats = excludepats
         # Number of ancestor changesets to pull from each pulled head.
         self.depth = depth
 
     @util.propertycache
     def pulledsubset(self):
         """heads of the set of changeset target by the pull"""
         # compute target subset
         if self.heads is None:
             # We pulled every thing possible
             # sync on everything common
             c = set(self.common)
             ret = list(self.common)
             for n in self.rheads:
                 if n not in c:
                     ret.append(n)
             return ret
         else:
             # We pulled a specific subset
             # sync on this subset
             return self.heads
 
     @util.propertycache
     def canusebundle2(self):
         return not _forcebundle1(self)
 
     @util.propertycache
     def remotebundle2caps(self):
         return bundle2.bundle2caps(self.remote)
 
     def gettransaction(self):
         # deprecated; talk to trmanager directly
         return self.trmanager.transaction()
 
 class transactionmanager(util.transactional):
     """An object to manage the life cycle of a transaction
 
     It creates the transaction on demand and calls the appropriate hooks when
     closing the transaction."""
     def __init__(self, repo, source, url):
         self.repo = repo
         self.source = source
         self.url = url
         self._tr = None
 
     def transaction(self):
         """Return an open transaction object, constructing if necessary"""
         if not self._tr:
             trname = '%s\n%s' % (self.source, util.hidepassword(self.url))
             self._tr = self.repo.transaction(trname)
             self._tr.hookargs['source'] = self.source
             self._tr.hookargs['url'] = self.url
         return self._tr
 
     def close(self):
         """close transaction if created"""
         if self._tr is not None:
             self._tr.close()
 
     def release(self):
         """release transaction if created"""
         if self._tr is not None:
             self._tr.release()
 
 def listkeys(remote, namespace):
     with remote.commandexecutor() as e:
         return e.callcommand('listkeys', {'namespace': namespace}).result()
 
 def _fullpullbundle2(repo, pullop):
     # The server may send a partial reply, i.e. when inlining
     # pre-computed bundles. In that case, update the common
     # set based on the results and pull another bundle.
     #
     # There are two indicators that the process is finished:
     # - no changeset has been added, or
     # - all remote heads are known locally.
     # The head check must use the unfiltered view as obsoletion
     # markers can hide heads.
     unfi = repo.unfiltered()
     unficl = unfi.changelog
     def headsofdiff(h1, h2):
         """Returns heads(h1 % h2)"""
         res = unfi.set('heads(%ln %% %ln)', h1, h2)
         return set(ctx.node() for ctx in res)
     def headsofunion(h1, h2):
         """Returns heads((h1 + h2) - null)"""
         res = unfi.set('heads((%ln + %ln - null))', h1, h2)
         return set(ctx.node() for ctx in res)
     while True:
         old_heads = unficl.heads()
         clstart = len(unficl)
         _pullbundle2(pullop)
         if repository.NARROW_REQUIREMENT in repo.requirements:
             # XXX narrow clones filter the heads on the server side during
             # XXX getbundle and result in partial replies as well.
             # XXX Disable pull bundles in this case as band aid to avoid
             # XXX extra round trips.
             break
         if clstart == len(unficl):
             break
         if all(unficl.hasnode(n) for n in pullop.rheads):
             break
         new_heads = headsofdiff(unficl.heads(), old_heads)
         pullop.common = headsofunion(new_heads, pullop.common)
         pullop.rheads = set(pullop.rheads) - pullop.common
 
 def pull(repo, remote, heads=None, force=False, bookmarks=(), opargs=None,
          streamclonerequested=None, includepats=None, excludepats=None,
          depth=None):
     """Fetch repository data from a remote.
 
     This is the main function used to retrieve data from a remote repository.
 
     ``repo`` is the local repository to clone into.
     ``remote`` is a peer instance.
     ``heads`` is an iterable of revisions we want to pull. ``None`` (the
     default) means to pull everything from the remote.
     ``bookmarks`` is an iterable of bookmarks requesting to be pulled. By
     default, all remote bookmarks are pulled.
     ``opargs`` are additional keyword arguments to pass to ``pulloperation``
     initialization.
     ``streamclonerequested`` is a boolean indicating whether a "streaming
     clone" is requested. A "streaming clone" is essentially a raw file copy
     of revlogs from the server. This only works when the local repository is
     empty. The default value of ``None`` means to respect the server
     configuration for preferring stream clones.
     ``includepats`` and ``excludepats`` define explicit file patterns to
     include and exclude in storage, respectively. If not defined, narrow
     patterns from the repo instance are used, if available.
     ``depth`` is an integer indicating the DAG depth of history we're
     interested in. If defined, for each revision specified in ``heads``, we
     will fetch up to this many of its ancestors and data associated with them.
 
     Returns the ``pulloperation`` created for this pull.
     """
     if opargs is None:
         opargs = {}
 
     # We allow the narrow patterns to be passed in explicitly to provide more
     # flexibility for API consumers.
     if includepats or excludepats:
         includepats = includepats or set()
         excludepats = excludepats or set()
     else:
         includepats, excludepats = repo.narrowpats
 
     narrowspec.validatepatterns(includepats)
     narrowspec.validatepatterns(excludepats)
 
     pullop = pulloperation(repo, remote, heads, force, bookmarks=bookmarks,
                            streamclonerequested=streamclonerequested,
                            includepats=includepats, excludepats=excludepats,
                            depth=depth,
                            **pycompat.strkwargs(opargs))
 
     peerlocal = pullop.remote.local()
     if peerlocal:
         missing = set(peerlocal.requirements) - pullop.repo.supported
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise error.Abort(msg)
 
     pullop.trmanager = transactionmanager(repo, 'pull', remote.url())
     wlock = util.nullcontextmanager()
     if not bookmod.bookmarksinstore(repo):
         wlock = repo.wlock()
     with wlock, repo.lock(), pullop.trmanager:
         # Use the modern wire protocol, if available.
         if remote.capable('command-changesetdata'):
             exchangev2.pull(pullop)
         else:
             # This should ideally be in _pullbundle2(). However, it needs to run
             # before discovery to avoid extra work.
             _maybeapplyclonebundle(pullop)
             streamclone.maybeperformlegacystreamclone(pullop)
             _pulldiscovery(pullop)
             if pullop.canusebundle2:
                 _fullpullbundle2(repo, pullop)
             _pullchangeset(pullop)
             _pullphase(pullop)
             _pullbookmarks(pullop)
             _pullobsolete(pullop)
 
     # storing remotenames
     if repo.ui.configbool('experimental', 'remotenames'):
         logexchange.pullremotenames(repo, remote)
 
     return pullop
 
 # list of steps to perform discovery before pull
 pulldiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pulldiscoverymapping = {}
 
 def pulldiscovery(stepname):
     """decorator for function performing discovery before pull
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pulldiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pulldiscoverymapping
         pulldiscoverymapping[stepname] = func
         pulldiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pulldiscovery(pullop):
     """Run all discovery steps"""
     for stepname in pulldiscoveryorder:
         step = pulldiscoverymapping[stepname]
         step(pullop)
 
 @pulldiscovery('b1:bookmarks')
 def _pullbookmarkbundle1(pullop):
     """fetch bookmark data in bundle1 case
 
     If not using bundle2, we have to fetch bookmarks before changeset
     discovery to reduce the chance and impact of race conditions."""
     if pullop.remotebookmarks is not None:
         return
     if pullop.canusebundle2 and 'listkeys' in pullop.remotebundle2caps:
         # all known bundle2 servers now support listkeys, but lets be nice with
         # new implementation.
         return
     books = listkeys(pullop.remote, 'bookmarks')
     pullop.remotebookmarks = bookmod.unhexlifybookmarks(books)
 
 
 @pulldiscovery('changegroup')
 def _pulldiscoverychangegroup(pullop):
     """discovery phase for the pull
 
     Current handle changeset discovery only, will change handle all discovery
     at some point."""
     tmp = discovery.findcommonincoming(pullop.repo,
                                        pullop.remote,
                                        heads=pullop.heads,
                                        force=pullop.force)
     common, fetch, rheads = tmp
     nm = pullop.repo.unfiltered().changelog.nodemap
     if fetch and rheads:
         # If a remote heads is filtered locally, put in back in common.
         #
         # This is a hackish solution to catch most of "common but locally
         # hidden situation".  We do not performs discovery on unfiltered
         # repository because it end up doing a pathological amount of round
         # trip for w huge amount of changeset we do not care about.
         #
         # If a set of such "common but filtered" changeset exist on the server
         # but are not including a remote heads, we'll not be able to detect it,
         scommon = set(common)
         for n in rheads:
             if n in nm:
                 if n not in scommon:
                     common.append(n)
         if set(rheads).issubset(set(common)):
             fetch = []
     pullop.common = common
     pullop.fetch = fetch
     pullop.rheads = rheads
 
 def _pullbundle2(pullop):
     """pull data using bundle2
 
     For now, the only supported data are changegroup."""
     kwargs = {'bundlecaps': caps20to10(pullop.repo, role='client')}
 
     # make ui easier to access
     ui = pullop.repo.ui
 
     # At the moment we don't do stream clones over bundle2. If that is
     # implemented then here's where the check for that will go.
     streaming = streamclone.canperformstreamclone(pullop, bundle2=True)[0]
 
     # declare pull perimeters
     kwargs['common'] = pullop.common
     kwargs['heads'] = pullop.heads or pullop.rheads
 
     # check server supports narrow and then adding includepats and excludepats
     servernarrow = pullop.remote.capable(wireprototypes.NARROWCAP)
     if servernarrow and pullop.includepats:
         kwargs['includepats'] = pullop.includepats
     if servernarrow and pullop.excludepats:
         kwargs['excludepats'] = pullop.excludepats
 
     if streaming:
         kwargs['cg'] = False
         kwargs['stream'] = True
         pullop.stepsdone.add('changegroup')
         pullop.stepsdone.add('phases')
 
     else:
         # pulling changegroup
         pullop.stepsdone.add('changegroup')
 
         kwargs['cg'] = pullop.fetch
 
         legacyphase = 'phases' in ui.configlist('devel', 'legacy.exchange')
         hasbinaryphase = 'heads' in pullop.remotebundle2caps.get('phases', ())
         if (not legacyphase and hasbinaryphase):
             kwargs['phases'] = True
             pullop.stepsdone.add('phases')
 
         if 'listkeys' in pullop.remotebundle2caps:
             if 'phases' not in pullop.stepsdone:
                 kwargs['listkeys'] = ['phases']
 
     bookmarksrequested = False
     legacybookmark = 'bookmarks' in ui.configlist('devel', 'legacy.exchange')
     hasbinarybook = 'bookmarks' in pullop.remotebundle2caps
 
     if pullop.remotebookmarks is not None:
         pullop.stepsdone.add('request-bookmarks')
 
     if ('request-bookmarks' not in pullop.stepsdone
         and pullop.remotebookmarks is None
         and not legacybookmark and hasbinarybook):
         kwargs['bookmarks'] = True
         bookmarksrequested = True
 
     if 'listkeys' in pullop.remotebundle2caps:
         if 'request-bookmarks' not in pullop.stepsdone:
             # make sure to always includes bookmark data when migrating
             # `hg incoming --bundle` to using this function.
             pullop.stepsdone.add('request-bookmarks')
             kwargs.setdefault('listkeys', []).append('bookmarks')
 
     # If this is a full pull / clone and the server supports the clone bundles
     # feature, tell the server whether we attempted a clone bundle. The
     # presence of this flag indicates the client supports clone bundles. This
     # will enable the server to treat clients that support clone bundles
     # differently from those that don't.
     if (pullop.remote.capable('clonebundles')
         and pullop.heads is None and list(pullop.common) == [nullid]):
         kwargs['cbattempted'] = pullop.clonebundleattempted
 
     if streaming:
         pullop.repo.ui.status(_('streaming all changes\n'))
     elif not pullop.fetch:
         pullop.repo.ui.status(_("no changes found\n"))
         pullop.cgresult = 0
     else:
         if pullop.heads is None and list(pullop.common) == [nullid]:
             pullop.repo.ui.status(_("requesting all changes\n"))
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         remoteversions = bundle2.obsmarkersversion(pullop.remotebundle2caps)
         if obsolete.commonversion(remoteversions) is not None:
             kwargs['obsmarkers'] = True
             pullop.stepsdone.add('obsmarkers')
     _pullbundle2extraprepare(pullop, kwargs)
 
     with pullop.remote.commandexecutor() as e:
         args = dict(kwargs)
         args['source'] = 'pull'
         bundle = e.callcommand('getbundle', args).result()
 
         try:
             op = bundle2.bundleoperation(pullop.repo, pullop.gettransaction,
                                          source='pull')
             op.modes['bookmarks'] = 'records'
             bundle2.processbundle(pullop.repo, bundle, op=op)
         except bundle2.AbortFromPart as exc:
             pullop.repo.ui.status(_('remote: abort: %s\n') % exc)
             raise error.Abort(_('pull failed on remote'), hint=exc.hint)
         except error.BundleValueError as exc:
             raise error.Abort(_('missing support for %s') % exc)
 
     if pullop.fetch:
         pullop.cgresult = bundle2.combinechangegroupresults(op)
 
     # processing phases change
     for namespace, value in op.records['listkeys']:
         if namespace == 'phases':
             _pullapplyphases(pullop, value)
 
     # processing bookmark update
     if bookmarksrequested:
         books = {}
         for record in op.records['bookmarks']:
             books[record['bookmark']] = record["node"]
         pullop.remotebookmarks = books
     else:
         for namespace, value in op.records['listkeys']:
             if namespace == 'bookmarks':
                 pullop.remotebookmarks = bookmod.unhexlifybookmarks(value)
 
     # bookmark data were either already there or pulled in the bundle
     if pullop.remotebookmarks is not None:
         _pullbookmarks(pullop)
 
 def _pullbundle2extraprepare(pullop, kwargs):
     """hook function so that extensions can extend the getbundle call"""
 
 def _pullchangeset(pullop):
     """pull changeset from unbundle into the local repo"""
     # We delay the open of the transaction as late as possible so we
     # don't open transaction for nothing or you break future useful
     # rollback call
     if 'changegroup' in pullop.stepsdone:
         return
     pullop.stepsdone.add('changegroup')
     if not pullop.fetch:
         pullop.repo.ui.status(_("no changes found\n"))
         pullop.cgresult = 0
         return
     tr = pullop.gettransaction()
     if pullop.heads is None and list(pullop.common) == [nullid]:
         pullop.repo.ui.status(_("requesting all changes\n"))
     elif pullop.heads is None and pullop.remote.capable('changegroupsubset'):
         # issue1320, avoid a race if remote changed after discovery
         pullop.heads = pullop.rheads
 
     if pullop.remote.capable('getbundle'):
         # TODO: get bundlecaps from remote
         cg = pullop.remote.getbundle('pull', common=pullop.common,
                                      heads=pullop.heads or pullop.rheads)
     elif pullop.heads is None:
         with pullop.remote.commandexecutor() as e:
             cg = e.callcommand('changegroup', {
                 'nodes': pullop.fetch,
                 'source': 'pull',
             }).result()
 
     elif not pullop.remote.capable('changegroupsubset'):
         raise error.Abort(_("partial pull cannot be done because "
                            "other repository doesn't support "
                            "changegroupsubset."))
     else:
         with pullop.remote.commandexecutor() as e:
             cg = e.callcommand('changegroupsubset', {
                 'bases': pullop.fetch,
                 'heads': pullop.heads,
                 'source': 'pull',
             }).result()
 
     bundleop = bundle2.applybundle(pullop.repo, cg, tr, 'pull',
                                    pullop.remote.url())
     pullop.cgresult = bundle2.combinechangegroupresults(bundleop)
 
 def _pullphase(pullop):
     # Get remote phases data from remote
     if 'phases' in pullop.stepsdone:
         return
     remotephases = listkeys(pullop.remote, 'phases')
     _pullapplyphases(pullop, remotephases)
 
 def _pullapplyphases(pullop, remotephases):
     """apply phase movement from observed remote state"""
     if 'phases' in pullop.stepsdone:
         return
     pullop.stepsdone.add('phases')
     publishing = bool(remotephases.get('publishing', False))
     if remotephases and not publishing:
         # remote is new and non-publishing
         pheads, _dr = phases.analyzeremotephases(pullop.repo,
                                                  pullop.pulledsubset,
                                                  remotephases)
         dheads = pullop.pulledsubset
     else:
         # Remote is old or publishing all common changesets
         # should be seen as public
         pheads = pullop.pulledsubset
         dheads = []
     unfi = pullop.repo.unfiltered()
     phase = unfi._phasecache.phase
     rev = unfi.changelog.nodemap.get
     public = phases.public
     draft = phases.draft
 
     # exclude changesets already public locally and update the others
     pheads = [pn for pn in pheads if phase(unfi, rev(pn)) > public]
     if pheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, public, pheads)
 
     # exclude changesets already draft locally and update the others
     dheads = [pn for pn in dheads if phase(unfi, rev(pn)) > draft]
     if dheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, draft, dheads)
 
 def _pullbookmarks(pullop):
     """process the remote bookmark information to update the local one"""
     if 'bookmarks' in pullop.stepsdone:
         return
     pullop.stepsdone.add('bookmarks')
     repo = pullop.repo
     remotebookmarks = pullop.remotebookmarks
     bookmod.updatefromremote(repo.ui, repo, remotebookmarks,
                              pullop.remote.url(),
                              pullop.gettransaction,
                              explicit=pullop.explicitbookmarks)
 
 def _pullobsolete(pullop):
     """utility function to pull obsolete markers from a remote
 
     The `gettransaction` is function that return the pull transaction, creating
     one if necessary. We return the transaction to inform the calling code that
     a new transaction have been created (when applicable).
 
     Exists mostly to allow overriding for experimentation purpose"""
     if 'obsmarkers' in pullop.stepsdone:
         return
     pullop.stepsdone.add('obsmarkers')
     tr = None
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         pullop.repo.ui.debug('fetching remote obsolete markers\n')
         remoteobs = listkeys(pullop.remote, 'obsolete')
         if 'dump0' in remoteobs:
             tr = pullop.gettransaction()
             markers = []
             for key in sorted(remoteobs, reverse=True):
                 if key.startswith('dump'):
                     data = util.b85decode(remoteobs[key])
                     version, newmarks = obsolete._readmarkers(data)
                     markers += newmarks
             if markers:
                 pullop.repo.obsstore.add(tr, markers)
             pullop.repo.invalidatevolatilesets()
     return tr
 
 def applynarrowacl(repo, kwargs):
     """Apply narrow fetch access control.
 
     This massages the named arguments for getbundle wire protocol commands
     so requested data is filtered through access control rules.
     """
     ui = repo.ui
     # TODO this assumes existence of HTTP and is a layering violation.
     username = ui.shortuser(ui.environ.get('REMOTE_USER') or ui.username())
     user_includes = ui.configlist(
         _NARROWACL_SECTION, username + '.includes',
         ui.configlist(_NARROWACL_SECTION, 'default.includes'))
     user_excludes = ui.configlist(
         _NARROWACL_SECTION, username + '.excludes',
         ui.configlist(_NARROWACL_SECTION, 'default.excludes'))
     if not user_includes:
         raise error.Abort(_("{} configuration for user {} is empty")
                           .format(_NARROWACL_SECTION, username))
 
     user_includes = [
         'path:.' if p == '*' else 'path:' + p for p in user_includes]
     user_excludes = [
         'path:.' if p == '*' else 'path:' + p for p in user_excludes]
 
     req_includes = set(kwargs.get(r'includepats', []))
     req_excludes = set(kwargs.get(r'excludepats', []))
 
     req_includes, req_excludes, invalid_includes = narrowspec.restrictpatterns(
         req_includes, req_excludes, user_includes, user_excludes)
 
     if invalid_includes:
         raise error.Abort(
             _("The following includes are not accessible for {}: {}")
             .format(username, invalid_includes))
 
     new_args = {}
     new_args.update(kwargs)
     new_args[r'narrow'] = True
     new_args[r'narrow_acl'] = True
     new_args[r'includepats'] = req_includes
     if req_excludes:
         new_args[r'excludepats'] = req_excludes
 
     return new_args
 
 def _computeellipsis(repo, common, heads, known, match, depth=None):
     """Compute the shape of a narrowed DAG.
 
     Args:
       repo: The repository we're transferring.
       common: The roots of the DAG range we're transferring.
               May be just [nullid], which means all ancestors of heads.
       heads: The heads of the DAG range we're transferring.
       match: The narrowmatcher that allows us to identify relevant changes.
       depth: If not None, only consider nodes to be full nodes if they are at
              most depth changesets away from one of heads.
 
     Returns:
       A tuple of (visitnodes, relevant_nodes, ellipsisroots) where:
 
         visitnodes: The list of nodes (either full or ellipsis) which
                     need to be sent to the client.
         relevant_nodes: The set of changelog nodes which change a file inside
                  the narrowspec. The client needs these as non-ellipsis nodes.
         ellipsisroots: A dict of {rev: parents} that is used in
                        narrowchangegroup to produce ellipsis nodes with the
                        correct parents.
     """
     cl = repo.changelog
     mfl = repo.manifestlog
 
     clrev = cl.rev
 
     commonrevs = {clrev(n) for n in common} | {nullrev}
     headsrevs = {clrev(n) for n in heads}
 
     if depth:
         revdepth = {h: 0 for h in headsrevs}
 
     ellipsisheads = collections.defaultdict(set)
     ellipsisroots = collections.defaultdict(set)
 
     def addroot(head, curchange):
         """Add a root to an ellipsis head, splitting heads with 3 roots."""
         ellipsisroots[head].add(curchange)
         # Recursively split ellipsis heads with 3 roots by finding the
         # roots' youngest common descendant which is an elided merge commit.
         # That descendant takes 2 of the 3 roots as its own, and becomes a
         # root of the head.
         while len(ellipsisroots[head]) > 2:
             child, roots = splithead(head)
             splitroots(head, child, roots)
             head = child  # Recurse in case we just added a 3rd root
 
     def splitroots(head, child, roots):
         ellipsisroots[head].difference_update(roots)
         ellipsisroots[head].add(child)
         ellipsisroots[child].update(roots)
         ellipsisroots[child].discard(child)
 
     def splithead(head):
         r1, r2, r3 = sorted(ellipsisroots[head])
         for nr1, nr2 in ((r2, r3), (r1, r3), (r1, r2)):
             mid = repo.revs('sort(merge() & %d::%d & %d::%d, -rev)',
                             nr1, head, nr2, head)
             for j in mid:
                 if j == nr2:
                     return nr2, (nr1, nr2)
                 if j not in ellipsisroots or len(ellipsisroots[j]) < 2:
                     return j, (nr1, nr2)
         raise error.Abort(_('Failed to split up ellipsis node! head: %d, '
                             'roots: %d %d %d') % (head, r1, r2, r3))
 
     missing = list(cl.findmissingrevs(common=commonrevs, heads=headsrevs))
     visit = reversed(missing)
     relevant_nodes = set()
     visitnodes = [cl.node(m) for m in missing]
     required = set(headsrevs) | known
     for rev in visit:
         clrev = cl.changelogrevision(rev)
         ps = [prev for prev in cl.parentrevs(rev) if prev != nullrev]
         if depth is not None:
             curdepth = revdepth[rev]
             for p in ps:
                 revdepth[p] = min(curdepth + 1, revdepth.get(p, depth + 1))
         needed = False
         shallow_enough = depth is None or revdepth[rev] <= depth
         if shallow_enough:
             curmf = mfl[clrev.manifest].read()
             if ps:
                 # We choose to not trust the changed files list in
                 # changesets because it's not always correct. TODO: could
                 # we trust it for the non-merge case?
                 p1mf = mfl[cl.changelogrevision(ps[0]).manifest].read()
                 needed = bool(curmf.diff(p1mf, match))
                 if not needed and len(ps) > 1:
                     # For merge changes, the list of changed files is not
                     # helpful, since we need to emit the merge if a file
                     # in the narrow spec has changed on either side of the
                     # merge. As a result, we do a manifest diff to check.
                     p2mf = mfl[cl.changelogrevision(ps[1]).manifest].read()
                     needed = bool(curmf.diff(p2mf, match))
             else:
                 # For a root node, we need to include the node if any
                 # files in the node match the narrowspec.
                 needed = any(curmf.walk(match))
 
         if needed:
             for head in ellipsisheads[rev]:
                 addroot(head, rev)
             for p in ps:
                 required.add(p)
             relevant_nodes.add(cl.node(rev))
         else:
             if not ps:
                 ps = [nullrev]
             if rev in required:
                 for head in ellipsisheads[rev]:
                     addroot(head, rev)
                 for p in ps:
                     ellipsisheads[p].add(rev)
             else:
                 for p in ps:
                     ellipsisheads[p] |= ellipsisheads[rev]
 
     # add common changesets as roots of their reachable ellipsis heads
     for c in commonrevs:
         for head in ellipsisheads[c]:
             addroot(head, c)
     return visitnodes, relevant_nodes, ellipsisroots
 
 def caps20to10(repo, role):
     """return a set with appropriate options to use bundle20 during getbundle"""
     caps = {'HG20'}
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(repo, role=role))
     caps.add('bundle2=' + urlreq.quote(capsblob))
     return caps
 
 # List of names of steps to perform for a bundle2 for getbundle, order matters.
 getbundle2partsorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 getbundle2partsmapping = {}
 
 def getbundle2partsgenerator(stepname, idx=None):
     """decorator for function generating bundle2 part for getbundle
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the getbundle2partsmapping dictionary directly."""
     def dec(func):
         assert stepname not in getbundle2partsmapping
         getbundle2partsmapping[stepname] = func
         if idx is None:
             getbundle2partsorder.append(stepname)
         else:
             getbundle2partsorder.insert(idx, stepname)
         return func
     return dec
 
 def bundle2requested(bundlecaps):
     if bundlecaps is not None:
         return any(cap.startswith('HG2') for cap in bundlecaps)
     return False
 
 def getbundlechunks(repo, source, heads=None, common=None, bundlecaps=None,
                     **kwargs):
     """Return chunks constituting a bundle's raw data.
 
     Could be a bundle HG10 or a bundle HG20 depending on bundlecaps
     passed.
 
     Returns a 2-tuple of a dict with metadata about the generated bundle
     and an iterator over raw chunks (of varying sizes).
     """
     kwargs = pycompat.byteskwargs(kwargs)
     info = {}
     usebundle2 = bundle2requested(bundlecaps)
     # bundle10 case
     if not usebundle2:
         if bundlecaps and not kwargs.get('cg', True):
             raise ValueError(_('request for bundle10 must include changegroup'))
 
         if kwargs:
             raise ValueError(_('unsupported getbundle arguments: %s')
                              % ', '.join(sorted(kwargs.keys())))
         outgoing = _computeoutgoing(repo, heads, common)
         info['bundleversion'] = 1
         return info, changegroup.makestream(repo, outgoing, '01', source,
                                             bundlecaps=bundlecaps)
 
     # bundle20 case
     info['bundleversion'] = 2
     b2caps = {}
     for bcaps in bundlecaps:
         if bcaps.startswith('bundle2='):
             blob = urlreq.unquote(bcaps[len('bundle2='):])
             b2caps.update(bundle2.decodecaps(blob))
     bundler = bundle2.bundle20(repo.ui, b2caps)
 
     kwargs['heads'] = heads
     kwargs['common'] = common
 
     for name in getbundle2partsorder:
         func = getbundle2partsmapping[name]
         func(bundler, repo, source, bundlecaps=bundlecaps, b2caps=b2caps,
              **pycompat.strkwargs(kwargs))
 
     info['prefercompressed'] = bundler.prefercompressed
 
     return info, bundler.getchunks()
 
 @getbundle2partsgenerator('stream2')
 def _getbundlestream2(bundler, repo, *args, **kwargs):
     return bundle2.addpartbundlestream2(bundler, repo, **kwargs)
 
 @getbundle2partsgenerator('changegroup')
 def _getbundlechangegrouppart(bundler, repo, source, bundlecaps=None,
                               b2caps=None, heads=None, common=None, **kwargs):
     """add a changegroup part to the requested bundle"""
     if not kwargs.get(r'cg', True):
         return
 
     version = '01'
     cgversions = b2caps.get('changegroup')
     if cgversions:  # 3.1 and 3.2 ship with an empty value
         cgversions = [v for v in cgversions
                       if v in changegroup.supportedoutgoingversions(repo)]
         if not cgversions:
             raise error.Abort(_('no common changegroup version'))
         version = max(cgversions)
 
     outgoing = _computeoutgoing(repo, heads, common)
     if not outgoing.missing:
         return
 
     if kwargs.get(r'narrow', False):
         include = sorted(filter(bool, kwargs.get(r'includepats', [])))
         exclude = sorted(filter(bool, kwargs.get(r'excludepats', [])))
         matcher = narrowspec.match(repo.root, include=include, exclude=exclude)
     else:
         matcher = None
 
     cgstream = changegroup.makestream(repo, outgoing, version, source,
                                       bundlecaps=bundlecaps, matcher=matcher)
 
     part = bundler.newpart('changegroup', data=cgstream)
     if cgversions:
         part.addparam('version', version)
 
     part.addparam('nbchanges', '%d' % len(outgoing.missing),
                   mandatory=False)
 
     if 'treemanifest' in repo.requirements:
         part.addparam('treemanifest', '1')
 
     if (kwargs.get(r'narrow', False) and kwargs.get(r'narrow_acl', False)
         and (include or exclude)):
         # this is mandatory because otherwise ACL clients won't work
         narrowspecpart = bundler.newpart('Narrow:responsespec')
         narrowspecpart.data = '%s\0%s' % ('\n'.join(include),
                                            '\n'.join(exclude))
 
 @getbundle2partsgenerator('bookmarks')
 def _getbundlebookmarkpart(bundler, repo, source, bundlecaps=None,
                               b2caps=None, **kwargs):
     """add a bookmark part to the requested bundle"""
     if not kwargs.get(r'bookmarks', False):
         return
     if 'bookmarks' not in b2caps:
         raise error.Abort(_('no common bookmarks exchange method'))
     books  = bookmod.listbinbookmarks(repo)
     data = bookmod.binaryencode(books)
     if data:
         bundler.newpart('bookmarks', data=data)
 
 @getbundle2partsgenerator('listkeys')
 def _getbundlelistkeysparts(bundler, repo, source, bundlecaps=None,
                             b2caps=None, **kwargs):
     """add parts containing listkeys namespaces to the requested bundle"""
     listkeys = kwargs.get(r'listkeys', ())
     for namespace in listkeys:
         part = bundler.newpart('listkeys')
         part.addparam('namespace', namespace)
         keys = repo.listkeys(namespace).items()
         part.data = pushkey.encodekeys(keys)
 
 @getbundle2partsgenerator('obsmarkers')
 def _getbundleobsmarkerpart(bundler, repo, source, bundlecaps=None,
                             b2caps=None, heads=None, **kwargs):
     """add an obsolescence markers part to the requested bundle"""
     if kwargs.get(r'obsmarkers', False):
         if heads is None:
             heads = repo.heads()
         subset = [c.node() for c in repo.set('::%ln', heads)]
         markers = repo.obsstore.relevantmarkers(subset)
         markers = sorted(markers)
         bundle2.buildobsmarkerspart(bundler, markers)
 
 @getbundle2partsgenerator('phases')
 def _getbundlephasespart(bundler, repo, source, bundlecaps=None,
                             b2caps=None, heads=None, **kwargs):
     """add phase heads part to the requested bundle"""
     if kwargs.get(r'phases', False):
         if not 'heads' in b2caps.get('phases'):
             raise error.Abort(_('no common phases exchange method'))
         if heads is None:
             heads = repo.heads()
 
         headsbyphase = collections.defaultdict(set)
         if repo.publishing():
             headsbyphase[phases.public] = heads
         else:
             # find the appropriate heads to move
 
             phase = repo._phasecache.phase
             node = repo.changelog.node
             rev = repo.changelog.rev
             for h in heads:
                 headsbyphase[phase(repo, rev(h))].add(h)
             seenphases = list(headsbyphase.keys())
 
             # We do not handle anything but public and draft phase for now)
             if seenphases:
                 assert max(seenphases) <= phases.draft
 
             # if client is pulling non-public changesets, we need to find
             # intermediate public heads.
             draftheads = headsbyphase.get(phases.draft, set())
             if draftheads:
                 publicheads = headsbyphase.get(phases.public, set())
 
                 revset = 'heads(only(%ln, %ln) and public())'
                 extraheads = repo.revs(revset, draftheads, publicheads)
                 for r in extraheads:
                     headsbyphase[phases.public].add(node(r))
 
         # transform data in a format used by the encoding function
         phasemapping = []
         for phase in phases.allphases:
             phasemapping.append(sorted(headsbyphase[phase]))
 
         # generate the actual part
         phasedata = phases.binaryencode(phasemapping)
         bundler.newpart('phase-heads', data=phasedata)
 
 @getbundle2partsgenerator('hgtagsfnodes')
 def _getbundletagsfnodes(bundler, repo, source, bundlecaps=None,
                          b2caps=None, heads=None, common=None,
                          **kwargs):
     """Transfer the .hgtags filenodes mapping.
 
     Only values for heads in this bundle will be transferred.
 
     The part data consists of pairs of 20 byte changeset node and .hgtags
     filenodes raw values.
     """
     # Don't send unless:
     # - changeset are being exchanged,
     # - the client supports it.
     if not (kwargs.get(r'cg', True) and 'hgtagsfnodes' in b2caps):
         return
 
     outgoing = _computeoutgoing(repo, heads, common)
     bundle2.addparttagsfnodescache(repo, bundler, outgoing)
 
 @getbundle2partsgenerator('cache:rev-branch-cache')
 def _getbundlerevbranchcache(bundler, repo, source, bundlecaps=None,
                              b2caps=None, heads=None, common=None,
                              **kwargs):
     """Transfer the rev-branch-cache mapping
 
     The payload is a series of data related to each branch
 
     1) branch name length
     2) number of open heads
     3) number of closed heads
     4) open heads nodes
     5) closed heads nodes
     """
     # Don't send unless:
     # - changeset are being exchanged,
     # - the client supports it.
     # - narrow bundle isn't in play (not currently compatible).
     if (not kwargs.get(r'cg', True)
         or 'rev-branch-cache' not in b2caps
         or kwargs.get(r'narrow', False)
         or repo.ui.has_section(_NARROWACL_SECTION)):
         return
 
     outgoing = _computeoutgoing(repo, heads, common)
     bundle2.addpartrevbranchcache(repo, bundler, outgoing)
 
 def check_heads(repo, their_heads, context):
     """check if the heads of a repo have been modified
 
     Used by peer for unbundling.
     """
     heads = repo.heads()
     heads_hash = hashlib.sha1(''.join(sorted(heads))).digest()
     if not (their_heads == ['force'] or their_heads == heads or
             their_heads == ['hashed', heads_hash]):
         # someone else committed/pushed/unbundled while we
         # were transferring data
         raise error.PushRaced('repository changed while %s - '
                               'please try again' % context)
 
 def unbundle(repo, cg, heads, source, url):
     """Apply a bundle to a repo.
 
     this function makes sure the repo is locked during the application and have
     mechanism to check that no push race occurred between the creation of the
     bundle and its application.
 
     If the push was raced as PushRaced exception is raised."""
     r = 0
     # need a transaction when processing a bundle2 stream
     # [wlock, lock, tr] - needs to be an array so nested functions can modify it
     lockandtr = [None, None, None]
     recordout = None
     # quick fix for output mismatch with bundle2 in 3.4
     captureoutput = repo.ui.configbool('experimental', 'bundle2-output-capture')
     if url.startswith('remote:http:') or url.startswith('remote:https:'):
         captureoutput = True
     try:
         # note: outside bundle1, 'heads' is expected to be empty and this
         # 'check_heads' call wil be a no-op
         check_heads(repo, heads, 'uploading changes')
         # push can proceed
         if not isinstance(cg, bundle2.unbundle20):
             # legacy case: bundle1 (changegroup 01)
             txnname = "\n".join([source, util.hidepassword(url)])
             with repo.lock(), repo.transaction(txnname) as tr:
                 op = bundle2.applybundle(repo, cg, tr, source, url)
                 r = bundle2.combinechangegroupresults(op)
         else:
             r = None
             try:
                 def gettransaction():
                     if not lockandtr[2]:
                         if not bookmod.bookmarksinstore(repo):
                             lockandtr[0] = repo.wlock()
                         lockandtr[1] = repo.lock()
                         lockandtr[2] = repo.transaction(source)
                         lockandtr[2].hookargs['source'] = source
                         lockandtr[2].hookargs['url'] = url
                         lockandtr[2].hookargs['bundle2'] = '1'
                     return lockandtr[2]
 
                 # Do greedy locking by default until we're satisfied with lazy
                 # locking.
                 if not repo.ui.configbool('experimental', 'bundle2lazylocking'):
                     gettransaction()
 
                 op = bundle2.bundleoperation(repo, gettransaction,
                                              captureoutput=captureoutput,
                                              source='push')
                 try:
                     op = bundle2.processbundle(repo, cg, op=op)
                 finally:
                     r = op.reply
                     if captureoutput and r is not None:
                         repo.ui.pushbuffer(error=True, subproc=True)
                         def recordout(output):
                             r.newpart('output', data=output, mandatory=False)
                 if lockandtr[2] is not None:
                     lockandtr[2].close()
             except BaseException as exc:
                 exc.duringunbundle2 = True
                 if captureoutput and r is not None:
                     parts = exc._bundle2salvagedoutput = r.salvageoutput()
                     def recordout(output):
                         part = bundle2.bundlepart('output', data=output,
                                                   mandatory=False)
                         parts.append(part)
                 raise
     finally:
         lockmod.release(lockandtr[2], lockandtr[1], lockandtr[0])
         if recordout is not None:
             recordout(repo.ui.popbuffer())
     return r
 
 def _maybeapplyclonebundle(pullop):
     """Apply a clone bundle from a remote, if possible."""
 
     repo = pullop.repo
     remote = pullop.remote
 
     if not repo.ui.configbool('ui', 'clonebundles'):
         return
 
     # Only run if local repo is empty.
     if len(repo):
         return
 
     if pullop.heads:
         return
 
     if not remote.capable('clonebundles'):
         return
 
     with remote.commandexecutor() as e:
         res = e.callcommand('clonebundles', {}).result()
 
     # If we call the wire protocol command, that's good enough to record the
     # attempt.
     pullop.clonebundleattempted = True
 
     entries = parseclonebundlesmanifest(repo, res)
     if not entries:
         repo.ui.note(_('no clone bundles available on remote; '
                        'falling back to regular clone\n'))
         return
 
     entries = filterclonebundleentries(
         repo, entries, streamclonerequested=pullop.streamclonerequested)
 
     if not entries:
         # There is a thundering herd concern here. However, if a server
         # operator doesn't advertise bundles appropriate for its clients,
         # they deserve what's coming. Furthermore, from a client's
         # perspective, no automatic fallback would mean not being able to
         # clone!
         repo.ui.warn(_('no compatible clone bundles available on server; '
                        'falling back to regular clone\n'))
         repo.ui.warn(_('(you may want to report this to the server '
                        'operator)\n'))
         return
 
     entries = sortclonebundleentries(repo.ui, entries)
 
     url = entries[0]['URL']
     repo.ui.status(_('applying clone bundle from %s\n') % url)
     if trypullbundlefromurl(repo.ui, repo, url):
         repo.ui.status(_('finished applying clone bundle\n'))
     # Bundle failed.
     #
     # We abort by default to avoid the thundering herd of
     # clients flooding a server that was expecting expensive
     # clone load to be offloaded.
     elif repo.ui.configbool('ui', 'clonebundlefallback'):
         repo.ui.warn(_('falling back to normal clone\n'))
     else:
         raise error.Abort(_('error applying bundle'),
                           hint=_('if this error persists, consider contacting '
                                  'the server operator or disable clone '
                                  'bundles via '
                                  '"--config ui.clonebundles=false"'))
 
 def parseclonebundlesmanifest(repo, s):
     """Parses the raw text of a clone bundles manifest.
 
     Returns a list of dicts. The dicts have a ``URL`` key corresponding
     to the URL and other keys are the attributes for the entry.
     """
     m = []
     for line in s.splitlines():
         fields = line.split()
         if not fields:
             continue
         attrs = {'URL': fields[0]}
         for rawattr in fields[1:]:
             key, value = rawattr.split('=', 1)
             key = urlreq.unquote(key)
             value = urlreq.unquote(value)
             attrs[key] = value
 
             # Parse BUNDLESPEC into components. This makes client-side
             # preferences easier to specify since you can prefer a single
             # component of the BUNDLESPEC.
             if key == 'BUNDLESPEC':
                 try:
                     bundlespec = parsebundlespec(repo, value)
                     attrs['COMPRESSION'] = bundlespec.compression
                     attrs['VERSION'] = bundlespec.version
                 except error.InvalidBundleSpecification:
                     pass
                 except error.UnsupportedBundleSpecification:
                     pass
 
         m.append(attrs)
 
     return m
 
 def isstreamclonespec(bundlespec):
     # Stream clone v1
     if (bundlespec.wirecompression == 'UN' and bundlespec.wireversion == 's1'):
         return True
 
     # Stream clone v2
     if (bundlespec.wirecompression == 'UN' and
         bundlespec.wireversion == '02' and
         bundlespec.contentopts.get('streamv2')):
         return True
 
     return False
 
 def filterclonebundleentries(repo, entries, streamclonerequested=False):
     """Remove incompatible clone bundle manifest entries.
 
     Accepts a list of entries parsed with ``parseclonebundlesmanifest``
     and returns a new list consisting of only the entries that this client
     should be able to apply.
 
     There is no guarantee we'll be able to apply all returned entries because
     the metadata we use to filter on may be missing or wrong.
     """
     newentries = []
     for entry in entries:
         spec = entry.get('BUNDLESPEC')
         if spec:
             try:
                 bundlespec = parsebundlespec(repo, spec, strict=True)
 
                 # If a stream clone was requested, filter out non-streamclone
                 # entries.
                 if streamclonerequested and not isstreamclonespec(bundlespec):
                     repo.ui.debug('filtering %s because not a stream clone\n' %
                                   entry['URL'])
                     continue
 
             except error.InvalidBundleSpecification as e:
                 repo.ui.debug(stringutil.forcebytestr(e) + '\n')
                 continue
             except error.UnsupportedBundleSpecification as e:
                 repo.ui.debug('filtering %s because unsupported bundle '
                               'spec: %s\n' % (
                                   entry['URL'], stringutil.forcebytestr(e)))
                 continue
         # If we don't have a spec and requested a stream clone, we don't know
         # what the entry is so don't attempt to apply it.
         elif streamclonerequested:
             repo.ui.debug('filtering %s because cannot determine if a stream '
                           'clone bundle\n' % entry['URL'])
             continue
 
         if 'REQUIRESNI' in entry and not sslutil.hassni:
             repo.ui.debug('filtering %s because SNI not supported\n' %
                           entry['URL'])
             continue
 
         newentries.append(entry)
 
     return newentries
 
 class clonebundleentry(object):
     """Represents an item in a clone bundles manifest.
 
     This rich class is needed to support sorting since sorted() in Python 3
     doesn't support ``cmp`` and our comparison is complex enough that ``key=``
     won't work.
     """
 
     def __init__(self, value, prefers):
         self.value = value
         self.prefers = prefers
 
     def _cmp(self, other):
         for prefkey, prefvalue in self.prefers:
             avalue = self.value.get(prefkey)
             bvalue = other.value.get(prefkey)
 
             # Special case for b missing attribute and a matches exactly.
             if avalue is not None and bvalue is None and avalue == prefvalue:
                 return -1
 
             # Special case for a missing attribute and b matches exactly.
             if bvalue is not None and avalue is None and bvalue == prefvalue:
                 return 1
 
             # We can't compare unless attribute present on both.
             if avalue is None or bvalue is None:
                 continue
 
             # Same values should fall back to next attribute.
             if avalue == bvalue:
                 continue
 
             # Exact matches come first.
             if avalue == prefvalue:
                 return -1
             if bvalue == prefvalue:
                 return 1
 
             # Fall back to next attribute.
             continue
 
         # If we got here we couldn't sort by attributes and prefers. Fall
         # back to index order.
         return 0
 
     def __lt__(self, other):
         return self._cmp(other) < 0
 
     def __gt__(self, other):
         return self._cmp(other) > 0
 
     def __eq__(self, other):
         return self._cmp(other) == 0
 
     def __le__(self, other):
         return self._cmp(other) <= 0
 
     def __ge__(self, other):
         return self._cmp(other) >= 0
 
     def __ne__(self, other):
         return self._cmp(other) != 0
 
 def sortclonebundleentries(ui, entries):
     prefers = ui.configlist('ui', 'clonebundleprefers')
     if not prefers:
         return list(entries)
 
     prefers = [p.split('=', 1) for p in prefers]
 
     items = sorted(clonebundleentry(v, prefers) for v in entries)
     return [i.value for i in items]
 
 def trypullbundlefromurl(ui, repo, url):
     """Attempt to apply a bundle from a URL."""
     with repo.lock(), repo.transaction('bundleurl') as tr:
         try:
             fh = urlmod.open(ui, url)
             cg = readbundle(ui, fh, 'stream')
 
             if isinstance(cg, streamclone.streamcloneapplier):
                 cg.apply(repo)
             else:
                 bundle2.applybundle(repo, cg, tr, 'clonebundles', url)
             return True
         except urlerr.httperror as e:
             ui.warn(_('HTTP error fetching bundle: %s\n') %
                     stringutil.forcebytestr(e))
         except urlerr.urlerror as e:
             ui.warn(_('error fetching bundle: %s\n') %
                     stringutil.forcebytestr(e.reason))
 
         return False

mercurial/exchangev2.py

@@ -1,697 +1,699
 # exchangev2.py - repository exchange for wire protocol version 2
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import weakref
 
 from .i18n import _
 from .node import (
     nullid,
     short,
 )
 from . import (
     bookmarks,
     error,
     mdiff,
     narrowspec,
     phases,
     pycompat,
+    setdiscovery,
+)
+from .interfaces import (
     repository,
-    setdiscovery,
 )
 
 def pull(pullop):
     """Pull using wire protocol version 2."""
     repo = pullop.repo
     remote = pullop.remote
 
     usingrawchangelogandmanifest = _checkuserawstorefiledata(pullop)
 
     # If this is a clone and it was requested to perform a "stream clone",
     # we obtain the raw files data from the remote then fall back to an
     # incremental pull. This is somewhat hacky and is not nearly robust enough
     # for long-term usage.
     if usingrawchangelogandmanifest:
         with repo.transaction('clone'):
             _fetchrawstorefiles(repo, remote)
             repo.invalidate(clearfilecache=True)
 
     tr = pullop.trmanager.transaction()
 
     # We don't use the repo's narrow matcher here because the patterns passed
     # to exchange.pull() could be different.
     narrowmatcher = narrowspec.match(repo.root,
                                      # Empty maps to nevermatcher. So always
                                      # set includes if missing.
                                      pullop.includepats or {'path:.'},
                                      pullop.excludepats)
 
     if pullop.includepats or pullop.excludepats:
         pathfilter = {}
         if pullop.includepats:
             pathfilter[b'include'] = sorted(pullop.includepats)
         if pullop.excludepats:
             pathfilter[b'exclude'] = sorted(pullop.excludepats)
     else:
         pathfilter = None
 
     # Figure out what needs to be fetched.
     common, fetch, remoteheads = _pullchangesetdiscovery(
         repo, remote, pullop.heads, abortwhenunrelated=pullop.force)
 
     # And fetch the data.
     pullheads = pullop.heads or remoteheads
     csetres = _fetchchangesets(repo, tr, remote, common, fetch, pullheads)
 
     # New revisions are written to the changelog. But all other updates
     # are deferred. Do those now.
 
     # Ensure all new changesets are draft by default. If the repo is
     # publishing, the phase will be adjusted by the loop below.
     if csetres['added']:
         phases.registernew(repo, tr, phases.draft, csetres['added'])
 
     # And adjust the phase of all changesets accordingly.
     for phase in phases.phasenames:
         if phase == b'secret' or not csetres['nodesbyphase'][phase]:
             continue
 
         phases.advanceboundary(repo, tr, phases.phasenames.index(phase),
                                csetres['nodesbyphase'][phase])
 
     # Write bookmark updates.
     bookmarks.updatefromremote(repo.ui, repo, csetres['bookmarks'],
                                remote.url(), pullop.gettransaction,
                                explicit=pullop.explicitbookmarks)
 
     manres = _fetchmanifests(repo, tr, remote, csetres['manifestnodes'])
 
     # We don't properly support shallow changeset and manifest yet. So we apply
     # depth limiting locally.
     if pullop.depth:
         relevantcsetnodes = set()
         clnode = repo.changelog.node
 
         for rev in repo.revs(b'ancestors(%ln, %s)',
                              pullheads, pullop.depth - 1):
             relevantcsetnodes.add(clnode(rev))
 
         csetrelevantfilter = lambda n: n in relevantcsetnodes
 
     else:
         csetrelevantfilter = lambda n: True
 
     # If obtaining the raw store files, we need to scan the full repo to
     # derive all the changesets, manifests, and linkrevs.
     if usingrawchangelogandmanifest:
         csetsforfiles = []
         mnodesforfiles = []
         manifestlinkrevs = {}
 
         for rev in repo:
             ctx = repo[rev]
             node = ctx.node()
 
             if not csetrelevantfilter(node):
                 continue
 
             mnode = ctx.manifestnode()
 
             csetsforfiles.append(node)
             mnodesforfiles.append(mnode)
             manifestlinkrevs[mnode] = rev
 
     else:
         csetsforfiles = [n for n in csetres['added'] if csetrelevantfilter(n)]
         mnodesforfiles = manres['added']
         manifestlinkrevs = manres['linkrevs']
 
     # Find all file nodes referenced by added manifests and fetch those
     # revisions.
     fnodes = _derivefilesfrommanifests(repo, narrowmatcher, mnodesforfiles)
     _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csetsforfiles,
                          manifestlinkrevs, shallow=bool(pullop.depth))
 
 def _checkuserawstorefiledata(pullop):
     """Check whether we should use rawstorefiledata command to retrieve data."""
 
     repo = pullop.repo
     remote = pullop.remote
 
     # Command to obtain raw store data isn't available.
     if b'rawstorefiledata' not in remote.apidescriptor[b'commands']:
         return False
 
     # Only honor if user requested stream clone operation.
     if not pullop.streamclonerequested:
         return False
 
     # Only works on empty repos.
     if len(repo):
         return False
 
     # TODO This is super hacky. There needs to be a storage API for this. We
     # also need to check for compatibility with the remote.
     if b'revlogv1' not in repo.requirements:
         return False
 
     return True
 
 def _fetchrawstorefiles(repo, remote):
     with remote.commandexecutor() as e:
         objs = e.callcommand(b'rawstorefiledata', {
             b'files': [b'changelog', b'manifestlog'],
         }).result()
 
         # First object is a summary of files data that follows.
         overall = next(objs)
 
         progress = repo.ui.makeprogress(_('clone'), total=overall[b'totalsize'],
                                         unit=_('bytes'))
         with progress:
             progress.update(0)
 
             # Next are pairs of file metadata, data.
             while True:
                 try:
                     filemeta = next(objs)
                 except StopIteration:
                     break
 
                 for k in (b'location', b'path', b'size'):
                     if k not in filemeta:
                         raise error.Abort(_(b'remote file data missing key: %s')
                                           % k)
 
                 if filemeta[b'location'] == b'store':
                     vfs = repo.svfs
                 else:
                     raise error.Abort(_(b'invalid location for raw file data: '
                                         b'%s') % filemeta[b'location'])
 
                 bytesremaining = filemeta[b'size']
 
                 with vfs.open(filemeta[b'path'], b'wb') as fh:
                     while True:
                         try:
                             chunk = next(objs)
                         except StopIteration:
                             break
 
                         bytesremaining -= len(chunk)
 
                         if bytesremaining < 0:
                             raise error.Abort(_(
                                 b'received invalid number of bytes for file '
                                 b'data; expected %d, got extra') %
                                               filemeta[b'size'])
 
                         progress.increment(step=len(chunk))
                         fh.write(chunk)
 
                         try:
                             if chunk.islast:
                                 break
                         except AttributeError:
                             raise error.Abort(_(
                                 b'did not receive indefinite length bytestring '
                                 b'for file data'))
 
                 if bytesremaining:
                     raise error.Abort(_(b'received invalid number of bytes for'
                                         b'file data; expected %d got %d') %
                                       (filemeta[b'size'],
                                        filemeta[b'size'] - bytesremaining))
 
 def _pullchangesetdiscovery(repo, remote, heads, abortwhenunrelated=True):
     """Determine which changesets need to be pulled."""
 
     if heads:
         knownnode = repo.changelog.hasnode
         if all(knownnode(head) for head in heads):
             return heads, False, heads
 
     # TODO wire protocol version 2 is capable of more efficient discovery
     # than setdiscovery. Consider implementing something better.
     common, fetch, remoteheads = setdiscovery.findcommonheads(
         repo.ui, repo, remote, abortwhenunrelated=abortwhenunrelated)
 
     common = set(common)
     remoteheads = set(remoteheads)
 
     # If a remote head is filtered locally, put it back in the common set.
     # See the comment in exchange._pulldiscoverychangegroup() for more.
 
     if fetch and remoteheads:
         nodemap = repo.unfiltered().changelog.nodemap
 
         common |= {head for head in remoteheads if head in nodemap}
 
         if set(remoteheads).issubset(common):
             fetch = []
 
     common.discard(nullid)
 
     return common, fetch, remoteheads
 
 def _fetchchangesets(repo, tr, remote, common, fetch, remoteheads):
     # TODO consider adding a step here where we obtain the DAG shape first
     # (or ask the server to slice changesets into chunks for us) so that
     # we can perform multiple fetches in batches. This will facilitate
     # resuming interrupted clones, higher server-side cache hit rates due
     # to smaller segments, etc.
     with remote.commandexecutor() as e:
         objs = e.callcommand(b'changesetdata', {
             b'revisions': [{
                 b'type': b'changesetdagrange',
                 b'roots': sorted(common),
                 b'heads': sorted(remoteheads),
             }],
             b'fields': {b'bookmarks', b'parents', b'phase', b'revision'},
         }).result()
 
         # The context manager waits on all response data when exiting. So
         # we need to remain in the context manager in order to stream data.
         return _processchangesetdata(repo, tr, objs)
 
 def _processchangesetdata(repo, tr, objs):
     repo.hook('prechangegroup', throw=True,
               **pycompat.strkwargs(tr.hookargs))
 
     urepo = repo.unfiltered()
     cl = urepo.changelog
 
     cl.delayupdate(tr)
 
     # The first emitted object is a header describing the data that
     # follows.
     meta = next(objs)
 
     progress = repo.ui.makeprogress(_('changesets'),
                                     unit=_('chunks'),
                                     total=meta.get(b'totalitems'))
 
     manifestnodes = {}
 
     def linkrev(node):
         repo.ui.debug('add changeset %s\n' % short(node))
         # Linkrev for changelog is always self.
         return len(cl)
 
     def onchangeset(cl, node):
         progress.increment()
 
         revision = cl.changelogrevision(node)
 
         # We need to preserve the mapping of changelog revision to node
         # so we can set the linkrev accordingly when manifests are added.
         manifestnodes[cl.rev(node)] = revision.manifest
 
     nodesbyphase = {phase: set() for phase in phases.phasenames}
     remotebookmarks = {}
 
     # addgroup() expects a 7-tuple describing revisions. This normalizes
     # the wire data to that format.
     #
     # This loop also aggregates non-revision metadata, such as phase
     # data.
     def iterrevisions():
         for cset in objs:
             node = cset[b'node']
 
             if b'phase' in cset:
                 nodesbyphase[cset[b'phase']].add(node)
 
             for mark in cset.get(b'bookmarks', []):
                 remotebookmarks[mark] = node
 
             # TODO add mechanism for extensions to examine records so they
             # can siphon off custom data fields.
 
             extrafields = {}
 
             for field, size in cset.get(b'fieldsfollowing', []):
                 extrafields[field] = next(objs)
 
             # Some entries might only be metadata only updates.
             if b'revision' not in extrafields:
                 continue
 
             data = extrafields[b'revision']
 
             yield (
                 node,
                 cset[b'parents'][0],
                 cset[b'parents'][1],
                 # Linknode is always itself for changesets.
                 cset[b'node'],
                 # We always send full revisions. So delta base is not set.
                 nullid,
                 mdiff.trivialdiffheader(len(data)) + data,
                 # Flags not yet supported.
                 0,
             )
 
     added = cl.addgroup(iterrevisions(), linkrev, weakref.proxy(tr),
                         addrevisioncb=onchangeset)
 
     progress.complete()
 
     return {
         'added': added,
         'nodesbyphase': nodesbyphase,
         'bookmarks': remotebookmarks,
         'manifestnodes': manifestnodes,
     }
 
 def _fetchmanifests(repo, tr, remote, manifestnodes):
     rootmanifest = repo.manifestlog.getstorage(b'')
 
     # Some manifests can be shared between changesets. Filter out revisions
     # we already know about.
     fetchnodes = []
     linkrevs = {}
     seen = set()
 
     for clrev, node in sorted(manifestnodes.iteritems()):
         if node in seen:
             continue
 
         try:
             rootmanifest.rev(node)
         except error.LookupError:
             fetchnodes.append(node)
             linkrevs[node] = clrev
 
         seen.add(node)
 
     # TODO handle tree manifests
 
     # addgroup() expects 7-tuple describing revisions. This normalizes
     # the wire data to that format.
     def iterrevisions(objs, progress):
         for manifest in objs:
             node = manifest[b'node']
 
             extrafields = {}
 
             for field, size in manifest.get(b'fieldsfollowing', []):
                 extrafields[field] = next(objs)
 
             if b'delta' in extrafields:
                 basenode = manifest[b'deltabasenode']
                 delta = extrafields[b'delta']
             elif b'revision' in extrafields:
                 basenode = nullid
                 revision = extrafields[b'revision']
                 delta = mdiff.trivialdiffheader(len(revision)) + revision
             else:
                 continue
 
             yield (
                 node,
                 manifest[b'parents'][0],
                 manifest[b'parents'][1],
                 # The value passed in is passed to the lookup function passed
                 # to addgroup(). We already have a map of manifest node to
                 # changelog revision number. So we just pass in the
                 # manifest node here and use linkrevs.__getitem__ as the
                 # resolution function.
                 node,
                 basenode,
                 delta,
                 # Flags not yet supported.
                 0
             )
 
             progress.increment()
 
     progress = repo.ui.makeprogress(_('manifests'), unit=_('chunks'),
                                     total=len(fetchnodes))
 
     commandmeta = remote.apidescriptor[b'commands'][b'manifestdata']
     batchsize = commandmeta.get(b'recommendedbatchsize', 10000)
     # TODO make size configurable on client?
 
     # We send commands 1 at a time to the remote. This is not the most
     # efficient because we incur a round trip at the end of each batch.
     # However, the existing frame-based reactor keeps consuming server
     # data in the background. And this results in response data buffering
     # in memory. This can consume gigabytes of memory.
     # TODO send multiple commands in a request once background buffering
     # issues are resolved.
 
     added = []
 
     for i in pycompat.xrange(0, len(fetchnodes), batchsize):
         batch = [node for node in fetchnodes[i:i + batchsize]]
         if not batch:
             continue
 
         with remote.commandexecutor() as e:
             objs = e.callcommand(b'manifestdata', {
                 b'tree': b'',
                 b'nodes': batch,
                 b'fields': {b'parents', b'revision'},
                 b'haveparents': True,
             }).result()
 
             # Chomp off header object.
             next(objs)
 
             added.extend(rootmanifest.addgroup(
                 iterrevisions(objs, progress),
                 linkrevs.__getitem__,
                 weakref.proxy(tr)))
 
     progress.complete()
 
     return {
         'added': added,
         'linkrevs': linkrevs,
     }
 
 def _derivefilesfrommanifests(repo, matcher, manifestnodes):
     """Determine what file nodes are relevant given a set of manifest nodes.
 
     Returns a dict mapping file paths to dicts of file node to first manifest
     node.
     """
     ml = repo.manifestlog
     fnodes = collections.defaultdict(dict)
 
     progress = repo.ui.makeprogress(
         _('scanning manifests'), total=len(manifestnodes))
 
     with progress:
         for manifestnode in manifestnodes:
             m = ml.get(b'', manifestnode)
 
             # TODO this will pull in unwanted nodes because it takes the storage
             # delta into consideration. What we really want is something that
             # takes the delta between the manifest's parents. And ideally we
             # would ignore file nodes that are known locally. For now, ignore
             # both these limitations. This will result in incremental fetches
             # requesting data we already have. So this is far from ideal.
             md = m.readfast()
 
             for path, fnode in md.items():
                 if matcher(path):
                     fnodes[path].setdefault(fnode, manifestnode)
 
             progress.increment()
 
     return fnodes
 
 def _fetchfiles(repo, tr, remote, fnodes, linkrevs):
     """Fetch file data from explicit file revisions."""
     def iterrevisions(objs, progress):
         for filerevision in objs:
             node = filerevision[b'node']
 
             extrafields = {}
 
             for field, size in filerevision.get(b'fieldsfollowing', []):
                 extrafields[field] = next(objs)
 
             if b'delta' in extrafields:
                 basenode = filerevision[b'deltabasenode']
                 delta = extrafields[b'delta']
             elif b'revision' in extrafields:
                 basenode = nullid
                 revision = extrafields[b'revision']
                 delta = mdiff.trivialdiffheader(len(revision)) + revision
             else:
                 continue
 
             yield (
                 node,
                 filerevision[b'parents'][0],
                 filerevision[b'parents'][1],
                 node,
                 basenode,
                 delta,
                 # Flags not yet supported.
                 0,
             )
 
             progress.increment()
 
     progress = repo.ui.makeprogress(
         _('files'), unit=_('chunks'),
          total=sum(len(v) for v in fnodes.itervalues()))
 
     # TODO make batch size configurable
     batchsize = 10000
     fnodeslist = [x for x in sorted(fnodes.items())]
 
     for i in pycompat.xrange(0, len(fnodeslist), batchsize):
         batch = [x for x in fnodeslist[i:i + batchsize]]
         if not batch:
             continue
 
         with remote.commandexecutor() as e:
             fs = []
             locallinkrevs = {}
 
             for path, nodes in batch:
                 fs.append((path, e.callcommand(b'filedata', {
                     b'path': path,
                     b'nodes': sorted(nodes),
                     b'fields': {b'parents', b'revision'},
                     b'haveparents': True,
                 })))
 
                 locallinkrevs[path] = {
                     node: linkrevs[manifestnode]
                     for node, manifestnode in nodes.iteritems()}
 
             for path, f in fs:
                 objs = f.result()
 
                 # Chomp off header objects.
                 next(objs)
 
                 store = repo.file(path)
                 store.addgroup(
                     iterrevisions(objs, progress),
                     locallinkrevs[path].__getitem__,
                     weakref.proxy(tr))
 
 def _fetchfilesfromcsets(repo, tr, remote, pathfilter, fnodes, csets,
                          manlinkrevs, shallow=False):
     """Fetch file data from explicit changeset revisions."""
 
     def iterrevisions(objs, remaining, progress):
         while remaining:
             filerevision = next(objs)
 
             node = filerevision[b'node']
 
             extrafields = {}
 
             for field, size in filerevision.get(b'fieldsfollowing', []):
                 extrafields[field] = next(objs)
 
             if b'delta' in extrafields:
                 basenode = filerevision[b'deltabasenode']
                 delta = extrafields[b'delta']
             elif b'revision' in extrafields:
                 basenode = nullid
                 revision = extrafields[b'revision']
                 delta = mdiff.trivialdiffheader(len(revision)) + revision
             else:
                 continue
 
             if b'linknode' in filerevision:
                 linknode = filerevision[b'linknode']
             else:
                 linknode = node
 
             yield (
                 node,
                 filerevision[b'parents'][0],
                 filerevision[b'parents'][1],
                 linknode,
                 basenode,
                 delta,
                 # Flags not yet supported.
                 0,
             )
 
             progress.increment()
             remaining -= 1
 
     progress = repo.ui.makeprogress(
         _('files'), unit=_('chunks'),
         total=sum(len(v) for v in fnodes.itervalues()))
 
     commandmeta = remote.apidescriptor[b'commands'][b'filesdata']
     batchsize = commandmeta.get(b'recommendedbatchsize', 50000)
 
     shallowfiles = repository.REPO_FEATURE_SHALLOW_FILE_STORAGE in repo.features
     fields = {b'parents', b'revision'}
     clrev = repo.changelog.rev
 
     # There are no guarantees that we'll have ancestor revisions if
     # a) this repo has shallow file storage b) shallow data fetching is enabled.
     # Force remote to not delta against possibly unknown revisions when these
     # conditions hold.
     haveparents = not (shallowfiles or shallow)
 
     # Similarly, we may not have calculated linkrevs for all incoming file
     # revisions. Ask the remote to do work for us in this case.
     if not haveparents:
         fields.add(b'linknode')
 
     for i in pycompat.xrange(0, len(csets), batchsize):
         batch = [x for x in csets[i:i + batchsize]]
         if not batch:
             continue
 
         with remote.commandexecutor() as e:
             args = {
                 b'revisions': [{
                     b'type': b'changesetexplicit',
                     b'nodes': batch,
                 }],
                 b'fields': fields,
                 b'haveparents': haveparents,
             }
 
             if pathfilter:
                 args[b'pathfilter'] = pathfilter
 
             objs = e.callcommand(b'filesdata', args).result()
 
             # First object is an overall header.
             overall = next(objs)
 
             # We have overall['totalpaths'] segments.
             for i in pycompat.xrange(overall[b'totalpaths']):
                 header = next(objs)
 
                 path = header[b'path']
                 store = repo.file(path)
 
                 linkrevs = {
                     fnode: manlinkrevs[mnode]
                     for fnode, mnode in fnodes[path].iteritems()}
 
                 def getlinkrev(node):
                     if node in linkrevs:
                         return linkrevs[node]
                     else:
                         return clrev(node)
 
                 store.addgroup(iterrevisions(objs, header[b'totalitems'],
                                              progress),
                                getlinkrev,
                                weakref.proxy(tr),
                                maybemissingparents=shallow)

mercurial/filelog.py

@@ -1,242 +1,244
 # filelog.py - file history class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import (
     nullid,
     nullrev,
 )
 from . import (
     error,
+    revlog,
+)
+from .interfaces import (
     repository,
-    revlog,
 )
 from .utils import (
     interfaceutil,
     storageutil,
 )
 
 @interfaceutil.implementer(repository.ifilestorage)
 class filelog(object):
     def __init__(self, opener, path):
         self._revlog = revlog.revlog(opener,
                                      '/'.join(('data', path + '.i')),
                                      censorable=True)
         # Full name of the user visible file, relative to the repository root.
         # Used by LFS.
         self._revlog.filename = path
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def hasnode(self, node):
         if node in (nullid, nullrev):
             return False
 
         try:
             self._revlog.rev(node)
             return True
         except (TypeError, ValueError, IndexError, error.LookupError):
             return False
 
     def revs(self, start=0, stop=None):
         return self._revlog.revs(start=start, stop=stop)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, node):
         return storageutil.fileidlookup(self._revlog, node,
                                         self._revlog.indexfile)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def commonancestorsheads(self, node1, node2):
         return self._revlog.commonancestorsheads(node1, node2)
 
     # Used by dagop.blockdescendants().
     def descendants(self, revs):
         return self._revlog.descendants(revs)
 
     def heads(self, start=None, stop=None):
         return self._revlog.heads(start, stop)
 
     # Used by hgweb, children extension.
     def children(self, node):
         return self._revlog.children(node)
 
     def iscensored(self, rev):
         return self._revlog.iscensored(rev)
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def emitrevisions(self, nodes, nodesorder=None,
                       revisiondata=False, assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         return self._revlog.emitrevisions(
             nodes, nodesorder=nodesorder, revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode)
 
     def addrevision(self, revisiondata, transaction, linkrev, p1, p2,
                     node=None, flags=revlog.REVIDX_DEFAULT_FLAGS,
                     cachedelta=None):
         return self._revlog.addrevision(revisiondata, transaction, linkrev,
                                     p1, p2, node=node, flags=flags,
                                     cachedelta=cachedelta)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None,
                  maybemissingparents=False):
         if maybemissingparents:
             raise error.Abort(_('revlog storage does not support missing '
                                 'parents write mode'))
 
         return self._revlog.addgroup(deltas, linkmapper, transaction,
                                      addrevisioncb=addrevisioncb)
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def censorrevision(self, tr, node, tombstone=b''):
         return self._revlog.censorrevision(tr, node, tombstone=tombstone)
 
     def files(self):
         return self._revlog.files()
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
             text = storageutil.packmeta(meta, text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
         if self.iscensored(rev):
             return 0
 
         # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
         return self._revlog.size(rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         return not storageutil.filedataequivalent(self, node, text)
 
     def verifyintegrity(self, state):
         return self._revlog.verifyintegrity(state)
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles, sharedfiles=sharedfiles,
             revisionscount=revisionscount, trackedsize=trackedsize,
             storedsize=storedsize)
 
     # TODO these aren't part of the interface and aren't internal methods.
     # Callers should be fixed to not use them.
 
     # Used by bundlefilelog, unionfilelog.
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     # Used by repo upgrade.
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, filelog):
             raise error.ProgrammingError('expected filelog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
 class narrowfilelog(filelog):
     """Filelog variation to be used with narrow stores."""
 
     def __init__(self, opener, path, narrowmatch):
         super(narrowfilelog, self).__init__(opener, path)
         self._narrowmatch = narrowmatch
 
     def renamed(self, node):
         res = super(narrowfilelog, self).renamed(node)
 
         # Renames that come from outside the narrowspec are problematic
         # because we may lack the base text for the rename. This can result
         # in code attempting to walk the ancestry or compute a diff
         # encountering a missing revision. We address this by silently
         # removing rename metadata if the source file is outside the
         # narrow spec.
         #
         # A better solution would be to see if the base revision is available,
         # rather than assuming it isn't.
         #
         # An even better solution would be to teach all consumers of rename
         # metadata that the base revision may not be available.
         #
         # TODO consider better ways of doing this.
         if res and not self._narrowmatch(res[0]):
             return None
 
         return res
 
     def size(self, rev):
         # Because we have a custom renamed() that may lie, we need to call
         # the base renamed() to report accurate results.
         node = self.node(rev)
         if super(narrowfilelog, self).renamed(node):
             return len(self.read(node))
         else:
             return super(narrowfilelog, self).size(rev)
 
     def cmp(self, node, text):
         different = super(narrowfilelog, self).cmp(node, text)
 
         # Because renamed() may lie, we may get false positives for
         # different content. Check for this by comparing against the original
         # renamed() implementation.
         if different:
             if super(narrowfilelog, self).renamed(node):
                 t2 = self.read(node)
                 return t2 != text
 
         return different

mercurial/hg.py

@@ -1,1237 +1,1240
 # hg.py - repository classes for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import shutil
 import stat
 
 from .i18n import _
 from .node import (
     nullid,
 )
 
 from . import (
     bookmarks,
     bundlerepo,
     cacheutil,
     cmdutil,
     destutil,
     discovery,
     error,
     exchange,
     extensions,
     httppeer,
     localrepo,
     lock,
     logcmdutil,
     logexchange,
     merge as mergemod,
     narrowspec,
     node,
     phases,
     pycompat,
-    repository as repositorymod,
     scmutil,
     sshpeer,
     statichttprepo,
     ui as uimod,
     unionrepo,
     url,
     util,
     verify as verifymod,
     vfs as vfsmod,
 )
 
+from .interfaces import (
+    repository as repositorymod,
+)
+
 release = lock.release
 
 # shared features
 sharedbookmarks = 'bookmarks'
 
 def _local(path):
     path = util.expandpath(util.urllocalpath(path))
 
     try:
         isfile = os.path.isfile(path)
     # Python 2 raises TypeError, Python 3 ValueError.
     except (TypeError, ValueError) as e:
         raise error.Abort(_('invalid path %s: %s') % (
             path, pycompat.bytestr(e)))
 
     return isfile and bundlerepo or localrepo
 
 def addbranchrevs(lrepo, other, branches, revs):
     peer = other.peer() # a courtesy to callers using a localrepo for other
     hashbranch, branches = branches
     if not hashbranch and not branches:
         x = revs or None
         if revs:
             y = revs[0]
         else:
             y = None
         return x, y
     if revs:
         revs = list(revs)
     else:
         revs = []
 
     if not peer.capable('branchmap'):
         if branches:
             raise error.Abort(_("remote branch lookup not supported"))
         revs.append(hashbranch)
         return revs, revs[0]
 
     with peer.commandexecutor() as e:
         branchmap = e.callcommand('branchmap', {}).result()
 
     def primary(branch):
         if branch == '.':
             if not lrepo:
                 raise error.Abort(_("dirstate branch not accessible"))
             branch = lrepo.dirstate.branch()
         if branch in branchmap:
             revs.extend(node.hex(r) for r in reversed(branchmap[branch]))
             return True
         else:
             return False
 
     for branch in branches:
         if not primary(branch):
             raise error.RepoLookupError(_("unknown branch '%s'") % branch)
     if hashbranch:
         if not primary(hashbranch):
             revs.append(hashbranch)
     return revs, revs[0]
 
 def parseurl(path, branches=None):
     '''parse url#branch, returning (url, (branch, branches))'''
 
     u = util.url(path)
     branch = None
     if u.fragment:
         branch = u.fragment
         u.fragment = None
     return bytes(u), (branch, branches or [])
 
 schemes = {
     'bundle': bundlerepo,
     'union': unionrepo,
     'file': _local,
     'http': httppeer,
     'https': httppeer,
     'ssh': sshpeer,
     'static-http': statichttprepo,
 }
 
 def _peerlookup(path):
     u = util.url(path)
     scheme = u.scheme or 'file'
     thing = schemes.get(scheme) or schemes['file']
     try:
         return thing(path)
     except TypeError:
         # we can't test callable(thing) because 'thing' can be an unloaded
         # module that implements __call__
         if not util.safehasattr(thing, 'instance'):
             raise
         return thing
 
 def islocal(repo):
     '''return true if repo (or path pointing to repo) is local'''
     if isinstance(repo, bytes):
         try:
             return _peerlookup(repo).islocal(repo)
         except AttributeError:
             return False
     return repo.local()
 
 def openpath(ui, path, sendaccept=True):
     '''open path with open if local, url.open if remote'''
     pathurl = util.url(path, parsequery=False, parsefragment=False)
     if pathurl.islocal():
         return util.posixfile(pathurl.localpath(), 'rb')
     else:
         return url.open(ui, path, sendaccept=sendaccept)
 
 # a list of (ui, repo) functions called for wire peer initialization
 wirepeersetupfuncs = []
 
 def _peerorrepo(ui, path, create=False, presetupfuncs=None,
                 intents=None, createopts=None):
     """return a repository object for the specified path"""
     obj = _peerlookup(path).instance(ui, path, create, intents=intents,
                                      createopts=createopts)
     ui = getattr(obj, "ui", ui)
     for f in presetupfuncs or []:
         f(ui, obj)
     ui.log(b'extension', b'- executing reposetup hooks\n')
     with util.timedcm('all reposetup') as allreposetupstats:
         for name, module in extensions.extensions(ui):
             ui.log(b'extension', b'  - running reposetup for %s\n', name)
             hook = getattr(module, 'reposetup', None)
             if hook:
                 with util.timedcm('reposetup %r', name) as stats:
                     hook(ui, obj)
                 ui.log(b'extension', b'  > reposetup for %s took %s\n',
                        name, stats)
     ui.log(b'extension', b'> all reposetup took %s\n', allreposetupstats)
     if not obj.local():
         for f in wirepeersetupfuncs:
             f(ui, obj)
     return obj
 
 def repository(ui, path='', create=False, presetupfuncs=None, intents=None,
                createopts=None):
     """return a repository object for the specified path"""
     peer = _peerorrepo(ui, path, create, presetupfuncs=presetupfuncs,
                        intents=intents, createopts=createopts)
     repo = peer.local()
     if not repo:
         raise error.Abort(_("repository '%s' is not local") %
                          (path or peer.url()))
     return repo.filtered('visible')
 
 def peer(uiorrepo, opts, path, create=False, intents=None, createopts=None):
     '''return a repository peer for the specified path'''
     rui = remoteui(uiorrepo, opts)
     return _peerorrepo(rui, path, create, intents=intents,
                        createopts=createopts).peer()
 
 def defaultdest(source):
     '''return default destination of clone if none is given
 
     >>> defaultdest(b'foo')
     'foo'
     >>> defaultdest(b'/foo/bar')
     'bar'
     >>> defaultdest(b'/')
     ''
     >>> defaultdest(b'')
     ''
     >>> defaultdest(b'http://example.org/')
     ''
     >>> defaultdest(b'http://example.org/foo/')
     'foo'
     '''
     path = util.url(source).path
     if not path:
         return ''
     return os.path.basename(os.path.normpath(path))
 
 def sharedreposource(repo):
     """Returns repository object for source repository of a shared repo.
 
     If repo is not a shared repository, returns None.
     """
     if repo.sharedpath == repo.path:
         return None
 
     if util.safehasattr(repo, 'srcrepo') and repo.srcrepo:
         return repo.srcrepo
 
     # the sharedpath always ends in the .hg; we want the path to the repo
     source = repo.vfs.split(repo.sharedpath)[0]
     srcurl, branches = parseurl(source)
     srcrepo = repository(repo.ui, srcurl)
     repo.srcrepo = srcrepo
     return srcrepo
 
 def share(ui, source, dest=None, update=True, bookmarks=True, defaultpath=None,
           relative=False):
     '''create a shared repository'''
 
     if not islocal(source):
         raise error.Abort(_('can only share local repositories'))
 
     if not dest:
         dest = defaultdest(source)
     else:
         dest = ui.expandpath(dest)
 
     if isinstance(source, bytes):
         origsource = ui.expandpath(source)
         source, branches = parseurl(origsource)
         srcrepo = repository(ui, source)
         rev, checkout = addbranchrevs(srcrepo, srcrepo, branches, None)
     else:
         srcrepo = source.local()
         checkout = None
 
     shareditems = set()
     if bookmarks:
         shareditems.add(sharedbookmarks)
 
     r = repository(ui, dest, create=True, createopts={
         'sharedrepo': srcrepo,
         'sharedrelative': relative,
         'shareditems': shareditems,
     })
 
     postshare(srcrepo, r, defaultpath=defaultpath)
     r = repository(ui, dest)
     _postshareupdate(r, update, checkout=checkout)
     return r
 
 def unshare(ui, repo):
     """convert a shared repository to a normal one
 
     Copy the store data to the repo and remove the sharedpath data.
 
     Returns a new repository object representing the unshared repository.
 
     The passed repository object is not usable after this function is
     called.
     """
 
     with repo.lock():
         # we use locks here because if we race with commit, we
         # can end up with extra data in the cloned revlogs that's
         # not pointed to by changesets, thus causing verify to
         # fail
         destlock = copystore(ui, repo, repo.path)
         with destlock or util.nullcontextmanager():
 
             sharefile = repo.vfs.join('sharedpath')
             util.rename(sharefile, sharefile + '.old')
 
             repo.requirements.discard('shared')
             repo.requirements.discard('relshared')
             repo._writerequirements()
 
     # Removing share changes some fundamental properties of the repo instance.
     # So we instantiate a new repo object and operate on it rather than
     # try to keep the existing repo usable.
     newrepo = repository(repo.baseui, repo.root, create=False)
 
     # TODO: figure out how to access subrepos that exist, but were previously
     #       removed from .hgsub
     c = newrepo['.']
     subs = c.substate
     for s in sorted(subs):
         c.sub(s).unshare()
 
     localrepo.poisonrepository(repo)
 
     return newrepo
 
 def postshare(sourcerepo, destrepo, defaultpath=None):
     """Called after a new shared repo is created.
 
     The new repo only has a requirements file and pointer to the source.
     This function configures additional shared data.
 
     Extensions can wrap this function and write additional entries to
     destrepo/.hg/shared to indicate additional pieces of data to be shared.
     """
     default = defaultpath or sourcerepo.ui.config('paths', 'default')
     if default:
         template = ('[paths]\n'
                     'default = %s\n')
         destrepo.vfs.write('hgrc', util.tonativeeol(template % default))
     if repositorymod.NARROW_REQUIREMENT in sourcerepo.requirements:
         with destrepo.wlock():
             narrowspec.copytoworkingcopy(destrepo)
 
 def _postshareupdate(repo, update, checkout=None):
     """Maybe perform a working directory update after a shared repo is created.
 
     ``update`` can be a boolean or a revision to update to.
     """
     if not update:
         return
 
     repo.ui.status(_("updating working directory\n"))
     if update is not True:
         checkout = update
     for test in (checkout, 'default', 'tip'):
         if test is None:
             continue
         try:
             uprev = repo.lookup(test)
             break
         except error.RepoLookupError:
             continue
     _update(repo, uprev)
 
 def copystore(ui, srcrepo, destpath):
     '''copy files from store of srcrepo in destpath
 
     returns destlock
     '''
     destlock = None
     try:
         hardlink = None
         topic = _('linking') if hardlink else _('copying')
         with ui.makeprogress(topic, unit=_('files')) as progress:
             num = 0
             srcpublishing = srcrepo.publishing()
             srcvfs = vfsmod.vfs(srcrepo.sharedpath)
             dstvfs = vfsmod.vfs(destpath)
             for f in srcrepo.store.copylist():
                 if srcpublishing and f.endswith('phaseroots'):
                     continue
                 dstbase = os.path.dirname(f)
                 if dstbase and not dstvfs.exists(dstbase):
                     dstvfs.mkdir(dstbase)
                 if srcvfs.exists(f):
                     if f.endswith('data'):
                         # 'dstbase' may be empty (e.g. revlog format 0)
                         lockfile = os.path.join(dstbase, "lock")
                         # lock to avoid premature writing to the target
                         destlock = lock.lock(dstvfs, lockfile)
                     hardlink, n = util.copyfiles(srcvfs.join(f), dstvfs.join(f),
                                                  hardlink, progress)
                     num += n
             if hardlink:
                 ui.debug("linked %d files\n" % num)
             else:
                 ui.debug("copied %d files\n" % num)
         return destlock
     except: # re-raises
         release(destlock)
         raise
 
 def clonewithshare(ui, peeropts, sharepath, source, srcpeer, dest, pull=False,
                    rev=None, update=True, stream=False):
     """Perform a clone using a shared repo.
 
     The store for the repository will be located at <sharepath>/.hg. The
     specified revisions will be cloned or pulled from "source". A shared repo
     will be created at "dest" and a working copy will be created if "update" is
     True.
     """
     revs = None
     if rev:
         if not srcpeer.capable('lookup'):
             raise error.Abort(_("src repository does not support "
                                "revision lookup and so doesn't "
                                "support clone by revision"))
 
         # TODO this is batchable.
         remoterevs = []
         for r in rev:
             with srcpeer.commandexecutor() as e:
                 remoterevs.append(e.callcommand('lookup', {
                     'key': r,
                 }).result())
         revs = remoterevs
 
     # Obtain a lock before checking for or cloning the pooled repo otherwise
     # 2 clients may race creating or populating it.
     pooldir = os.path.dirname(sharepath)
     # lock class requires the directory to exist.
     try:
         util.makedir(pooldir, False)
     except OSError as e:
         if e.errno != errno.EEXIST:
             raise
 
     poolvfs = vfsmod.vfs(pooldir)
     basename = os.path.basename(sharepath)
 
     with lock.lock(poolvfs, '%s.lock' % basename):
         if os.path.exists(sharepath):
             ui.status(_('(sharing from existing pooled repository %s)\n') %
                       basename)
         else:
             ui.status(_('(sharing from new pooled repository %s)\n') % basename)
             # Always use pull mode because hardlinks in share mode don't work
             # well. Never update because working copies aren't necessary in
             # share mode.
             clone(ui, peeropts, source, dest=sharepath, pull=True,
                   revs=rev, update=False, stream=stream)
 
     # Resolve the value to put in [paths] section for the source.
     if islocal(source):
         defaultpath = os.path.abspath(util.urllocalpath(source))
     else:
         defaultpath = source
 
     sharerepo = repository(ui, path=sharepath)
     destrepo = share(ui, sharerepo, dest=dest, update=False, bookmarks=False,
                      defaultpath=defaultpath)
 
     # We need to perform a pull against the dest repo to fetch bookmarks
     # and other non-store data that isn't shared by default. In the case of
     # non-existing shared repo, this means we pull from the remote twice. This
     # is a bit weird. But at the time it was implemented, there wasn't an easy
     # way to pull just non-changegroup data.
     exchange.pull(destrepo, srcpeer, heads=revs)
 
     _postshareupdate(destrepo, update)
 
     return srcpeer, peer(ui, peeropts, dest)
 
 # Recomputing branch cache might be slow on big repos,
 # so just copy it
 def _copycache(srcrepo, dstcachedir, fname):
     """copy a cache from srcrepo to destcachedir (if it exists)"""
     srcbranchcache = srcrepo.vfs.join('cache/%s' % fname)
     dstbranchcache = os.path.join(dstcachedir, fname)
     if os.path.exists(srcbranchcache):
         if not os.path.exists(dstcachedir):
             os.mkdir(dstcachedir)
         util.copyfile(srcbranchcache, dstbranchcache)
 
 def clone(ui, peeropts, source, dest=None, pull=False, revs=None,
           update=True, stream=False, branch=None, shareopts=None,
           storeincludepats=None, storeexcludepats=None, depth=None):
     """Make a copy of an existing repository.
 
     Create a copy of an existing repository in a new directory.  The
     source and destination are URLs, as passed to the repository
     function.  Returns a pair of repository peers, the source and
     newly created destination.
 
     The location of the source is added to the new repository's
     .hg/hgrc file, as the default to be used for future pulls and
     pushes.
 
     If an exception is raised, the partly cloned/updated destination
     repository will be deleted.
 
     Arguments:
 
     source: repository object or URL
 
     dest: URL of destination repository to create (defaults to base
     name of source repository)
 
     pull: always pull from source repository, even in local case or if the
     server prefers streaming
 
     stream: stream raw data uncompressed from repository (fast over
     LAN, slow over WAN)
 
     revs: revision to clone up to (implies pull=True)
 
     update: update working directory after clone completes, if
     destination is local repository (True means update to default rev,
     anything else is treated as a revision)
 
     branch: branches to clone
 
     shareopts: dict of options to control auto sharing behavior. The "pool" key
     activates auto sharing mode and defines the directory for stores. The
     "mode" key determines how to construct the directory name of the shared
     repository. "identity" means the name is derived from the node of the first
     changeset in the repository. "remote" means the name is derived from the
     remote's path/URL. Defaults to "identity."
 
     storeincludepats and storeexcludepats: sets of file patterns to include and
     exclude in the repository copy, respectively. If not defined, all files
     will be included (a "full" clone). Otherwise a "narrow" clone containing
     only the requested files will be performed. If ``storeincludepats`` is not
     defined but ``storeexcludepats`` is, ``storeincludepats`` is assumed to be
     ``path:.``. If both are empty sets, no files will be cloned.
     """
 
     if isinstance(source, bytes):
         origsource = ui.expandpath(source)
         source, branches = parseurl(origsource, branch)
         srcpeer = peer(ui, peeropts, source)
     else:
         srcpeer = source.peer() # in case we were called with a localrepo
         branches = (None, branch or [])
         origsource = source = srcpeer.url()
     revs, checkout = addbranchrevs(srcpeer, srcpeer, branches, revs)
 
     if dest is None:
         dest = defaultdest(source)
         if dest:
             ui.status(_("destination directory: %s\n") % dest)
     else:
         dest = ui.expandpath(dest)
 
     dest = util.urllocalpath(dest)
     source = util.urllocalpath(source)
 
     if not dest:
         raise error.Abort(_("empty destination path is not valid"))
 
     destvfs = vfsmod.vfs(dest, expandpath=True)
     if destvfs.lexists():
         if not destvfs.isdir():
             raise error.Abort(_("destination '%s' already exists") % dest)
         elif destvfs.listdir():
             raise error.Abort(_("destination '%s' is not empty") % dest)
 
     createopts = {}
     narrow = False
 
     if storeincludepats is not None:
         narrowspec.validatepatterns(storeincludepats)
         narrow = True
 
     if storeexcludepats is not None:
         narrowspec.validatepatterns(storeexcludepats)
         narrow = True
 
     if narrow:
         # Include everything by default if only exclusion patterns defined.
         if storeexcludepats and not storeincludepats:
             storeincludepats = {'path:.'}
 
         createopts['narrowfiles'] = True
 
     if depth:
         createopts['shallowfilestore'] = True
 
     if srcpeer.capable(b'lfs-serve'):
         # Repository creation honors the config if it disabled the extension, so
         # we can't just announce that lfs will be enabled.  This check avoids
         # saying that lfs will be enabled, and then saying it's an unknown
         # feature.  The lfs creation option is set in either case so that a
         # requirement is added.  If the extension is explicitly disabled but the
         # requirement is set, the clone aborts early, before transferring any
         # data.
         createopts['lfs'] = True
 
         if extensions.disabledext('lfs'):
             ui.status(_('(remote is using large file support (lfs), but it is '
                         'explicitly disabled in the local configuration)\n'))
         else:
             ui.status(_('(remote is using large file support (lfs); lfs will '
                         'be enabled for this repository)\n'))
 
     shareopts = shareopts or {}
     sharepool = shareopts.get('pool')
     sharenamemode = shareopts.get('mode')
     if sharepool and islocal(dest):
         sharepath = None
         if sharenamemode == 'identity':
             # Resolve the name from the initial changeset in the remote
             # repository. This returns nullid when the remote is empty. It
             # raises RepoLookupError if revision 0 is filtered or otherwise
             # not available. If we fail to resolve, sharing is not enabled.
             try:
                 with srcpeer.commandexecutor() as e:
                     rootnode = e.callcommand('lookup', {
                         'key': '0',
                     }).result()
 
                 if rootnode != node.nullid:
                     sharepath = os.path.join(sharepool, node.hex(rootnode))
                 else:
                     ui.status(_('(not using pooled storage: '
                                 'remote appears to be empty)\n'))
             except error.RepoLookupError:
                 ui.status(_('(not using pooled storage: '
                             'unable to resolve identity of remote)\n'))
         elif sharenamemode == 'remote':
             sharepath = os.path.join(
                 sharepool, node.hex(hashlib.sha1(source).digest()))
         else:
             raise error.Abort(_('unknown share naming mode: %s') %
                               sharenamemode)
 
         # TODO this is a somewhat arbitrary restriction.
         if narrow:
             ui.status(_('(pooled storage not supported for narrow clones)\n'))
             sharepath = None
 
         if sharepath:
             return clonewithshare(ui, peeropts, sharepath, source, srcpeer,
                                   dest, pull=pull, rev=revs, update=update,
                                   stream=stream)
 
     srclock = destlock = cleandir = None
     srcrepo = srcpeer.local()
     try:
         abspath = origsource
         if islocal(origsource):
             abspath = os.path.abspath(util.urllocalpath(origsource))
 
         if islocal(dest):
             cleandir = dest
 
         copy = False
         if (srcrepo and srcrepo.cancopy() and islocal(dest)
             and not phases.hassecret(srcrepo)):
             copy = not pull and not revs
 
         # TODO this is a somewhat arbitrary restriction.
         if narrow:
             copy = False
 
         if copy:
             try:
                 # we use a lock here because if we race with commit, we
                 # can end up with extra data in the cloned revlogs that's
                 # not pointed to by changesets, thus causing verify to
                 # fail
                 srclock = srcrepo.lock(wait=False)
             except error.LockError:
                 copy = False
 
         if copy:
             srcrepo.hook('preoutgoing', throw=True, source='clone')
             hgdir = os.path.realpath(os.path.join(dest, ".hg"))
             if not os.path.exists(dest):
                 util.makedirs(dest)
             else:
                 # only clean up directories we create ourselves
                 cleandir = hgdir
             try:
                 destpath = hgdir
                 util.makedir(destpath, notindexed=True)
             except OSError as inst:
                 if inst.errno == errno.EEXIST:
                     cleandir = None
                     raise error.Abort(_("destination '%s' already exists")
                                      % dest)
                 raise
 
             destlock = copystore(ui, srcrepo, destpath)
             # copy bookmarks over
             srcbookmarks = srcrepo.vfs.join('bookmarks')
             dstbookmarks = os.path.join(destpath, 'bookmarks')
             if os.path.exists(srcbookmarks):
                 util.copyfile(srcbookmarks, dstbookmarks)
 
             dstcachedir = os.path.join(destpath, 'cache')
             for cache in cacheutil.cachetocopy(srcrepo):
                 _copycache(srcrepo, dstcachedir, cache)
 
             # we need to re-init the repo after manually copying the data
             # into it
             destpeer = peer(srcrepo, peeropts, dest)
             srcrepo.hook('outgoing', source='clone',
                           node=node.hex(node.nullid))
         else:
             try:
                 # only pass ui when no srcrepo
                 destpeer = peer(srcrepo or ui, peeropts, dest, create=True,
                                 createopts=createopts)
             except OSError as inst:
                 if inst.errno == errno.EEXIST:
                     cleandir = None
                     raise error.Abort(_("destination '%s' already exists")
                                      % dest)
                 raise
 
             if revs:
                 if not srcpeer.capable('lookup'):
                     raise error.Abort(_("src repository does not support "
                                        "revision lookup and so doesn't "
                                        "support clone by revision"))
 
                 # TODO this is batchable.
                 remoterevs = []
                 for rev in revs:
                     with srcpeer.commandexecutor() as e:
                         remoterevs.append(e.callcommand('lookup', {
                             'key': rev,
                         }).result())
                 revs = remoterevs
 
                 checkout = revs[0]
             else:
                 revs = None
             local = destpeer.local()
             if local:
                 if narrow:
                     with local.wlock(), local.lock():
                         local.setnarrowpats(storeincludepats, storeexcludepats)
                         narrowspec.copytoworkingcopy(local)
 
                 u = util.url(abspath)
                 defaulturl = bytes(u)
                 local.ui.setconfig('paths', 'default', defaulturl, 'clone')
                 if not stream:
                     if pull:
                         stream = False
                     else:
                         stream = None
                 # internal config: ui.quietbookmarkmove
                 overrides = {('ui', 'quietbookmarkmove'): True}
                 with local.ui.configoverride(overrides, 'clone'):
                     exchange.pull(local, srcpeer, revs,
                                   streamclonerequested=stream,
                                   includepats=storeincludepats,
                                   excludepats=storeexcludepats,
                                   depth=depth)
             elif srcrepo:
                 # TODO lift restriction once exchange.push() accepts narrow
                 # push.
                 if narrow:
                     raise error.Abort(_('narrow clone not available for '
                                         'remote destinations'))
 
                 exchange.push(srcrepo, destpeer, revs=revs,
                               bookmarks=srcrepo._bookmarks.keys())
             else:
                 raise error.Abort(_("clone from remote to remote not supported")
                                  )
 
         cleandir = None
 
         destrepo = destpeer.local()
         if destrepo:
             template = uimod.samplehgrcs['cloned']
             u = util.url(abspath)
             u.passwd = None
             defaulturl = bytes(u)
             destrepo.vfs.write('hgrc', util.tonativeeol(template % defaulturl))
             destrepo.ui.setconfig('paths', 'default', defaulturl, 'clone')
 
             if ui.configbool('experimental', 'remotenames'):
                 logexchange.pullremotenames(destrepo, srcpeer)
 
             if update:
                 if update is not True:
                     with srcpeer.commandexecutor() as e:
                         checkout = e.callcommand('lookup', {
                             'key': update,
                         }).result()
 
                 uprev = None
                 status = None
                 if checkout is not None:
                     # Some extensions (at least hg-git and hg-subversion) have
                     # a peer.lookup() implementation that returns a name instead
                     # of a nodeid. We work around it here until we've figured
                     # out a better solution.
                     if len(checkout) == 20 and checkout in destrepo:
                         uprev = checkout
                     elif scmutil.isrevsymbol(destrepo, checkout):
                         uprev = scmutil.revsymbol(destrepo, checkout).node()
                     else:
                         if update is not True:
                             try:
                                 uprev = destrepo.lookup(update)
                             except error.RepoLookupError:
                                 pass
                 if uprev is None:
                     try:
                         uprev = destrepo._bookmarks['@']
                         update = '@'
                         bn = destrepo[uprev].branch()
                         if bn == 'default':
                             status = _("updating to bookmark @\n")
                         else:
                             status = (_("updating to bookmark @ on branch %s\n")
                                       % bn)
                     except KeyError:
                         try:
                             uprev = destrepo.branchtip('default')
                         except error.RepoLookupError:
                             uprev = destrepo.lookup('tip')
                 if not status:
                     bn = destrepo[uprev].branch()
                     status = _("updating to branch %s\n") % bn
                 destrepo.ui.status(status)
                 _update(destrepo, uprev)
                 if update in destrepo._bookmarks:
                     bookmarks.activate(destrepo, update)
     finally:
         release(srclock, destlock)
         if cleandir is not None:
             shutil.rmtree(cleandir, True)
         if srcpeer is not None:
             srcpeer.close()
     return srcpeer, destpeer
 
 def _showstats(repo, stats, quietempty=False):
     if quietempty and stats.isempty():
         return
     repo.ui.status(_("%d files updated, %d files merged, "
                      "%d files removed, %d files unresolved\n") % (
                    stats.updatedcount, stats.mergedcount,
                    stats.removedcount, stats.unresolvedcount))
 
 def updaterepo(repo, node, overwrite, updatecheck=None):
     """Update the working directory to node.
 
     When overwrite is set, changes are clobbered, merged else
 
     returns stats (see pydoc mercurial.merge.applyupdates)"""
     return mergemod.update(repo, node, branchmerge=False, force=overwrite,
                            labels=['working copy', 'destination'],
                            updatecheck=updatecheck)
 
 def update(repo, node, quietempty=False, updatecheck=None):
     """update the working directory to node"""
     stats = updaterepo(repo, node, False, updatecheck=updatecheck)
     _showstats(repo, stats, quietempty)
     if stats.unresolvedcount:
         repo.ui.status(_("use 'hg resolve' to retry unresolved file merges\n"))
     return stats.unresolvedcount > 0
 
 # naming conflict in clone()
 _update = update
 
 def clean(repo, node, show_stats=True, quietempty=False):
     """forcibly switch the working directory to node, clobbering changes"""
     stats = updaterepo(repo, node, True)
     repo.vfs.unlinkpath('graftstate', ignoremissing=True)
     if show_stats:
         _showstats(repo, stats, quietempty)
     return stats.unresolvedcount > 0
 
 # naming conflict in updatetotally()
 _clean = clean
 
 def updatetotally(ui, repo, checkout, brev, clean=False, updatecheck=None):
     """Update the working directory with extra care for non-file components
 
     This takes care of non-file components below:
 
     :bookmark: might be advanced or (in)activated
 
     This takes arguments below:
 
     :checkout: to which revision the working directory is updated
     :brev: a name, which might be a bookmark to be activated after updating
     :clean: whether changes in the working directory can be discarded
     :updatecheck: how to deal with a dirty working directory
 
     Valid values for updatecheck are (None => linear):
 
      * abort: abort if the working directory is dirty
      * none: don't check (merge working directory changes into destination)
      * linear: check that update is linear before merging working directory
                changes into destination
      * noconflict: check that the update does not result in file merges
 
     This returns whether conflict is detected at updating or not.
     """
     if updatecheck is None:
         updatecheck = ui.config('commands', 'update.check')
         if updatecheck not in ('abort', 'none', 'linear', 'noconflict'):
             # If not configured, or invalid value configured
             updatecheck = 'linear'
     with repo.wlock():
         movemarkfrom = None
         warndest = False
         if checkout is None:
             updata = destutil.destupdate(repo, clean=clean)
             checkout, movemarkfrom, brev = updata
             warndest = True
 
         if clean:
             ret = _clean(repo, checkout)
         else:
             if updatecheck == 'abort':
                 cmdutil.bailifchanged(repo, merge=False)
                 updatecheck = 'none'
             ret = _update(repo, checkout, updatecheck=updatecheck)
 
         if not ret and movemarkfrom:
             if movemarkfrom == repo['.'].node():
                 pass # no-op update
             elif bookmarks.update(repo, [movemarkfrom], repo['.'].node()):
                 b = ui.label(repo._activebookmark, 'bookmarks.active')
                 ui.status(_("updating bookmark %s\n") % b)
             else:
                 # this can happen with a non-linear update
                 b = ui.label(repo._activebookmark, 'bookmarks')
                 ui.status(_("(leaving bookmark %s)\n") % b)
                 bookmarks.deactivate(repo)
         elif brev in repo._bookmarks:
             if brev != repo._activebookmark:
                 b = ui.label(brev, 'bookmarks.active')
                 ui.status(_("(activating bookmark %s)\n") % b)
             bookmarks.activate(repo, brev)
         elif brev:
             if repo._activebookmark:
                 b = ui.label(repo._activebookmark, 'bookmarks')
                 ui.status(_("(leaving bookmark %s)\n") % b)
             bookmarks.deactivate(repo)
 
         if warndest:
             destutil.statusotherdests(ui, repo)
 
     return ret
 
 def merge(repo, node, force=None, remind=True, mergeforce=False, labels=None,
           abort=False):
     """Branch merge with node, resolving changes. Return true if any
     unresolved conflicts."""
     if abort:
         return abortmerge(repo.ui, repo)
 
     stats = mergemod.update(repo, node, branchmerge=True, force=force,
                             mergeforce=mergeforce, labels=labels)
     _showstats(repo, stats)
     if stats.unresolvedcount:
         repo.ui.status(_("use 'hg resolve' to retry unresolved file merges "
                          "or 'hg merge --abort' to abandon\n"))
     elif remind:
         repo.ui.status(_("(branch merge, don't forget to commit)\n"))
     return stats.unresolvedcount > 0
 
 def abortmerge(ui, repo):
     ms = mergemod.mergestate.read(repo)
     if ms.active():
         # there were conflicts
         node = ms.localctx.hex()
     else:
         # there were no conficts, mergestate was not stored
         node = repo['.'].hex()
 
     repo.ui.status(_("aborting the merge, updating back to"
                      " %s\n") % node[:12])
     stats = mergemod.update(repo, node, branchmerge=False, force=True)
     _showstats(repo, stats)
     return stats.unresolvedcount > 0
 
 def _incoming(displaychlist, subreporecurse, ui, repo, source,
         opts, buffered=False):
     """
     Helper for incoming / gincoming.
     displaychlist gets called with
         (remoterepo, incomingchangesetlist, displayer) parameters,
     and is supposed to contain only code that can't be unified.
     """
     source, branches = parseurl(ui.expandpath(source), opts.get('branch'))
     other = peer(repo, opts, source)
     ui.status(_('comparing with %s\n') % util.hidepassword(source))
     revs, checkout = addbranchrevs(repo, other, branches, opts.get('rev'))
 
     if revs:
         revs = [other.lookup(rev) for rev in revs]
     other, chlist, cleanupfn = bundlerepo.getremotechanges(ui, repo, other,
                                 revs, opts["bundle"], opts["force"])
     try:
         if not chlist:
             ui.status(_("no changes found\n"))
             return subreporecurse()
         ui.pager('incoming')
         displayer = logcmdutil.changesetdisplayer(ui, other, opts,
                                                   buffered=buffered)
         displaychlist(other, chlist, displayer)
         displayer.close()
     finally:
         cleanupfn()
     subreporecurse()
     return 0 # exit code is zero since we found incoming changes
 
 def incoming(ui, repo, source, opts):
     def subreporecurse():
         ret = 1
         if opts.get('subrepos'):
             ctx = repo[None]
             for subpath in sorted(ctx.substate):
                 sub = ctx.sub(subpath)
                 ret = min(ret, sub.incoming(ui, source, opts))
         return ret
 
     def display(other, chlist, displayer):
         limit = logcmdutil.getlimit(opts)
         if opts.get('newest_first'):
             chlist.reverse()
         count = 0
         for n in chlist:
             if limit is not None and count >= limit:
                 break
             parents = [p for p in other.changelog.parents(n) if p != nullid]
             if opts.get('no_merges') and len(parents) == 2:
                 continue
             count += 1
             displayer.show(other[n])
     return _incoming(display, subreporecurse, ui, repo, source, opts)
 
 def _outgoing(ui, repo, dest, opts):
     path = ui.paths.getpath(dest, default=('default-push', 'default'))
     if not path:
         raise error.Abort(_('default repository not configured!'),
                 hint=_("see 'hg help config.paths'"))
     dest = path.pushloc or path.loc
     branches = path.branch, opts.get('branch') or []
 
     ui.status(_('comparing with %s\n') % util.hidepassword(dest))
     revs, checkout = addbranchrevs(repo, repo, branches, opts.get('rev'))
     if revs:
         revs = [repo[rev].node() for rev in scmutil.revrange(repo, revs)]
 
     other = peer(repo, opts, dest)
     outgoing = discovery.findcommonoutgoing(repo, other, revs,
                                             force=opts.get('force'))
     o = outgoing.missing
     if not o:
         scmutil.nochangesfound(repo.ui, repo, outgoing.excluded)
     return o, other
 
 def outgoing(ui, repo, dest, opts):
     def recurse():
         ret = 1
         if opts.get('subrepos'):
             ctx = repo[None]
             for subpath in sorted(ctx.substate):
                 sub = ctx.sub(subpath)
                 ret = min(ret, sub.outgoing(ui, dest, opts))
         return ret
 
     limit = logcmdutil.getlimit(opts)
     o, other = _outgoing(ui, repo, dest, opts)
     if not o:
         cmdutil.outgoinghooks(ui, repo, other, opts, o)
         return recurse()
 
     if opts.get('newest_first'):
         o.reverse()
     ui.pager('outgoing')
     displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
     count = 0
     for n in o:
         if limit is not None and count >= limit:
             break
         parents = [p for p in repo.changelog.parents(n) if p != nullid]
         if opts.get('no_merges') and len(parents) == 2:
             continue
         count += 1
         displayer.show(repo[n])
     displayer.close()
     cmdutil.outgoinghooks(ui, repo, other, opts, o)
     recurse()
     return 0 # exit code is zero since we found outgoing changes
 
 def verify(repo, level=None):
     """verify the consistency of a repository"""
     ret = verifymod.verify(repo, level=level)
 
     # Broken subrepo references in hidden csets don't seem worth worrying about,
     # since they can't be pushed/pulled, and --hidden can be used if they are a
     # concern.
 
     # pathto() is needed for -R case
     revs = repo.revs("filelog(%s)",
                      util.pathto(repo.root, repo.getcwd(), '.hgsubstate'))
 
     if revs:
         repo.ui.status(_('checking subrepo links\n'))
         for rev in revs:
             ctx = repo[rev]
             try:
                 for subpath in ctx.substate:
                     try:
                         ret = (ctx.sub(subpath, allowcreate=False).verify()
                                or ret)
                     except error.RepoError as e:
                         repo.ui.warn(('%d: %s\n') % (rev, e))
             except Exception:
                 repo.ui.warn(_('.hgsubstate is corrupt in revision %s\n') %
                              node.short(ctx.node()))
 
     return ret
 
 def remoteui(src, opts):
     'build a remote ui from ui or repo and opts'
     if util.safehasattr(src, 'baseui'): # looks like a repository
         dst = src.baseui.copy() # drop repo-specific config
         src = src.ui # copy target options from repo
     else: # assume it's a global ui object
         dst = src.copy() # keep all global options
 
     # copy ssh-specific options
     for o in 'ssh', 'remotecmd':
         v = opts.get(o) or src.config('ui', o)
         if v:
             dst.setconfig("ui", o, v, 'copied')
 
     # copy bundle-specific options
     r = src.config('bundle', 'mainreporoot')
     if r:
         dst.setconfig('bundle', 'mainreporoot', r, 'copied')
 
     # copy selected local settings to the remote ui
     for sect in ('auth', 'hostfingerprints', 'hostsecurity', 'http_proxy'):
         for key, val in src.configitems(sect):
             dst.setconfig(sect, key, val, 'copied')
     v = src.config('web', 'cacerts')
     if v:
         dst.setconfig('web', 'cacerts', util.expandpath(v), 'copied')
 
     return dst
 
 # Files of interest
 # Used to check if the repository has changed looking at mtime and size of
 # these files.
 foi = [('spath', '00changelog.i'),
        ('spath', 'phaseroots'), # ! phase can change content at the same size
        ('spath', 'obsstore'),
        ('path', 'bookmarks'), # ! bookmark can change content at the same size
       ]
 
 class cachedlocalrepo(object):
     """Holds a localrepository that can be cached and reused."""
 
     def __init__(self, repo):
         """Create a new cached repo from an existing repo.
 
         We assume the passed in repo was recently created. If the
         repo has changed between when it was created and when it was
         turned into a cache, it may not refresh properly.
         """
         assert isinstance(repo, localrepo.localrepository)
         self._repo = repo
         self._state, self.mtime = self._repostate()
         self._filtername = repo.filtername
 
     def fetch(self):
         """Refresh (if necessary) and return a repository.
 
         If the cached instance is out of date, it will be recreated
         automatically and returned.
 
         Returns a tuple of the repo and a boolean indicating whether a new
         repo instance was created.
         """
         # We compare the mtimes and sizes of some well-known files to
         # determine if the repo changed. This is not precise, as mtimes
         # are susceptible to clock skew and imprecise filesystems and
         # file content can change while maintaining the same size.
 
         state, mtime = self._repostate()
         if state == self._state:
             return self._repo, False
 
         repo = repository(self._repo.baseui, self._repo.url())
         if self._filtername:
             self._repo = repo.filtered(self._filtername)
         else:
             self._repo = repo.unfiltered()
         self._state = state
         self.mtime = mtime
 
         return self._repo, True
 
     def _repostate(self):
         state = []
         maxmtime = -1
         for attr, fname in foi:
             prefix = getattr(self._repo, attr)
             p = os.path.join(prefix, fname)
             try:
                 st = os.stat(p)
             except OSError:
                 st = os.stat(prefix)
             state.append((st[stat.ST_MTIME], st.st_size))
             maxmtime = max(maxmtime, st[stat.ST_MTIME])
 
         return tuple(state), maxmtime
 
     def copy(self):
         """Obtain a copy of this class instance.
 
         A new localrepository instance is obtained. The new instance should be
         completely independent of the original.
         """
         repo = repository(self._repo.baseui, self._repo.origroot)
         if self._filtername:
             repo = repo.filtered(self._filtername)
         else:
             repo = repo.unfiltered()
         c = cachedlocalrepo(repo)
         c._state = self._state
         c.mtime = self.mtime
         return c

mercurial/httppeer.py

@@ -1,1010 +1,1012
 # httppeer.py - HTTP repository proxy classes for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import io
 import os
 import socket
 import struct
 import weakref
 
 from .i18n import _
+from .interfaces import (
+    repository,
+)
 from . import (
     bundle2,
     error,
     httpconnection,
     pycompat,
-    repository,
     statichttprepo,
     url as urlmod,
     util,
     wireprotoframing,
     wireprototypes,
     wireprotov1peer,
     wireprotov2peer,
     wireprotov2server,
 )
 from .utils import (
     cborutil,
     interfaceutil,
     stringutil,
 )
 
 httplib = util.httplib
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 def encodevalueinheaders(value, header, limit):
     """Encode a string value into multiple HTTP headers.
 
     ``value`` will be encoded into 1 or more HTTP headers with the names
     ``header-<N>`` where ``<N>`` is an integer starting at 1. Each header
     name + value will be at most ``limit`` bytes long.
 
     Returns an iterable of 2-tuples consisting of header names and
     values as native strings.
     """
     # HTTP Headers are ASCII. Python 3 requires them to be unicodes,
     # not bytes. This function always takes bytes in as arguments.
     fmt = pycompat.strurl(header) + r'-%s'
     # Note: it is *NOT* a bug that the last bit here is a bytestring
     # and not a unicode: we're just getting the encoded length anyway,
     # and using an r-string to make it portable between Python 2 and 3
     # doesn't work because then the \r is a literal backslash-r
     # instead of a carriage return.
     valuelen = limit - len(fmt % r'000') - len(': \r\n')
     result = []
 
     n = 0
     for i in pycompat.xrange(0, len(value), valuelen):
         n += 1
         result.append((fmt % str(n), pycompat.strurl(value[i:i + valuelen])))
 
     return result
 
 class _multifile(object):
     def __init__(self, *fileobjs):
         for f in fileobjs:
             if not util.safehasattr(f, 'length'):
                 raise ValueError(
                     '_multifile only supports file objects that '
                     'have a length but this one does not:', type(f), f)
         self._fileobjs = fileobjs
         self._index = 0
 
     @property
     def length(self):
         return sum(f.length for f in self._fileobjs)
 
     def read(self, amt=None):
         if amt <= 0:
             return ''.join(f.read() for f in self._fileobjs)
         parts = []
         while amt and self._index < len(self._fileobjs):
             parts.append(self._fileobjs[self._index].read(amt))
             got = len(parts[-1])
             if got < amt:
                 self._index += 1
             amt -= got
         return ''.join(parts)
 
     def seek(self, offset, whence=os.SEEK_SET):
         if whence != os.SEEK_SET:
             raise NotImplementedError(
                 '_multifile does not support anything other'
                 ' than os.SEEK_SET for whence on seek()')
         if offset != 0:
             raise NotImplementedError(
                 '_multifile only supports seeking to start, but that '
                 'could be fixed if you need it')
         for f in self._fileobjs:
             f.seek(0)
         self._index = 0
 
 def makev1commandrequest(ui, requestbuilder, caps, capablefn,
                          repobaseurl, cmd, args):
     """Make an HTTP request to run a command for a version 1 client.
 
     ``caps`` is a set of known server capabilities. The value may be
     None if capabilities are not yet known.
 
     ``capablefn`` is a function to evaluate a capability.
 
     ``cmd``, ``args``, and ``data`` define the command, its arguments, and
     raw data to pass to it.
     """
     if cmd == 'pushkey':
         args['data'] = ''
     data = args.pop('data', None)
     headers = args.pop('headers', {})
 
     ui.debug("sending %s command\n" % cmd)
     q = [('cmd', cmd)]
     headersize = 0
     # Important: don't use self.capable() here or else you end up
     # with infinite recursion when trying to look up capabilities
     # for the first time.
     postargsok = caps is not None and 'httppostargs' in caps
 
     # Send arguments via POST.
     if postargsok and args:
         strargs = urlreq.urlencode(sorted(args.items()))
         if not data:
             data = strargs
         else:
             if isinstance(data, bytes):
                 i = io.BytesIO(data)
                 i.length = len(data)
                 data = i
             argsio = io.BytesIO(strargs)
             argsio.length = len(strargs)
             data = _multifile(argsio, data)
         headers[r'X-HgArgs-Post'] = len(strargs)
     elif args:
         # Calling self.capable() can infinite loop if we are calling
         # "capabilities". But that command should never accept wire
         # protocol arguments. So this should never happen.
         assert cmd != 'capabilities'
         httpheader = capablefn('httpheader')
         if httpheader:
             headersize = int(httpheader.split(',', 1)[0])
 
         # Send arguments via HTTP headers.
         if headersize > 0:
             # The headers can typically carry more data than the URL.
             encargs = urlreq.urlencode(sorted(args.items()))
             for header, value in encodevalueinheaders(encargs, 'X-HgArg',
                                                       headersize):
                 headers[header] = value
         # Send arguments via query string (Mercurial <1.9).
         else:
             q += sorted(args.items())
 
     qs = '?%s' % urlreq.urlencode(q)
     cu = "%s%s" % (repobaseurl, qs)
     size = 0
     if util.safehasattr(data, 'length'):
         size = data.length
     elif data is not None:
         size = len(data)
     if data is not None and r'Content-Type' not in headers:
         headers[r'Content-Type'] = r'application/mercurial-0.1'
 
     # Tell the server we accept application/mercurial-0.2 and multiple
     # compression formats if the server is capable of emitting those
     # payloads.
     # Note: Keep this set empty by default, as client advertisement of
     # protocol parameters should only occur after the handshake.
     protoparams = set()
 
     mediatypes = set()
     if caps is not None:
         mt = capablefn('httpmediatype')
         if mt:
             protoparams.add('0.1')
             mediatypes = set(mt.split(','))
 
         protoparams.add('partial-pull')
 
     if '0.2tx' in mediatypes:
         protoparams.add('0.2')
 
     if '0.2tx' in mediatypes and capablefn('compression'):
         # We /could/ compare supported compression formats and prune
         # non-mutually supported or error if nothing is mutually supported.
         # For now, send the full list to the server and have it error.
         comps = [e.wireprotosupport().name for e in
                  util.compengines.supportedwireengines(util.CLIENTROLE)]
         protoparams.add('comp=%s' % ','.join(comps))
 
     if protoparams:
         protoheaders = encodevalueinheaders(' '.join(sorted(protoparams)),
                                             'X-HgProto',
                                             headersize or 1024)
         for header, value in protoheaders:
             headers[header] = value
 
     varyheaders = []
     for header in headers:
         if header.lower().startswith(r'x-hg'):
             varyheaders.append(header)
 
     if varyheaders:
         headers[r'Vary'] = r','.join(sorted(varyheaders))
 
     req = requestbuilder(pycompat.strurl(cu), data, headers)
 
     if data is not None:
         ui.debug("sending %d bytes\n" % size)
         req.add_unredirected_header(r'Content-Length', r'%d' % size)
 
     return req, cu, qs
 
 def _reqdata(req):
     """Get request data, if any. If no data, returns None."""
     if pycompat.ispy3:
         return req.data
     if not req.has_data():
         return None
     return req.get_data()
 
 def sendrequest(ui, opener, req):
     """Send a prepared HTTP request.
 
     Returns the response object.
     """
     dbg = ui.debug
     if (ui.debugflag
         and ui.configbool('devel', 'debug.peer-request')):
         line = 'devel-peer-request: %s\n'
         dbg(line % '%s %s' % (pycompat.bytesurl(req.get_method()),
                               pycompat.bytesurl(req.get_full_url())))
         hgargssize = None
 
         for header, value in sorted(req.header_items()):
             header = pycompat.bytesurl(header)
             value = pycompat.bytesurl(value)
             if header.startswith('X-hgarg-'):
                 if hgargssize is None:
                     hgargssize = 0
                 hgargssize += len(value)
             else:
                 dbg(line % '  %s %s' % (header, value))
 
         if hgargssize is not None:
             dbg(line % '  %d bytes of commands arguments in headers'
                 % hgargssize)
         data = _reqdata(req)
         if data is not None:
             length = getattr(data, 'length', None)
             if length is None:
                 length = len(data)
             dbg(line % '  %d bytes of data' % length)
 
         start = util.timer()
 
     res = None
     try:
         res = opener.open(req)
     except urlerr.httperror as inst:
         if inst.code == 401:
             raise error.Abort(_('authorization failed'))
         raise
     except httplib.HTTPException as inst:
         ui.debug('http error requesting %s\n' %
                  util.hidepassword(req.get_full_url()))
         ui.traceback()
         raise IOError(None, inst)
     finally:
         if ui.debugflag and ui.configbool('devel', 'debug.peer-request'):
             code = res.code if res else -1
             dbg(line % '  finished in %.4f seconds (%d)'
                 % (util.timer() - start, code))
 
     # Insert error handlers for common I/O failures.
     urlmod.wrapresponse(res)
 
     return res
 
 class RedirectedRepoError(error.RepoError):
     def __init__(self, msg, respurl):
         super(RedirectedRepoError, self).__init__(msg)
         self.respurl = respurl
 
 def parsev1commandresponse(ui, baseurl, requrl, qs, resp, compressible,
                            allowcbor=False):
     # record the url we got redirected to
     redirected = False
     respurl = pycompat.bytesurl(resp.geturl())
     if respurl.endswith(qs):
         respurl = respurl[:-len(qs)]
         qsdropped = False
     else:
         qsdropped = True
 
     if baseurl.rstrip('/') != respurl.rstrip('/'):
         redirected = True
         if not ui.quiet:
             ui.warn(_('real URL is %s\n') % respurl)
 
     try:
         proto = pycompat.bytesurl(resp.getheader(r'content-type', r''))
     except AttributeError:
         proto = pycompat.bytesurl(resp.headers.get(r'content-type', r''))
 
     safeurl = util.hidepassword(baseurl)
     if proto.startswith('application/hg-error'):
         raise error.OutOfBandError(resp.read())
 
     # Pre 1.0 versions of Mercurial used text/plain and
     # application/hg-changegroup. We don't support such old servers.
     if not proto.startswith('application/mercurial-'):
         ui.debug("requested URL: '%s'\n" % util.hidepassword(requrl))
         msg = _("'%s' does not appear to be an hg repository:\n"
                 "---%%<--- (%s)\n%s\n---%%<---\n") % (
             safeurl, proto or 'no content-type', resp.read(1024))
 
         # Some servers may strip the query string from the redirect. We
         # raise a special error type so callers can react to this specially.
         if redirected and qsdropped:
             raise RedirectedRepoError(msg, respurl)
         else:
             raise error.RepoError(msg)
 
     try:
         subtype = proto.split('-', 1)[1]
 
         # Unless we end up supporting CBOR in the legacy wire protocol,
         # this should ONLY be encountered for the initial capabilities
         # request during handshake.
         if subtype == 'cbor':
             if allowcbor:
                 return respurl, proto, resp
             else:
                 raise error.RepoError(_('unexpected CBOR response from '
                                         'server'))
 
         version_info = tuple([int(n) for n in subtype.split('.')])
     except ValueError:
         raise error.RepoError(_("'%s' sent a broken Content-Type "
                                 "header (%s)") % (safeurl, proto))
 
     # TODO consider switching to a decompression reader that uses
     # generators.
     if version_info == (0, 1):
         if compressible:
             resp = util.compengines['zlib'].decompressorreader(resp)
 
     elif version_info == (0, 2):
         # application/mercurial-0.2 always identifies the compression
         # engine in the payload header.
         elen = struct.unpack('B', util.readexactly(resp, 1))[0]
         ename = util.readexactly(resp, elen)
         engine = util.compengines.forwiretype(ename)
 
         resp = engine.decompressorreader(resp)
     else:
         raise error.RepoError(_("'%s' uses newer protocol %s") %
                               (safeurl, subtype))
 
     return respurl, proto, resp
 
 class httppeer(wireprotov1peer.wirepeer):
     def __init__(self, ui, path, url, opener, requestbuilder, caps):
         self.ui = ui
         self._path = path
         self._url = url
         self._caps = caps
         self.limitedarguments = caps is not None and 'httppostargs' not in caps
         self._urlopener = opener
         self._requestbuilder = requestbuilder
 
     def __del__(self):
         for h in self._urlopener.handlers:
             h.close()
             getattr(h, "close_all", lambda: None)()
 
     # Begin of ipeerconnection interface.
 
     def url(self):
         return self._path
 
     def local(self):
         return None
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         try:
             reqs, sent, recv = (self._urlopener.requestscount,
                                 self._urlopener.sentbytescount,
                                 self._urlopener.receivedbytescount)
         except AttributeError:
             return
         self.ui.note(_('(sent %d HTTP requests and %d bytes; '
                        'received %d bytes in responses)\n') %
                      (reqs, sent, recv))
 
     # End of ipeerconnection interface.
 
     # Begin of ipeercommands interface.
 
     def capabilities(self):
         return self._caps
 
     # End of ipeercommands interface.
 
     def _callstream(self, cmd, _compressible=False, **args):
         args = pycompat.byteskwargs(args)
 
         req, cu, qs = makev1commandrequest(self.ui, self._requestbuilder,
                                            self._caps, self.capable,
                                            self._url, cmd, args)
 
         resp = sendrequest(self.ui, self._urlopener, req)
 
         self._url, ct, resp = parsev1commandresponse(self.ui, self._url, cu, qs,
                                                      resp, _compressible)
 
         return resp
 
     def _call(self, cmd, **args):
         fp = self._callstream(cmd, **args)
         try:
             return fp.read()
         finally:
             # if using keepalive, allow connection to be reused
             fp.close()
 
     def _callpush(self, cmd, cg, **args):
         # have to stream bundle to a temp file because we do not have
         # http 1.1 chunked transfer.
 
         types = self.capable('unbundle')
         try:
             types = types.split(',')
         except AttributeError:
             # servers older than d1b16a746db6 will send 'unbundle' as a
             # boolean capability. They only support headerless/uncompressed
             # bundles.
             types = [""]
         for x in types:
             if x in bundle2.bundletypes:
                 type = x
                 break
 
         tempname = bundle2.writebundle(self.ui, cg, None, type)
         fp = httpconnection.httpsendfile(self.ui, tempname, "rb")
         headers = {r'Content-Type': r'application/mercurial-0.1'}
 
         try:
             r = self._call(cmd, data=fp, headers=headers, **args)
             vals = r.split('\n', 1)
             if len(vals) < 2:
                 raise error.ResponseError(_("unexpected response:"), r)
             return vals
         except urlerr.httperror:
             # Catch and re-raise these so we don't try and treat them
             # like generic socket errors. They lack any values in
             # .args on Python 3 which breaks our socket.error block.
             raise
         except socket.error as err:
             if err.args[0] in (errno.ECONNRESET, errno.EPIPE):
                 raise error.Abort(_('push failed: %s') % err.args[1])
             raise error.Abort(err.args[1])
         finally:
             fp.close()
             os.unlink(tempname)
 
     def _calltwowaystream(self, cmd, fp, **args):
         fh = None
         fp_ = None
         filename = None
         try:
             # dump bundle to disk
             fd, filename = pycompat.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, r"wb")
             d = fp.read(4096)
             while d:
                 fh.write(d)
                 d = fp.read(4096)
             fh.close()
             # start http push
             fp_ = httpconnection.httpsendfile(self.ui, filename, "rb")
             headers = {r'Content-Type': r'application/mercurial-0.1'}
             return self._callstream(cmd, data=fp_, headers=headers, **args)
         finally:
             if fp_ is not None:
                 fp_.close()
             if fh is not None:
                 fh.close()
                 os.unlink(filename)
 
     def _callcompressable(self, cmd, **args):
         return self._callstream(cmd, _compressible=True, **args)
 
     def _abort(self, exception):
         raise exception
 
 def sendv2request(ui, opener, requestbuilder, apiurl, permission, requests,
                   redirect):
     wireprotoframing.populatestreamencoders()
 
     uiencoders = ui.configlist(b'experimental', b'httppeer.v2-encoder-order')
 
     if uiencoders:
         encoders = []
 
         for encoder in uiencoders:
             if encoder not in wireprotoframing.STREAM_ENCODERS:
                 ui.warn(_(b'wire protocol version 2 encoder referenced in '
                           b'config (%s) is not known; ignoring\n') % encoder)
             else:
                 encoders.append(encoder)
 
     else:
         encoders = wireprotoframing.STREAM_ENCODERS_ORDER
 
     reactor = wireprotoframing.clientreactor(ui,
                                              hasmultiplesend=False,
                                              buffersends=True,
                                              clientcontentencoders=encoders)
 
     handler = wireprotov2peer.clienthandler(ui, reactor,
                                             opener=opener,
                                             requestbuilder=requestbuilder)
 
     url = '%s/%s' % (apiurl, permission)
 
     if len(requests) > 1:
         url += '/multirequest'
     else:
         url += '/%s' % requests[0][0]
 
     ui.debug('sending %d commands\n' % len(requests))
     for command, args, f in requests:
         ui.debug('sending command %s: %s\n' % (
             command, stringutil.pprint(args, indent=2)))
         assert not list(handler.callcommand(command, args, f,
                                             redirect=redirect))
 
     # TODO stream this.
     body = b''.join(map(bytes, handler.flushcommands()))
 
     # TODO modify user-agent to reflect v2
     headers = {
         r'Accept': wireprotov2server.FRAMINGTYPE,
         r'Content-Type': wireprotov2server.FRAMINGTYPE,
     }
 
     req = requestbuilder(pycompat.strurl(url), body, headers)
     req.add_unredirected_header(r'Content-Length', r'%d' % len(body))
 
     try:
         res = opener.open(req)
     except urlerr.httperror as e:
         if e.code == 401:
             raise error.Abort(_('authorization failed'))
 
         raise
     except httplib.HTTPException as e:
         ui.traceback()
         raise IOError(None, e)
 
     return handler, res
 
 class queuedcommandfuture(pycompat.futures.Future):
     """Wraps result() on command futures to trigger submission on call."""
 
     def result(self, timeout=None):
         if self.done():
             return pycompat.futures.Future.result(self, timeout)
 
         self._peerexecutor.sendcommands()
 
         # sendcommands() will restore the original __class__ and self.result
         # will resolve to Future.result.
         return self.result(timeout)
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class httpv2executor(object):
     def __init__(self, ui, opener, requestbuilder, apiurl, descriptor,
                  redirect):
         self._ui = ui
         self._opener = opener
         self._requestbuilder = requestbuilder
         self._apiurl = apiurl
         self._descriptor = descriptor
         self._redirect = redirect
         self._sent = False
         self._closed = False
         self._neededpermissions = set()
         self._calls = []
         self._futures = weakref.WeakSet()
         self._responseexecutor = None
         self._responsef = None
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'commands are sent')
 
         if self._closed:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'close()')
 
         # The service advertises which commands are available. So if we attempt
         # to call an unknown command or pass an unknown argument, we can screen
         # for this.
         if command not in self._descriptor['commands']:
             raise error.ProgrammingError(
                 'wire protocol command %s is not available' % command)
 
         cmdinfo = self._descriptor['commands'][command]
         unknownargs = set(args.keys()) - set(cmdinfo.get('args', {}))
 
         if unknownargs:
             raise error.ProgrammingError(
                 'wire protocol command %s does not accept argument: %s' % (
                     command, ', '.join(sorted(unknownargs))))
 
         self._neededpermissions |= set(cmdinfo['permissions'])
 
         # TODO we /could/ also validate types here, since the API descriptor
         # includes types...
 
         f = pycompat.futures.Future()
 
         # Monkeypatch it so result() triggers sendcommands(), otherwise result()
         # could deadlock.
         f.__class__ = queuedcommandfuture
         f._peerexecutor = self
 
         self._futures.add(f)
         self._calls.append((command, args, f))
 
         return f
 
     def sendcommands(self):
         if self._sent:
             return
 
         if not self._calls:
             return
 
         self._sent = True
 
         # Unhack any future types so caller sees a clean type and so we
         # break reference cycle.
         for f in self._futures:
             if isinstance(f, queuedcommandfuture):
                 f.__class__ = pycompat.futures.Future
                 f._peerexecutor = None
 
         # Mark the future as running and filter out cancelled futures.
         calls = [(command, args, f)
                  for command, args, f in self._calls
                  if f.set_running_or_notify_cancel()]
 
         # Clear out references, prevent improper object usage.
         self._calls = None
 
         if not calls:
             return
 
         permissions = set(self._neededpermissions)
 
         if 'push' in permissions and 'pull' in permissions:
             permissions.remove('pull')
 
         if len(permissions) > 1:
             raise error.RepoError(_('cannot make request requiring multiple '
                                     'permissions: %s') %
                                   _(', ').join(sorted(permissions)))
 
         permission = {
             'push': 'rw',
             'pull': 'ro',
         }[permissions.pop()]
 
         handler, resp = sendv2request(
             self._ui, self._opener, self._requestbuilder, self._apiurl,
             permission, calls, self._redirect)
 
         # TODO we probably want to validate the HTTP code, media type, etc.
 
         self._responseexecutor = pycompat.futures.ThreadPoolExecutor(1)
         self._responsef = self._responseexecutor.submit(self._handleresponse,
                                                         handler, resp)
 
     def close(self):
         if self._closed:
             return
 
         self.sendcommands()
 
         self._closed = True
 
         if not self._responsef:
             return
 
         # TODO ^C here may not result in immediate program termination.
 
         try:
             self._responsef.result()
         finally:
             self._responseexecutor.shutdown(wait=True)
             self._responsef = None
             self._responseexecutor = None
 
             # If any of our futures are still in progress, mark them as
             # errored, otherwise a result() could wait indefinitely.
             for f in self._futures:
                 if not f.done():
                     f.set_exception(error.ResponseError(
                         _('unfulfilled command response')))
 
             self._futures = None
 
     def _handleresponse(self, handler, resp):
         # Called in a thread to read the response.
 
         while handler.readdata(resp):
             pass
 
 @interfaceutil.implementer(repository.ipeerv2)
 class httpv2peer(object):
 
     limitedarguments = False
 
     def __init__(self, ui, repourl, apipath, opener, requestbuilder,
                  apidescriptor):
         self.ui = ui
         self.apidescriptor = apidescriptor
 
         if repourl.endswith('/'):
             repourl = repourl[:-1]
 
         self._url = repourl
         self._apipath = apipath
         self._apiurl = '%s/%s' % (repourl, apipath)
         self._opener = opener
         self._requestbuilder = requestbuilder
 
         self._redirect = wireprotov2peer.supportedredirects(ui, apidescriptor)
 
     # Start of ipeerconnection.
 
     def url(self):
         return self._url
 
     def local(self):
         return None
 
     def peer(self):
         return self
 
     def canpush(self):
         # TODO change once implemented.
         return False
 
     def close(self):
         self.ui.note(_('(sent %d HTTP requests and %d bytes; '
                        'received %d bytes in responses)\n') %
                      (self._opener.requestscount,
                       self._opener.sentbytescount,
                       self._opener.receivedbytescount))
 
     # End of ipeerconnection.
 
     # Start of ipeercapabilities.
 
     def capable(self, name):
         # The capabilities used internally historically map to capabilities
         # advertised from the "capabilities" wire protocol command. However,
         # version 2 of that command works differently.
 
         # Maps to commands that are available.
         if name in ('branchmap', 'getbundle', 'known', 'lookup', 'pushkey'):
             return True
 
         # Other concepts.
         if name in ('bundle2'):
             return True
 
         # Alias command-* to presence of command of that name.
         if name.startswith('command-'):
             return name[len('command-'):] in self.apidescriptor['commands']
 
         return False
 
     def requirecap(self, name, purpose):
         if self.capable(name):
             return
 
         raise error.CapabilityError(
             _('cannot %s; client or remote repository does not support the '
               '\'%s\' capability') % (purpose, name))
 
     # End of ipeercapabilities.
 
     def _call(self, name, **args):
         with self.commandexecutor() as e:
             return e.callcommand(name, args).result()
 
     def commandexecutor(self):
         return httpv2executor(self.ui, self._opener, self._requestbuilder,
                               self._apiurl, self.apidescriptor, self._redirect)
 
 # Registry of API service names to metadata about peers that handle it.
 #
 # The following keys are meaningful:
 #
 # init
 #    Callable receiving (ui, repourl, servicepath, opener, requestbuilder,
 #                        apidescriptor) to create a peer.
 #
 # priority
 #    Integer priority for the service. If we could choose from multiple
 #    services, we choose the one with the highest priority.
 API_PEERS = {
     wireprototypes.HTTP_WIREPROTO_V2: {
         'init': httpv2peer,
         'priority': 50,
     },
 }
 
 def performhandshake(ui, url, opener, requestbuilder):
     # The handshake is a request to the capabilities command.
 
     caps = None
     def capable(x):
         raise error.ProgrammingError('should not be called')
 
     args = {}
 
     # The client advertises support for newer protocols by adding an
     # X-HgUpgrade-* header with a list of supported APIs and an
     # X-HgProto-* header advertising which serializing formats it supports.
     # We only support the HTTP version 2 transport and CBOR responses for
     # now.
     advertisev2 = ui.configbool('experimental', 'httppeer.advertise-v2')
 
     if advertisev2:
         args['headers'] = {
             r'X-HgProto-1': r'cbor',
         }
 
         args['headers'].update(
             encodevalueinheaders(' '.join(sorted(API_PEERS)),
                                  'X-HgUpgrade',
                                  # We don't know the header limit this early.
                                  # So make it small.
                                  1024))
 
     req, requrl, qs = makev1commandrequest(ui, requestbuilder, caps,
                                            capable, url, 'capabilities',
                                            args)
     resp = sendrequest(ui, opener, req)
 
     # The server may redirect us to the repo root, stripping the
     # ?cmd=capabilities query string from the URL. The server would likely
     # return HTML in this case and ``parsev1commandresponse()`` would raise.
     # We catch this special case and re-issue the capabilities request against
     # the new URL.
     #
     # We should ideally not do this, as a redirect that drops the query
     # string from the URL is arguably a server bug. (Garbage in, garbage out).
     # However,  Mercurial clients for several years appeared to handle this
     # issue without behavior degradation. And according to issue 5860, it may
     # be a longstanding bug in some server implementations. So we allow a
     # redirect that drops the query string to "just work."
     try:
         respurl, ct, resp = parsev1commandresponse(ui, url, requrl, qs, resp,
                                                    compressible=False,
                                                    allowcbor=advertisev2)
     except RedirectedRepoError as e:
         req, requrl, qs = makev1commandrequest(ui, requestbuilder, caps,
                                                capable, e.respurl,
                                                'capabilities', args)
         resp = sendrequest(ui, opener, req)
         respurl, ct, resp = parsev1commandresponse(ui, url, requrl, qs, resp,
                                                    compressible=False,
                                                    allowcbor=advertisev2)
 
     try:
         rawdata = resp.read()
     finally:
         resp.close()
 
     if not ct.startswith('application/mercurial-'):
         raise error.ProgrammingError('unexpected content-type: %s' % ct)
 
     if advertisev2:
         if ct == 'application/mercurial-cbor':
             try:
                 info = cborutil.decodeall(rawdata)[0]
             except cborutil.CBORDecodeError:
                 raise error.Abort(_('error decoding CBOR from remote server'),
                                   hint=_('try again and consider contacting '
                                          'the server operator'))
 
         # We got a legacy response. That's fine.
         elif ct in ('application/mercurial-0.1', 'application/mercurial-0.2'):
             info = {
                 'v1capabilities': set(rawdata.split())
             }
 
         else:
             raise error.RepoError(
                 _('unexpected response type from server: %s') % ct)
     else:
         info = {
             'v1capabilities': set(rawdata.split())
         }
 
     return respurl, info
 
 def makepeer(ui, path, opener=None, requestbuilder=urlreq.request):
     """Construct an appropriate HTTP peer instance.
 
     ``opener`` is an ``url.opener`` that should be used to establish
     connections, perform HTTP requests.
 
     ``requestbuilder`` is the type used for constructing HTTP requests.
     It exists as an argument so extensions can override the default.
     """
     u = util.url(path)
     if u.query or u.fragment:
         raise error.Abort(_('unsupported URL component: "%s"') %
                           (u.query or u.fragment))
 
     # urllib cannot handle URLs with embedded user or passwd.
     url, authinfo = u.authinfo()
     ui.debug('using %s\n' % url)
 
     opener = opener or urlmod.opener(ui, authinfo)
 
     respurl, info = performhandshake(ui, url, opener, requestbuilder)
 
     # Given the intersection of APIs that both we and the server support,
     # sort by their advertised priority and pick the first one.
     #
     # TODO consider making this request-based and interface driven. For
     # example, the caller could say "I want a peer that does X." It's quite
     # possible that not all peers would do that. Since we know the service
     # capabilities, we could filter out services not meeting the
     # requirements. Possibly by consulting the interfaces defined by the
     # peer type.
     apipeerchoices = set(info.get('apis', {}).keys()) & set(API_PEERS.keys())
 
     preferredchoices = sorted(apipeerchoices,
                               key=lambda x: API_PEERS[x]['priority'],
                               reverse=True)
 
     for service in preferredchoices:
         apipath = '%s/%s' % (info['apibase'].rstrip('/'), service)
 
         return API_PEERS[service]['init'](ui, respurl, apipath, opener,
                                           requestbuilder,
                                           info['apis'][service])
 
     # Failed to construct an API peer. Fall back to legacy.
     return httppeer(ui, path, respurl, opener, requestbuilder,
                     info['v1capabilities'])
 
 def instance(ui, path, create, intents=None, createopts=None):
     if create:
         raise error.Abort(_('cannot create new http repository'))
     try:
         if path.startswith('https:') and not urlmod.has_https:
             raise error.Abort(_('Python support for SSL and HTTPS '
                                 'is not installed'))
 
         inst = makepeer(ui, path)
 
         return inst
     except error.RepoError as httpexception:
         try:
             r = statichttprepo.instance(ui, "static-" + path, create)
             ui.note(_('(falling back to static-http)\n'))
             return r
         except error.RepoError:
             raise httpexception # use the original http RepoError instead

mercurial/interfaces/repository.py

@@ -1,1877 +1,1877
 # repository.py - Interfaces and base classes for repositories and peers.
 #
 # Copyright 2017 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
-from .i18n import _
-from . import (
+from ..i18n import _
+from .. import (
     error,
 )
-from .utils import (
+from ..utils import (
     interfaceutil,
 )
 
 # When narrowing is finalized and no longer subject to format changes,
 # we should move this to just "narrow" or similar.
 NARROW_REQUIREMENT = 'narrowhg-experimental'
 
 # Local repository feature string.
 
 # Revlogs are being used for file storage.
 REPO_FEATURE_REVLOG_FILE_STORAGE = b'revlogfilestorage'
 # The storage part of the repository is shared from an external source.
 REPO_FEATURE_SHARED_STORAGE = b'sharedstore'
 # LFS supported for backing file storage.
 REPO_FEATURE_LFS = b'lfs'
 # Repository supports being stream cloned.
 REPO_FEATURE_STREAM_CLONE = b'streamclone'
 # Files storage may lack data for all ancestors.
 REPO_FEATURE_SHALLOW_FILE_STORAGE = b'shallowfilestorage'
 
 REVISION_FLAG_CENSORED = 1 << 15
 REVISION_FLAG_ELLIPSIS = 1 << 14
 REVISION_FLAG_EXTSTORED = 1 << 13
 
 REVISION_FLAGS_KNOWN = (
     REVISION_FLAG_CENSORED | REVISION_FLAG_ELLIPSIS | REVISION_FLAG_EXTSTORED)
 
 CG_DELTAMODE_STD = b'default'
 CG_DELTAMODE_PREV = b'previous'
 CG_DELTAMODE_FULL = b'fulltext'
 CG_DELTAMODE_P1 = b'p1'
 
 class ipeerconnection(interfaceutil.Interface):
     """Represents a "connection" to a repository.
 
     This is the base interface for representing a connection to a repository.
     It holds basic properties and methods applicable to all peer types.
 
     This is not a complete interface definition and should not be used
     outside of this module.
     """
     ui = interfaceutil.Attribute("""ui.ui instance""")
 
     def url():
         """Returns a URL string representing this peer.
 
         Currently, implementations expose the raw URL used to construct the
         instance. It may contain credentials as part of the URL. The
         expectations of the value aren't well-defined and this could lead to
         data leakage.
 
         TODO audit/clean consumers and more clearly define the contents of this
         value.
         """
 
     def local():
         """Returns a local repository instance.
 
         If the peer represents a local repository, returns an object that
         can be used to interface with it. Otherwise returns ``None``.
         """
 
     def peer():
         """Returns an object conforming to this interface.
 
         Most implementations will ``return self``.
         """
 
     def canpush():
         """Returns a boolean indicating if this peer can be pushed to."""
 
     def close():
         """Close the connection to this peer.
 
         This is called when the peer will no longer be used. Resources
         associated with the peer should be cleaned up.
         """
 
 class ipeercapabilities(interfaceutil.Interface):
     """Peer sub-interface related to capabilities."""
 
     def capable(name):
         """Determine support for a named capability.
 
         Returns ``False`` if capability not supported.
 
         Returns ``True`` if boolean capability is supported. Returns a string
         if capability support is non-boolean.
 
         Capability strings may or may not map to wire protocol capabilities.
         """
 
     def requirecap(name, purpose):
         """Require a capability to be present.
 
         Raises a ``CapabilityError`` if the capability isn't present.
         """
 
 class ipeercommands(interfaceutil.Interface):
     """Client-side interface for communicating over the wire protocol.
 
     This interface is used as a gateway to the Mercurial wire protocol.
     methods commonly call wire protocol commands of the same name.
     """
 
     def branchmap():
         """Obtain heads in named branches.
 
         Returns a dict mapping branch name to an iterable of nodes that are
         heads on that branch.
         """
 
     def capabilities():
         """Obtain capabilities of the peer.
 
         Returns a set of string capabilities.
         """
 
     def clonebundles():
         """Obtains the clone bundles manifest for the repo.
 
         Returns the manifest as unparsed bytes.
         """
 
     def debugwireargs(one, two, three=None, four=None, five=None):
         """Used to facilitate debugging of arguments passed over the wire."""
 
     def getbundle(source, **kwargs):
         """Obtain remote repository data as a bundle.
 
         This command is how the bulk of repository data is transferred from
         the peer to the local repository
 
         Returns a generator of bundle data.
         """
 
     def heads():
         """Determine all known head revisions in the peer.
 
         Returns an iterable of binary nodes.
         """
 
     def known(nodes):
         """Determine whether multiple nodes are known.
 
         Accepts an iterable of nodes whose presence to check for.
 
         Returns an iterable of booleans indicating of the corresponding node
         at that index is known to the peer.
         """
 
     def listkeys(namespace):
         """Obtain all keys in a pushkey namespace.
 
         Returns an iterable of key names.
         """
 
     def lookup(key):
         """Resolve a value to a known revision.
 
         Returns a binary node of the resolved revision on success.
         """
 
     def pushkey(namespace, key, old, new):
         """Set a value using the ``pushkey`` protocol.
 
         Arguments correspond to the pushkey namespace and key to operate on and
         the old and new values for that key.
 
         Returns a string with the peer result. The value inside varies by the
         namespace.
         """
 
     def stream_out():
         """Obtain streaming clone data.
 
         Successful result should be a generator of data chunks.
         """
 
     def unbundle(bundle, heads, url):
         """Transfer repository data to the peer.
 
         This is how the bulk of data during a push is transferred.
 
         Returns the integer number of heads added to the peer.
         """
 
 class ipeerlegacycommands(interfaceutil.Interface):
     """Interface for implementing support for legacy wire protocol commands.
 
     Wire protocol commands transition to legacy status when they are no longer
     used by modern clients. To facilitate identifying which commands are
     legacy, the interfaces are split.
     """
 
     def between(pairs):
         """Obtain nodes between pairs of nodes.
 
         ``pairs`` is an iterable of node pairs.
 
         Returns an iterable of iterables of nodes corresponding to each
         requested pair.
         """
 
     def branches(nodes):
         """Obtain ancestor changesets of specific nodes back to a branch point.
 
         For each requested node, the peer finds the first ancestor node that is
         a DAG root or is a merge.
 
         Returns an iterable of iterables with the resolved values for each node.
         """
 
     def changegroup(nodes, source):
         """Obtain a changegroup with data for descendants of specified nodes."""
 
     def changegroupsubset(bases, heads, source):
         pass
 
 class ipeercommandexecutor(interfaceutil.Interface):
     """Represents a mechanism to execute remote commands.
 
     This is the primary interface for requesting that wire protocol commands
     be executed. Instances of this interface are active in a context manager
     and have a well-defined lifetime. When the context manager exits, all
     outstanding requests are waited on.
     """
 
     def callcommand(name, args):
         """Request that a named command be executed.
 
         Receives the command name and a dictionary of command arguments.
 
         Returns a ``concurrent.futures.Future`` that will resolve to the
         result of that command request. That exact value is left up to
         the implementation and possibly varies by command.
 
         Not all commands can coexist with other commands in an executor
         instance: it depends on the underlying wire protocol transport being
         used and the command itself.
 
         Implementations MAY call ``sendcommands()`` automatically if the
         requested command can not coexist with other commands in this executor.
 
         Implementations MAY call ``sendcommands()`` automatically when the
         future's ``result()`` is called. So, consumers using multiple
         commands with an executor MUST ensure that ``result()`` is not called
         until all command requests have been issued.
         """
 
     def sendcommands():
         """Trigger submission of queued command requests.
 
         Not all transports submit commands as soon as they are requested to
         run. When called, this method forces queued command requests to be
         issued. It will no-op if all commands have already been sent.
 
         When called, no more new commands may be issued with this executor.
         """
 
     def close():
         """Signal that this command request is finished.
 
         When called, no more new commands may be issued. All outstanding
         commands that have previously been issued are waited on before
         returning. This not only includes waiting for the futures to resolve,
         but also waiting for all response data to arrive. In other words,
         calling this waits for all on-wire state for issued command requests
         to finish.
 
         When used as a context manager, this method is called when exiting the
         context manager.
 
         This method may call ``sendcommands()`` if there are buffered commands.
         """
 
 class ipeerrequests(interfaceutil.Interface):
     """Interface for executing commands on a peer."""
 
     limitedarguments = interfaceutil.Attribute(
         """True if the peer cannot receive large argument value for commands."""
     )
 
     def commandexecutor():
         """A context manager that resolves to an ipeercommandexecutor.
 
         The object this resolves to can be used to issue command requests
         to the peer.
 
         Callers should call its ``callcommand`` method to issue command
         requests.
 
         A new executor should be obtained for each distinct set of commands
         (possibly just a single command) that the consumer wants to execute
         as part of a single operation or round trip. This is because some
         peers are half-duplex and/or don't support persistent connections.
         e.g. in the case of HTTP peers, commands sent to an executor represent
         a single HTTP request. While some peers may support multiple command
         sends over the wire per executor, consumers need to code to the least
         capable peer. So it should be assumed that command executors buffer
         called commands until they are told to send them and that each
         command executor could result in a new connection or wire-level request
         being issued.
         """
 
 class ipeerbase(ipeerconnection, ipeercapabilities, ipeerrequests):
     """Unified interface for peer repositories.
 
     All peer instances must conform to this interface.
     """
 
 class ipeerv2(ipeerconnection, ipeercapabilities, ipeerrequests):
     """Unified peer interface for wire protocol version 2 peers."""
 
     apidescriptor = interfaceutil.Attribute(
         """Data structure holding description of server API.""")
 
 @interfaceutil.implementer(ipeerbase)
 class peer(object):
     """Base class for peer repositories."""
 
     limitedarguments = False
 
     def capable(self, name):
         caps = self.capabilities()
         if name in caps:
             return True
 
         name = '%s=' % name
         for cap in caps:
             if cap.startswith(name):
                 return cap[len(name):]
 
         return False
 
     def requirecap(self, name, purpose):
         if self.capable(name):
             return
 
         raise error.CapabilityError(
             _('cannot %s; remote repository does not support the '
               '\'%s\' capability') % (purpose, name))
 
 class iverifyproblem(interfaceutil.Interface):
     """Represents a problem with the integrity of the repository.
 
     Instances of this interface are emitted to describe an integrity issue
     with a repository (e.g. corrupt storage, missing data, etc).
 
     Instances are essentially messages associated with severity.
     """
     warning = interfaceutil.Attribute(
         """Message indicating a non-fatal problem.""")
 
     error = interfaceutil.Attribute(
         """Message indicating a fatal problem.""")
 
     node = interfaceutil.Attribute(
         """Revision encountering the problem.
 
         ``None`` means the problem doesn't apply to a single revision.
         """)
 
 class irevisiondelta(interfaceutil.Interface):
     """Represents a delta between one revision and another.
 
     Instances convey enough information to allow a revision to be exchanged
     with another repository.
 
     Instances represent the fulltext revision data or a delta against
     another revision. Therefore the ``revision`` and ``delta`` attributes
     are mutually exclusive.
 
     Typically used for changegroup generation.
     """
 
     node = interfaceutil.Attribute(
         """20 byte node of this revision.""")
 
     p1node = interfaceutil.Attribute(
         """20 byte node of 1st parent of this revision.""")
 
     p2node = interfaceutil.Attribute(
         """20 byte node of 2nd parent of this revision.""")
 
     linknode = interfaceutil.Attribute(
         """20 byte node of the changelog revision this node is linked to.""")
 
     flags = interfaceutil.Attribute(
         """2 bytes of integer flags that apply to this revision.
 
         This is a bitwise composition of the ``REVISION_FLAG_*`` constants.
         """)
 
     basenode = interfaceutil.Attribute(
         """20 byte node of the revision this data is a delta against.
 
         ``nullid`` indicates that the revision is a full revision and not
         a delta.
         """)
 
     baserevisionsize = interfaceutil.Attribute(
         """Size of base revision this delta is against.
 
         May be ``None`` if ``basenode`` is ``nullid``.
         """)
 
     revision = interfaceutil.Attribute(
         """Raw fulltext of revision data for this node.""")
 
     delta = interfaceutil.Attribute(
         """Delta between ``basenode`` and ``node``.
 
         Stored in the bdiff delta format.
         """)
 
 class ifilerevisionssequence(interfaceutil.Interface):
     """Contains index data for all revisions of a file.
 
     Types implementing this behave like lists of tuples. The index
     in the list corresponds to the revision number. The values contain
     index metadata.
 
     The *null* revision (revision number -1) is always the last item
     in the index.
     """
 
     def __len__():
         """The total number of revisions."""
 
     def __getitem__(rev):
         """Returns the object having a specific revision number.
 
         Returns an 8-tuple with the following fields:
 
         offset+flags
            Contains the offset and flags for the revision. 64-bit unsigned
            integer where first 6 bytes are the offset and the next 2 bytes
            are flags. The offset can be 0 if it is not used by the store.
         compressed size
             Size of the revision data in the store. It can be 0 if it isn't
             needed by the store.
         uncompressed size
             Fulltext size. It can be 0 if it isn't needed by the store.
         base revision
             Revision number of revision the delta for storage is encoded
             against. -1 indicates not encoded against a base revision.
         link revision
             Revision number of changelog revision this entry is related to.
         p1 revision
             Revision number of 1st parent. -1 if no 1st parent.
         p2 revision
             Revision number of 2nd parent. -1 if no 1st parent.
         node
             Binary node value for this revision number.
 
         Negative values should index off the end of the sequence. ``-1``
         should return the null revision. ``-2`` should return the most
         recent revision.
         """
 
     def __contains__(rev):
         """Whether a revision number exists."""
 
     def insert(self, i, entry):
         """Add an item to the index at specific revision."""
 
 class ifileindex(interfaceutil.Interface):
     """Storage interface for index data of a single file.
 
     File storage data is divided into index metadata and data storage.
     This interface defines the index portion of the interface.
 
     The index logically consists of:
 
     * A mapping between revision numbers and nodes.
     * DAG data (storing and querying the relationship between nodes).
     * Metadata to facilitate storage.
     """
     def __len__():
         """Obtain the number of revisions stored for this file."""
 
     def __iter__():
         """Iterate over revision numbers for this file."""
 
     def hasnode(node):
         """Returns a bool indicating if a node is known to this store.
 
         Implementations must only return True for full, binary node values:
         hex nodes, revision numbers, and partial node matches must be
         rejected.
 
         The null node is never present.
         """
 
     def revs(start=0, stop=None):
         """Iterate over revision numbers for this file, with control."""
 
     def parents(node):
         """Returns a 2-tuple of parent nodes for a revision.
 
         Values will be ``nullid`` if the parent is empty.
         """
 
     def parentrevs(rev):
         """Like parents() but operates on revision numbers."""
 
     def rev(node):
         """Obtain the revision number given a node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
     def node(rev):
         """Obtain the node value given a revision number.
 
         Raises ``IndexError`` if the node is not known.
         """
 
     def lookup(node):
         """Attempt to resolve a value to a node.
 
         Value can be a binary node, hex node, revision number, or a string
         that can be converted to an integer.
 
         Raises ``error.LookupError`` if a node could not be resolved.
         """
 
     def linkrev(rev):
         """Obtain the changeset revision number a revision is linked to."""
 
     def iscensored(rev):
         """Return whether a revision's content has been censored."""
 
     def commonancestorsheads(node1, node2):
         """Obtain an iterable of nodes containing heads of common ancestors.
 
         See ``ancestor.commonancestorsheads()``.
         """
 
     def descendants(revs):
         """Obtain descendant revision numbers for a set of revision numbers.
 
         If ``nullrev`` is in the set, this is equivalent to ``revs()``.
         """
 
     def heads(start=None, stop=None):
         """Obtain a list of nodes that are DAG heads, with control.
 
         The set of revisions examined can be limited by specifying
         ``start`` and ``stop``. ``start`` is a node. ``stop`` is an
         iterable of nodes. DAG traversal starts at earlier revision
         ``start`` and iterates forward until any node in ``stop`` is
         encountered.
         """
 
     def children(node):
         """Obtain nodes that are children of a node.
 
         Returns a list of nodes.
         """
 
 class ifiledata(interfaceutil.Interface):
     """Storage interface for data storage of a specific file.
 
     This complements ``ifileindex`` and provides an interface for accessing
     data for a tracked file.
     """
     def size(rev):
         """Obtain the fulltext size of file data.
 
         Any metadata is excluded from size measurements.
         """
 
     def revision(node, raw=False):
         """"Obtain fulltext data for a node.
 
         By default, any storage transformations are applied before the data
         is returned. If ``raw`` is True, non-raw storage transformations
         are not applied.
 
         The fulltext data may contain a header containing metadata. Most
         consumers should use ``read()`` to obtain the actual file data.
         """
 
     def rawdata(node):
         """Obtain raw data for a node.
         """
 
     def read(node):
         """Resolve file fulltext data.
 
         This is similar to ``revision()`` except any metadata in the data
         headers is stripped.
         """
 
     def renamed(node):
         """Obtain copy metadata for a node.
 
         Returns ``False`` if no copy metadata is stored or a 2-tuple of
         (path, node) from which this revision was copied.
         """
 
     def cmp(node, fulltext):
         """Compare fulltext to another revision.
 
         Returns True if the fulltext is different from what is stored.
 
         This takes copy metadata into account.
 
         TODO better document the copy metadata and censoring logic.
         """
 
     def emitrevisions(nodes,
                       nodesorder=None,
                       revisiondata=False,
                       assumehaveparentrevisions=False,
                       deltamode=CG_DELTAMODE_STD):
         """Produce ``irevisiondelta`` for revisions.
 
         Given an iterable of nodes, emits objects conforming to the
         ``irevisiondelta`` interface that describe revisions in storage.
 
         This method is a generator.
 
         The input nodes may be unordered. Implementations must ensure that a
         node's parents are emitted before the node itself. Transitively, this
         means that a node may only be emitted once all its ancestors in
         ``nodes`` have also been emitted.
 
         By default, emits "index" data (the ``node``, ``p1node``, and
         ``p2node`` attributes). If ``revisiondata`` is set, revision data
         will also be present on the emitted objects.
 
         With default argument values, implementations can choose to emit
         either fulltext revision data or a delta. When emitting deltas,
         implementations must consider whether the delta's base revision
         fulltext is available to the receiver.
 
         The base revision fulltext is guaranteed to be available if any of
         the following are met:
 
         * Its fulltext revision was emitted by this method call.
         * A delta for that revision was emitted by this method call.
         * ``assumehaveparentrevisions`` is True and the base revision is a
           parent of the node.
 
         ``nodesorder`` can be used to control the order that revisions are
         emitted. By default, revisions can be reordered as long as they are
         in DAG topological order (see above). If the value is ``nodes``,
         the iteration order from ``nodes`` should be used. If the value is
         ``storage``, then the native order from the backing storage layer
         is used. (Not all storage layers will have strong ordering and behavior
         of this mode is storage-dependent.) ``nodes`` ordering can force
         revisions to be emitted before their ancestors, so consumers should
         use it with care.
 
         The ``linknode`` attribute on the returned ``irevisiondelta`` may not
         be set and it is the caller's responsibility to resolve it, if needed.
 
         If ``deltamode`` is CG_DELTAMODE_PREV and revision data is requested,
         all revision data should be emitted as deltas against the revision
         emitted just prior. The initial revision should be a delta against its
         1st parent.
         """
 
 class ifilemutation(interfaceutil.Interface):
     """Storage interface for mutation events of a tracked file."""
 
     def add(filedata, meta, transaction, linkrev, p1, p2):
         """Add a new revision to the store.
 
         Takes file data, dictionary of metadata, a transaction, linkrev,
         and parent nodes.
 
         Returns the node that was added.
 
         May no-op if a revision matching the supplied data is already stored.
         """
 
     def addrevision(revisiondata, transaction, linkrev, p1, p2, node=None,
                     flags=0, cachedelta=None):
         """Add a new revision to the store.
 
         This is similar to ``add()`` except it operates at a lower level.
 
         The data passed in already contains a metadata header, if any.
 
         ``node`` and ``flags`` can be used to define the expected node and
         the flags to use with storage. ``flags`` is a bitwise value composed
         of the various ``REVISION_FLAG_*`` constants.
 
         ``add()`` is usually called when adding files from e.g. the working
         directory. ``addrevision()`` is often called by ``add()`` and for
         scenarios where revision data has already been computed, such as when
         applying raw data from a peer repo.
         """
 
     def addgroup(deltas, linkmapper, transaction, addrevisioncb=None,
                  maybemissingparents=False):
         """Process a series of deltas for storage.
 
         ``deltas`` is an iterable of 7-tuples of
         (node, p1, p2, linknode, deltabase, delta, flags) defining revisions
         to add.
 
         The ``delta`` field contains ``mpatch`` data to apply to a base
         revision, identified by ``deltabase``. The base node can be
         ``nullid``, in which case the header from the delta can be ignored
         and the delta used as the fulltext.
 
         ``addrevisioncb`` should be called for each node as it is committed.
 
         ``maybemissingparents`` is a bool indicating whether the incoming
         data may reference parents/ancestor revisions that aren't present.
         This flag is set when receiving data into a "shallow" store that
         doesn't hold all history.
 
         Returns a list of nodes that were processed. A node will be in the list
         even if it existed in the store previously.
         """
 
     def censorrevision(tr, node, tombstone=b''):
         """Remove the content of a single revision.
 
         The specified ``node`` will have its content purged from storage.
         Future attempts to access the revision data for this node will
         result in failure.
 
         A ``tombstone`` message can optionally be stored. This message may be
         displayed to users when they attempt to access the missing revision
         data.
 
         Storage backends may have stored deltas against the previous content
         in this revision. As part of censoring a revision, these storage
         backends are expected to rewrite any internally stored deltas such
         that they no longer reference the deleted content.
         """
 
     def getstrippoint(minlink):
         """Find the minimum revision that must be stripped to strip a linkrev.
 
         Returns a 2-tuple containing the minimum revision number and a set
         of all revisions numbers that would be broken by this strip.
 
         TODO this is highly revlog centric and should be abstracted into
         a higher-level deletion API. ``repair.strip()`` relies on this.
         """
 
     def strip(minlink, transaction):
         """Remove storage of items starting at a linkrev.
 
         This uses ``getstrippoint()`` to determine the first node to remove.
         Then it effectively truncates storage for all revisions after that.
 
         TODO this is highly revlog centric and should be abstracted into a
         higher-level deletion API.
         """
 
 class ifilestorage(ifileindex, ifiledata, ifilemutation):
     """Complete storage interface for a single tracked file."""
 
     def files():
         """Obtain paths that are backing storage for this file.
 
         TODO this is used heavily by verify code and there should probably
         be a better API for that.
         """
 
     def storageinfo(exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         """Obtain information about storage for this file's data.
 
         Returns a dict describing storage for this tracked path. The keys
         in the dict map to arguments of the same. The arguments are bools
         indicating whether to calculate and obtain that data.
 
         exclusivefiles
            Iterable of (vfs, path) describing files that are exclusively
            used to back storage for this tracked path.
 
         sharedfiles
            Iterable of (vfs, path) describing files that are used to back
            storage for this tracked path. Those files may also provide storage
            for other stored entities.
 
         revisionscount
            Number of revisions available for retrieval.
 
         trackedsize
            Total size in bytes of all tracked revisions. This is a sum of the
            length of the fulltext of all revisions.
 
         storedsize
            Total size in bytes used to store data for all tracked revisions.
            This is commonly less than ``trackedsize`` due to internal usage
            of deltas rather than fulltext revisions.
 
         Not all storage backends may support all queries are have a reasonable
         value to use. In that case, the value should be set to ``None`` and
         callers are expected to handle this special value.
         """
 
     def verifyintegrity(state):
         """Verifies the integrity of file storage.
 
         ``state`` is a dict holding state of the verifier process. It can be
         used to communicate data between invocations of multiple storage
         primitives.
 
         If individual revisions cannot have their revision content resolved,
         the method is expected to set the ``skipread`` key to a set of nodes
         that encountered problems.
 
         The method yields objects conforming to the ``iverifyproblem``
         interface.
         """
 
 class idirs(interfaceutil.Interface):
     """Interface representing a collection of directories from paths.
 
     This interface is essentially a derived data structure representing
     directories from a collection of paths.
     """
 
     def addpath(path):
         """Add a path to the collection.
 
         All directories in the path will be added to the collection.
         """
 
     def delpath(path):
         """Remove a path from the collection.
 
         If the removal was the last path in a particular directory, the
         directory is removed from the collection.
         """
 
     def __iter__():
         """Iterate over the directories in this collection of paths."""
 
     def __contains__(path):
         """Whether a specific directory is in this collection."""
 
 class imanifestdict(interfaceutil.Interface):
     """Interface representing a manifest data structure.
 
     A manifest is effectively a dict mapping paths to entries. Each entry
     consists of a binary node and extra flags affecting that entry.
     """
 
     def __getitem__(path):
         """Returns the binary node value for a path in the manifest.
 
         Raises ``KeyError`` if the path does not exist in the manifest.
 
         Equivalent to ``self.find(path)[0]``.
         """
 
     def find(path):
         """Returns the entry for a path in the manifest.
 
         Returns a 2-tuple of (node, flags).
 
         Raises ``KeyError`` if the path does not exist in the manifest.
         """
 
     def __len__():
         """Return the number of entries in the manifest."""
 
     def __nonzero__():
         """Returns True if the manifest has entries, False otherwise."""
 
     __bool__ = __nonzero__
 
     def __setitem__(path, node):
         """Define the node value for a path in the manifest.
 
         If the path is already in the manifest, its flags will be copied to
         the new entry.
         """
 
     def __contains__(path):
         """Whether a path exists in the manifest."""
 
     def __delitem__(path):
         """Remove a path from the manifest.
 
         Raises ``KeyError`` if the path is not in the manifest.
         """
 
     def __iter__():
         """Iterate over paths in the manifest."""
 
     def iterkeys():
         """Iterate over paths in the manifest."""
 
     def keys():
         """Obtain a list of paths in the manifest."""
 
     def filesnotin(other, match=None):
         """Obtain the set of paths in this manifest but not in another.
 
         ``match`` is an optional matcher function to be applied to both
         manifests.
 
         Returns a set of paths.
         """
 
     def dirs():
         """Returns an object implementing the ``idirs`` interface."""
 
     def hasdir(dir):
         """Returns a bool indicating if a directory is in this manifest."""
 
     def matches(match):
         """Generate a new manifest filtered through a matcher.
 
         Returns an object conforming to the ``imanifestdict`` interface.
         """
 
     def walk(match):
         """Generator of paths in manifest satisfying a matcher.
 
         This is equivalent to ``self.matches(match).iterkeys()`` except a new
         manifest object is not created.
 
         If the matcher has explicit files listed and they don't exist in
         the manifest, ``match.bad()`` is called for each missing file.
         """
 
     def diff(other, match=None, clean=False):
         """Find differences between this manifest and another.
 
         This manifest is compared to ``other``.
 
         If ``match`` is provided, the two manifests are filtered against this
         matcher and only entries satisfying the matcher are compared.
 
         If ``clean`` is True, unchanged files are included in the returned
         object.
 
         Returns a dict with paths as keys and values of 2-tuples of 2-tuples of
         the form ``((node1, flag1), (node2, flag2))`` where ``(node1, flag1)``
         represents the node and flags for this manifest and ``(node2, flag2)``
         are the same for the other manifest.
         """
 
     def setflag(path, flag):
         """Set the flag value for a given path.
 
         Raises ``KeyError`` if the path is not already in the manifest.
         """
 
     def get(path, default=None):
         """Obtain the node value for a path or a default value if missing."""
 
     def flags(path, default=''):
         """Return the flags value for a path or a default value if missing."""
 
     def copy():
         """Return a copy of this manifest."""
 
     def items():
         """Returns an iterable of (path, node) for items in this manifest."""
 
     def iteritems():
         """Identical to items()."""
 
     def iterentries():
         """Returns an iterable of (path, node, flags) for this manifest.
 
         Similar to ``iteritems()`` except items are a 3-tuple and include
         flags.
         """
 
     def text():
         """Obtain the raw data representation for this manifest.
 
         Result is used to create a manifest revision.
         """
 
     def fastdelta(base, changes):
         """Obtain a delta between this manifest and another given changes.
 
         ``base`` in the raw data representation for another manifest.
 
         ``changes`` is an iterable of ``(path, to_delete)``.
 
         Returns a 2-tuple containing ``bytearray(self.text())`` and the
         delta between ``base`` and this manifest.
         """
 
 class imanifestrevisionbase(interfaceutil.Interface):
     """Base interface representing a single revision of a manifest.
 
     Should not be used as a primary interface: should always be inherited
     as part of a larger interface.
     """
 
     def new():
         """Obtain a new manifest instance.
 
         Returns an object conforming to the ``imanifestrevisionwritable``
         interface. The instance will be associated with the same
         ``imanifestlog`` collection as this instance.
         """
 
     def copy():
         """Obtain a copy of this manifest instance.
 
         Returns an object conforming to the ``imanifestrevisionwritable``
         interface. The instance will be associated with the same
         ``imanifestlog`` collection as this instance.
         """
 
     def read():
         """Obtain the parsed manifest data structure.
 
         The returned object conforms to the ``imanifestdict`` interface.
         """
 
 class imanifestrevisionstored(imanifestrevisionbase):
     """Interface representing a manifest revision committed to storage."""
 
     def node():
         """The binary node for this manifest."""
 
     parents = interfaceutil.Attribute(
         """List of binary nodes that are parents for this manifest revision."""
     )
 
     def readdelta(shallow=False):
         """Obtain the manifest data structure representing changes from parent.
 
         This manifest is compared to its 1st parent. A new manifest representing
         those differences is constructed.
 
         The returned object conforms to the ``imanifestdict`` interface.
         """
 
     def readfast(shallow=False):
         """Calls either ``read()`` or ``readdelta()``.
 
         The faster of the two options is called.
         """
 
     def find(key):
         """Calls self.read().find(key)``.
 
         Returns a 2-tuple of ``(node, flags)`` or raises ``KeyError``.
         """
 
 class imanifestrevisionwritable(imanifestrevisionbase):
     """Interface representing a manifest revision that can be committed."""
 
     def write(transaction, linkrev, p1node, p2node, added, removed, match=None):
         """Add this revision to storage.
 
         Takes a transaction object, the changeset revision number it will
         be associated with, its parent nodes, and lists of added and
         removed paths.
 
         If match is provided, storage can choose not to inspect or write out
         items that do not match. Storage is still required to be able to provide
         the full manifest in the future for any directories written (these
         manifests should not be "narrowed on disk").
 
         Returns the binary node of the created revision.
         """
 
 class imanifeststorage(interfaceutil.Interface):
     """Storage interface for manifest data."""
 
     tree = interfaceutil.Attribute(
         """The path to the directory this manifest tracks.
 
         The empty bytestring represents the root manifest.
         """)
 
     index = interfaceutil.Attribute(
         """An ``ifilerevisionssequence`` instance.""")
 
     indexfile = interfaceutil.Attribute(
         """Path of revlog index file.
 
         TODO this is revlog specific and should not be exposed.
         """)
 
     opener = interfaceutil.Attribute(
         """VFS opener to use to access underlying files used for storage.
 
         TODO this is revlog specific and should not be exposed.
         """)
 
     version = interfaceutil.Attribute(
         """Revlog version number.
 
         TODO this is revlog specific and should not be exposed.
         """)
 
     _generaldelta = interfaceutil.Attribute(
         """Whether generaldelta storage is being used.
 
         TODO this is revlog specific and should not be exposed.
         """)
 
     fulltextcache = interfaceutil.Attribute(
         """Dict with cache of fulltexts.
 
         TODO this doesn't feel appropriate for the storage interface.
         """)
 
     def __len__():
         """Obtain the number of revisions stored for this manifest."""
 
     def __iter__():
         """Iterate over revision numbers for this manifest."""
 
     def rev(node):
         """Obtain the revision number given a binary node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
     def node(rev):
         """Obtain the node value given a revision number.
 
         Raises ``error.LookupError`` if the revision is not known.
         """
 
     def lookup(value):
         """Attempt to resolve a value to a node.
 
         Value can be a binary node, hex node, revision number, or a bytes
         that can be converted to an integer.
 
         Raises ``error.LookupError`` if a ndoe could not be resolved.
         """
 
     def parents(node):
         """Returns a 2-tuple of parent nodes for a node.
 
         Values will be ``nullid`` if the parent is empty.
         """
 
     def parentrevs(rev):
         """Like parents() but operates on revision numbers."""
 
     def linkrev(rev):
         """Obtain the changeset revision number a revision is linked to."""
 
     def revision(node, _df=None, raw=False):
         """Obtain fulltext data for a node."""
 
     def rawdata(node, _df=None):
         """Obtain raw data for a node."""
 
     def revdiff(rev1, rev2):
         """Obtain a delta between two revision numbers.
 
         The returned data is the result of ``bdiff.bdiff()`` on the raw
         revision data.
         """
 
     def cmp(node, fulltext):
         """Compare fulltext to another revision.
 
         Returns True if the fulltext is different from what is stored.
         """
 
     def emitrevisions(nodes,
                       nodesorder=None,
                       revisiondata=False,
                       assumehaveparentrevisions=False):
         """Produce ``irevisiondelta`` describing revisions.
 
         See the documentation for ``ifiledata`` for more.
         """
 
     def addgroup(deltas, linkmapper, transaction, addrevisioncb=None):
         """Process a series of deltas for storage.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def rawsize(rev):
         """Obtain the size of tracked data.
 
         Is equivalent to ``len(m.rawdata(node))``.
 
         TODO this method is only used by upgrade code and may be removed.
         """
 
     def getstrippoint(minlink):
         """Find minimum revision that must be stripped to strip a linkrev.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def strip(minlink, transaction):
         """Remove storage of items starting at a linkrev.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def checksize():
         """Obtain the expected sizes of backing files.
 
         TODO this is used by verify and it should not be part of the interface.
         """
 
     def files():
         """Obtain paths that are backing storage for this manifest.
 
         TODO this is used by verify and there should probably be a better API
         for this functionality.
         """
 
     def deltaparent(rev):
         """Obtain the revision that a revision is delta'd against.
 
         TODO delta encoding is an implementation detail of storage and should
         not be exposed to the storage interface.
         """
 
     def clone(tr, dest, **kwargs):
         """Clone this instance to another."""
 
     def clearcaches(clear_persisted_data=False):
         """Clear any caches associated with this instance."""
 
     def dirlog(d):
         """Obtain a manifest storage instance for a tree."""
 
     def add(m, transaction, link, p1, p2, added, removed, readtree=None,
             match=None):
         """Add a revision to storage.
 
         ``m`` is an object conforming to ``imanifestdict``.
 
         ``link`` is the linkrev revision number.
 
         ``p1`` and ``p2`` are the parent revision numbers.
 
         ``added`` and ``removed`` are iterables of added and removed paths,
         respectively.
 
         ``readtree`` is a function that can be used to read the child tree(s)
         when recursively writing the full tree structure when using
         treemanifets.
 
         ``match`` is a matcher that can be used to hint to storage that not all
         paths must be inspected; this is an optimization and can be safely
         ignored. Note that the storage must still be able to reproduce a full
         manifest including files that did not match.
         """
 
     def storageinfo(exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         """Obtain information about storage for this manifest's data.
 
         See ``ifilestorage.storageinfo()`` for a description of this method.
         This one behaves the same way, except for manifest data.
         """
 
 class imanifestlog(interfaceutil.Interface):
     """Interface representing a collection of manifest snapshots.
 
     Represents the root manifest in a repository.
 
     Also serves as a means to access nested tree manifests and to cache
     tree manifests.
     """
 
     def __getitem__(node):
         """Obtain a manifest instance for a given binary node.
 
         Equivalent to calling ``self.get('', node)``.
 
         The returned object conforms to the ``imanifestrevisionstored``
         interface.
         """
 
     def get(tree, node, verify=True):
         """Retrieve the manifest instance for a given directory and binary node.
 
         ``node`` always refers to the node of the root manifest (which will be
         the only manifest if flat manifests are being used).
 
         If ``tree`` is the empty string, the root manifest is returned.
         Otherwise the manifest for the specified directory will be returned
         (requires tree manifests).
 
         If ``verify`` is True, ``LookupError`` is raised if the node is not
         known.
 
         The returned object conforms to the ``imanifestrevisionstored``
         interface.
         """
 
     def getstorage(tree):
         """Retrieve an interface to storage for a particular tree.
 
         If ``tree`` is the empty bytestring, storage for the root manifest will
         be returned. Otherwise storage for a tree manifest is returned.
 
         TODO formalize interface for returned object.
         """
 
     def clearcaches():
         """Clear caches associated with this collection."""
 
     def rev(node):
         """Obtain the revision number for a binary node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
 class ilocalrepositoryfilestorage(interfaceutil.Interface):
     """Local repository sub-interface providing access to tracked file storage.
 
     This interface defines how a repository accesses storage for a single
     tracked file path.
     """
 
     def file(f):
         """Obtain a filelog for a tracked path.
 
         The returned type conforms to the ``ifilestorage`` interface.
         """
 
 class ilocalrepositorymain(interfaceutil.Interface):
     """Main interface for local repositories.
 
     This currently captures the reality of things - not how things should be.
     """
 
     supportedformats = interfaceutil.Attribute(
         """Set of requirements that apply to stream clone.
 
         This is actually a class attribute and is shared among all instances.
         """)
 
     supported = interfaceutil.Attribute(
         """Set of requirements that this repo is capable of opening.""")
 
     requirements = interfaceutil.Attribute(
         """Set of requirements this repo uses.""")
 
     features = interfaceutil.Attribute(
         """Set of "features" this repository supports.
 
         A "feature" is a loosely-defined term. It can refer to a feature
         in the classical sense or can describe an implementation detail
         of the repository. For example, a ``readonly`` feature may denote
         the repository as read-only. Or a ``revlogfilestore`` feature may
         denote that the repository is using revlogs for file storage.
 
         The intent of features is to provide a machine-queryable mechanism
         for repo consumers to test for various repository characteristics.
 
         Features are similar to ``requirements``. The main difference is that
         requirements are stored on-disk and represent requirements to open the
         repository. Features are more run-time capabilities of the repository
         and more granular capabilities (which may be derived from requirements).
         """)
 
     filtername = interfaceutil.Attribute(
         """Name of the repoview that is active on this repo.""")
 
     wvfs = interfaceutil.Attribute(
         """VFS used to access the working directory.""")
 
     vfs = interfaceutil.Attribute(
         """VFS rooted at the .hg directory.
 
         Used to access repository data not in the store.
         """)
 
     svfs = interfaceutil.Attribute(
         """VFS rooted at the store.
 
         Used to access repository data in the store. Typically .hg/store.
         But can point elsewhere if the store is shared.
         """)
 
     root = interfaceutil.Attribute(
         """Path to the root of the working directory.""")
 
     path = interfaceutil.Attribute(
         """Path to the .hg directory.""")
 
     origroot = interfaceutil.Attribute(
         """The filesystem path that was used to construct the repo.""")
 
     auditor = interfaceutil.Attribute(
         """A pathauditor for the working directory.
 
         This checks if a path refers to a nested repository.
 
         Operates on the filesystem.
         """)
 
     nofsauditor = interfaceutil.Attribute(
         """A pathauditor for the working directory.
 
         This is like ``auditor`` except it doesn't do filesystem checks.
         """)
 
     baseui = interfaceutil.Attribute(
         """Original ui instance passed into constructor.""")
 
     ui = interfaceutil.Attribute(
         """Main ui instance for this instance.""")
 
     sharedpath = interfaceutil.Attribute(
         """Path to the .hg directory of the repo this repo was shared from.""")
 
     store = interfaceutil.Attribute(
         """A store instance.""")
 
     spath = interfaceutil.Attribute(
         """Path to the store.""")
 
     sjoin = interfaceutil.Attribute(
         """Alias to self.store.join.""")
 
     cachevfs = interfaceutil.Attribute(
         """A VFS used to access the cache directory.
 
         Typically .hg/cache.
         """)
 
     wcachevfs = interfaceutil.Attribute(
         """A VFS used to access the cache directory dedicated to working copy
 
         Typically .hg/wcache.
         """)
 
     filteredrevcache = interfaceutil.Attribute(
         """Holds sets of revisions to be filtered.""")
 
     names = interfaceutil.Attribute(
         """A ``namespaces`` instance.""")
 
     def close():
         """Close the handle on this repository."""
 
     def peer():
         """Obtain an object conforming to the ``peer`` interface."""
 
     def unfiltered():
         """Obtain an unfiltered/raw view of this repo."""
 
     def filtered(name, visibilityexceptions=None):
         """Obtain a named view of this repository."""
 
     obsstore = interfaceutil.Attribute(
         """A store of obsolescence data.""")
 
     changelog = interfaceutil.Attribute(
         """A handle on the changelog revlog.""")
 
     manifestlog = interfaceutil.Attribute(
         """An instance conforming to the ``imanifestlog`` interface.
 
         Provides access to manifests for the repository.
         """)
 
     dirstate = interfaceutil.Attribute(
         """Working directory state.""")
 
     narrowpats = interfaceutil.Attribute(
         """Matcher patterns for this repository's narrowspec.""")
 
     def narrowmatch(match=None, includeexact=False):
         """Obtain a matcher for the narrowspec."""
 
     def setnarrowpats(newincludes, newexcludes):
         """Define the narrowspec for this repository."""
 
     def __getitem__(changeid):
         """Try to resolve a changectx."""
 
     def __contains__(changeid):
         """Whether a changeset exists."""
 
     def __nonzero__():
         """Always returns True."""
         return True
 
     __bool__ = __nonzero__
 
     def __len__():
         """Returns the number of changesets in the repo."""
 
     def __iter__():
         """Iterate over revisions in the changelog."""
 
     def revs(expr, *args):
         """Evaluate a revset.
 
         Emits revisions.
         """
 
     def set(expr, *args):
         """Evaluate a revset.
 
         Emits changectx instances.
         """
 
     def anyrevs(specs, user=False, localalias=None):
         """Find revisions matching one of the given revsets."""
 
     def url():
         """Returns a string representing the location of this repo."""
 
     def hook(name, throw=False, **args):
         """Call a hook."""
 
     def tags():
         """Return a mapping of tag to node."""
 
     def tagtype(tagname):
         """Return the type of a given tag."""
 
     def tagslist():
         """Return a list of tags ordered by revision."""
 
     def nodetags(node):
         """Return the tags associated with a node."""
 
     def nodebookmarks(node):
         """Return the list of bookmarks pointing to the specified node."""
 
     def branchmap():
         """Return a mapping of branch to heads in that branch."""
 
     def revbranchcache():
         pass
 
     def branchtip(branchtip, ignoremissing=False):
         """Return the tip node for a given branch."""
 
     def lookup(key):
         """Resolve the node for a revision."""
 
     def lookupbranch(key):
         """Look up the branch name of the given revision or branch name."""
 
     def known(nodes):
         """Determine whether a series of nodes is known.
 
         Returns a list of bools.
         """
 
     def local():
         """Whether the repository is local."""
         return True
 
     def publishing():
         """Whether the repository is a publishing repository."""
 
     def cancopy():
         pass
 
     def shared():
         """The type of shared repository or None."""
 
     def wjoin(f, *insidef):
         """Calls self.vfs.reljoin(self.root, f, *insidef)"""
 
     def setparents(p1, p2):
         """Set the parent nodes of the working directory."""
 
     def filectx(path, changeid=None, fileid=None):
         """Obtain a filectx for the given file revision."""
 
     def getcwd():
         """Obtain the current working directory from the dirstate."""
 
     def pathto(f, cwd=None):
         """Obtain the relative path to a file."""
 
     def adddatafilter(name, fltr):
         pass
 
     def wread(filename):
         """Read a file from wvfs, using data filters."""
 
     def wwrite(filename, data, flags, backgroundclose=False, **kwargs):
         """Write data to a file in the wvfs, using data filters."""
 
     def wwritedata(filename, data):
         """Resolve data for writing to the wvfs, using data filters."""
 
     def currenttransaction():
         """Obtain the current transaction instance or None."""
 
     def transaction(desc, report=None):
         """Open a new transaction to write to the repository."""
 
     def undofiles():
         """Returns a list of (vfs, path) for files to undo transactions."""
 
     def recover():
         """Roll back an interrupted transaction."""
 
     def rollback(dryrun=False, force=False):
         """Undo the last transaction.
 
         DANGEROUS.
         """
 
     def updatecaches(tr=None, full=False):
         """Warm repo caches."""
 
     def invalidatecaches():
         """Invalidate cached data due to the repository mutating."""
 
     def invalidatevolatilesets():
         pass
 
     def invalidatedirstate():
         """Invalidate the dirstate."""
 
     def invalidate(clearfilecache=False):
         pass
 
     def invalidateall():
         pass
 
     def lock(wait=True):
         """Lock the repository store and return a lock instance."""
 
     def wlock(wait=True):
         """Lock the non-store parts of the repository."""
 
     def currentwlock():
         """Return the wlock if it's held or None."""
 
     def checkcommitpatterns(wctx, vdirs, match, status, fail):
         pass
 
     def commit(text='', user=None, date=None, match=None, force=False,
                editor=False, extra=None):
         """Add a new revision to the repository."""
 
     def commitctx(ctx, error=False, origctx=None):
         """Commit a commitctx instance to the repository."""
 
     def destroying():
         """Inform the repository that nodes are about to be destroyed."""
 
     def destroyed():
         """Inform the repository that nodes have been destroyed."""
 
     def status(node1='.', node2=None, match=None, ignored=False,
                clean=False, unknown=False, listsubrepos=False):
         """Convenience method to call repo[x].status()."""
 
     def addpostdsstatus(ps):
         pass
 
     def postdsstatus():
         pass
 
     def clearpostdsstatus():
         pass
 
     def heads(start=None):
         """Obtain list of nodes that are DAG heads."""
 
     def branchheads(branch=None, start=None, closed=False):
         pass
 
     def branches(nodes):
         pass
 
     def between(pairs):
         pass
 
     def checkpush(pushop):
         pass
 
     prepushoutgoinghooks = interfaceutil.Attribute(
         """util.hooks instance.""")
 
     def pushkey(namespace, key, old, new):
         pass
 
     def listkeys(namespace):
         pass
 
     def debugwireargs(one, two, three=None, four=None, five=None):
         pass
 
     def savecommitmessage(text):
         pass
 
 class completelocalrepository(ilocalrepositorymain,
                               ilocalrepositoryfilestorage):
     """Complete interface for a local repository."""
 
 class iwireprotocolcommandcacher(interfaceutil.Interface):
     """Represents a caching backend for wire protocol commands.
 
     Wire protocol version 2 supports transparent caching of many commands.
     To leverage this caching, servers can activate objects that cache
     command responses. Objects handle both cache writing and reading.
     This interface defines how that response caching mechanism works.
 
     Wire protocol version 2 commands emit a series of objects that are
     serialized and sent to the client. The caching layer exists between
     the invocation of the command function and the sending of its output
     objects to an output layer.
 
     Instances of this interface represent a binding to a cache that
     can serve a response (in place of calling a command function) and/or
     write responses to a cache for subsequent use.
 
     When a command request arrives, the following happens with regards
     to this interface:
 
     1. The server determines whether the command request is cacheable.
     2. If it is, an instance of this interface is spawned.
     3. The cacher is activated in a context manager (``__enter__`` is called).
     4. A cache *key* for that request is derived. This will call the
        instance's ``adjustcachekeystate()`` method so the derivation
        can be influenced.
     5. The cacher is informed of the derived cache key via a call to
        ``setcachekey()``.
     6. The cacher's ``lookup()`` method is called to test for presence of
        the derived key in the cache.
     7. If ``lookup()`` returns a hit, that cached result is used in place
        of invoking the command function. ``__exit__`` is called and the instance
        is discarded.
     8. The command function is invoked.
     9. ``onobject()`` is called for each object emitted by the command
        function.
     10. After the final object is seen, ``onfinished()`` is called.
     11. ``__exit__`` is called to signal the end of use of the instance.
 
     Cache *key* derivation can be influenced by the instance.
 
     Cache keys are initially derived by a deterministic representation of
     the command request. This includes the command name, arguments, protocol
     version, etc. This initial key derivation is performed by CBOR-encoding a
     data structure and feeding that output into a hasher.
 
     Instances of this interface can influence this initial key derivation
     via ``adjustcachekeystate()``.
 
     The instance is informed of the derived cache key via a call to
     ``setcachekey()``. The instance must store the key locally so it can
     be consulted on subsequent operations that may require it.
 
     When constructed, the instance has access to a callable that can be used
     for encoding response objects. This callable receives as its single
     argument an object emitted by a command function. It returns an iterable
     of bytes chunks representing the encoded object. Unless the cacher is
     caching native Python objects in memory or has a way of reconstructing
     the original Python objects, implementations typically call this function
     to produce bytes from the output objects and then store those bytes in
     the cache. When it comes time to re-emit those bytes, they are wrapped
     in a ``wireprototypes.encodedresponse`` instance to tell the output
     layer that they are pre-encoded.
 
     When receiving the objects emitted by the command function, instances
     can choose what to do with those objects. The simplest thing to do is
     re-emit the original objects. They will be forwarded to the output
     layer and will be processed as if the cacher did not exist.
 
     Implementations could also choose to not emit objects - instead locally
     buffering objects or their encoded representation. They could then emit
     a single "coalesced" object when ``onfinished()`` is called. In
     this way, the implementation would function as a filtering layer of
     sorts.
 
     When caching objects, typically the encoded form of the object will
     be stored. Keep in mind that if the original object is forwarded to
     the output layer, it will need to be encoded there as well. For large
     output, this redundant encoding could add overhead. Implementations
     could wrap the encoded object data in ``wireprototypes.encodedresponse``
     instances to avoid this overhead.
     """
     def __enter__():
         """Marks the instance as active.
 
         Should return self.
         """
 
     def __exit__(exctype, excvalue, exctb):
         """Called when cacher is no longer used.
 
         This can be used by implementations to perform cleanup actions (e.g.
         disconnecting network sockets, aborting a partially cached response.
         """
 
     def adjustcachekeystate(state):
         """Influences cache key derivation by adjusting state to derive key.
 
         A dict defining the state used to derive the cache key is passed.
 
         Implementations can modify this dict to record additional state that
         is wanted to influence key derivation.
 
         Implementations are *highly* encouraged to not modify or delete
         existing keys.
         """
 
     def setcachekey(key):
         """Record the derived cache key for this request.
 
         Instances may mutate the key for internal usage, as desired. e.g.
         instances may wish to prepend the repo name, introduce path
         components for filesystem or URL addressing, etc. Behavior is up to
         the cache.
 
         Returns a bool indicating if the request is cacheable by this
         instance.
         """
 
     def lookup():
         """Attempt to resolve an entry in the cache.
 
         The instance is instructed to look for the cache key that it was
         informed about via the call to ``setcachekey()``.
 
         If there's no cache hit or the cacher doesn't wish to use the cached
         entry, ``None`` should be returned.
 
         Else, a dict defining the cached result should be returned. The
         dict may have the following keys:
 
         objs
            An iterable of objects that should be sent to the client. That
            iterable of objects is expected to be what the command function
            would return if invoked or an equivalent representation thereof.
         """
 
     def onobject(obj):
         """Called when a new object is emitted from the command function.
 
         Receives as its argument the object that was emitted from the
         command function.
 
         This method returns an iterator of objects to forward to the output
         layer. The easiest implementation is a generator that just
         ``yield obj``.
         """
 
     def onfinished():
         """Called after all objects have been emitted from the command function.
 
         Implementations should return an iterator of objects to forward to
         the output layer.
 
         This method can be a generator.
         """

mercurial/localrepo.py

@@ -1,3312 +1,3316
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import random
 import sys
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     changegroup,
     changelog,
     color,
     context,
     dirstate,
     dirstateguard,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     manifest,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     namespaces,
     narrowspec,
     obsolete,
     pathutil,
     phases,
     pushkey,
     pycompat,
-    repository,
     repoview,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store as storemod,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
 )
+
+from .interfaces import (
+    repository,
+)
+
 from .utils import (
     interfaceutil,
     procutil,
     stringutil,
 )
 
 from .revlogutils import (
     constants as revlogconst,
 )
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # set of (path, vfs-location) tuples. vfs-location is:
 # - 'plain for vfs relative paths
 # - '' for svfs relative paths
 _cachedfiles = set()
 
 class _basefilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         # proxy to unfiltered __dict__ since filtered repo has no entry
         unfi = repo.unfiltered()
         try:
             return unfi.__dict__[self.sname]
         except KeyError:
             pass
         return super(_basefilecache, self).__get__(unfi, type)
 
     def set(self, repo, value):
         return super(_basefilecache, self).set(repo.unfiltered(), value)
 
 class repofilecache(_basefilecache):
     """filecache for files in .hg but outside of .hg/store"""
     def __init__(self, *paths):
         super(repofilecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, 'plain'))
 
     def join(self, obj, fname):
         return obj.vfs.join(fname)
 
 class storecache(_basefilecache):
     """filecache for files in the store"""
     def __init__(self, *paths):
         super(storecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, ''))
 
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 class mixedrepostorecache(_basefilecache):
     """filecache for a mix files in .hg/store and outside"""
     def __init__(self, *pathsandlocations):
         # scmutil.filecache only uses the path for passing back into our
         # join(), so we can safely pass a list of paths and locations
         super(mixedrepostorecache, self).__init__(*pathsandlocations)
         _cachedfiles.update(pathsandlocations)
 
     def join(self, obj, fnameandlocation):
         fname, location = fnameandlocation
         if location == 'plain':
             return obj.vfs.join(fname)
         else:
             if location != '':
                 raise error.ProgrammingError('unexpected location: %s' %
                                              location)
             return obj.sjoin(fname)
 
 def isfilecached(repo, name):
     """check if a repo has already cached "name" filecache-ed property
 
     This returns (cachedobj-or-None, iscached) tuple.
     """
     cacheentry = repo.unfiltered()._filecache.get(name, None)
     if not cacheentry:
         return None, False
     return cacheentry.obj, True
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 moderncaps = {'lookup', 'branchmap', 'pushkey', 'known', 'getbundle',
               'unbundle'}
 legacycaps = moderncaps.union({'changegroupsubset'})
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class localcommandexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'sendcommands()')
 
         if self._closed:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'close()')
 
         # We don't need to support anything fancy. Just call the named
         # method on the peer and return a resolved future.
         fn = getattr(self._peer, pycompat.sysstr(command))
 
         f = pycompat.futures.Future()
 
         try:
             result = fn(**pycompat.strkwargs(args))
         except Exception:
             pycompat.future_set_exception_info(f, sys.exc_info()[1:])
         else:
             f.set_result(result)
 
         return f
 
     def sendcommands(self):
         self._sent = True
 
     def close(self):
         self._closed = True
 
 @interfaceutil.implementer(repository.ipeercommands)
 class localpeer(repository.peer):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=None):
         super(localpeer, self).__init__()
 
         if caps is None:
             caps = moderncaps.copy()
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
 
     # Begin of _basepeer interface.
 
     def url(self):
         return self._repo.url()
 
     def local(self):
         return self._repo
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         self._repo.close()
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def capabilities(self):
         return self._caps
 
     def clonebundles(self):
         return self._repo.tryread('clonebundles.manifest')
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         """Used to test argument passing over the wire"""
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None,
                   **kwargs):
         chunks = exchange.getbundlechunks(self._repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps,
                                           **kwargs)[1]
         cb = util.chunkbuffer(chunks)
 
         if exchange.bundle2requested(bundlecaps):
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler('01', cb, None)
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def stream_out(self):
         raise error.Abort(_('cannot perform stream clone against local '
                             'peer'))
 
     def unbundle(self, bundle, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 bundle = exchange.readbundle(self.ui, bundle, None)
                 ret = exchange.unbundle(self._repo, bundle, heads, 'push', url)
                 if util.safehasattr(ret, 'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(_('push failed:'),
                                       stringutil.forcebytestr(exc))
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def commandexecutor(self):
         return localcommandexecutor(self)
 
     # End of peer interface.
 
 @interfaceutil.implementer(repository.ipeerlegacycommands)
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         super(locallegacypeer, self).__init__(repo, caps=legacycaps)
 
     # Begin of baselegacywirecommands interface.
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def changegroup(self, nodes, source):
         outgoing = discovery.outgoing(self._repo, missingroots=nodes,
                                       missingheads=self._repo.heads())
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     def changegroupsubset(self, bases, heads, source):
         outgoing = discovery.outgoing(self._repo, missingroots=bases,
                                       missingheads=heads)
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     # End of baselegacywirecommands interface.
 
 # Increment the sub-version when the revlog v2 format changes to lock out old
 # clients.
 REVLOGV2_REQUIREMENT = 'exp-revlogv2.1'
 
 # A repository with the sparserevlog feature will have delta chains that
 # can spread over a larger span. Sparse reading cuts these large spans into
 # pieces, so that each piece isn't too big.
 # Without the sparserevlog capability, reading from the repository could use
 # huge amounts of memory, because the whole span would be read at once,
 # including all the intermediate revisions that aren't pertinent for the chain.
 # This is why once a repository has enabled sparse-read, it becomes required.
 SPARSEREVLOG_REQUIREMENT = 'sparserevlog'
 
 # Functions receiving (ui, features) that extensions can register to impact
 # the ability to load repositories with custom requirements. Only
 # functions defined in loaded extensions are called.
 #
 # The function receives a set of requirement strings that the repository
 # is capable of opening. Functions will typically add elements to the
 # set to reflect that the extension knows how to handle that requirements.
 featuresetupfuncs = set()
 
 def makelocalrepository(baseui, path, intents=None):
     """Create a local repository object.
 
     Given arguments needed to construct a local repository, this function
     performs various early repository loading functionality (such as
     reading the ``.hg/requires`` and ``.hg/hgrc`` files), validates that
     the repository can be opened, derives a type suitable for representing
     that repository, and returns an instance of it.
 
     The returned object conforms to the ``repository.completelocalrepository``
     interface.
 
     The repository type is derived by calling a series of factory functions
     for each aspect/interface of the final repository. These are defined by
     ``REPO_INTERFACES``.
 
     Each factory function is called to produce a type implementing a specific
     interface. The cumulative list of returned types will be combined into a
     new type and that type will be instantiated to represent the local
     repository.
 
     The factory functions each receive various state that may be consulted
     as part of deriving a type.
 
     Extensions should wrap these factory functions to customize repository type
     creation. Note that an extension's wrapped function may be called even if
     that extension is not loaded for the repo being constructed. Extensions
     should check if their ``__name__`` appears in the
     ``extensionmodulenames`` set passed to the factory function and no-op if
     not.
     """
     ui = baseui.copy()
     # Prevent copying repo configuration.
     ui.copy = baseui.copy
 
     # Working directory VFS rooted at repository root.
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     # Main VFS for .hg/ directory.
     hgpath = wdirvfs.join(b'.hg')
     hgvfs = vfsmod.vfs(hgpath, cacheaudited=True)
 
     # The .hg/ path should exist and should be a directory. All other
     # cases are errors.
     if not hgvfs.isdir():
         try:
             hgvfs.stat()
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
         raise error.RepoError(_(b'repository %s not found') % path)
 
     # .hg/requires file contains a newline-delimited list of
     # features/capabilities the opener (us) must have in order to use
     # the repository. This file was introduced in Mercurial 0.9.2,
     # which means very old repositories may not have one. We assume
     # a missing file translates to no requirements.
     try:
         requirements = set(hgvfs.read(b'requires').splitlines())
     except IOError as e:
         if e.errno != errno.ENOENT:
             raise
         requirements = set()
 
     # The .hg/hgrc file may load extensions or contain config options
     # that influence repository construction. Attempt to load it and
     # process any new extensions that it may have pulled in.
     if loadhgrc(ui, wdirvfs, hgvfs, requirements):
         afterhgrcload(ui, wdirvfs, hgvfs, requirements)
         extensions.loadall(ui)
         extensions.populateui(ui)
 
     # Set of module names of extensions loaded for this repository.
     extensionmodulenames = {m.__name__ for n, m in extensions.extensions(ui)}
 
     supportedrequirements = gathersupportedrequirements(ui)
 
     # We first validate the requirements are known.
     ensurerequirementsrecognized(requirements, supportedrequirements)
 
     # Then we validate that the known set is reasonable to use together.
     ensurerequirementscompatible(ui, requirements)
 
     # TODO there are unhandled edge cases related to opening repositories with
     # shared storage. If storage is shared, we should also test for requirements
     # compatibility in the pointed-to repo. This entails loading the .hg/hgrc in
     # that repo, as that repo may load extensions needed to open it. This is a
     # bit complicated because we don't want the other hgrc to overwrite settings
     # in this hgrc.
     #
     # This bug is somewhat mitigated by the fact that we copy the .hg/requires
     # file when sharing repos. But if a requirement is added after the share is
     # performed, thereby introducing a new requirement for the opener, we may
     # will not see that and could encounter a run-time error interacting with
     # that shared store since it has an unknown-to-us requirement.
 
     # At this point, we know we should be capable of opening the repository.
     # Now get on with doing that.
 
     features = set()
 
     # The "store" part of the repository holds versioned data. How it is
     # accessed is determined by various requirements. The ``shared`` or
     # ``relshared`` requirements indicate the store lives in the path contained
     # in the ``.hg/sharedpath`` file. This is an absolute path for
     # ``shared`` and relative to ``.hg/`` for ``relshared``.
     if b'shared' in requirements or b'relshared' in requirements:
         sharedpath = hgvfs.read(b'sharedpath').rstrip(b'\n')
         if b'relshared' in requirements:
             sharedpath = hgvfs.join(sharedpath)
 
         sharedvfs = vfsmod.vfs(sharedpath, realpath=True)
 
         if not sharedvfs.exists():
             raise error.RepoError(_(b'.hg/sharedpath points to nonexistent '
                                     b'directory %s') % sharedvfs.base)
 
         features.add(repository.REPO_FEATURE_SHARED_STORAGE)
 
         storebasepath = sharedvfs.base
         cachepath = sharedvfs.join(b'cache')
     else:
         storebasepath = hgvfs.base
         cachepath = hgvfs.join(b'cache')
     wcachepath = hgvfs.join(b'wcache')
 
 
     # The store has changed over time and the exact layout is dictated by
     # requirements. The store interface abstracts differences across all
     # of them.
     store = makestore(requirements, storebasepath,
                       lambda base: vfsmod.vfs(base, cacheaudited=True))
     hgvfs.createmode = store.createmode
 
     storevfs = store.vfs
     storevfs.options = resolvestorevfsoptions(ui, requirements, features)
 
     # The cache vfs is used to manage cache files.
     cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
     cachevfs.createmode = store.createmode
     # The cache vfs is used to manage cache files related to the working copy
     wcachevfs = vfsmod.vfs(wcachepath, cacheaudited=True)
     wcachevfs.createmode = store.createmode
 
     # Now resolve the type for the repository object. We do this by repeatedly
     # calling a factory function to produces types for specific aspects of the
     # repo's operation. The aggregate returned types are used as base classes
     # for a dynamically-derived type, which will represent our new repository.
 
     bases = []
     extrastate = {}
 
     for iface, fn in REPO_INTERFACES:
         # We pass all potentially useful state to give extensions tons of
         # flexibility.
         typ = fn()(ui=ui,
                  intents=intents,
                  requirements=requirements,
                  features=features,
                  wdirvfs=wdirvfs,
                  hgvfs=hgvfs,
                  store=store,
                  storevfs=storevfs,
                  storeoptions=storevfs.options,
                  cachevfs=cachevfs,
                  wcachevfs=wcachevfs,
                  extensionmodulenames=extensionmodulenames,
                  extrastate=extrastate,
                  baseclasses=bases)
 
         if not isinstance(typ, type):
             raise error.ProgrammingError('unable to construct type for %s' %
                                          iface)
 
         bases.append(typ)
 
     # type() allows you to use characters in type names that wouldn't be
     # recognized as Python symbols in source code. We abuse that to add
     # rich information about our constructed repo.
     name = pycompat.sysstr(b'derivedrepo:%s<%s>' % (
         wdirvfs.base,
         b','.join(sorted(requirements))))
 
     cls = type(name, tuple(bases), {})
 
     return cls(
         baseui=baseui,
         ui=ui,
         origroot=path,
         wdirvfs=wdirvfs,
         hgvfs=hgvfs,
         requirements=requirements,
         supportedrequirements=supportedrequirements,
         sharedpath=storebasepath,
         store=store,
         cachevfs=cachevfs,
         wcachevfs=wcachevfs,
         features=features,
         intents=intents)
 
 def loadhgrc(ui, wdirvfs, hgvfs, requirements):
     """Load hgrc files/content into a ui instance.
 
     This is called during repository opening to load any additional
     config files or settings relevant to the current repository.
 
     Returns a bool indicating whether any additional configs were loaded.
 
     Extensions should monkeypatch this function to modify how per-repo
     configs are loaded. For example, an extension may wish to pull in
     configs from alternate files or sources.
     """
     try:
         ui.readconfig(hgvfs.join(b'hgrc'), root=wdirvfs.base)
         return True
     except IOError:
         return False
 
 def afterhgrcload(ui, wdirvfs, hgvfs, requirements):
     """Perform additional actions after .hg/hgrc is loaded.
 
     This function is called during repository loading immediately after
     the .hg/hgrc file is loaded and before per-repo extensions are loaded.
 
     The function can be used to validate configs, automatically add
     options (including extensions) based on requirements, etc.
     """
 
     # Map of requirements to list of extensions to load automatically when
     # requirement is present.
     autoextensions = {
         b'largefiles': [b'largefiles'],
         b'lfs': [b'lfs'],
     }
 
     for requirement, names in sorted(autoextensions.items()):
         if requirement not in requirements:
             continue
 
         for name in names:
             if not ui.hasconfig(b'extensions', name):
                 ui.setconfig(b'extensions', name, b'', source='autoload')
 
 def gathersupportedrequirements(ui):
     """Determine the complete set of recognized requirements."""
     # Start with all requirements supported by this file.
     supported = set(localrepository._basesupported)
 
     # Execute ``featuresetupfuncs`` entries if they belong to an extension
     # relevant to this ui instance.
     modules = {m.__name__ for n, m in extensions.extensions(ui)}
 
     for fn in featuresetupfuncs:
         if fn.__module__ in modules:
             fn(ui, supported)
 
     # Add derived requirements from registered compression engines.
     for name in util.compengines:
         engine = util.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == 'zstd':
                 supported.add(b'revlog-compression-zstd')
 
     return supported
 
 def ensurerequirementsrecognized(requirements, supported):
     """Validate that a set of local requirements is recognized.
 
     Receives a set of requirements. Raises an ``error.RepoError`` if there
     exists any requirement in that set that currently loaded code doesn't
     recognize.
 
     Returns a set of supported requirements.
     """
     missing = set()
 
     for requirement in requirements:
         if requirement in supported:
             continue
 
         if not requirement or not requirement[0:1].isalnum():
             raise error.RequirementError(_(b'.hg/requires file is corrupt'))
 
         missing.add(requirement)
 
     if missing:
         raise error.RequirementError(
             _(b'repository requires features unknown to this Mercurial: %s') %
             b' '.join(sorted(missing)),
             hint=_(b'see https://mercurial-scm.org/wiki/MissingRequirement '
                    b'for more information'))
 
 def ensurerequirementscompatible(ui, requirements):
     """Validates that a set of recognized requirements is mutually compatible.
 
     Some requirements may not be compatible with others or require
     config options that aren't enabled. This function is called during
     repository opening to ensure that the set of requirements needed
     to open a repository is sane and compatible with config options.
 
     Extensions can monkeypatch this function to perform additional
     checking.
 
     ``error.RepoError`` should be raised on failure.
     """
     if b'exp-sparse' in requirements and not sparse.enabled:
         raise error.RepoError(_(b'repository is using sparse feature but '
                                 b'sparse is not enabled; enable the '
                                 b'"sparse" extensions to access'))
 
 def makestore(requirements, path, vfstype):
     """Construct a storage object for a repository."""
     if b'store' in requirements:
         if b'fncache' in requirements:
             return storemod.fncachestore(path, vfstype,
                                          b'dotencode' in requirements)
 
         return storemod.encodedstore(path, vfstype)
 
     return storemod.basicstore(path, vfstype)
 
 def resolvestorevfsoptions(ui, requirements, features):
     """Resolve the options to pass to the store vfs opener.
 
     The returned dict is used to influence behavior of the storage layer.
     """
     options = {}
 
     if b'treemanifest' in requirements:
         options[b'treemanifest'] = True
 
     # experimental config: format.manifestcachesize
     manifestcachesize = ui.configint(b'format', b'manifestcachesize')
     if manifestcachesize is not None:
         options[b'manifestcachesize'] = manifestcachesize
 
     # In the absence of another requirement superseding a revlog-related
     # requirement, we have to assume the repo is using revlog version 0.
     # This revlog format is super old and we don't bother trying to parse
     # opener options for it because those options wouldn't do anything
     # meaningful on such old repos.
     if b'revlogv1' in requirements or REVLOGV2_REQUIREMENT in requirements:
         options.update(resolverevlogstorevfsoptions(ui, requirements, features))
 
     return options
 
 def resolverevlogstorevfsoptions(ui, requirements, features):
     """Resolve opener options specific to revlogs."""
 
     options = {}
     options[b'flagprocessors'] = {}
 
     if b'revlogv1' in requirements:
         options[b'revlogv1'] = True
     if REVLOGV2_REQUIREMENT in requirements:
         options[b'revlogv2'] = True
 
     if b'generaldelta' in requirements:
         options[b'generaldelta'] = True
 
     # experimental config: format.chunkcachesize
     chunkcachesize = ui.configint(b'format', b'chunkcachesize')
     if chunkcachesize is not None:
         options[b'chunkcachesize'] = chunkcachesize
 
     deltabothparents = ui.configbool(b'storage',
                                      b'revlog.optimize-delta-parent-choice')
     options[b'deltabothparents'] = deltabothparents
 
     lazydelta = ui.configbool(b'storage', b'revlog.reuse-external-delta')
     lazydeltabase = False
     if lazydelta:
         lazydeltabase = ui.configbool(b'storage',
                                       b'revlog.reuse-external-delta-parent')
     if lazydeltabase is None:
         lazydeltabase = not scmutil.gddeltaconfig(ui)
     options[b'lazydelta'] = lazydelta
     options[b'lazydeltabase'] = lazydeltabase
 
     chainspan = ui.configbytes(b'experimental', b'maxdeltachainspan')
     if 0 <= chainspan:
         options[b'maxdeltachainspan'] = chainspan
 
     mmapindexthreshold = ui.configbytes(b'experimental',
                                         b'mmapindexthreshold')
     if mmapindexthreshold is not None:
         options[b'mmapindexthreshold'] = mmapindexthreshold
 
     withsparseread = ui.configbool(b'experimental', b'sparse-read')
     srdensitythres = float(ui.config(b'experimental',
                                      b'sparse-read.density-threshold'))
     srmingapsize = ui.configbytes(b'experimental',
                                   b'sparse-read.min-gap-size')
     options[b'with-sparse-read'] = withsparseread
     options[b'sparse-read-density-threshold'] = srdensitythres
     options[b'sparse-read-min-gap-size'] = srmingapsize
 
     sparserevlog = SPARSEREVLOG_REQUIREMENT in requirements
     options[b'sparse-revlog'] = sparserevlog
     if sparserevlog:
         options[b'generaldelta'] = True
 
     maxchainlen = None
     if sparserevlog:
         maxchainlen = revlogconst.SPARSE_REVLOG_MAX_CHAIN_LENGTH
     # experimental config: format.maxchainlen
     maxchainlen = ui.configint(b'format', b'maxchainlen', maxchainlen)
     if maxchainlen is not None:
         options[b'maxchainlen'] = maxchainlen
 
     for r in requirements:
         # we allow multiple compression engine requirement to co-exist because
         # strickly speaking, revlog seems to support mixed compression style.
         #
         # The compression used for new entries will be "the last one"
         prefix = r.startswith
         if prefix('revlog-compression-') or prefix('exp-compression-'):
             options[b'compengine'] = r.split('-', 2)[2]
 
     options[b'zlib.level'] = ui.configint(b'storage', b'revlog.zlib.level')
     if options[b'zlib.level'] is not None:
         if not (0 <= options[b'zlib.level'] <= 9):
             msg = _('invalid value for `storage.revlog.zlib.level` config: %d')
             raise error.Abort(msg % options[b'zlib.level'])
     options[b'zstd.level'] = ui.configint(b'storage', b'revlog.zstd.level')
     if options[b'zstd.level'] is not None:
         if not (0 <= options[b'zstd.level'] <= 22):
             msg = _('invalid value for `storage.revlog.zstd.level` config: %d')
             raise error.Abort(msg % options[b'zstd.level'])
 
     if repository.NARROW_REQUIREMENT in requirements:
         options[b'enableellipsis'] = True
 
     return options
 
 def makemain(**kwargs):
     """Produce a type conforming to ``ilocalrepositorymain``."""
     return localrepository
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlogfilestorage(object):
     """File storage when using revlogs."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.filelog(self.svfs, path)
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlognarrowfilestorage(object):
     """File storage when using revlogs and narrow files."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.narrowfilelog(self.svfs, path, self._storenarrowmatch)
 
 def makefilestorage(requirements, features, **kwargs):
     """Produce a type conforming to ``ilocalrepositoryfilestorage``."""
     features.add(repository.REPO_FEATURE_REVLOG_FILE_STORAGE)
     features.add(repository.REPO_FEATURE_STREAM_CLONE)
 
     if repository.NARROW_REQUIREMENT in requirements:
         return revlognarrowfilestorage
     else:
         return revlogfilestorage
 
 # List of repository interfaces and factory functions for them. Each
 # will be called in order during ``makelocalrepository()`` to iteratively
 # derive the final type for a local repository instance. We capture the
 # function as a lambda so we don't hold a reference and the module-level
 # functions can be wrapped.
 REPO_INTERFACES = [
     (repository.ilocalrepositorymain, lambda: makemain),
     (repository.ilocalrepositoryfilestorage, lambda: makefilestorage),
 ]
 
 @interfaceutil.implementer(repository.ilocalrepositorymain)
 class localrepository(object):
     """Main class for representing local repositories.
 
     All local repositories are instances of this class.
 
     Constructed on its own, instances of this class are not usable as
     repository objects. To obtain a usable repository object, call
     ``hg.repository()``, ``localrepo.instance()``, or
     ``localrepo.makelocalrepository()``. The latter is the lowest-level.
     ``instance()`` adds support for creating new repositories.
     ``hg.repository()`` adds more extension integration, including calling
     ``reposetup()``. Generally speaking, ``hg.repository()`` should be
     used.
     """
 
     # obsolete experimental requirements:
     #  - manifestv2: An experimental new manifest format that allowed
     #    for stem compression of long paths. Experiment ended up not
     #    being successful (repository sizes went up due to worse delta
     #    chains), and the code was deleted in 4.6.
     supportedformats = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
         REVLOGV2_REQUIREMENT,
         SPARSEREVLOG_REQUIREMENT,
         bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         'store',
         'fncache',
         'shared',
         'relshared',
         'dotencode',
         'exp-sparse',
         'internal-phase'
     }
 
     # list of prefix for file which can be written without 'wlock'
     # Extensions should extend this list when needed
     _wlockfreeprefix = {
         # We migh consider requiring 'wlock' for the next
         # two, but pretty much all the existing code assume
         # wlock is not needed so we keep them excluded for
         # now.
         'hgrc',
         'requires',
         # XXX cache is a complicatged business someone
         # should investigate this in depth at some point
         'cache/',
         # XXX shouldn't be dirstate covered by the wlock?
         'dirstate',
         # XXX bisect was still a bit too messy at the time
         # this changeset was introduced. Someone should fix
         # the remainig bit and drop this line
         'bisect.state',
     }
 
     def __init__(self, baseui, ui, origroot, wdirvfs, hgvfs, requirements,
                  supportedrequirements, sharedpath, store, cachevfs, wcachevfs,
                  features, intents=None):
         """Create a new local repository instance.
 
         Most callers should use ``hg.repository()``, ``localrepo.instance()``,
         or ``localrepo.makelocalrepository()`` for obtaining a new repository
         object.
 
         Arguments:
 
         baseui
            ``ui.ui`` instance that ``ui`` argument was based off of.
 
         ui
            ``ui.ui`` instance for use by the repository.
 
         origroot
            ``bytes`` path to working directory root of this repository.
 
         wdirvfs
            ``vfs.vfs`` rooted at the working directory.
 
         hgvfs
            ``vfs.vfs`` rooted at .hg/
 
         requirements
            ``set`` of bytestrings representing repository opening requirements.
 
         supportedrequirements
            ``set`` of bytestrings representing repository requirements that we
            know how to open. May be a supetset of ``requirements``.
 
         sharedpath
            ``bytes`` Defining path to storage base directory. Points to a
            ``.hg/`` directory somewhere.
 
         store
            ``store.basicstore`` (or derived) instance providing access to
            versioned storage.
 
         cachevfs
            ``vfs.vfs`` used for cache files.
 
         wcachevfs
            ``vfs.vfs`` used for cache files related to the working copy.
 
         features
            ``set`` of bytestrings defining features/capabilities of this
            instance.
 
         intents
            ``set`` of system strings indicating what this repo will be used
            for.
         """
         self.baseui = baseui
         self.ui = ui
         self.origroot = origroot
         # vfs rooted at working directory.
         self.wvfs = wdirvfs
         self.root = wdirvfs.base
         # vfs rooted at .hg/. Used to access most non-store paths.
         self.vfs = hgvfs
         self.path = hgvfs.base
         self.requirements = requirements
         self.supported = supportedrequirements
         self.sharedpath = sharedpath
         self.store = store
         self.cachevfs = cachevfs
         self.wcachevfs = wcachevfs
         self.features = features
 
         self.filtername = None
 
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             self.vfs.audit = self._getvfsward(self.vfs.audit)
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
 
         color.setup(self.ui)
 
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             if util.safehasattr(self.svfs, 'vfs'): # this is filtervfs
                 self.svfs.vfs.audit = self._getsvfsward(self.svfs.vfs.audit)
             else: # standard vfs
                 self.svfs.audit = self._getsvfsward(self.svfs.audit)
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = branchmap.BranchMapCache()
         self._revbranchcache = None
         self._filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # post-dirstate-status hooks
         self._postdsstatus = []
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
         # Key to signature value.
         self._sparsesignaturecache = {}
         # Signature to cached matcher instance.
         self._sparsematchercache = {}
 
         self._extrafilterid = repoview.extrafilter(ui)
 
     def _getvfsward(self, origfunc):
         """build a ward for self.vfs"""
         rref = weakref.ref(self)
         def checkvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if (repo is None
                 or not util.safehasattr(repo, '_wlockref')
                 or not util.safehasattr(repo, '_lockref')):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.path):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.path) + 1:]
             if path.startswith('cache/'):
                 msg = 'accessing cache with vfs instead of cachevfs: "%s"'
                 repo.ui.develwarn(msg % path, stacklevel=3, config="cache-vfs")
             if path.startswith('journal.') or path.startswith('undo.'):
                 # journal is covered by 'lock'
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn('write with no lock: "%s"' % path,
                                       stacklevel=3, config='check-locks')
             elif repo._currentlock(repo._wlockref) is None:
                 # rest of vfs files are covered by 'wlock'
                 #
                 # exclude special files
                 for prefix in self._wlockfreeprefix:
                     if path.startswith(prefix):
                         return
                 repo.ui.develwarn('write with no wlock: "%s"' % path,
                                   stacklevel=3, config='check-locks')
             return ret
         return checkvfs
 
     def _getsvfsward(self, origfunc):
         """build a ward for self.svfs"""
         rref = weakref.ref(self)
         def checksvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if repo is None or not util.safehasattr(repo, '_lockref'):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.sharedpath):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.sharedpath) + 1:]
             if repo._currentlock(repo._lockref) is None:
                 repo.ui.develwarn('write with no lock: "%s"' % path,
                                   stacklevel=4)
             return ret
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool('experimental', 'bundle2-advertise'):
             caps = set(caps)
             capsblob = bundle2.encodecaps(bundle2.getrepocaps(self,
                                                               role='client'))
             caps.add('bundle2=' + urlreq.quote(capsblob))
         return caps
 
     def _writerequirements(self):
         scmutil.writerequires(self.vfs, self.requirements)
 
     # Don't cache auditor/nofsauditor, or you'll end up with reference cycle:
     # self -> auditor -> self._checknested -> self
 
     @property
     def auditor(self):
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested)
 
     @property
     def nofsauditor(self):
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested,
                                     realfs=False, cached=True)
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository
 
         The `name` parameter is the identifier of the requested view. This
         will return a repoview object set "exactly" to the specified view.
 
         This function does not apply recursive filtering to a repository. For
         example calling `repo.filtered("served")` will return a repoview using
         the "served" view, regardless of the initial view used by `repo`.
 
         In other word, there is always only one level of `repoview` "filtering".
         """
         if self._extrafilterid is not None and '%' not in name:
             name = name + '%'  + self._extrafilterid
 
         cls = repoview.newtype(self.unfiltered().__class__)
         return cls(self, name, visibilityexceptions)
 
     @mixedrepostorecache(('bookmarks', 'plain'), ('bookmarks.current', 'plain'),
                          ('bookmarks', ''), ('00changelog.i', ''))
     def _bookmarks(self):
         # Since the multiple files involved in the transaction cannot be
         # written atomically (with current repository format), there is a race
         # condition here.
         #
         # 1) changelog content A is read
         # 2) outside transaction update changelog to content B
         # 3) outside transaction update bookmark file referring to content B
         # 4) bookmarks file content is read and filtered against changelog-A
         #
         # When this happens, bookmarks against nodes missing from A are dropped.
         #
         # Having this happening during read is not great, but it become worse
         # when this happen during write because the bookmarks to the "unknown"
         # nodes will be dropped for good. However, writes happen within locks.
         # This locking makes it possible to have a race free consistent read.
         # For this purpose data read from disc before locking  are
         # "invalidated" right after the locks are taken. This invalidations are
         # "light", the `filecache` mechanism keep the data in memory and will
         # reuse them if the underlying files did not changed. Not parsing the
         # same data multiple times helps performances.
         #
         # Unfortunately in the case describe above, the files tracked by the
         # bookmarks file cache might not have changed, but the in-memory
         # content is still "wrong" because we used an older changelog content
         # to process the on-disk data. So after locking, the changelog would be
         # refreshed but `_bookmarks` would be preserved.
         # Adding `00changelog.i` to the list of tracked file is not
         # enough, because at the time we build the content for `_bookmarks` in
         # (4), the changelog file has already diverged from the content used
         # for loading `changelog` in (1)
         #
         # To prevent the issue, we force the changelog to be explicitly
         # reloaded while computing `_bookmarks`. The data race can still happen
         # without the lock (with a narrower window), but it would no longer go
         # undetected during the lock time refresh.
         #
         # The new schedule is as follow
         #
         # 1) filecache logic detect that `_bookmarks` needs to be computed
         # 2) cachestat for `bookmarks` and `changelog` are captured (for book)
         # 3) We force `changelog` filecache to be tested
         # 4) cachestat for `changelog` are captured (for changelog)
         # 5) `_bookmarks` is computed and cached
         #
         # The step in (3) ensure we have a changelog at least as recent as the
         # cache stat computed in (1). As a result at locking time:
         #  * if the changelog did not changed since (1) -> we can reuse the data
         #  * otherwise -> the bookmarks get refreshed.
         self._refreshchangelog()
         return bookmarks.bmstore(self)
 
     def _refreshchangelog(self):
         """make sure the in memory changelog match the on-disk one"""
         if ('changelog' in vars(self) and self.currenttransaction() is None):
             del self.changelog
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     # _phasesets depend on changelog. what we need is to call
     # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache('phaseroots', '00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         return obsolete.makestore(self.ui, self)
 
     @storecache('00changelog.i')
     def changelog(self):
         return changelog.changelog(self.svfs,
                                    trypending=txnutil.mayhavepending(self.root))
 
     @storecache('00manifest.i')
     def manifestlog(self):
         rootstore = manifest.manifestrevlog(self.svfs)
         return manifest.manifestlog(self.svfs, self, rootstore,
                                     self._storenarrowmatch)
 
     @repofilecache('dirstate')
     def dirstate(self):
         return self._makedirstate()
 
     def _makedirstate(self):
         """Extension point for wrapping the dirstate per-repo."""
         sparsematchfn = lambda: sparse.matcher(self)
 
         return dirstate.dirstate(self.vfs, self.ui, self.root,
                                  self._dirstatevalidate, sparsematchfn)
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(_("warning: ignoring unknown"
                                " working parent %s!\n") % short(node))
             return nullid
 
     @storecache(narrowspec.FILENAME)
     def narrowpats(self):
         """matcher patterns for this repository's narrowspec
 
         A tuple of (includes, excludes).
         """
         return narrowspec.load(self)
 
     @storecache(narrowspec.FILENAME)
     def _storenarrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         narrowspec.checkworkingcopynarrowspec(self)
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     def narrowmatch(self, match=None, includeexact=False):
         """matcher corresponding the the repo's narrowspec
 
         If `match` is given, then that will be intersected with the narrow
         matcher.
 
         If `includeexact` is True, then any exact matches from `match` will
         be included even if they're outside the narrowspec.
         """
         if match:
             if includeexact and not self._narrowmatch.always():
                 # do not exclude explicitly-specified paths so that they can
                 # be warned later on
                 em = matchmod.exact(match.files())
                 nm = matchmod.unionmatcher([self._narrowmatch, em])
                 return matchmod.intersectmatchers(match, nm)
             return matchmod.intersectmatchers(match, self._narrowmatch)
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         narrowspec.save(self, newincludes, newexcludes)
         self.invalidate(clearfilecache=True)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, context.basectx):
             return changeid
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [self[i]
                     for i in pycompat.xrange(*changeid.indices(len(self)))
                     if i not in self.changelog.filteredrevs]
         try:
             if isinstance(changeid, int):
                 node = self.changelog.node(changeid)
                 rev = changeid
             elif changeid == 'null':
                 node = nullid
                 rev = nullrev
             elif changeid == 'tip':
                 node = self.changelog.tip()
                 rev = self.changelog.rev(node)
             elif changeid == '.':
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 node = self.dirstate.p1()
                 rev = self.unfiltered().changelog.rev(node)
             elif len(changeid) == 20:
                 try:
                     node = changeid
                     rev = self.changelog.rev(changeid)
                 except error.FilteredLookupError:
                     changeid = hex(changeid) # for the error message
                     raise
                 except LookupError:
                     # check if it might have come from damaged dirstate
                     #
                     # XXX we could avoid the unfiltered if we had a recognizable
                     # exception for filtered changeset access
                     if (self.local()
                         and changeid in self.unfiltered().dirstate.parents()):
                         msg = _("working directory has unknown parent '%s'!")
                         raise error.Abort(msg % short(changeid))
                     changeid = hex(changeid) # for the error message
                     raise
 
             elif len(changeid) == 40:
                 node = bin(changeid)
                 rev = self.changelog.rev(node)
             else:
                 raise error.ProgrammingError(
                         "unsupported changeid '%s' of type %s" %
                         (changeid, type(changeid)))
 
             return context.changectx(self, rev, node)
 
         except (error.FilteredIndexError, error.FilteredLookupError):
             raise error.FilteredRepoLookupError(_("filtered revision '%s'")
                                                 % pycompat.bytestr(changeid))
         except (IndexError, LookupError):
             raise error.RepoLookupError(
                 _("unknown revision '%s'") % pycompat.bytestr(changeid))
         except error.WdirUnsupported:
             return context.workingctx(self)
 
     def __contains__(self, changeid):
         """True if the given changeid exists
 
         error.AmbiguousPrefixLookupError is raised if an ambiguous node
         specified.
         """
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         # no need to pay the cost of repoview.changelog
         unfi = self.unfiltered()
         return len(unfi.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revsetlang.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()`` or
         ``repo.anyrevs([expr], user=True)``.
 
         Returns a revset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         '''
         tree = revsetlang.spectree(expr, *args)
         return revset.makematcher(tree)(self)
 
     def set(self, expr, *args):
         '''Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def anyrevs(self, specs, user=False, localalias=None):
         '''Find revisions matching one of the given revsets.
 
         Revset aliases from the configuration are not expanded by default. To
         expand user aliases, specify ``user=True``. To provide some local
         definitions overriding user aliases, set ``localalias`` to
         ``{name: definitionstring}``.
         '''
         if user:
             m = revset.matchany(self.ui, specs,
                                 lookup=revset.lookupfn(self),
                                 localalias=localalias)
         else:
             m = revset.matchany(None, specs, localalias=localalias)
         return m(self)
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         rev = self.changelog.rev
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
 
         # map tag name to (node, hist)
         alltags = tagsmod.findglobaltags(self.ui, self)
         # map tag name to tag type
         tagtypes = dict((tag, 'global') for tag in alltags)
 
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         return self._bookmarks.names(node)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         return self._branchcaches[self]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def branchtip(self, branch, ignoremissing=False):
         '''return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         '''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_("unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         node = scmutil.revsymbol(self, key).node()
         if node is None:
             raise error.RepoLookupError(_("unknown revision '%s'") % key)
         return node
 
     def lookupbranch(self, key):
         if self.branchmap().hasbranch(key):
             return key
 
         return scmutil.revsymbol(self, key).branch()
 
     def known(self, nodes):
         cl = self.changelog
         nm = cl.nodemap
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool('phases', 'publish', untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered('visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return 'store'
         return None
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def setparents(self, p1, p2=nullid):
         with self.dirstate.parentchange():
             copies = self.dirstate.setparents(p1, p2)
             pctx = self[p1]
             if copies:
                 # Adjust copy records, the dirstate cannot do it, it
                 # requires access to parents manifests. Preserve them
                 # only for entries added to first parent.
                 for f in copies:
                     if f not in pctx and copies[f] in pctx:
                         self.dirstate.copy(copies[f], f)
             if p2 == nullid:
                 for f, s in sorted(self.dirstate.copies().items()):
                     if f not in pctx and s not in pctx:
                         self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None, changectx=None):
         """changeid must be a changeset revision, if specified.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid,
                                changectx=changectx)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def _loadfilter(self, filter):
         if filter not in self._filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: procutil.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not pycompat.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self._filterpats[filter] = l
         return self._filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self.wvfs.islink(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False, **kwargs):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(filename, data, backgroundclose=backgroundclose,
                             **kwargs)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
             else:
                 self.wvfs.setflags(filename, False, False)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if (self.ui.configbool('devel', 'all-warnings')
                 or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError('transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest(name=desc)
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found"),
                 hint=_("run 'hg recover' to clean up transaction"))
 
         idbase = "%.40f#%f" % (random.random(), time.time())
         ha = hex(hashlib.sha1(idbase).digest())
         txnid = 'TXN:' + ha
         self.hook('pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {'plain': self.vfs, 'store': self.svfs} # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         # Code to track tag movement
         #
         # Since tags are all handled as file content, it is actually quite hard
         # to track these movement from a code perspective. So we fallback to a
         # tracking at the repository level. One could envision to track changes
         # to the '.hgtags' file through changegroup apply but that fails to
         # cope with case where transaction expose new heads without changegroup
         # being involved (eg: phase movement).
         #
         # For now, We gate the feature behind a flag since this likely comes
         # with performance impacts. The current code run more often than needed
         # and do not use caches as much as it could.  The current focus is on
         # the behavior of the feature so we disable it by default. The flag
         # will be removed when we are happy with the performance impact.
         #
         # Once this feature is no longer experimental move the following
         # documentation to the appropriate help section:
         #
         # The ``HG_TAG_MOVED`` variable will be set if the transaction touched
         # tags (new or changed or deleted tags). In addition the details of
         # these changes are made available in a file at:
         #     ``REPOROOT/.hg/changes/tags.changes``.
         # Make sure you check for HG_TAG_MOVED before reading that file as it
         # might exist from a previous transaction even if no tag were touched
         # in this one. Changes are recorded in a line base format::
         #
         #     <action> <hex-node> <tag-name>\n
         #
         # Actions are defined as follow:
         #   "-R": tag is removed,
         #   "+A": tag is added,
         #   "-M": tag is moved (old value),
         #   "+M": tag is moved (new value),
         tracktags = lambda x: None
         # experimental config: experimental.hook-track-tags
         shouldtracktags = self.ui.configbool('experimental', 'hook-track-tags')
         if desc != 'strip' and shouldtracktags:
             oldheads = self.changelog.headrevs()
             def tracktags(tr2):
                 repo = reporef()
                 oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads)
                 newheads = repo.changelog.headrevs()
                 newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads)
                 # notes: we compare lists here.
                 # As we do it only once buiding set would not be cheaper
                 changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes)
                 if changes:
                     tr2.hookargs['tag_moved'] = '1'
                     with repo.vfs('changes/tags.changes', 'w',
                                   atomictemp=True) as changesfile:
                         # note: we do not register the file to the transaction
                         # because we needs it to still exist on the transaction
                         # is close (for txnclose hooks)
                         tagsmod.writediff(changesfile, changes)
         def validate(tr2):
             """will run pre-closing hooks"""
             # XXX the transaction API is a bit lacking here so we take a hacky
             # path for now
             #
             # We cannot add this as a "pending" hooks since the 'tr.hookargs'
             # dict is copied before these run. In addition we needs the data
             # available to in memory hooks too.
             #
             # Moreover, we also need to make sure this runs before txnclose
             # hooks and there is no "pending" mechanism that would execute
             # logic only if hooks are about to run.
             #
             # Fixing this limitation of the transaction is also needed to track
             # other families of changes (bookmarks, phases, obsolescence).
             #
             # This will have to be fixed before we remove the experimental
             # gating.
             tracktags(tr2)
             repo = reporef()
             if repo.ui.configbool('experimental', 'single-head-per-branch'):
                 scmutil.enforcesinglehead(repo, tr2, desc)
             if hook.hashook(repo.ui, 'pretxnclose-bookmark'):
                 for name, (old, new) in sorted(tr.changes['bookmarks'].items()):
                     args = tr.hookargs.copy()
                     args.update(bookmarks.preparehookargs(name, old, new))
                     repo.hook('pretxnclose-bookmark', throw=True,
                               **pycompat.strkwargs(args))
             if hook.hashook(repo.ui, 'pretxnclose-phase'):
                 cl = repo.unfiltered().changelog
                 for rev, (old, new) in tr.changes['phases'].items():
                     args = tr.hookargs.copy()
                     node = hex(cl.node(rev))
                     args.update(phases.preparehookargs(node, old, new))
                     repo.hook('pretxnclose-phase', throw=True,
                               **pycompat.strkwargs(args))
 
             repo.hook('pretxnclose', throw=True,
                       **pycompat.strkwargs(tr.hookargs))
         def releasefn(tr, success):
             repo = reporef()
             if repo is None:
                 # If the repo has been GC'd (and this release function is being
                 # called from transaction.__del__), there's not much we can do,
                 # so just leave the unfinished transaction there and let the
                 # user run `hg recover`.
                 return
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 narrowspec.restorebackup(self, 'journal.narrowspec')
                 narrowspec.restorewcbackup(self, 'journal.narrowspec.dirstate')
                 repo.dirstate.restorebackup(None, 'journal.dirstate')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(rp, self.svfs, vfsmap,
                                      "journal",
                                      "undo",
                                      aftertrans(renames),
                                      self.store.createmode,
                                      validator=validate,
                                      releasefn=releasefn,
                                      checkambigfiles=_cachedfiles,
                                      name=desc)
         tr.changes['origrepolen'] = len(self)
         tr.changes['obsmarkers'] = set()
         tr.changes['phases'] = {}
         tr.changes['bookmarks'] = {}
 
         tr.hookargs['txnid'] = txnid
         tr.hookargs['txnname'] = desc
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize('flush-fncache', self.store.write)
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run
             """
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hookfunc():
                 repo = reporef()
                 if hook.hashook(repo.ui, 'txnclose-bookmark'):
                     bmchanges = sorted(tr.changes['bookmarks'].items())
                     for name, (old, new) in bmchanges:
                         args = tr.hookargs.copy()
                         args.update(bookmarks.preparehookargs(name, old, new))
                         repo.hook('txnclose-bookmark', throw=False,
                                   **pycompat.strkwargs(args))
 
                 if hook.hashook(repo.ui, 'txnclose-phase'):
                     cl = repo.unfiltered().changelog
                     phasemv = sorted(tr.changes['phases'].items())
                     for rev, (old, new) in phasemv:
                         args = tr.hookargs.copy()
                         node = hex(cl.node(rev))
                         args.update(phases.preparehookargs(node, old, new))
                         repo.hook('txnclose-phase', throw=False,
                                   **pycompat.strkwargs(args))
 
                 repo.hook('txnclose', throw=False,
                           **pycompat.strkwargs(hookargs))
             reporef()._afterlock(hookfunc)
         tr.addfinalize('txnclose-hook', txnclosehook)
         # Include a leading "-" to make it happen before the transaction summary
         # reports registered via scmutil.registersummarycallback() whose names
         # are 00-txnreport etc. That way, the caches will be warm when the
         # callbacks run.
         tr.addpostclose('-warm-cache', self._buildcacheupdater(tr))
         def txnaborthook(tr2):
             """To be run if transaction is aborted
             """
             reporef().hook('txnabort', throw=False,
                            **pycompat.strkwargs(tr2.hookargs))
         tr.addabort('txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose('refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         scmutil.registersummarycallback(self, tr, desc)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.svfs, 'journal.narrowspec'),
                 (self.vfs, 'journal.narrowspec.dirstate'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (bookmarks.bookmarksvfs(self), 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     @unfilteredmethod
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, 'journal.dirstate')
         narrowspec.savewcbackup(self, 'journal.narrowspec.dirstate')
         narrowspec.savebackup(self, 'journal.narrowspec')
         self.vfs.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.vfs.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         bookmarksvfs.write("journal.bookmarks",
                            bookmarksvfs.tryread("bookmarks"))
         self.svfs.write("journal.phaseroots",
                            self.svfs.tryread("phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 vfsmap = {'': self.svfs,
                           'plain': self.vfs,}
                 transaction.rollback(self.svfs, vfsmap, "journal",
                                      self.ui.warn,
                                      checkambigfiles=_cachedfiles)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 dsguard = dirstateguard.dirstateguard(self, 'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise error.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {'plain': self.vfs, '': self.svfs}
         transaction.rollback(self.svfs, vfsmap, 'undo', ui.warn,
                              checkambigfiles=_cachedfiles)
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         if bookmarksvfs.exists('undo.bookmarks'):
             bookmarksvfs.rename('undo.bookmarks', 'bookmarks', checkambig=True)
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots', checkambig=True)
         self.invalidate()
 
         parentgone = any(p not in self.changelog.nodemap for p in parents)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, 'undo.narrowspec')
             narrowspec.restorewcbackup(self, 'undo.narrowspec.dirstate')
             self.dirstate.restorebackup(None, 'undo.dirstate')
             try:
                 branch = self.vfs.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
             mergemod.mergestate.clean(self, self['.'].node())
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def _buildcacheupdater(self, newtransaction):
         """called during transaction to build the callback updating cache
 
         Lives on the repository to help extension who might want to augment
         this logic. For this purpose, the created transaction is passed to the
         method.
         """
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         def updater(tr):
             repo = reporef()
             repo.updatecaches(tr)
         return updater
 
     @unfilteredmethod
     def updatecaches(self, tr=None, full=False):
         """warm appropriate caches
 
         If this function is called after a transaction closed. The transaction
         will be available in the 'tr' argument. This can be used to selectively
         update caches relevant to the changes in that transaction.
 
         If 'full' is set, make sure all caches the function knows about have
         up-to-date data. Even the ones usually loaded more lazily.
         """
         if tr is not None and tr.hookargs.get('source') == 'strip':
             # During strip, many caches are invalid but
             # later call to `destroyed` will refresh them.
             return
 
         if tr is None or tr.changes['origrepolen'] < len(self):
             # accessing the 'ser ved' branchmap should refresh all the others,
             self.ui.debug('updating the branch cache\n')
             self.filtered('served').branchmap()
             self.filtered('served.hidden').branchmap()
 
         if full:
             unfi = self.unfiltered()
             rbc = unfi.revbranchcache()
             for r in unfi.changelog:
                 rbc.branchinfo(r)
             rbc.write()
 
             # ensure the working copy parents are in the manifestfulltextcache
             for ctx in self['.'].parents():
                 ctx.manifest()  # accessing the manifest is enough
 
             # accessing fnode cache warms the cache
             tagsmod.fnoderevs(self.ui, unfi, unfi.changelog.revs())
             # accessing tags warm the cache
             self.tags()
             self.filtered('served').tags()
 
             # The `full` arg is documented as updating even the lazily-loaded
             # caches immediately, so we're forcing a write to cause these caches
             # to be warmed up even if they haven't explicitly been requested
             # yet (if they've never been used by hg, they won't ever have been
             # written, even if they're a subset of another kind of cache that
             # *has* been used).
             for filt in repoview.filtertable.keys():
                 filtered = self.filtered(filt)
                 filtered.branchmap().write(filtered)
 
     def invalidatecaches(self):
 
         if r'_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__[r'_tagscache']
 
         self._branchcaches.clear()
         self.invalidatevolatilesets()
         self._sparsesignaturecache.clear()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, r'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), r'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
             if (k == 'changelog' and
                 self.currenttransaction() and
                 self.changelog._delayed):
                 # The changelog object may store unwritten revisions. We don't
                 # want to lose them.
                 # TODO: Solve the problem instead of working around it.
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             k = pycompat.sysstr(k)
             if k == r'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(self, vfs, lockname, wait, releasefn, acquirefn, desc,
               inheritchecker=None, parentenvvar=None):
         parentlock = None
         # the contents of parentenvvar are used by the underlying lock to
         # determine whether it can be inherited
         if parentenvvar is not None:
             parentlock = encoding.environ.get(parentenvvar)
 
         timeout = 0
         warntimeout = 0
         if wait:
             timeout = self.ui.configint("ui", "timeout")
             warntimeout = self.ui.configint("ui", "timeout.warn")
         # internal config: ui.signal-safe-lock
         signalsafe = self.ui.configbool('ui', 'signal-safe-lock')
 
         l = lockmod.trylock(self.ui, vfs, lockname, timeout, warntimeout,
                             releasefn=releasefn,
                             acquirefn=acquirefn, desc=desc,
                             inheritchecker=inheritchecker,
                             parentlock=parentlock,
                             signalsafe=signalsafe)
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else: # no lock have been found.
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(vfs=self.svfs,
                        lockname="lock",
                        wait=wait,
                        releasefn=None,
                        acquirefn=self.invalidate,
                        desc=_('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def _wlockchecktransaction(self):
         if self.currenttransaction() is not None:
             raise error.LockInheritanceContractViolation(
                 'wlock cannot be inherited in the middle of a transaction')
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (self.ui.configbool('devel', 'all-warnings')
                      or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn('"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.vfs, "wlock", wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot,
                        inheritchecker=self._wlockchecktransaction,
                        parentenvvar='HG_WLOCK_LOCKER')
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist,
                     includecopymeta):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = manifest2.get(fname, nullid)
         if isinstance(fctx, context.filectx):
             node = fctx.filenode()
             if node in [fparent1, fparent2]:
                 self.ui.debug('reusing %s filelog entry\n' % fname)
                 if ((fparent1 != nullid and
                      manifest1.flags(fname) != fctx.flags()) or
                     (fparent2 != nullid and
                      manifest2.flags(fname) != fctx.flags())):
                     changelist.append(fname)
                 return node
 
         flog = self.file(fname)
         meta = {}
         cfname = fctx.copysource()
         if cfname and cfname != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cnode = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or cnode is None: # copied on remote side
                     if cfname in manifest2:
                         cnode = manifest2[cfname]
                         newfparent = fparent1
 
             # Here, we used to search backwards through history to try to find
             # where the file copy came from if the source of a copy was not in
             # the parent directory. However, this doesn't actually make sense to
             # do (what does a copy from something not in your working copy even
             # mean?) and it causes bugs (eg, issue4476). Instead, we will warn
             # the user that copy information was dropped, so if they didn't
             # expect this outcome it can be fixed, but this is the correct
             # behavior in this circumstance.
 
             if cnode:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(cnode)))
                 if includecopymeta:
                     meta["copy"] = cfname
                     meta["copyrev"] = hex(cnode)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         text = fctx.data()
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
         # are just the flags changed during merge?
         elif fname in manifest1 and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def checkcommitpatterns(self, wctx, vdirs, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == '.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _('file not found!'))
                 if f in vdirs: # visited directory
                     d = f + '/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _("no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _("file not tracked!"))
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra=None):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always()
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         # lock() for recent changelog (see issue4368)
         with self.wlock(), self.lock():
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and not match.always():
                 raise error.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(status.clean) # mq may commit clean files
 
             # check subrepos
             subs, commitsubs, newstate = subrepoutil.precommit(
                 self.ui, wctx, status, match, force=force)
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, vdirs, match, status, fail)
 
             cctx = context.workingcommitctx(self, status,
                                             text, user, date, extra)
 
             # internal config: ui.allowemptycommit
             allowemptycommit = (wctx.branch() != wctx.p1().branch()
                                 or extra.get('close') or merge or cctx.files()
                                 or self.ui.configbool('ui', 'allowemptycommit'))
             if not allowemptycommit:
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 uipathfn = scmutil.getuipathfn(self)
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                                    uipathfn(subrepoutil.subrelpath(sub)))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepoutil.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 with self.transaction('commit'):
                     ret = self.commitctx(cctx, True)
                     # update bookmarks, dirstate and mergestate
                     bookmarks.update(self, [p1, p2], ret)
                     cctx.markcommitted(ret)
                     ms.reset()
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
         def commithook():
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook("commit", node=hex(ret), parent1=hookp1,
                           parent2=hookp2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False, origctx=None):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
 
         ctx.files() should list all files involved in this commit, i.e.
         modified/added/removed files. On merge, it may be wider than the
         ctx.files() to be committed, since any file nodes derived directly
         from p1 or p2 are excluded from the committed ctx.files().
 
         origctx is for convert to work around the problem that bug
         fixes to the files list in changesets change hashes. For
         convert to be the identity, it can pass an origctx and this
         function will use the same files list when it makes sense to
         do so.
         """
 
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         writecopiesto = self.ui.config('experimental', 'copies.write-to')
         writefilecopymeta = writecopiesto != 'changeset-only'
         writechangesetcopy = (writecopiesto in
                               ('changeset-only', 'compatibility'))
         p1copies, p2copies = None, None
         if writechangesetcopy:
             p1copies = ctx.p1copies()
             p2copies = ctx.p2copies()
         filesadded, filesremoved = None, None
         with self.lock(), self.transaction("commit") as tr:
             trp = weakref.proxy(tr)
 
             if ctx.manifestnode():
                 # reuse an existing manifest revision
                 self.ui.debug('reusing known manifest\n')
                 mn = ctx.manifestnode()
                 files = ctx.files()
                 if writechangesetcopy:
                     filesadded = ctx.filesadded()
                     filesremoved = ctx.filesremoved()
             elif ctx.files():
                 m1ctx = p1.manifestctx()
                 m2ctx = p2.manifestctx()
                 mctx = m1ctx.copy()
 
                 m = mctx.read()
                 m1 = m1ctx.read()
                 m2 = m2ctx.read()
 
                 # check in files
                 added = []
                 changed = []
                 removed = list(ctx.removed())
                 linkrev = len(self)
                 self.ui.note(_("committing files:\n"))
                 uipathfn = scmutil.getuipathfn(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(uipathfn(f) + "\n")
                     try:
                         fctx = ctx[f]
                         if fctx is None:
                             removed.append(f)
                         else:
                             added.append(f)
                             m[f] = self._filecommit(fctx, m1, m2, linkrev,
                                                     trp, changed,
                                                     writefilecopymeta)
                             m.setflag(f, fctx.flags())
                     except OSError:
                         self.ui.warn(_("trouble committing %s!\n") %
                                      uipathfn(f))
                         raise
                     except IOError as inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") %
                                          uipathfn(f))
                         raise
 
                 # update manifest
                 removed = [f for f in removed if f in m1 or f in m2]
                 drop = sorted([f for f in removed if f in m])
                 for f in drop:
                     del m[f]
                 if p2.rev() != nullrev:
                     @util.cachefunc
                     def mas():
                         p1n = p1.node()
                         p2n = p2.node()
                         cahs = self.changelog.commonancestorsheads(p1n, p2n)
                         if not cahs:
                             cahs = [nullrev]
                         return [self[r].manifest() for r in cahs]
                     def deletionfromparent(f):
                         # When a file is removed relative to p1 in a merge, this
                         # function determines whether the absence is due to a
                         # deletion from a parent, or whether the merge commit
                         # itself deletes the file. We decide this by doing a
                         # simplified three way merge of the manifest entry for
                         # the file. There are two ways we decide the merge
                         # itself didn't delete a file:
                         # - neither parent (nor the merge) contain the file
                         # - exactly one parent contains the file, and that
                         #   parent has the same filelog entry as the merge
                         #   ancestor (or all of them if there two). In other
                         #   words, that parent left the file unchanged while the
                         #   other one deleted it.
                         # One way to think about this is that deleting a file is
                         # similar to emptying it, so the list of changed files
                         # should be similar either way. The computation
                         # described above is not done directly in _filecommit
                         # when creating the list of changed files, however
                         # it does something very similar by comparing filelog
                         # nodes.
                         if f in m1:
                             return (f not in m2
                                     and all(f in ma and ma.find(f) == m1.find(f)
                                             for ma in mas()))
                         elif f in m2:
                             return all(f in ma and ma.find(f) == m2.find(f)
                                        for ma in mas())
                         else:
                             return True
                     removed = [f for f in removed if not deletionfromparent(f)]
 
                 files = changed + removed
                 md = None
                 if not files:
                     # if no "files" actually changed in terms of the changelog,
                     # try hard to detect unmodified manifest entry so that the
                     # exact same commit can be reproduced later on convert.
                     md = m1.diff(m, scmutil.matchfiles(self, ctx.files()))
                 if not files and md:
                     self.ui.debug('not reusing manifest (no file change in '
                                   'changelog, but manifest differs)\n')
                 if files or md:
                     self.ui.note(_("committing manifest\n"))
                     # we're using narrowmatch here since it's already applied at
                     # other stages (such as dirstate.walk), so we're already
                     # ignoring things outside of narrowspec in most cases. The
                     # one case where we might have files outside the narrowspec
                     # at this point is merges, and we already error out in the
                     # case where the merge has files outside of the narrowspec,
                     # so this is safe.
                     mn = mctx.write(trp, linkrev,
                                     p1.manifestnode(), p2.manifestnode(),
                                     added, drop, match=self.narrowmatch())
 
                     if writechangesetcopy:
                         filesadded = [f for f in changed
                                       if not (f in m1 or f in m2)]
                         filesremoved = removed
                 else:
                     self.ui.debug('reusing manifest from p1 (listed files '
                                   'actually unchanged)\n')
                     mn = p1.manifestnode()
             else:
                 self.ui.debug('reusing manifest from p1 (no file change)\n')
                 mn = p1.manifestnode()
                 files = []
 
             if writecopiesto == 'changeset-only':
                 # If writing only to changeset extras, use None to indicate that
                 # no entry should be written. If writing to both, write an empty
                 # entry to prevent the reader from falling back to reading
                 # filelogs.
                 p1copies = p1copies or None
                 p2copies = p2copies or None
                 filesadded = filesadded or None
                 filesremoved = filesremoved or None
 
             if origctx and origctx.manifestnode() == mn:
                 files = origctx.files()
 
             # update changelog
             self.ui.note(_("committing changelog\n"))
             self.changelog.delayupdate(tr)
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy(),
                                    p1copies, p2copies, filesadded, filesremoved)
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             # set the new commit is proper phase
             targetphase = subrepoutil.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.registernew(self, tr, targetphase, [n])
             return n
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # refresh all repository caches
         self.updatecaches()
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(node2, match, ignored, clean, unknown,
                                   listsubrepos)
 
     def addpostdsstatus(self, ps):
         """Add a callback to run within the wlock, at the point at which status
         fixups happen.
 
         On status completion, callback(wctx, status) will be called with the
         wlock held, unless the dirstate has changed from underneath or the wlock
         couldn't be grabbed.
 
         Callbacks should not capture and use a cached copy of the dirstate --
         it might change in the meanwhile. Instead, they should access the
         dirstate via wctx.repo().dirstate.
 
         This list is emptied out after each status run -- extensions should
         make sure it adds to this list each time dirstate.status is called.
         Extensions should also make sure they don't call this for statuses
         that don't involve the dirstate.
         """
 
         # The list is located here for uniqueness reasons -- it is actually
         # managed by the workingctx, but that isn't unique per-repo.
         self._postdsstatus.append(ps)
 
     def postdsstatus(self):
         """Used by workingctx to get the list of post-dirstate-status hooks."""
         return self._postdsstatus
 
     def clearpostdsstatus(self):
         """Used by workingctx to clear post-dirstate-status hooks."""
         del self._postdsstatus[:]
 
     def heads(self, start=None):
         if start is None:
             cl = self.changelog
             headrevs = reversed(cl.headrevs())
             return [cl.node(rev) for rev in headrevs]
 
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if not branches.hasbranch(branch):
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs = pycompat.strkwargs(hookargs)
             hookargs[r'namespace'] = namespace
             hookargs[r'key'] = key
             hookargs[r'old'] = old
             hookargs[r'new'] = new
             self.hook('prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_("pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_("(%s)\n") % exc.hint)
             return False
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         def runhook():
             self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                       ret=ret)
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def savecommitmessage(self, text):
         fp = self.vfs('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             # if src and dest refer to a same file, vfs.rename is a no-op,
             # leaving both src and dest on disk. delete dest to make sure
             # the rename couldn't be such a no-op.
             vfs.tryunlink(dest)
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create, intents=None, createopts=None):
     localpath = util.urllocalpath(path)
     if create:
         createrepository(ui, localpath, createopts=createopts)
 
     return makelocalrepository(ui, localpath, intents=intents)
 
 def islocal(path):
     return True
 
 def defaultcreateopts(ui, createopts=None):
     """Populate the default creation options for a repository.
 
     A dictionary of explicitly requested creation options can be passed
     in. Missing keys will be populated.
     """
     createopts = dict(createopts or {})
 
     if 'backend' not in createopts:
         # experimental config: storage.new-repo-backend
         createopts['backend'] = ui.config('storage', 'new-repo-backend')
 
     return createopts
 
 def newreporequirements(ui, createopts):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     # If the repo is being created from a shared repository, we copy
     # its requirements.
     if 'sharedrepo' in createopts:
         requirements = set(createopts['sharedrepo'].requirements)
         if createopts.get('sharedrelative'):
             requirements.add('relshared')
         else:
             requirements.add('shared')
 
         return requirements
 
     if 'backend' not in createopts:
         raise error.ProgrammingError('backend key not present in createopts; '
                                      'was defaultcreateopts() called?')
 
     if createopts['backend'] != 'revlogv1':
         raise error.Abort(_('unable to determine repository requirements for '
                             'storage backend: %s') % createopts['backend'])
 
     requirements = {'revlogv1'}
     if ui.configbool('format', 'usestore'):
         requirements.add('store')
         if ui.configbool('format', 'usefncache'):
             requirements.add('fncache')
             if ui.configbool('format', 'dotencode'):
                 requirements.add('dotencode')
 
     compengine = ui.config('format', 'revlog-compression')
     if compengine not in util.compengines:
         raise error.Abort(_('compression engine %s defined by '
                             'format.revlog-compression not available') %
                           compengine,
                           hint=_('run "hg debuginstall" to list available '
                                  'compression engines'))
 
     # zlib is the historical default and doesn't need an explicit requirement.
     elif compengine == 'zstd':
         requirements.add('revlog-compression-zstd')
     elif compengine != 'zlib':
         requirements.add('exp-compression-%s' % compengine)
 
     if scmutil.gdinitconfig(ui):
         requirements.add('generaldelta')
         if ui.configbool('format', 'sparse-revlog'):
             requirements.add(SPARSEREVLOG_REQUIREMENT)
     if ui.configbool('experimental', 'treemanifest'):
         requirements.add('treemanifest')
 
     revlogv2 = ui.config('experimental', 'revlogv2')
     if revlogv2 == 'enable-unstable-format-and-corrupt-my-data':
         requirements.remove('revlogv1')
         # generaldelta is implied by revlogv2.
         requirements.discard('generaldelta')
         requirements.add(REVLOGV2_REQUIREMENT)
     # experimental config: format.internal-phase
     if ui.configbool('format', 'internal-phase'):
         requirements.add('internal-phase')
 
     if createopts.get('narrowfiles'):
         requirements.add(repository.NARROW_REQUIREMENT)
 
     if createopts.get('lfs'):
         requirements.add('lfs')
 
     if ui.configbool('format', 'bookmarks-in-store'):
         requirements.add(bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT)
 
     return requirements
 
 def filterknowncreateopts(ui, createopts):
     """Filters a dict of repo creation options against options that are known.
 
     Receives a dict of repo creation options and returns a dict of those
     options that we don't know how to handle.
 
     This function is called as part of repository creation. If the
     returned dict contains any items, repository creation will not
     be allowed, as it means there was a request to create a repository
     with options not recognized by loaded code.
 
     Extensions can wrap this function to filter out creation options
     they know how to handle.
     """
     known = {
         'backend',
         'lfs',
         'narrowfiles',
         'sharedrepo',
         'sharedrelative',
         'shareditems',
         'shallowfilestore',
     }
 
     return {k: v for k, v in createopts.items() if k not in known}
 
 def createrepository(ui, path, createopts=None):
     """Create a new repository in a vfs.
 
     ``path`` path to the new repo's working directory.
     ``createopts`` options for the new repository.
 
     The following keys for ``createopts`` are recognized:
 
     backend
        The storage backend to use.
     lfs
        Repository will be created with ``lfs`` requirement. The lfs extension
        will automatically be loaded when the repository is accessed.
     narrowfiles
        Set up repository to support narrow file storage.
     sharedrepo
        Repository object from which storage should be shared.
     sharedrelative
        Boolean indicating if the path to the shared repo should be
        stored as relative. By default, the pointer to the "parent" repo
        is stored as an absolute path.
     shareditems
        Set of items to share to the new repository (in addition to storage).
     shallowfilestore
        Indicates that storage for files should be shallow (not all ancestor
        revisions are known).
     """
     createopts = defaultcreateopts(ui, createopts=createopts)
 
     unknownopts = filterknowncreateopts(ui, createopts)
 
     if not isinstance(unknownopts, dict):
         raise error.ProgrammingError('filterknowncreateopts() did not return '
                                      'a dict')
 
     if unknownopts:
         raise error.Abort(_('unable to create repository because of unknown '
                             'creation option: %s') %
                           ', '.join(sorted(unknownopts)),
                           hint=_('is a required extension not loaded?'))
 
     requirements = newreporequirements(ui, createopts=createopts)
 
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     hgvfs = vfsmod.vfs(wdirvfs.join(b'.hg'))
     if hgvfs.exists():
         raise error.RepoError(_('repository %s already exists') % path)
 
     if 'sharedrepo' in createopts:
         sharedpath = createopts['sharedrepo'].sharedpath
 
         if createopts.get('sharedrelative'):
             try:
                 sharedpath = os.path.relpath(sharedpath, hgvfs.base)
             except (IOError, ValueError) as e:
                 # ValueError is raised on Windows if the drive letters differ
                 # on each path.
                 raise error.Abort(_('cannot calculate relative path'),
                                   hint=stringutil.forcebytestr(e))
 
     if not wdirvfs.exists():
         wdirvfs.makedirs()
 
     hgvfs.makedir(notindexed=True)
     if 'sharedrepo' not in createopts:
         hgvfs.mkdir(b'cache')
     hgvfs.mkdir(b'wcache')
 
     if b'store' in requirements and 'sharedrepo' not in createopts:
         hgvfs.mkdir(b'store')
 
         # We create an invalid changelog outside the store so very old
         # Mercurial versions (which didn't know about the requirements
         # file) encounter an error on reading the changelog. This
         # effectively locks out old clients and prevents them from
         # mucking with a repo in an unknown format.
         #
         # The revlog header has version 2, which won't be recognized by
         # such old clients.
         hgvfs.append(b'00changelog.i',
                      b'\0\0\0\2 dummy changelog to prevent using the old repo '
                      b'layout')
 
     scmutil.writerequires(hgvfs, requirements)
 
     # Write out file telling readers where to find the shared store.
     if 'sharedrepo' in createopts:
         hgvfs.write(b'sharedpath', sharedpath)
 
     if createopts.get('shareditems'):
         shared = b'\n'.join(sorted(createopts['shareditems'])) + b'\n'
         hgvfs.write(b'shared', shared)
 
 def poisonrepository(repo):
     """Poison a repository instance so it can no longer be used."""
     # Perform any cleanup on the instance.
     repo.close()
 
     # Our strategy is to replace the type of the object with one that
     # has all attribute lookups result in error.
     #
     # But we have to allow the close() method because some constructors
     # of repos call close() on repo references.
     class poisonedrepository(object):
         def __getattribute__(self, item):
             if item == r'close':
                 return object.__getattribute__(self, item)
 
             raise error.ProgrammingError('repo instances should not be used '
                                          'after unshare')
 
         def close(self):
             pass
 
     # We may have a repoview, which intercepts __setattr__. So be sure
     # we operate at the lowest level possible.
     object.__setattr__(repo, r'__class__', poisonedrepository)

mercurial/manifest.py

@@ -1,2103 +1,2105
 # manifest.py - manifest revision class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import heapq
 import itertools
 import struct
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     error,
     mdiff,
     policy,
     pycompat,
-    repository,
     revlog,
     util,
 )
+from .interfaces import (
+    repository,
+)
 from .utils import (
     interfaceutil,
 )
 
 parsers = policy.importmod(r'parsers')
 propertycache = util.propertycache
 
 # Allow tests to more easily test the alternate path in manifestdict.fastdelta()
 FASTDELTA_TEXTDIFF_THRESHOLD = 1000
 
 def _parse(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1:] != '\n':
         raise ValueError('Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError('Manifest lines not in sorted order.')
         prev = l
         f, n = l.split('\0')
         if len(n) > 40:
             yield f, bin(n[:40]), n[40:]
         else:
             yield f, bin(n), ''
 
 def _text(it):
     files = []
     lines = []
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append("%s\0%s%s\n" % (f, hex(n), fl))
 
     _checkforbidden(files)
     return ''.join(lines)
 
 class lazymanifestiter(object):
     def __init__(self, lm):
         self.pos = 0
         self.lm = lm
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data[0]
         self.pos += 1
         zeropos = data.find('\x00', pos)
         return data[pos:zeropos]
 
     __next__ = next
 
 class lazymanifestiterentries(object):
     def __init__(self, lm):
         self.lm = lm
         self.pos = 0
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data
         zeropos = data.find('\x00', pos)
         hashval = unhexlify(data, self.lm.extrainfo[self.pos],
                             zeropos + 1, 40)
         flags = self.lm._getflags(data, self.pos, zeropos)
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
     __next__ = next
 
 def unhexlify(data, extra, pos, length):
     s = bin(data[pos:pos + length])
     if extra:
         s += chr(extra & 0xff)
     return s
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 class _lazymanifest(object):
     """A pure python manifest backed by a byte string.  It is supplimented with
     internal lists as it is modified, until it is compacted back to a pure byte
     string.
 
     ``data`` is the initial manifest data.
 
     ``positions`` is a list of offsets, one per manifest entry.  Positive
     values are offsets into ``data``, negative values are offsets into the
     ``extradata`` list.  When an entry is removed, its entry is dropped from
     ``positions``.  The values are encoded such that when walking the list and
     indexing into ``data`` or ``extradata`` as appropriate, the entries are
     sorted by filename.
 
     ``extradata`` is a list of (key, hash, flags) for entries that were added or
     modified since the manifest was created or compacted.
     """
     def __init__(self, data, positions=None, extrainfo=None, extradata=None,
                  hasremovals=False):
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
             self.hasremovals = False
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
             self.hasremovals = hasremovals
 
     def findlines(self, data):
         if not data:
             return []
         pos = data.find("\n")
         if pos == -1 or data[-1:] != '\n':
             raise ValueError("Manifest did not end in a newline.")
         positions = [0]
         prev = data[:data.find('\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1:data.find('\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError("Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find("\n", pos + 1)
         return positions
 
     def _get(self, index):
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos):
         if pos >= 0:
             return self.data[pos:self.data.find('\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key):
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key):
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key):
         return self.bsearch(key) != -1
 
     def _getflags(self, data, needle, pos):
         start = pos + 41
         end = data.find("\n", start)
         if end == -1:
             end = len(data) - 1
         if start == end:
             return ''
         return self.data[start:end]
 
     def __getitem__(self, key):
         if not isinstance(key, bytes):
             raise TypeError("getitem: manifest keys must be a bytes.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             return (data[1], data[2])
         zeropos = data.find('\x00', pos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, 40)
         flags = self._getflags(data, needle, zeropos)
         return (hashval, flags)
 
     def __delitem__(self, key):
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1:]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
         if cur >= 0:
             # This does NOT unsort the list as far as the search functions are
             # concerned, as they only examine lines mapped by self.positions.
             self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]
             self.hasremovals = True
 
     def __setitem__(self, key, value):
         if not isinstance(key, bytes):
             raise TypeError("setitem: manifest keys must be a byte string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError("Manifest values must be a tuple of (node, flags).")
         hashval = value[0]
         if not isinstance(hashval, bytes) or not 20 <= len(hashval) <= 22:
             raise TypeError("node must be a 20-byte byte string")
         flags = value[1]
         if len(hashval) == 22:
             hashval = hashval[:-1]
         if not isinstance(flags, bytes) or len(flags) > 1:
             raise TypeError("flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (self.positions[:needle] + [-len(self.extradata)]
                               + self.positions[needle:])
             self.extrainfo = (self.extrainfo[:needle] + [0] +
                               self.extrainfo[needle:])
 
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(self.data, self.positions, self.extrainfo,
             self.extradata, self.hasremovals)
 
     def _compact(self):
         # hopefully not called TOO often
         if len(self.extradata) == 0 and not self.hasremovals:
             return
         l = []
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
 
                 # Collect all contiguous entries in the buffer at the current
                 # offset, breaking out only for added/modified items held in
                 # extradata, or a deleted line prior to the next position.
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
 
                     # A removed file has no positions[] entry, but does have an
                     # overwritten first byte.  Break out and find the end of the
                     # current good entry/entries if there is a removed file
                     # before the next position.
                     if (self.hasremovals
                         and self.data.find('\n\x00', cur,
                                            self.positions[i]) != -1):
                         break
 
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find('\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     if len(t[1]) > 20:
                         self.extrainfo[i] = ord(t[1][21])
                     offset += len(l[-1])
                     i += 1
         self.data = ''.join(l)
         self.hasremovals = False
         self.extradata = []
 
     def _pack(self, d):
         return d[0] + '\x00' + hex(d[1][:20]) + d[2] + '\n'
 
     def text(self):
         self._compact()
         return self.data
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, '')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, ''), (e2, flags)
 
         return diff
 
     def iterentries(self):
         return lazymanifestiterentries(self)
 
     def iterkeys(self):
         return lazymanifestiter(self)
 
     def __iter__(self):
         return lazymanifestiter(self)
 
     def __len__(self):
         return len(self.positions)
 
     def filtercopy(self, filterfn):
         # XXX should be optimized
         c = _lazymanifest('')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 @interfaceutil.implementer(repository.imanifestdict)
 class manifestdict(object):
     def __init__(self, data=''):
         self._lm = _lazymanifest(data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __nonzero__(self):
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     __bool__ = __nonzero__
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key, '')
 
     def __contains__(self, key):
         if key is None:
             return False
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
         diff = self.diff(m2)
         files = set(filepath
                     for filepath, hashflags in diff.iteritems()
                     if hashflags[1][0] is None)
         return files
 
     @propertycache
     def _dirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         '''Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files.'''
         files = match.files()
         return (len(files) < 100 and (match.isexact() or
             (match.prefix() and all(fn in self for fn in files))))
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard('')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict()
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict()
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key, default=''):
         try:
             return self._lm[key][1]
         except KeyError:
             return default
 
     def copy(self):
         c = manifestdict()
         c._lm = self._lm.copy()
         return c
 
     def items(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iteritems(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self):
         return self._lm.iterentries()
 
     def text(self):
         # most likely uses native version
         return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as a bytearray and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = "%s\0%s%s\n" % (f, hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                                 _("failed to remove %s from manifest") % f)
                     l = ""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, "".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, "".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = bytearray(self.text())
             deltatext = mdiff.textdiff(
                 util.buffer(base), util.buffer(arraytext))
 
         return arraytext, deltatext
 
 def _msearch(m, s, lo=0, hi=None):
     '''return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer, a memoryview or a byte string.
     s is a byte string'''
     def advance(i, c):
         while i < lenm and m[i:i + 1] != c:
             i += 1
         return i
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1:start] != '\n':
             start -= 1
         end = advance(start, '\0')
         if bytes(m[start:end]) < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, '\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, '\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, '\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if '\n' in f or '\r' in f:
             raise error.StorageError(
                 _("'\\n' and '\\r' disallowed in filenames: %r")
                 % pycompat.bytestr(f))
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = "".join(struct.pack(">lll", start, end, len(content))
                    + content for start, end, content in x)
     return deltatext, newaddlist
 
 def _splittopdir(f):
     if '/' in f:
         dir, subpath = f.split('/', 1)
         return dir + '/', subpath
     else:
         return '', f
 
 _noop = lambda s: None
 
 class treemanifest(object):
     def __init__(self, dir='', text=''):
         self._dir = dir
         self._node = nullid
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         self._lazydirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
             def readsubtree(subdir, subm):
                 raise AssertionError('treemanifest constructor only accepts '
                                      'flat manifests')
             self.parse(text, readsubtree)
             self._dirty = True # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def _loadalllazy(self):
         selfdirs = self._dirs
         for d, (path, node, readsubtree, docopy) in self._lazydirs.iteritems():
             if docopy:
                 selfdirs[d] = readsubtree(path, node).copy()
             else:
                 selfdirs[d] = readsubtree(path, node)
         self._lazydirs = {}
 
     def _loadlazy(self, d):
         v = self._lazydirs.get(d)
         if v:
             path, node, readsubtree, docopy = v
             if docopy:
                 self._dirs[d] = readsubtree(path, node).copy()
             else:
                 self._dirs[d] = readsubtree(path, node)
             del self._lazydirs[d]
 
     def _loadchildrensetlazy(self, visit):
         if not visit:
             return None
         if visit == 'all' or visit == 'this':
             self._loadalllazy()
             return None
 
         loadlazy = self._loadlazy
         for k in visit:
             loadlazy(k + '/')
         return visit
 
     def _loaddifflazy(self, t1, t2):
         """load items in t1 and t2 if they're needed for diffing.
 
         The criteria currently is:
         - if it's not present in _lazydirs in either t1 or t2, load it in the
           other (it may already be loaded or it may not exist, doesn't matter)
         - if it's present in _lazydirs in both, compare the nodeid; if it
           differs, load it in both
         """
         toloadlazy = []
         for d, v1 in t1._lazydirs.iteritems():
             v2 = t2._lazydirs.get(d)
             if not v2 or v2[1] != v1[1]:
                 toloadlazy.append(d)
         for d, v1 in t2._lazydirs.iteritems():
             if d not in t1._lazydirs:
                 toloadlazy.append(d)
 
         for d in toloadlazy:
             t1._loadlazy(d)
             t2._loadlazy(d)
 
     def __len__(self):
         self._load()
         size = len(self._files)
         self._loadalllazy()
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def __nonzero__(self):
         # Faster than "__len() != 0" since it avoids loading sub-manifests
         return not self._isempty()
 
     __bool__ = __nonzero__
 
     def _isempty(self):
         self._load() # for consistency; already loaded by all callers
         # See if we can skip loading everything.
         if self._files or (self._dirs and
                            any(not m._isempty() for m in self._dirs.values())):
             return False
         self._loadalllazy()
         return (not self._dirs or
                 all(m._isempty() for m in self._dirs.values()))
 
     def __repr__(self):
         return ('<treemanifest dir=%s, node=%s, loaded=%s, dirty=%s at 0x%x>' %
                 (self._dir, hex(self._node),
                  bool(self._loadfunc is _noop),
                  self._dirty, id(self)))
 
     def dir(self):
         '''The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory.'''
         return self._dir
 
     def node(self):
         '''This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         '''
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(itertools.chain(self._dirs.items(),
                                            self._files.items())):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, '')
             else:
                 for x in n.iterentries():
                     yield x
 
     def items(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(itertools.chain(self._dirs.items(),
                                            self._files.items())):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in n.iteritems():
                     yield f, sn
 
     iteritems = items
 
     def iterkeys(self):
         self._load()
         self._loadalllazy()
         for p in sorted(itertools.chain(self._dirs, self._files)):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p]:
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return False
 
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return ''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._lazydirs or f in self._dirs:
                 return ''
             return self._flags.get(f, '')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, '')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].__setitem__(subpath, n)
         else:
             self._files[f] = n[:21] # to match manifestdict's behavior
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
             def _copyfunc(s):
                 self._load()
                 s._lazydirs = {d: (p, n, r, True) for
                                d, (p, n, r, c) in self._lazydirs.iteritems()}
                 sdirs = s._dirs
                 for d, v in self._dirs.iteritems():
                     sdirs[d] = v.copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match and not match.always():
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
 
         files = set()
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
             for d, m1 in t1._dirs.iteritems():
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files:
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             self._loadlazy(topdir)
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         dirslash = dir + '/'
         return dirslash in self._dirs or dirslash in self._lazydirs
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard('')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         visit = match.visitchildrenset(self._dir[:-1])
         if not visit:
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         visit = self._loadchildrensetlazy(visit)
         for p in sorted(list(self._dirs) + list(self._files)):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 if not visit or p[:-1] in visit:
                     for f in self._dirs[p]._walk(match):
                         yield f
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         return self._matches(match)
 
     def _matches(self, match):
         '''recursively generate a new manifest filtered by the match argument.
         '''
 
         visit = match.visitchildrenset(self._dir[:-1])
         if visit == 'all':
             return self.copy()
         ret = treemanifest(self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             # While visitchildrenset *usually* lists only subdirs, this is
             # actually up to the matcher and may have some files in the set().
             # If visit == 'this', we should obviously look at the files in this
             # directory; if visit is a set, and fn is in it, we should inspect
             # fn (but no need to inspect things not in the set).
             if visit != 'this' and fn not in visit:
                 continue
             fullp = self._subpath(fn)
             # visitchildrenset isn't perfect, we still need to call the regular
             # matcher code to further filter results.
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         visit = self._loadchildrensetlazy(visit)
         for dir, subm in self._dirs.iteritems():
             if visit and dir[:-1] not in visit:
                 continue
             m = subm._matches(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match and not match.always():
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest()
 
         def _iterativediff(t1, t2, stack):
             """compares two tree manifests and append new tree-manifests which
             needs to be compared to stack"""
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
 
             for d, m1 in t1._dirs.iteritems():
                 m2 = t2._dirs.get(d, emptytree)
                 stack.append((m1, m2))
 
             for d, m2 in t2._dirs.iteritems():
                 if d not in t1._dirs:
                     stack.append((emptytree, m2))
 
             for fn, n1 in t1._files.iteritems():
                 fl1 = t1._flags.get(fn, '')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, '')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in t2._files.iteritems():
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, '')
                     result[t2._subpath(fn)] = ((None, ''), (n2, fl2))
 
         stackls = []
         _iterativediff(self, m2, stackls)
         while stackls:
             t1, t2 = stackls.pop()
             # stackls is populated in the function call
             _iterativediff(t1, t2, stackls)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         selflazy = self._lazydirs
         subpath = self._subpath
         for f, n, fl in _parse(text):
             if fl == 't':
                 f = f + '/'
                 # False below means "doesn't need to be copied" and can use the
                 # cached value from readsubtree directly.
                 selflazy[f] = (subpath(f), n, readsubtree, False)
             elif '/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self):
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries())
 
     def dirtext(self):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         lazydirs = [(d[:-1], v[1], 't') for d, v in self._lazydirs.iteritems()]
         dirs = [(d[:-1], self._dirs[d]._node, 't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files + lazydirs))
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree, match):
         self._load() # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest()
         def getnode(m, d):
             ld = m._lazydirs.get(d)
             if ld:
                 return ld[1]
             return m._dirs.get(d, emptytree)._node
 
         # let's skip investigating things that `match` says we do not need.
         visit = match.visitchildrenset(self._dir[:-1])
         visit = self._loadchildrensetlazy(visit)
         if visit == 'this' or visit == 'all':
             visit = None
         for d, subm in self._dirs.iteritems():
             if visit and d[:-1] not in visit:
                 continue
             subp1 = getnode(m1, d)
             subp2 = getnode(m2, d)
             if subp1 == nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2, match)
 
     def walksubtrees(self, matcher=None):
         """Returns an iterator of the subtrees of this manifest, including this
         manifest itself.
 
         If `matcher` is provided, it only returns subtrees that match.
         """
         if matcher and not matcher.visitdir(self._dir[:-1]):
             return
         if not matcher or matcher(self._dir[:-1]):
             yield self
 
         self._load()
         # OPT: use visitchildrenset to avoid loading everything.
         self._loadalllazy()
         for d, subm in self._dirs.iteritems():
             for subtree in subm.walksubtrees(matcher=matcher):
                 yield subtree
 
 class manifestfulltextcache(util.lrucachedict):
     """File-backed LRU cache for the manifest cache
 
     File consists of entries, up to EOF:
 
     - 20 bytes node, 4 bytes length, <length> manifest data
 
     These are written in reverse cache order (oldest to newest).
 
     """
 
     _file = 'manifestfulltextcache'
 
     def __init__(self, max):
         super(manifestfulltextcache, self).__init__(max)
         self._dirty = False
         self._read = False
         self._opener = None
 
     def read(self):
         if self._read or self._opener is None:
             return
 
         try:
             with self._opener(self._file) as fp:
                 set = super(manifestfulltextcache, self).__setitem__
                 # ignore trailing data, this is a cache, corruption is skipped
                 while True:
                     node = fp.read(20)
                     if len(node) < 20:
                         break
                     try:
                         size = struct.unpack('>L', fp.read(4))[0]
                     except struct.error:
                         break
                     value = bytearray(fp.read(size))
                     if len(value) != size:
                         break
                     set(node, value)
         except IOError:
             # the file is allowed to be missing
             pass
 
         self._read = True
         self._dirty = False
 
     def write(self):
         if not self._dirty or self._opener is None:
             return
         # rotate backwards to the first used node
         with self._opener(self._file, 'w', atomictemp=True, checkambig=True
             ) as fp:
             node = self._head.prev
             while True:
                 if node.key in self._cache:
                     fp.write(node.key)
                     fp.write(struct.pack('>L', len(node.value)))
                     fp.write(node.value)
                 if node is self._head:
                     break
                 node = node.prev
 
     def __len__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__len__()
 
     def __contains__(self, k):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__contains__(k)
 
     def __iter__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__iter__()
 
     def __getitem__(self, k):
         if not self._read:
             self.read()
         # the cache lru order can change on read
         setdirty = self._cache.get(k) is not self._head
         value = super(manifestfulltextcache, self).__getitem__(k)
         if setdirty:
             self._dirty = True
         return value
 
     def __setitem__(self, k, v):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__setitem__(k, v)
         self._dirty = True
 
     def __delitem__(self, k):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__delitem__(k)
         self._dirty = True
 
     def get(self, k, default=None):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).get(k, default=default)
 
     def clear(self, clear_persisted_data=False):
         super(manifestfulltextcache, self).clear()
         if clear_persisted_data:
             self._dirty = True
             self.write()
         self._read = False
 
 # and upper bound of what we expect from compression
 # (real live value seems to be "3")
 MAXCOMPRESSION = 3
 
 @interfaceutil.implementer(repository.imanifeststorage)
 class manifestrevlog(object):
     '''A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     '''
     def __init__(self, opener, tree='', dirlogcache=None, indexfile=None,
                  treemanifest=False):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
 
         `treemanifest` - used to indicate this is a tree manifest revlog. Opener
         options can also be used to make this a tree manifest revlog. The opener
         option takes precedence, so if it is set to True, we ignore whatever
         value is passed in to the constructor.
         """
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         optiontreemanifest = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get('manifestcachesize', cachesize)
             optiontreemanifest = opts.get('treemanifest', False)
 
         self._treeondisk = optiontreemanifest or treemanifest
 
         self._fulltextcache = manifestfulltextcache(cachesize)
 
         if tree:
             assert self._treeondisk, 'opts is %r' % opts
 
         if indexfile is None:
             indexfile = '00manifest.i'
             if tree:
                 indexfile = "meta/" + tree + indexfile
 
         self.tree = tree
 
         # The dirlogcache is kept on the root manifest log
         if tree:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {'': self}
 
         self._revlog = revlog.revlog(opener, indexfile,
                                      # only root indexfile is cached
                                      checkambig=not bool(tree),
                                      mmaplargeindex=True,
                                      upperboundcomp=MAXCOMPRESSION)
 
         self.index = self._revlog.index
         self.version = self._revlog.version
         self._generaldelta = self._revlog._generaldelta
 
     def _setupmanifestcachehooks(self, repo):
         """Persist the manifestfulltextcache on lock release"""
         if not util.safehasattr(repo, '_wlockref'):
             return
 
         self._fulltextcache._opener = repo.wcachevfs
         if repo._currentlock(repo._wlockref) is None:
             return
 
         reporef = weakref.ref(repo)
         manifestrevlogref = weakref.ref(self)
 
         def persistmanifestcache():
             repo = reporef()
             self = manifestrevlogref()
             if repo is None or self is None:
                 return
             if repo.manifestlog.getstorage(b'') is not self:
                 # there's a different manifest in play now, abort
                 return
             self._fulltextcache.write()
 
         repo._afterlock(persistmanifestcache)
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self, clear_persisted_data=False):
         self._revlog.clearcaches()
         self._fulltextcache.clear(clear_persisted_data=clear_persisted_data)
         self._dirlogcache = {self.tree: self}
 
     def dirlog(self, d):
         if d:
             assert self._treeondisk
         if d not in self._dirlogcache:
             mfrevlog = manifestrevlog(self.opener, d,
                                       self._dirlogcache,
                                       treemanifest=self._treeondisk)
             self._dirlogcache[d] = mfrevlog
         return self._dirlogcache[d]
 
     def add(self, m, transaction, link, p1, p2, added, removed, readtree=None,
             match=None):
         if p1 in self.fulltextcache and util.safehasattr(m, 'fastdelta'):
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge([(x, False) for x in sorted(added)],
                                [(x, True) for x in sorted(removed)])
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self._revlog.rev(p1), deltatext
             text = util.buffer(arraytext)
             n = self._revlog.addrevision(text, transaction, link, p1, p2,
                                          cachedelta)
         else:
             # The first parent manifest isn't already loaded, so we'll
             # just encode a fulltext of the manifest and pass that
             # through to the revlog layer, and let it handle the delta
             # process.
             if self._treeondisk:
                 assert readtree, "readtree must be set for treemanifest writes"
                 assert match, "match must be specified for treemanifest writes"
                 m1 = readtree(self.tree, p1)
                 m2 = readtree(self.tree, p2)
                 n = self._addtree(m, transaction, link, m1, m2, readtree,
                                   match=match)
                 arraytext = None
             else:
                 text = m.text()
                 n = self._revlog.addrevision(text, transaction, link, p1, p2)
                 arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree, match):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self.tree != '' and (m.unmodifiedsince(m1) or m.unmodifiedsince(
             m2)):
             return m.node()
         def writesubtree(subm, subp1, subp2, match):
             sublog = self.dirlog(subm.dir())
             sublog.add(subm, transaction, link, subp1, subp2, None, None,
                        readtree=readtree, match=match)
         m.writesubtrees(m1, m2, writesubtree, match)
         text = m.dirtext()
         n = None
         if self.tree != '':
             # Double-check whether contents are unchanged to one parent
             if text == m1.dirtext():
                 n = m1.node()
             elif text == m2.dirtext():
                 n = m2.node()
 
         if not n:
             n = self._revlog.addrevision(text, transaction, link, m1.node(),
                                          m2.node())
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, value):
         return self._revlog.lookup(value)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def checksize(self):
         return self._revlog.checksize()
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def revdiff(self, rev1, rev2):
         return self._revlog.revdiff(rev1, rev2)
 
     def cmp(self, node, text):
         return self._revlog.cmp(node, text)
 
     def deltaparent(self, rev):
         return self._revlog.deltaparent(rev)
 
     def emitrevisions(self, nodes, nodesorder=None,
                       revisiondata=False, assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         return self._revlog.emitrevisions(
             nodes, nodesorder=nodesorder, revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         return self._revlog.addgroup(deltas, linkmapper, transaction,
                                      addrevisioncb=addrevisioncb)
 
     def rawsize(self, rev):
         return self._revlog.rawsize(rev)
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def files(self):
         return self._revlog.files()
 
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, manifestrevlog):
             raise error.ProgrammingError('expected manifestrevlog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles, sharedfiles=sharedfiles,
             revisionscount=revisionscount, trackedsize=trackedsize,
             storedsize=storedsize)
 
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     @property
     def opener(self):
         return self._revlog.opener
 
     @opener.setter
     def opener(self, value):
         self._revlog.opener = value
 
 @interfaceutil.implementer(repository.imanifestlog)
 class manifestlog(object):
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
     def __init__(self, opener, repo, rootstore, narrowmatch):
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get('treemanifest', usetreemanifest)
             cachesize = opts.get('manifestcachesize', cachesize)
 
         self._treemanifests = usetreemanifest
 
         self._rootstore = rootstore
         self._rootstore._setupmanifestcachehooks(repo)
         self._narrowmatch = narrowmatch
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[''] = util.lrucachedict(cachesize)
 
         self._cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get('', node)
 
     def get(self, tree, node, verify=True):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(tree, ()):
             return self._dirmancache[tree][node]
 
         if not self._narrowmatch.always():
             if not self._narrowmatch.visitdir(tree[:-1]):
                 return excludeddirmanifestctx(tree, node)
         if tree:
             if self._rootstore._treeondisk:
                 if verify:
                     # Side-effect is LookupError is raised if node doesn't
                     # exist.
                     self.getstorage(tree).rev(node)
 
                 m = treemanifestctx(self, tree, node)
             else:
                 raise error.Abort(
                         _("cannot ask for manifest directory '%s' in a flat "
                           "manifest") % tree)
         else:
             if verify:
                 # Side-effect is LookupError is raised if node doesn't exist.
                 self._rootstore.rev(node)
 
             if self._treemanifests:
                 m = treemanifestctx(self, '', node)
             else:
                 m = manifestctx(self, node)
 
         if node != nullid:
             mancache = self._dirmancache.get(tree)
             if not mancache:
                 mancache = util.lrucachedict(self._cachesize)
                 self._dirmancache[tree] = mancache
             mancache[node] = m
         return m
 
     def getstorage(self, tree):
         return self._rootstore.dirlog(tree)
 
     def clearcaches(self, clear_persisted_data=False):
         self._dirmancache.clear()
         self._rootstore.clearcaches(clear_persisted_data=clear_persisted_data)
 
     def rev(self, node):
         return self._rootstore.rev(node)
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memmanifestctx(object):
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict()
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self):
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         return self._storage().add(self._manifestdict, transaction, link,
                                    p1, p2, added, removed, match=match)
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class manifestctx(object):
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         #self.p1, self.p2 = store.parents(node)
         #rev = store.rev(node)
         #self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def node(self):
         return self._node
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def read(self):
         if self._data is None:
             if self._node == nullid:
                 self._data = manifestdict()
             else:
                 store = self._storage()
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = manifestdict(text)
         return self._data
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         '''
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         '''
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(d)
 
     def find(self, key):
         return self.read().find(key)
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memtreemanifestctx(object):
     def __init__(self, manifestlog, dir=''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest()
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self):
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
         return self._storage().add(self._treemanifest, transaction, link,
                                    p1, p2, added, removed, readtree=readtree,
                                    match=match)
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class treemanifestctx(object):
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         #self.p1, self.p2 = store.parents(node)
         #rev = store.rev(node)
         #self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         narrowmatch = self._manifestlog._narrowmatch
         if not narrowmatch.always():
             if not narrowmatch.visitdir(self._dir[:-1]):
                 return excludedmanifestrevlog(self._dir)
         return self._manifestlog.getstorage(self._dir)
 
     def read(self):
         if self._data is None:
             store = self._storage()
             if self._node == nullid:
                 self._data = treemanifest()
             # TODO accessing non-public API
             elif store._treeondisk:
                 m = treemanifest(dir=self._dir)
                 def gettext():
                     return store.revision(self._node)
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(dir=self._dir, text=text)
 
         return self._data
 
     def node(self):
         return self._node
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         If `shallow` is True, this will read the delta for this directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifest, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.
         '''
         store = self._storage()
         if shallow:
             r = store.rev(self._node)
             d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
             return manifestdict(d)
         else:
             # Need to perform a slow delta
             r0 = store.deltaparent(store.rev(self._node))
             m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
             m1 = self.read()
             md = treemanifest(dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         '''
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if (deltaparent != nullrev and
             deltaparent in store.parentrevs(r)):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(store.revision(self._node))
         else:
             return self.read()
 
     def find(self, key):
         return self.read().find(key)
 
 class excludeddir(treemanifest):
     """Stand-in for a directory that is excluded from the repository.
 
     With narrowing active on a repository that uses treemanifests,
     some of the directory revlogs will be excluded from the resulting
     clone. This is a huge storage win for clients, but means we need
     some sort of pseudo-manifest to surface to internals so we can
     detect a merge conflict outside the narrowspec. That's what this
     class is: it stands in for a directory whose node is known, but
     whose contents are unknown.
     """
     def __init__(self, dir, node):
         super(excludeddir, self).__init__(dir)
         self._node = node
         # Add an empty file, which will be included by iterators and such,
         # appearing as the directory itself (i.e. something like "dir/")
         self._files[''] = node
         self._flags[''] = 't'
 
     # Manifests outside the narrowspec should never be modified, so avoid
     # copying. This makes a noticeable difference when there are very many
     # directories outside the narrowspec. Also, it makes sense for the copy to
     # be of the same type as the original, which would not happen with the
     # super type's copy().
     def copy(self):
         return self
 
 class excludeddirmanifestctx(treemanifestctx):
     """context wrapper for excludeddir - see that docstring for rationale"""
     def __init__(self, dir, node):
         self._dir = dir
         self._node = node
 
     def read(self):
         return excludeddir(self._dir, self._node)
 
     def write(self, *args):
         raise error.ProgrammingError(
             'attempt to write manifest from excluded dir %s' % self._dir)
 
 class excludedmanifestrevlog(manifestrevlog):
     """Stand-in for excluded treemanifest revlogs.
 
     When narrowing is active on a treemanifest repository, we'll have
     references to directories we can't see due to the revlog being
     skipped. This class exists to conform to the manifestrevlog
     interface for those directories and proactively prevent writes to
     outside the narrowspec.
     """
 
     def __init__(self, dir):
         self._dir = dir
 
     def __len__(self):
         raise error.ProgrammingError(
             'attempt to get length of excluded dir %s' % self._dir)
 
     def rev(self, node):
         raise error.ProgrammingError(
             'attempt to get rev from excluded dir %s' % self._dir)
 
     def linkrev(self, node):
         raise error.ProgrammingError(
             'attempt to get linkrev from excluded dir %s' % self._dir)
 
     def node(self, rev):
         raise error.ProgrammingError(
             'attempt to get node from excluded dir %s' % self._dir)
 
     def add(self, *args, **kwargs):
         # We should never write entries in dirlogs outside the narrow clone.
         # However, the method still gets called from writesubtree() in
         # _addtree(), so we need to handle it. We should possibly make that
         # avoid calling add() with a clean manifest (_dirty is always False
         # in excludeddir instances).
         pass

mercurial/narrowspec.py

@@ -1,317 +1,319
 # narrowspec.py - methods for working with a narrow view of a repository
 #
 # Copyright 2017 Google, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from .i18n import _
+from .interfaces import (
+    repository,
+)
 from . import (
     error,
     match as matchmod,
     merge,
-    repository,
     scmutil,
     sparse,
     util,
 )
 
 # The file in .hg/store/ that indicates which paths exit in the store
 FILENAME = 'narrowspec'
 # The file in .hg/ that indicates which paths exit in the dirstate
 DIRSTATE_FILENAME = 'narrowspec.dirstate'
 
 # Pattern prefixes that are allowed in narrow patterns. This list MUST
 # only contain patterns that are fast and safe to evaluate. Keep in mind
 # that patterns are supplied by clients and executed on remote servers
 # as part of wire protocol commands. That means that changes to this
 # data structure influence the wire protocol and should not be taken
 # lightly - especially removals.
 VALID_PREFIXES = (
     b'path:',
     b'rootfilesin:',
 )
 
 def normalizesplitpattern(kind, pat):
     """Returns the normalized version of a pattern and kind.
 
     Returns a tuple with the normalized kind and normalized pattern.
     """
     pat = pat.rstrip('/')
     _validatepattern(pat)
     return kind, pat
 
 def _numlines(s):
     """Returns the number of lines in s, including ending empty lines."""
     # We use splitlines because it is Unicode-friendly and thus Python 3
     # compatible. However, it does not count empty lines at the end, so trick
     # it by adding a character at the end.
     return len((s + 'x').splitlines())
 
 def _validatepattern(pat):
     """Validates the pattern and aborts if it is invalid.
 
     Patterns are stored in the narrowspec as newline-separated
     POSIX-style bytestring paths. There's no escaping.
     """
 
     # We use newlines as separators in the narrowspec file, so don't allow them
     # in patterns.
     if _numlines(pat) > 1:
         raise error.Abort(_('newlines are not allowed in narrowspec paths'))
 
     components = pat.split('/')
     if '.' in components or '..' in components:
         raise error.Abort(_('"." and ".." are not allowed in narrowspec paths'))
 
 def normalizepattern(pattern, defaultkind='path'):
     """Returns the normalized version of a text-format pattern.
 
     If the pattern has no kind, the default will be added.
     """
     kind, pat = matchmod._patsplit(pattern, defaultkind)
     return '%s:%s' % normalizesplitpattern(kind, pat)
 
 def parsepatterns(pats):
     """Parses an iterable of patterns into a typed pattern set.
 
     Patterns are assumed to be ``path:`` if no prefix is present.
     For safety and performance reasons, only some prefixes are allowed.
     See ``validatepatterns()``.
 
     This function should be used on patterns that come from the user to
     normalize and validate them to the internal data structure used for
     representing patterns.
     """
     res = {normalizepattern(orig) for orig in pats}
     validatepatterns(res)
     return res
 
 def validatepatterns(pats):
     """Validate that patterns are in the expected data structure and format.
 
     And that is a set of normalized patterns beginning with ``path:`` or
     ``rootfilesin:``.
 
     This function should be used to validate internal data structures
     and patterns that are loaded from sources that use the internal,
     prefixed pattern representation (but can't necessarily be fully trusted).
     """
     if not isinstance(pats, set):
         raise error.ProgrammingError('narrow patterns should be a set; '
                                      'got %r' % pats)
 
     for pat in pats:
         if not pat.startswith(VALID_PREFIXES):
             # Use a Mercurial exception because this can happen due to user
             # bugs (e.g. manually updating spec file).
             raise error.Abort(_('invalid prefix on narrow pattern: %s') % pat,
                               hint=_('narrow patterns must begin with one of '
                                      'the following: %s') %
                                    ', '.join(VALID_PREFIXES))
 
 def format(includes, excludes):
     output = '[include]\n'
     for i in sorted(includes - excludes):
         output += i + '\n'
     output += '[exclude]\n'
     for e in sorted(excludes):
         output += e + '\n'
     return output
 
 def match(root, include=None, exclude=None):
     if not include:
         # Passing empty include and empty exclude to matchmod.match()
         # gives a matcher that matches everything, so explicitly use
         # the nevermatcher.
         return matchmod.never()
     return matchmod.match(root, '', [], include=include or [],
                           exclude=exclude or [])
 
 def parseconfig(ui, spec):
     # maybe we should care about the profiles returned too
     includepats, excludepats, profiles = sparse.parseconfig(ui, spec, 'narrow')
     if profiles:
         raise error.Abort(_("including other spec files using '%include' is not"
                             " supported in narrowspec"))
 
     validatepatterns(includepats)
     validatepatterns(excludepats)
 
     return includepats, excludepats
 
 def load(repo):
     # Treat "narrowspec does not exist" the same as "narrowspec file exists
     # and is empty".
     spec = repo.svfs.tryread(FILENAME)
     return parseconfig(repo.ui, spec)
 
 def save(repo, includepats, excludepats):
     validatepatterns(includepats)
     validatepatterns(excludepats)
     spec = format(includepats, excludepats)
     repo.svfs.write(FILENAME, spec)
 
 def copytoworkingcopy(repo):
     spec = repo.svfs.read(FILENAME)
     repo.vfs.write(DIRSTATE_FILENAME, spec)
 
 def savebackup(repo, backupname):
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return
     svfs = repo.svfs
     svfs.tryunlink(backupname)
     util.copyfile(svfs.join(FILENAME), svfs.join(backupname), hardlink=True)
 
 def restorebackup(repo, backupname):
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return
     util.rename(repo.svfs.join(backupname), repo.svfs.join(FILENAME))
 
 def savewcbackup(repo, backupname):
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return
     vfs = repo.vfs
     vfs.tryunlink(backupname)
     # It may not exist in old repos
     if vfs.exists(DIRSTATE_FILENAME):
         util.copyfile(vfs.join(DIRSTATE_FILENAME), vfs.join(backupname),
                       hardlink=True)
 
 def restorewcbackup(repo, backupname):
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return
     # It may not exist in old repos
     if repo.vfs.exists(backupname):
         util.rename(repo.vfs.join(backupname), repo.vfs.join(DIRSTATE_FILENAME))
 
 def clearwcbackup(repo, backupname):
     if repository.NARROW_REQUIREMENT not in repo.requirements:
         return
     repo.vfs.tryunlink(backupname)
 
 def restrictpatterns(req_includes, req_excludes, repo_includes, repo_excludes):
     r""" Restricts the patterns according to repo settings,
     results in a logical AND operation
 
     :param req_includes: requested includes
     :param req_excludes: requested excludes
     :param repo_includes: repo includes
     :param repo_excludes: repo excludes
     :return: include patterns, exclude patterns, and invalid include patterns.
 
     >>> restrictpatterns({'f1','f2'}, {}, ['f1'], [])
     (set(['f1']), {}, [])
     >>> restrictpatterns({'f1'}, {}, ['f1','f2'], [])
     (set(['f1']), {}, [])
     >>> restrictpatterns({'f1/fc1', 'f3/fc3'}, {}, ['f1','f2'], [])
     (set(['f1/fc1']), {}, [])
     >>> restrictpatterns({'f1_fc1'}, {}, ['f1','f2'], [])
     ([], set(['path:.']), [])
     >>> restrictpatterns({'f1/../f2/fc2'}, {}, ['f1','f2'], [])
     (set(['f2/fc2']), {}, [])
     >>> restrictpatterns({'f1/../f3/fc3'}, {}, ['f1','f2'], [])
     ([], set(['path:.']), [])
     >>> restrictpatterns({'f1/$non_exitent_var'}, {}, ['f1','f2'], [])
     (set(['f1/$non_exitent_var']), {}, [])
     """
     res_excludes = set(req_excludes)
     res_excludes.update(repo_excludes)
     invalid_includes = []
     if not req_includes:
         res_includes = set(repo_includes)
     elif 'path:.' not in repo_includes:
         res_includes = []
         for req_include in req_includes:
             req_include = util.expandpath(util.normpath(req_include))
             if req_include in repo_includes:
                 res_includes.append(req_include)
                 continue
             valid = False
             for repo_include in repo_includes:
                 if req_include.startswith(repo_include + '/'):
                     valid = True
                     res_includes.append(req_include)
                     break
             if not valid:
                 invalid_includes.append(req_include)
         if len(res_includes) == 0:
             res_excludes = {'path:.'}
         else:
             res_includes = set(res_includes)
     else:
         res_includes = set(req_includes)
     return res_includes, res_excludes, invalid_includes
 
 # These two are extracted for extensions (specifically for Google's CitC file
 # system)
 def _deletecleanfiles(repo, files):
     for f in files:
         repo.wvfs.unlinkpath(f)
 
 def _writeaddedfiles(repo, pctx, files):
     actions = merge.emptyactions()
     addgaction = actions[merge.ACTION_GET].append
     mf = repo['.'].manifest()
     for f in files:
         if not repo.wvfs.exists(f):
             addgaction((f, (mf.flags(f), False), "narrowspec updated"))
     merge.applyupdates(repo, actions, wctx=repo[None],
                        mctx=repo['.'], overwrite=False, wantfiledata=False)
 
 def checkworkingcopynarrowspec(repo):
     # Avoid infinite recursion when updating the working copy
     if getattr(repo, '_updatingnarrowspec', False):
         return
     storespec = repo.svfs.tryread(FILENAME)
     wcspec = repo.vfs.tryread(DIRSTATE_FILENAME)
     if wcspec != storespec:
         raise error.Abort(_("working copy's narrowspec is stale"),
                           hint=_("run 'hg tracked --update-working-copy'"))
 
 def updateworkingcopy(repo, assumeclean=False):
     """updates the working copy and dirstate from the store narrowspec
 
     When assumeclean=True, files that are not known to be clean will also
     be deleted. It is then up to the caller to make sure they are clean.
     """
     oldspec = repo.vfs.tryread(DIRSTATE_FILENAME)
     newspec = repo.svfs.tryread(FILENAME)
     repo._updatingnarrowspec = True
 
     oldincludes, oldexcludes = parseconfig(repo.ui, oldspec)
     newincludes, newexcludes = parseconfig(repo.ui, newspec)
     oldmatch = match(repo.root, include=oldincludes, exclude=oldexcludes)
     newmatch = match(repo.root, include=newincludes, exclude=newexcludes)
     addedmatch = matchmod.differencematcher(newmatch, oldmatch)
     removedmatch = matchmod.differencematcher(oldmatch, newmatch)
 
     ds = repo.dirstate
     lookup, status = ds.status(removedmatch, subrepos=[], ignored=True,
                                clean=True, unknown=True)
     trackeddirty = status.modified + status.added
     clean = status.clean
     if assumeclean:
         assert not trackeddirty
         clean.extend(lookup)
     else:
         trackeddirty.extend(lookup)
     _deletecleanfiles(repo, clean)
     uipathfn = scmutil.getuipathfn(repo)
     for f in sorted(trackeddirty):
         repo.ui.status(_('not deleting possibly dirty file %s\n') % uipathfn(f))
     for f in sorted(status.unknown):
         repo.ui.status(_('not deleting unknown file %s\n') % uipathfn(f))
     for f in sorted(status.ignored):
         repo.ui.status(_('not deleting ignored file %s\n') % uipathfn(f))
     for f in clean + trackeddirty:
         ds.drop(f)
 
     pctx = repo['.']
     newfiles = [f for f in pctx.manifest().walk(addedmatch) if f not in ds]
     for f in newfiles:
         ds.normallookup(f)
     _writeaddedfiles(repo, pctx, newfiles)
     repo._updatingnarrowspec = False

mercurial/revlog.py

@@ -1,2676 +1,2678
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullhex,
     nullid,
     nullrev,
     short,
     wdirfilenodeids,
     wdirhex,
     wdirid,
     wdirrev,
 )
 from .i18n import _
 from .revlogutils.constants import (
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
 )
 from .thirdparty import (
     attr,
 )
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
-    repository,
     templatefilters,
     util,
 )
+from .interfaces import (
+    repository,
+)
 from .revlogutils import (
     deltas as deltautil,
     flagutil,
 )
 from .utils import (
     interfaceutil,
     storageutil,
     stringutil,
 )
 
 # blanked usage of all the name to prevent pyflakes constraints
 # We need these name available in the module for extensions.
 REVLOGV0
 REVLOGV1
 REVLOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod(r'parsers')
 rustancestor = policy.importrust(r'ancestor')
 rustdagop = policy.importrust(r'dagop')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     if (type & ~flagutil.REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError('unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
     node:       expected hash of the revision
     p1, p2:     parent revs of the revision
     btext:      built text cache consisting of a one-element list
     cachedelta: (baserev, uncompressed_delta) or None
     flags:      flags associated to the revision storage
 
     One of btext[0] or cachedelta must be set.
     """
     node = attr.ib()
     p1 = attr.ib()
     p2 = attr.ib()
     btext = attr.ib()
     textlen = attr.ib()
     cachedelta = attr.ib()
     flags = attr.ib()
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     linknode = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class revlogproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 # index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 indexformatv0 = struct.Struct(">4l20s20s20s")
 indexformatv0_pack = indexformatv0.pack
 indexformatv0_unpack = indexformatv0.unpack
 
 class revlogoldindex(list):
     def __getitem__(self, i):
         if i == -1:
             return (0, 0, 0, -1, -1, -1, -1, nullid)
         return list.__getitem__(self, i)
 
 class revlogoldio(object):
     def __init__(self):
         self.size = indexformatv0.size
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap = {nullid: nullrev}
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = indexformatv0_unpack(cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         return revlogoldindex(index), nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise error.RevlogError(_('index entry flags need revlog '
                                       'version 1'))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return indexformatv0_pack(*e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = struct.Struct(">Qiiiiii20s12x")
 indexformatng_pack = indexformatng.pack
 versionformat = struct.Struct(">I")
 versionformat_pack = versionformat.pack
 versionformat_unpack = versionformat.unpack
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7fffffff
 
 class revlogio(object):
     def __init__(self):
         self.size = indexformatng.size
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
         p = indexformatng_pack(*entry)
         if rev == 0:
             p = versionformat_pack(version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
     """
     def __init__(self, opener, indexfile, datafile=None, checkambig=False,
                  mmaplargeindex=False, censorable=False,
                  upperboundcomp=None):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
 
         """
         self.upperboundcomp = upperboundcomp
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + ".d")
         self.opener = opener
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._mmaplargeindex = mmaplargeindex
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, '')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = []
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._nodecache = {nullid: nullrev}
         self._nodepos = None
         self._compengine = 'zlib'
         self._compengineopts = {}
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
 
         # 2-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._loadindex()
 
     def _loadindex(self):
         mmapindexthreshold = None
         opts = getattr(self.opener, 'options', {}) or {}
 
         if 'revlogv2' in opts:
             newversionflags = REVLOGV2 | FLAG_INLINE_DATA
         elif 'revlogv1' in opts:
             newversionflags = REVLOGV1 | FLAG_INLINE_DATA
             if 'generaldelta' in opts:
                 newversionflags |= FLAG_GENERALDELTA
         elif getattr(self.opener, 'options', None) is not None:
             # If options provided but no 'revlog*' found, the repository
             # would have no 'requires' file in it, which means we have to
             # stick to the old format.
             newversionflags = REVLOGV0
         else:
             newversionflags = REVLOG_DEFAULT_VERSION
 
         if 'chunkcachesize' in opts:
             self._chunkcachesize = opts['chunkcachesize']
         if 'maxchainlen' in opts:
             self._maxchainlen = opts['maxchainlen']
         if 'deltabothparents' in opts:
             self._deltabothparents = opts['deltabothparents']
         self._lazydelta = bool(opts.get('lazydelta', True))
         self._lazydeltabase = False
         if self._lazydelta:
             self._lazydeltabase = bool(opts.get('lazydeltabase', False))
         if 'compengine' in opts:
             self._compengine = opts['compengine']
         if 'zlib.level' in opts:
             self._compengineopts['zlib.level'] = opts['zlib.level']
         if 'zstd.level' in opts:
             self._compengineopts['zstd.level'] = opts['zstd.level']
         if 'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts['maxdeltachainspan']
         if self._mmaplargeindex and 'mmapindexthreshold' in opts:
             mmapindexthreshold = opts['mmapindexthreshold']
         self._sparserevlog = bool(opts.get('sparse-revlog', False))
         withsparseread = bool(opts.get('with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if 'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts['sparse-read-density-threshold']
         if 'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts['sparse-read-min-gap-size']
         if opts.get('enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in opts.get(b'flagprocessors', {}).iteritems():
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(_('revlog chunk cache size %r is not '
                                       'greater than 0') % self._chunkcachesize)
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(_('revlog chunk cache size %r is not a '
                                       'power of 2') % self._chunkcachesize)
 
         indexdata = ''
         self._initempty = True
         try:
             with self._indexfp() as f:
                 if (mmapindexthreshold is not None and
                     self.opener.fstat(f).st_size >= mmapindexthreshold):
                     # TODO: should .close() to release resources without
                     # relying on Python GC
                     indexdata = util.buffer(util.mmapread(f))
                 else:
                     indexdata = f.read()
             if len(indexdata) > 0:
                 versionflags = versionformat_unpack(indexdata[:4])[0]
                 self._initempty = False
             else:
                 versionflags = newversionflags
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
             versionflags = newversionflags
 
         self.version = versionflags
 
         flags = versionflags & ~0xFFFF
         fmt = versionflags & 0xFFFF
 
         if fmt == REVLOGV0:
             if flags:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = False
             self._generaldelta = False
 
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = versionflags & FLAG_INLINE_DATA
             self._generaldelta = versionflags & FLAG_GENERALDELTA
 
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = versionflags & FLAG_INLINE_DATA
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(_('unknown version (%d) in revlog %s') %
                                     (fmt, self.indexfile))
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self._generaldelta:
             self._sparserevlog = False
 
         self._storedeltachains = True
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(indexdata, self._inline)
         except (ValueError, IndexError):
             raise error.RevlogError(_("index %s is corrupted") %
                                     self.indexfile)
         self.index, nodemap, self._chunkcache = d
         if nodemap is not None:
             self.nodemap = self._nodecache = nodemap
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = {}
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     def _indexfp(self, mode='r'):
         """file object for the revlog's index file"""
         args = {r'mode': mode}
         if mode != 'r':
             args[r'checkambig'] = self._checkambig
         if mode == 'w':
             args[r'atomictemp'] = True
         return self.opener(self.indexfile, **args)
 
     def _datafp(self, mode='r'):
         """file object for the revlog's data file"""
         return self.opener(self.datafile, mode=mode)
 
     @contextlib.contextmanager
     def _datareadfp(self, existingfp=None):
         """file object suitable to read data"""
         # Use explicit file handle, if given.
         if existingfp is not None:
             yield existingfp
 
         # Use a file handle being actively used for writes, if available.
         # There is some danger to doing this because reads will seek the
         # file. However, _writeentry() performs a SEEK_END before all writes,
         # so we should be safe.
         elif self._writinghandles:
             if self._inline:
                 yield self._writinghandles[0]
             else:
                 yield self._writinghandles[1]
 
         # Otherwise open a new file handle.
         else:
             if self._inline:
                 func = self._indexfp
             else:
                 func = self._datafp
             with func() as fp:
                 yield fp
 
     def tip(self):
         return self.node(len(self.index) - 1)
     def __contains__(self, rev):
         return 0 <= rev < len(self)
     def __len__(self):
         return len(self.index)
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         return storageutil.iterrevs(len(self), start=start, stop=stop)
 
     @util.propertycache
     def nodemap(self):
         if self.index:
             # populate mapping down to the initial node
             node0 = self.index[0][7]  # get around changelog filtering
             self.rev(node0)
         return self._nodecache
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if ((self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS)
             or (self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS)):
             return False
         return True
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, '')
         self._pcache = {}
 
         try:
             # If we are using the native C version, you are in a fun case
             # where self.index, self.nodemap and self._nodecaches is the same
             # object.
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _('no node'))
         except KeyError:
             # pure python cache lookup failed
             n = self._nodecache
             i = self.index
             p = self._nodepos
             if p is None:
                 p = len(i) - 1
             else:
                 assert p < len(i)
             for r in pycompat.xrange(p, -1, -1):
                 v = i[r][7]
                 n[v] = r
                 if v == node:
                     self._nodepos = r - 1
                     return r
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _('no node'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.rawdata(rev)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (flagutil.REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev, raw=False))
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
         return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse revision order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         # first, make sure start revisions aren't filtered
         revs = list(revs)
         checkrev = self.node
         for r in revs:
             checkrev(r)
         # and we're sure ancestors aren't filtered as well
 
         if rustancestor is not None:
             lazyancestors = rustancestor.LazyAncestors
             arg = self.index
         elif util.safehasattr(parsers, 'rustlazyancestors'):
             lazyancestors = ancestor.rustlazyancestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         if rustancestor is not None:
             return rustancestor.MissingAncestors(self.index, common)
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in heads.iteritems() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevs()
             except AttributeError:
                 return self._headrevs()
         if rustdagop is not None:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     def computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = set(self.rev(n) for n in stop or [])
 
         revs = dagop.headrevssubset(self.revs, self.parentrevs, startrev=start,
                                     stoprevs=stoprevs)
 
         return [self.node(rev) for rev in revs]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError): # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::<roots> and <roots>::<heads>))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(minroot, heads, roots,
                                               includepath)
         except AttributeError:
             return dagop._reachablerootspure(self.parentrevs,
                                              minroot, roots, heads, includepath)
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except error.LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if "%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = wdirhex.startswith(id)
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     raise error.RevlogError
                 return partial
             if maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             return None
         except error.RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise error.AmbiguousPrefixLookupError(
                     id, self.indexfile, _('ambiguous identifier'))
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[:l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [n for n in nl if hex(n).startswith(id) and
                       self.hasnode(n)]
                 if nullhex.startswith(id):
                     nl.append(nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.indexfile, _('ambiguous identifier'))
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise error.LookupError(id, self.indexfile, _('no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
         def isvalid(prefix):
             try:
                 matchednode = self._partialmatch(prefix)
             except error.AmbiguousPrefixLookupError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if matchednode is None:
                 raise error.LookupError(node, self.indexfile, _('no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == 'f' for c in pycompat.iterbytestr(prefix))
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != wdirid:
                     raise error.LookupError(node, self.indexfile, _('no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == wdirid:
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, 41):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def _cachesegment(self, offset, data):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _readsegment(self, offset, length, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
 
         Raises if the requested number of bytes could not be read.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (((offset + length + cachesize) & ~(cachesize - 1))
                       - realoffset)
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
 
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
             startoffset = offset - realoffset
             if len(d) - startoffset < length:
                 raise error.RevlogError(
                     _('partial read of revlog %s; expected %d bytes from '
                       'offset %d, got %d') %
                     (self.indexfile if self._inline else self.datafile,
                      length, realoffset, len(d) - startoffset))
 
             return util.buffer(d, startoffset, length)
 
         if len(d) < length:
             raise error.RevlogError(
                 _('partial read of revlog %s; expected %d bytes from offset '
                   '%d, got %d') %
                 (self.indexfile if self._inline else self.datafile,
                  length, offset, len(d)))
 
         return d
 
     def _getsegment(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._readsegment(offset, length, df=df)
 
     def _getsegmentforrevs(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self._io.size
             end += (endrev + 1) * self._io.size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self._io.size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = deltautil.slicechunk(self, revs,
                                                 targetsize=targetsize)
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, df=df)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev, df=df) for rev in revschunk]
 
             decomp = self.decompress
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(decomp(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot
         """
         if not self._sparserevlog:
             return self.deltaparent(rev) == nullrev
         elif util.safehasattr(self.index, 'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         p2 = entry[6]
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     def snapshotdepth(self, rev):
         """number of snapshot in the chain before this one"""
         if not self.issnapshot(rev):
             raise error.ProgrammingError('revision %d not a snapshot')
         return len(self._deltachain(rev)[0]) - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.rawdata(rev1),
                               self.rawdata(rev2))
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         raw - an optional argument specifying if the revision data is to be
         treated as raw data when applying flag transforms. 'raw' should be set
         to True when generating changegroups or in debug commands.
         """
         return self._revisiondata(nodeorrev, _df, raw=raw)
 
     def _revisiondata(self, nodeorrev, _df=None, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == nullid:
             return ""
 
         # The text as stored inside the revlog. Might be the revision or might
         # need to be processed to retrieve the revision.
         rawtext = None
 
         rev, rawtext, validated = self._rawtext(node, rev, _df=_df)
 
         if raw and validated:
             # if we don't want to process the raw text and that raw
             # text is cached, we can exit early.
             return rawtext
         if rev is None:
             rev = self.rev(node)
         # the revlog's flag for this revision
         # (usually alter its state or content)
         flags = self.flags(rev)
 
         if validated and flags == REVIDX_DEFAULT_FLAGS:
             # no extra flags set, no flag processor runs, text = rawtext
             return rawtext
 
         text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._revisioncache = (node, rev, rawtext)
 
         return text
 
     def _rawtext(self, node, rev, _df=None):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
 
         # revision in the cache (could be useful to apply delta)
         cachedrev = None
         # An intermediate text to apply deltas to
         basetext = None
 
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 return (rev, self._revisioncache[2], True)
             cachedrev = self._revisioncache[1]
 
         if rev is None:
             rev = self.rev(node)
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             basetext = self._revisioncache[2]
 
         # drop cache to save memory, the caller is expected to
         # update self._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         bins = self._chunks(chain, df=_df, targetsize=targetsize)
         if basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def rawdata(self, nodeorrev, _df=None):
         """return an uncompressed raw data of a given node or revision number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df, raw=True)
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return storageutil.hashrevisionsha1(text, p1, p2)
 
     def _processflags(self, text, flags, operation, raw=False):
         """Inspect revision data flags and applies transforms defined by
         registered flag processors.
 
         ``text`` - the revision data to process
         ``flags`` - the revision flags
         ``operation`` - the operation being performed (read or write)
         ``raw`` - an optional argument describing if the raw transform should be
         applied.
 
         This method processes the flags in the order (or reverse order if
         ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
         flag processors registered for present flags. The order of flags defined
         in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.
 
         Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
         processed text and ``validatehash`` is a bool indicating whether the
         returned text should be checked for hash integrity.
 
         Note: If the ``raw`` argument is set, it has precedence over the
         operation and will only update the value of ``validatehash``.
         """
         # fast path: no flag processors will run
         if flags == 0:
             return text, True
         if not operation in ('read', 'write'):
             raise error.ProgrammingError(_("invalid '%s' operation") %
                                          operation)
         # Check all flags are known.
         if flags & ~flagutil.REVIDX_KNOWN_FLAGS:
             raise error.RevlogError(_("incompatible revision flag '%#x'") %
                                     (flags & ~flagutil.REVIDX_KNOWN_FLAGS))
         validatehash = True
         # Depending on the operation (read or write), the order might be
         # reversed due to non-commutative transforms.
         orderedflags = REVIDX_FLAGS_ORDER
         if operation == 'write':
             orderedflags = reversed(orderedflags)
 
         for flag in orderedflags:
             # If a flagprocessor has been registered for a known flag, apply the
             # related operation transform and update result tuple.
             if flag & flags:
                 vhash = True
 
                 if flag not in self._flagprocessors:
                     message = _("missing processor for flag '%#x'") % (flag)
                     raise error.RevlogError(message)
 
                 processor = self._flagprocessors[flag]
                 if processor is not None:
                     readtransform, writetransform, rawtransform = processor
 
                     if raw:
                         vhash = rawtransform(self, text)
                     elif operation == 'read':
                         text, vhash = readtransform(self, text)
                     else: # write operation
                         text, vhash = writetransform(self, text)
                 validatehash = validatehash and vhash
 
         return text, validatehash
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 # Clear the revision cache on hash failure. The revision cache
                 # only stores the raw revision and clearing the cache does have
                 # the side-effect that we won't have a cache hit when the raw
                 # revision data is accessed. But this case should be rare and
                 # it is extra work to teach the cache about the hash
                 # verification state.
                 if self._revisioncache and self._revisioncache[0] == node:
                     self._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(_("integrity check failed on %s:%s")
                     % (self.indexfile, pycompat.bytestr(revornode)))
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.indexfile, node, text)
             raise
 
     def _enforceinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         tiprev = len(self) - 1
         if (not self._inline or
             (self.start(tiprev) + self.length(tiprev)) < _maxinline):
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise error.RevlogError(_("%s not found in the transaction")
                                     % self.indexfile)
 
         trindex = trinfo[2]
         if trindex is not None:
             dataoff = self.start(trindex)
         else:
             # revlog was stripped at start of transaction, use all leftover data
             trindex = len(self) - 1
             dataoff = self.end(tiprev)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
 
         with self._indexfp('r') as ifh, self._datafp('w') as dfh:
             for r in self:
                 dfh.write(self._getsegmentforrevs(r, r, df=ifh)[1])
 
         with self._indexfp('w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             io = self._io
             for i in self:
                 e = io.packentry(self.index[i], self.node, self.version, i)
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored.
         """
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None,
                     node=None, flags=REVIDX_DEFAULT_FLAGS, deltacomputer=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         node - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         flags - the known flags to set on the revision
         deltacomputer - an optional deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise error.RevlogError(_("attempted to add linkrev -1 to %s")
                                     % self.indexfile)
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = self._processflags(text, flags, 'write')
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _("%s: size of %d bytes exceeds maximum revlog storage of 2GiB")
                 % (self.indexfile, len(rawtext)))
 
         node = node or self.hash(rawtext, p1, p2)
         if node in self.nodemap:
             return node
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(rawtext, transaction, link, p1, p2, node,
                                    flags, cachedelta=cachedelta,
                                    deltacomputer=deltacomputer)
 
     def addrawrevision(self, rawtext, transaction, link, p1, p2, node, flags,
                        cachedelta=None, deltacomputer=None):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp("a+")
         ifh = self._indexfp("a+")
         try:
             return self._addrevision(node, rawtext, transaction, link, p1, p2,
                                      flags, cachedelta, ifh, dfh,
                                      deltacomputer=deltacomputer)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return '', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return '', compressed
 
         if data[0:1] == '\0':
             return '', data
         return 'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == 'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(_('revlog decompress error: %s') %
                                         stringutil.forcebytestr(e))
         # '\0' is more common than 'u' so it goes first.
         elif t == '\0':
             return data
         elif t == 'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(self._compengineopts)
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(_('unknown compression type %r') % t)
 
         return compressor.decompress(data)
 
     def _addrevision(self, node, rawtext, transaction, link, p1, p2, flags,
                      cachedelta, ifh, dfh, alwayscache=False,
                      deltacomputer=None):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == nullid:
             raise error.RevlogError(_("%s: attempt to add null revision") %
                                     self.indexfile)
         if node == wdirid or node in wdirfilenodeids:
             raise error.RevlogError(_("%s: attempt to add wdir revision") %
                                     self.indexfile)
 
         if self._inline:
             fh = ifh
         else:
             fh = dfh
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
         offset = self.end(prev)
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(revlog.size(self, cachedelta[0]),
                                         cachedelta[1])
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         e = (offset_type(offset, flags), deltainfo.deltalen, textlen,
              deltainfo.base, link, p1r, p2r, node)
         self.index.append(e)
         self.nodemap[node] = curr
 
         # Reset the pure node cache start lookup offset to account for new
         # revision.
         if self._nodepos is not None:
             self._nodepos = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         self._writeentry(transaction, ifh, dfh, entry, deltainfo.data,
                          link, offset)
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo, fh)
 
         if type(rawtext) == bytes: # only accept immutable objects
             self._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return node
 
     def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self._enforceinlinesize(transaction, ifh)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         if self._writinghandles:
             raise error.ProgrammingError('cannot nest addgroup() calls')
 
         nodes = []
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp("a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self._datafp("a+")
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 nodes.append(node)
 
                 if node in self.nodemap:
                     self._nodeduplicatecallback(transaction, node)
                     # this can happen if two branches make the same change
                     continue
 
                 for p in (p1, p2):
                     if p not in self.nodemap:
                         raise error.LookupError(p, self.indexfile,
                                                 _('unknown parent'))
 
                 if deltabase not in self.nodemap:
                     raise error.LookupError(deltabase, self.indexfile,
                                             _('unknown delta base'))
 
                 baserev = self.rev(deltabase)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(self.indexfile,
                                                       self.node(baserev))
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
                 # We're only using addgroup() in the context of changegroup
                 # generation so the revision data can always be handled as raw
                 # by the flagprocessor.
                 self._addrevision(node, None, transaction, link,
                                   p1, p2, flags, (baserev, delta),
                                   ifh, dfh,
                                   alwayscache=bool(addrevisioncb),
                                   deltacomputer=deltacomputer)
 
                 if addrevisioncb:
                     addrevisioncb(self, node)
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp("a+")
                     ifh = self._indexfp("a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
 
         return nodes
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         return storageutil.deltaiscensored(delta, baserev, self.rawsize)
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         return storageutil.resolvestripinfo(minlink, len(self) - 1,
                                             self.headrevs(),
                                             self.linkrev, self.parentrevs)
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = {}
         self._chunkclear()
         for x in pycompat.xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
         self._nodepos = None
 
     def checksize(self):
         """Check size of index and data files
 
         return a (dd, di) tuple.
         - dd: extra bytes for the "data" file
         - di: extra bytes for the "index" file
 
         A healthy revlog will return (0, 0).
         """
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, io.SEEK_END)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     def emitrevisions(self, nodes, nodesorder=None, revisiondata=False,
                       assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         if nodesorder not in ('nodes', 'storage', 'linear', None):
             raise error.ProgrammingError('unhandled value for nodesorder: %s' %
                                          nodesorder)
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = 'storage'
 
         if (not self._storedeltachains and
                 deltamode != repository.CG_DELTAMODE_PREV):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self, nodes, nodesorder, revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self.candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions)
 
     DELTAREUSEALWAYS = 'always'
     DELTAREUSESAMEREVS = 'samerevs'
     DELTAREUSENEVER = 'never'
 
     DELTAREUSEFULLADD = 'fulladd'
 
     DELTAREUSEALL = {'always', 'samerevs', 'never', 'fulladd'}
 
     def clone(self, tr, destrevlog, addrevisioncb=None,
               deltareuse=DELTAREUSESAMEREVS, forcedeltabothparents=None):
         """Copy this revlog to another, possibly with format changes.
 
         The destination revlog will contain the same revisions and nodes.
         However, it may not be bit-for-bit identical due to e.g. delta encoding
         differences.
 
         The ``deltareuse`` argument control how deltas from the existing revlog
         are preserved in the destination revlog. The argument can have the
         following values:
 
         DELTAREUSEALWAYS
            Deltas will always be reused (if possible), even if the destination
            revlog would not select the same revisions for the delta. This is the
            fastest mode of operation.
         DELTAREUSESAMEREVS
            Deltas will be reused if the destination revlog would pick the same
            revisions for the delta. This mode strikes a balance between speed
            and optimization.
         DELTAREUSENEVER
            Deltas will never be reused. This is the slowest mode of execution.
            This mode can be used to recompute deltas (e.g. if the diff/delta
            algorithm changes).
 
         Delta computation can be slow, so the choice of delta reuse policy can
         significantly affect run time.
 
         The default policy (``DELTAREUSESAMEREVS``) strikes a balance between
         two extremes. Deltas will be reused if they are appropriate. But if the
         delta could choose a better revision, it will do so. This means if you
         are converting a non-generaldelta revlog to a generaldelta revlog,
         deltas will be recomputed if the delta's parent isn't a parent of the
         revision.
 
         In addition to the delta policy, the ``forcedeltabothparents``
         argument controls whether to force compute deltas against both parents
         for merges. By default, the current default is used.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(_('value for deltareuse invalid: %s') % deltareuse)
 
         if len(destrevlog):
             raise ValueError(_('destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_('source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_('destination revlog has filtered revisions'))
 
         # lazydelta and lazydeltabase controls whether to reuse a cached delta,
         # if possible.
         oldlazydelta = destrevlog._lazydelta
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             deltacomputer = deltautil.deltacomputer(destrevlog)
             index = self.index
             for rev in self:
                 entry = index[rev]
 
                 # Some classes override linkrev to take filtered revs into
                 # account. Use raw entry from index.
                 flags = entry[0] & 0xffff
                 linkrev = entry[4]
                 p1 = index[entry[5]][7]
                 p2 = index[entry[6]][7]
                 node = entry[7]
 
                 # (Possibly) reuse the delta from the revlog if allowed and
                 # the revlog chunk is a delta.
                 cachedelta = None
                 rawtext = None
                 if (deltareuse != self.DELTAREUSEFULLADD
                         and destrevlog._lazydelta):
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 if not cachedelta:
                     rawtext = self.rawdata(rev)
 
 
                 if deltareuse == self.DELTAREUSEFULLADD:
                     destrevlog.addrevision(rawtext, tr, linkrev, p1, p2,
                                            cachedelta=cachedelta,
                                            node=node, flags=flags,
                                            deltacomputer=deltacomputer)
                 else:
                     ifh = destrevlog.opener(destrevlog.indexfile, 'a+',
                                             checkambig=False)
                     dfh = None
                     if not destrevlog._inline:
                         dfh = destrevlog.opener(destrevlog.datafile, 'a+')
                     try:
                         destrevlog._addrevision(node, rawtext, tr, linkrev, p1,
                                                 p2, flags, cachedelta, ifh, dfh,
                                                 deltacomputer=deltacomputer)
                     finally:
                         if dfh:
                             dfh.close()
                         ifh.close()
 
                 if addrevisioncb:
                     addrevisioncb(self, rev, node)
         finally:
             destrevlog._lazydelta = oldlazydelta
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if (self.version & 0xFFFF) == REVLOGV0:
             raise error.RevlogError(_('cannot censor with version %d revlogs') %
                                     self.version)
 
         censorrev = self.rev(censornode)
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(censorrev):
             raise error.Abort(_('censor tombstone must be no longer than '
                                 'censored data'))
 
         # Rewriting the revlog in place is hard. Our strategy for censoring is
         # to create a new revlog, copy all revisions to it, then replace the
         # revlogs on transaction close.
 
         newindexfile = self.indexfile + b'.tmpcensored'
         newdatafile = self.datafile + b'.tmpcensored'
 
         # This is a bit dangerous. We could easily have a mismatch of state.
         newrl = revlog(self.opener, newindexfile, newdatafile,
                        censorable=True)
         newrl.version = self.version
         newrl._generaldelta = self._generaldelta
         newrl._io = self._io
 
         for rev in self.revs():
             node = self.node(rev)
             p1, p2 = self.parents(node)
 
             if rev == censorrev:
                 newrl.addrawrevision(tombstone, tr, self.linkrev(censorrev),
                                      p1, p2, censornode, REVIDX_ISCENSORED)
 
                 if newrl.deltaparent(rev) != nullrev:
                     raise error.Abort(_('censored revision stored as delta; '
                                         'cannot censor'),
                                       hint=_('censoring of revlogs is not '
                                              'fully implemented; please report '
                                              'this bug'))
                 continue
 
             if self.iscensored(rev):
                 if self.deltaparent(rev) != nullrev:
                     raise error.Abort(_('cannot censor due to censored '
                                         'revision having delta stored'))
                 rawtext = self._chunk(rev)
             else:
                 rawtext = self.rawdata(rev)
 
             newrl.addrawrevision(rawtext, tr, self.linkrev(rev), p1, p2, node,
                                  self.flags(rev))
 
         tr.addbackup(self.indexfile, location='store')
         if not self._inline:
             tr.addbackup(self.datafile, location='store')
 
         self.opener.rename(newrl.indexfile, self.indexfile)
         if not self._inline:
             self.opener.rename(newrl.datafile, self.datafile)
 
         self.clearcaches()
         self._loadindex()
 
     def verifyintegrity(self, state):
         """Verifies the integrity of the revlog.
 
         Yields ``revlogproblem`` instances describing problems that are
         found.
         """
         dd, di = self.checksize()
         if dd:
             yield revlogproblem(error=_('data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_('index contains %d extra bytes') % di)
 
         version = self.version & 0xFFFF
 
         # The verifier tells us what version revlog we should be.
         if version != state['expectedversion']:
             yield revlogproblem(
                 warning=_("warning: '%s' uses revlog format %d; expected %d") %
                         (self.indexfile, version, state['expectedversion']))
 
         state['skipread'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see flagutil.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get('skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 if skipflags:
                     state['skipread'].add(node)
                 else:
                     # Side-effect: read content and verify hash.
                     self.revision(node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_('unpacked size is %d, %d expected') % (l2, l1),
                         node=node)
 
             except error.CensoredNodeError:
                 if state['erroroncensored']:
                     yield revlogproblem(error=_('censored file data'),
                                         node=node)
                     state['skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_('unpacking %s: %s') % (short(node),
                                                    stringutil.forcebytestr(e)),
                     node=node)
                 state['skipread'].add(node)
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         d = {}
 
         if exclusivefiles:
             d['exclusivefiles'] = [(self.opener, self.indexfile)]
             if not self._inline:
                 d['exclusivefiles'].append((self.opener, self.datafile))
 
         if sharedfiles:
             d['sharedfiles'] = []
 
         if revisionscount:
             d['revisionscount'] = len(self)
 
         if trackedsize:
             d['trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d['storedsize'] = sum(self.opener.stat(path).st_size
                                   for path in self.files())
 
         return d

mercurial/revlogutils/constants.py

@@ -1,55 +1,55
 # revlogdeltas.py - constant used for revlog logic
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 # Copyright 2018 Octobus <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """Helper class to compute deltas stored inside revlogs"""
 
 from __future__ import absolute_import
 
-from .. import (
+from ..interfaces import (
     repository,
 )
 
 # revlog header flags
 REVLOGV0 = 0
 REVLOGV1 = 1
 # Dummy value until file format is finalized.
 # Reminder: change the bounds check in revlog.__init__ when this is changed.
 REVLOGV2 = 0xDEAD
 # Shared across v1 and v2.
 FLAG_INLINE_DATA = (1 << 16)
 # Only used by v1, implied by v2.
 FLAG_GENERALDELTA = (1 << 17)
 REVLOG_DEFAULT_FLAGS = FLAG_INLINE_DATA
 REVLOG_DEFAULT_FORMAT = REVLOGV1
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGV1_FLAGS = FLAG_INLINE_DATA | FLAG_GENERALDELTA
 REVLOGV2_FLAGS = FLAG_INLINE_DATA
 
 # revlog index flags
 
 # For historical reasons, revlog's internal flags were exposed via the
 # wire protocol and are even exposed in parts of the storage APIs.
 
 # revision has censor metadata, must be verified
 REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED
 # revision hash does not match data (narrowhg)
 REVIDX_ELLIPSIS = repository.REVISION_FLAG_ELLIPSIS
 # revision data is stored externally
 REVIDX_EXTSTORED = repository.REVISION_FLAG_EXTSTORED
 REVIDX_DEFAULT_FLAGS = 0
 # stable order in which flags need to be processed and their processors applied
 REVIDX_FLAGS_ORDER = [
     REVIDX_ISCENSORED,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
 ]
 
 # bitmark for flags that could cause rawdata content change
 REVIDX_RAWTEXT_CHANGING_FLAGS = REVIDX_ISCENSORED | REVIDX_EXTSTORED
 
 SPARSE_REVLOG_MAX_CHAIN_LENGTH = 1000
 

mercurial/streamclone.py

@@ -1,658 +1,660
 # streamclone.py - producing and consuming streaming repository data
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import contextlib
 import os
 import struct
 
 from .i18n import _
+from .interfaces import (
+    repository,
+)
 from . import (
     cacheutil,
     error,
     narrowspec,
     phases,
     pycompat,
-    repository,
     store,
     util,
 )
 
 def canperformstreamclone(pullop, bundle2=False):
     """Whether it is possible to perform a streaming clone as part of pull.
 
     ``bundle2`` will cause the function to consider stream clone through
     bundle2 and only through bundle2.
 
     Returns a tuple of (supported, requirements). ``supported`` is True if
     streaming clone is supported and False otherwise. ``requirements`` is
     a set of repo requirements from the remote, or ``None`` if stream clone
     isn't supported.
     """
     repo = pullop.repo
     remote = pullop.remote
 
     bundle2supported = False
     if pullop.canusebundle2:
         if 'v2' in pullop.remotebundle2caps.get('stream', []):
             bundle2supported = True
         # else
             # Server doesn't support bundle2 stream clone or doesn't support
             # the versions we support. Fall back and possibly allow legacy.
 
     # Ensures legacy code path uses available bundle2.
     if bundle2supported and not bundle2:
         return False, None
     # Ensures bundle2 doesn't try to do a stream clone if it isn't supported.
     elif bundle2 and not bundle2supported:
         return False, None
 
     # Streaming clone only works on empty repositories.
     if len(repo):
         return False, None
 
     # Streaming clone only works if all data is being requested.
     if pullop.heads:
         return False, None
 
     streamrequested = pullop.streamclonerequested
 
     # If we don't have a preference, let the server decide for us. This
     # likely only comes into play in LANs.
     if streamrequested is None:
         # The server can advertise whether to prefer streaming clone.
         streamrequested = remote.capable('stream-preferred')
 
     if not streamrequested:
         return False, None
 
     # In order for stream clone to work, the client has to support all the
     # requirements advertised by the server.
     #
     # The server advertises its requirements via the "stream" and "streamreqs"
     # capability. "stream" (a value-less capability) is advertised if and only
     # if the only requirement is "revlogv1." Else, the "streamreqs" capability
     # is advertised and contains a comma-delimited list of requirements.
     requirements = set()
     if remote.capable('stream'):
         requirements.add('revlogv1')
     else:
         streamreqs = remote.capable('streamreqs')
         # This is weird and shouldn't happen with modern servers.
         if not streamreqs:
             pullop.repo.ui.warn(_(
                 'warning: stream clone requested but server has them '
                 'disabled\n'))
             return False, None
 
         streamreqs = set(streamreqs.split(','))
         # Server requires something we don't support. Bail.
         missingreqs = streamreqs - repo.supportedformats
         if missingreqs:
             pullop.repo.ui.warn(_(
                 'warning: stream clone requested but client is missing '
                 'requirements: %s\n') % ', '.join(sorted(missingreqs)))
             pullop.repo.ui.warn(
                 _('(see https://www.mercurial-scm.org/wiki/MissingRequirement '
                   'for more information)\n'))
             return False, None
         requirements = streamreqs
 
     return True, requirements
 
 def maybeperformlegacystreamclone(pullop):
     """Possibly perform a legacy stream clone operation.
 
     Legacy stream clones are performed as part of pull but before all other
     operations.
 
     A legacy stream clone will not be performed if a bundle2 stream clone is
     supported.
     """
     from . import localrepo
 
     supported, requirements = canperformstreamclone(pullop)
 
     if not supported:
         return
 
     repo = pullop.repo
     remote = pullop.remote
 
     # Save remote branchmap. We will use it later to speed up branchcache
     # creation.
     rbranchmap = None
     if remote.capable('branchmap'):
         with remote.commandexecutor() as e:
             rbranchmap = e.callcommand('branchmap', {}).result()
 
     repo.ui.status(_('streaming all changes\n'))
 
     with remote.commandexecutor() as e:
         fp = e.callcommand('stream_out', {}).result()
 
     # TODO strictly speaking, this code should all be inside the context
     # manager because the context manager is supposed to ensure all wire state
     # is flushed when exiting. But the legacy peers don't do this, so it
     # doesn't matter.
     l = fp.readline()
     try:
         resp = int(l)
     except ValueError:
         raise error.ResponseError(
             _('unexpected response from remote server:'), l)
     if resp == 1:
         raise error.Abort(_('operation forbidden by server'))
     elif resp == 2:
         raise error.Abort(_('locking the remote repository failed'))
     elif resp != 0:
         raise error.Abort(_('the server sent an unknown error code'))
 
     l = fp.readline()
     try:
         filecount, bytecount = map(int, l.split(' ', 1))
     except (ValueError, TypeError):
         raise error.ResponseError(
             _('unexpected response from remote server:'), l)
 
     with repo.lock():
         consumev1(repo, fp, filecount, bytecount)
 
         # new requirements = old non-format requirements +
         #                    new format-related remote requirements
         # requirements from the streamed-in repository
         repo.requirements = requirements | (
                 repo.requirements - repo.supportedformats)
         repo.svfs.options = localrepo.resolvestorevfsoptions(
             repo.ui, repo.requirements, repo.features)
         repo._writerequirements()
 
         if rbranchmap:
             repo._branchcaches.replace(repo, rbranchmap)
 
         repo.invalidate()
 
 def allowservergeneration(repo):
     """Whether streaming clones are allowed from the server."""
     if repository.REPO_FEATURE_STREAM_CLONE not in repo.features:
         return False
 
     if not repo.ui.configbool('server', 'uncompressed', untrusted=True):
         return False
 
     # The way stream clone works makes it impossible to hide secret changesets.
     # So don't allow this by default.
     secret = phases.hassecret(repo)
     if secret:
         return repo.ui.configbool('server', 'uncompressedallowsecret')
 
     return True
 
 # This is it's own function so extensions can override it.
 def _walkstreamfiles(repo, matcher=None):
     return repo.store.walk(matcher)
 
 def generatev1(repo):
     """Emit content for version 1 of a streaming clone.
 
     This returns a 3-tuple of (file count, byte size, data iterator).
 
     The data iterator consists of N entries for each file being transferred.
     Each file entry starts as a line with the file name and integer size
     delimited by a null byte.
 
     The raw file data follows. Following the raw file data is the next file
     entry, or EOF.
 
     When used on the wire protocol, an additional line indicating protocol
     success will be prepended to the stream. This function is not responsible
     for adding it.
 
     This function will obtain a repository lock to ensure a consistent view of
     the store is captured. It therefore may raise LockError.
     """
     entries = []
     total_bytes = 0
     # Get consistent snapshot of repo, lock during scan.
     with repo.lock():
         repo.ui.debug('scanning\n')
         for name, ename, size in _walkstreamfiles(repo):
             if size:
                 entries.append((name, size))
                 total_bytes += size
 
     repo.ui.debug('%d files, %d bytes to transfer\n' %
                   (len(entries), total_bytes))
 
     svfs = repo.svfs
     debugflag = repo.ui.debugflag
 
     def emitrevlogdata():
         for name, size in entries:
             if debugflag:
                 repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
             # partially encode name over the wire for backwards compat
             yield '%s\0%d\n' % (store.encodedir(name), size)
             # auditing at this stage is both pointless (paths are already
             # trusted by the local repo) and expensive
             with svfs(name, 'rb', auditpath=False) as fp:
                 if size <= 65536:
                     yield fp.read(size)
                 else:
                     for chunk in util.filechunkiter(fp, limit=size):
                         yield chunk
 
     return len(entries), total_bytes, emitrevlogdata()
 
 def generatev1wireproto(repo):
     """Emit content for version 1 of streaming clone suitable for the wire.
 
     This is the data output from ``generatev1()`` with 2 header lines. The
     first line indicates overall success. The 2nd contains the file count and
     byte size of payload.
 
     The success line contains "0" for success, "1" for stream generation not
     allowed, and "2" for error locking the repository (possibly indicating
     a permissions error for the server process).
     """
     if not allowservergeneration(repo):
         yield '1\n'
         return
 
     try:
         filecount, bytecount, it = generatev1(repo)
     except error.LockError:
         yield '2\n'
         return
 
     # Indicates successful response.
     yield '0\n'
     yield '%d %d\n' % (filecount, bytecount)
     for chunk in it:
         yield chunk
 
 def generatebundlev1(repo, compression='UN'):
     """Emit content for version 1 of a stream clone bundle.
 
     The first 4 bytes of the output ("HGS1") denote this as stream clone
     bundle version 1.
 
     The next 2 bytes indicate the compression type. Only "UN" is currently
     supported.
 
     The next 16 bytes are two 64-bit big endian unsigned integers indicating
     file count and byte count, respectively.
 
     The next 2 bytes is a 16-bit big endian unsigned short declaring the length
     of the requirements string, including a trailing \0. The following N bytes
     are the requirements string, which is ASCII containing a comma-delimited
     list of repo requirements that are needed to support the data.
 
     The remaining content is the output of ``generatev1()`` (which may be
     compressed in the future).
 
     Returns a tuple of (requirements, data generator).
     """
     if compression != 'UN':
         raise ValueError('we do not support the compression argument yet')
 
     requirements = repo.requirements & repo.supportedformats
     requires = ','.join(sorted(requirements))
 
     def gen():
         yield 'HGS1'
         yield compression
 
         filecount, bytecount, it = generatev1(repo)
         repo.ui.status(_('writing %d bytes for %d files\n') %
                          (bytecount, filecount))
 
         yield struct.pack('>QQ', filecount, bytecount)
         yield struct.pack('>H', len(requires) + 1)
         yield requires + '\0'
 
         # This is where we'll add compression in the future.
         assert compression == 'UN'
 
         progress = repo.ui.makeprogress(_('bundle'), total=bytecount,
                                         unit=_('bytes'))
         progress.update(0)
 
         for chunk in it:
             progress.increment(step=len(chunk))
             yield chunk
 
         progress.complete()
 
     return requirements, gen()
 
 def consumev1(repo, fp, filecount, bytecount):
     """Apply the contents from version 1 of a streaming clone file handle.
 
     This takes the output from "stream_out" and applies it to the specified
     repository.
 
     Like "stream_out," the status line added by the wire protocol is not
     handled by this function.
     """
     with repo.lock():
         repo.ui.status(_('%d files to transfer, %s of data\n') %
                        (filecount, util.bytecount(bytecount)))
         progress = repo.ui.makeprogress(_('clone'), total=bytecount,
                                         unit=_('bytes'))
         progress.update(0)
         start = util.timer()
 
         # TODO: get rid of (potential) inconsistency
         #
         # If transaction is started and any @filecache property is
         # changed at this point, it causes inconsistency between
         # in-memory cached property and streamclone-ed file on the
         # disk. Nested transaction prevents transaction scope "clone"
         # below from writing in-memory changes out at the end of it,
         # even though in-memory changes are discarded at the end of it
         # regardless of transaction nesting.
         #
         # But transaction nesting can't be simply prohibited, because
         # nesting occurs also in ordinary case (e.g. enabling
         # clonebundles).
 
         with repo.transaction('clone'):
             with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                 for i in pycompat.xrange(filecount):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split('\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _('unexpected response from remote server:'), l)
                     if repo.ui.debugflag:
                         repo.ui.debug('adding %s (%s)\n' %
                                       (name, util.bytecount(size)))
                     # for backwards compat, name was partially encoded
                     path = store.decodedir(name)
                     with repo.svfs(path, 'w', backgroundclose=True) as ofp:
                         for chunk in util.filechunkiter(fp, limit=size):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         progress.complete()
         repo.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(bytecount), elapsed,
                         util.bytecount(bytecount / elapsed)))
 
 def readbundle1header(fp):
     compression = fp.read(2)
     if compression != 'UN':
         raise error.Abort(_('only uncompressed stream clone bundles are '
             'supported; got %s') % compression)
 
     filecount, bytecount = struct.unpack('>QQ', fp.read(16))
     requireslen = struct.unpack('>H', fp.read(2))[0]
     requires = fp.read(requireslen)
 
     if not requires.endswith('\0'):
         raise error.Abort(_('malformed stream clone bundle: '
                             'requirements not properly encoded'))
 
     requirements = set(requires.rstrip('\0').split(','))
 
     return filecount, bytecount, requirements
 
 def applybundlev1(repo, fp):
     """Apply the content from a stream clone bundle version 1.
 
     We assume the 4 byte header has been read and validated and the file handle
     is at the 2 byte compression identifier.
     """
     if len(repo):
         raise error.Abort(_('cannot apply stream clone bundle on non-empty '
                             'repo'))
 
     filecount, bytecount, requirements = readbundle1header(fp)
     missingreqs = requirements - repo.supportedformats
     if missingreqs:
         raise error.Abort(_('unable to apply stream clone: '
                             'unsupported format: %s') %
                             ', '.join(sorted(missingreqs)))
 
     consumev1(repo, fp, filecount, bytecount)
 
 class streamcloneapplier(object):
     """Class to manage applying streaming clone bundles.
 
     We need to wrap ``applybundlev1()`` in a dedicated type to enable bundle
     readers to perform bundle type-specific functionality.
     """
     def __init__(self, fh):
         self._fh = fh
 
     def apply(self, repo):
         return applybundlev1(repo, self._fh)
 
 # type of file to stream
 _fileappend = 0 # append only file
 _filefull = 1   # full snapshot file
 
 # Source of the file
 _srcstore = 's' # store (svfs)
 _srccache = 'c' # cache (cache)
 
 # This is it's own function so extensions can override it.
 def _walkstreamfullstorefiles(repo):
     """list snapshot file from the store"""
     fnames = []
     if not repo.publishing():
         fnames.append('phaseroots')
     return fnames
 
 def _filterfull(entry, copy, vfsmap):
     """actually copy the snapshot files"""
     src, name, ftype, data = entry
     if ftype != _filefull:
         return entry
     return (src, name, ftype, copy(vfsmap[src].join(name)))
 
 @contextlib.contextmanager
 def maketempcopies():
     """return a function to temporary copy file"""
     files = []
     try:
         def copy(src):
             fd, dst = pycompat.mkstemp()
             os.close(fd)
             files.append(dst)
             util.copyfiles(src, dst, hardlink=True)
             return dst
         yield copy
     finally:
         for tmp in files:
             util.tryunlink(tmp)
 
 def _makemap(repo):
     """make a (src -> vfs) map for the repo"""
     vfsmap = {
         _srcstore: repo.svfs,
         _srccache: repo.cachevfs,
     }
     # we keep repo.vfs out of the on purpose, ther are too many danger there
     # (eg: .hg/hgrc)
     assert repo.vfs not in vfsmap.values()
 
     return vfsmap
 
 def _emit2(repo, entries, totalfilesize):
     """actually emit the stream bundle"""
     vfsmap = _makemap(repo)
     progress = repo.ui.makeprogress(_('bundle'), total=totalfilesize,
                                     unit=_('bytes'))
     progress.update(0)
     with maketempcopies() as copy, progress:
         # copy is delayed until we are in the try
         entries = [_filterfull(e, copy, vfsmap) for e in entries]
         yield None # this release the lock on the repository
         seen = 0
 
         for src, name, ftype, data in entries:
             vfs = vfsmap[src]
             yield src
             yield util.uvarintencode(len(name))
             if ftype == _fileappend:
                 fp = vfs(name)
                 size = data
             elif ftype == _filefull:
                 fp = open(data, 'rb')
                 size = util.fstat(fp).st_size
             try:
                 yield util.uvarintencode(size)
                 yield name
                 if size <= 65536:
                     chunks = (fp.read(size),)
                 else:
                     chunks = util.filechunkiter(fp, limit=size)
                 for chunk in chunks:
                     seen += len(chunk)
                     progress.update(seen)
                     yield chunk
             finally:
                 fp.close()
 
 def generatev2(repo, includes, excludes, includeobsmarkers):
     """Emit content for version 2 of a streaming clone.
 
     the data stream consists the following entries:
     1) A char representing the file destination (eg: store or cache)
     2) A varint containing the length of the filename
     3) A varint containing the length of file data
     4) N bytes containing the filename (the internal, store-agnostic form)
     5) N bytes containing the file data
 
     Returns a 3-tuple of (file count, file size, data iterator).
     """
 
     with repo.lock():
 
         entries = []
         totalfilesize = 0
 
         matcher = None
         if includes or excludes:
             matcher = narrowspec.match(repo.root, includes, excludes)
 
         repo.ui.debug('scanning\n')
         for name, ename, size in _walkstreamfiles(repo, matcher):
             if size:
                 entries.append((_srcstore, name, _fileappend, size))
                 totalfilesize += size
         for name in _walkstreamfullstorefiles(repo):
             if repo.svfs.exists(name):
                 totalfilesize += repo.svfs.lstat(name).st_size
                 entries.append((_srcstore, name, _filefull, None))
         if includeobsmarkers and repo.svfs.exists('obsstore'):
             totalfilesize += repo.svfs.lstat('obsstore').st_size
             entries.append((_srcstore, 'obsstore', _filefull, None))
         for name in cacheutil.cachetocopy(repo):
             if repo.cachevfs.exists(name):
                 totalfilesize += repo.cachevfs.lstat(name).st_size
                 entries.append((_srccache, name, _filefull, None))
 
         chunks = _emit2(repo, entries, totalfilesize)
         first = next(chunks)
         assert first is None
 
     return len(entries), totalfilesize, chunks
 
 @contextlib.contextmanager
 def nested(*ctxs):
     this = ctxs[0]
     rest = ctxs[1:]
     with this:
         if rest:
             with nested(*rest):
                 yield
         else:
             yield
 
 def consumev2(repo, fp, filecount, filesize):
     """Apply the contents from a version 2 streaming clone.
 
     Data is read from an object that only needs to provide a ``read(size)``
     method.
     """
     with repo.lock():
         repo.ui.status(_('%d files to transfer, %s of data\n') %
                        (filecount, util.bytecount(filesize)))
 
         start = util.timer()
         progress = repo.ui.makeprogress(_('clone'), total=filesize,
                                         unit=_('bytes'))
         progress.update(0)
 
         vfsmap = _makemap(repo)
 
         with repo.transaction('clone'):
             ctxs = (vfs.backgroundclosing(repo.ui)
                     for vfs in vfsmap.values())
             with nested(*ctxs):
                 for i in range(filecount):
                     src = util.readexactly(fp, 1)
                     vfs = vfsmap[src]
                     namelen = util.uvarintdecodestream(fp)
                     datalen = util.uvarintdecodestream(fp)
 
                     name = util.readexactly(fp, namelen)
 
                     if repo.ui.debugflag:
                         repo.ui.debug('adding [%s] %s (%s)\n' %
                                       (src, name, util.bytecount(datalen)))
 
                     with vfs(name, 'w') as ofp:
                         for chunk in util.filechunkiter(fp, limit=datalen):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         repo.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(progress.pos), elapsed,
                         util.bytecount(progress.pos / elapsed)))
         progress.complete()
 
 def applybundlev2(repo, fp, filecount, filesize, requirements):
     from . import localrepo
 
     missingreqs = [r for r in requirements if r not in repo.supported]
     if missingreqs:
         raise error.Abort(_('unable to apply stream clone: '
                             'unsupported format: %s') %
                           ', '.join(sorted(missingreqs)))
 
     consumev2(repo, fp, filecount, filesize)
 
     # new requirements = old non-format requirements +
     #                    new format-related remote requirements
     # requirements from the streamed-in repository
     repo.requirements = set(requirements) | (
             repo.requirements - repo.supportedformats)
     repo.svfs.options = localrepo.resolvestorevfsoptions(
         repo.ui, repo.requirements, repo.features)
     repo._writerequirements()

mercurial/testing/storage.py

@@ -1,1346 +1,1348
 # storage.py - Testing of storage primitives.
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import unittest
 
 from ..node import (
     hex,
     nullid,
     nullrev,
 )
 from .. import (
     error,
     mdiff,
+)
+from ..interfaces import (
     repository,
 )
 from ..utils import (
     storageutil,
 )
 
 class basetestcase(unittest.TestCase):
     if not getattr(unittest.TestCase, r'assertRaisesRegex', False):
         assertRaisesRegex = (# camelcase-required
             unittest.TestCase.assertRaisesRegexp)
 
 class ifileindextests(basetestcase):
     """Generic tests for the ifileindex interface.
 
     All file storage backends for index data should conform to the tests in this
     class.
 
     Use ``makeifileindextests()`` to create an instance of this type.
     """
     def testempty(self):
         f = self._makefilefn()
         self.assertEqual(len(f), 0, 'new file store has 0 length by default')
         self.assertEqual(list(f), [], 'iter yields nothing by default')
 
         gen = iter(f)
         with self.assertRaises(StopIteration):
             next(gen)
 
         self.assertFalse(f.hasnode(None))
         self.assertFalse(f.hasnode(0))
         self.assertFalse(f.hasnode(nullrev))
         self.assertFalse(f.hasnode(nullid))
         self.assertFalse(f.hasnode(b'0'))
         self.assertFalse(f.hasnode(b'a' * 20))
 
         # revs() should evaluate to an empty list.
         self.assertEqual(list(f.revs()), [])
 
         revs = iter(f.revs())
         with self.assertRaises(StopIteration):
             next(revs)
 
         self.assertEqual(list(f.revs(start=20)), [])
 
         # parents() and parentrevs() work with nullid/nullrev.
         self.assertEqual(f.parents(nullid), (nullid, nullid))
         self.assertEqual(f.parentrevs(nullrev), (nullrev, nullrev))
 
         with self.assertRaises(error.LookupError):
             f.parents(b'\x01' * 20)
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(IndexError):
                 f.parentrevs(i)
 
         # nullid/nullrev lookup always works.
         self.assertEqual(f.rev(nullid), nullrev)
         self.assertEqual(f.node(nullrev), nullid)
 
         with self.assertRaises(error.LookupError):
             f.rev(b'\x01' * 20)
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(IndexError):
                 f.node(i)
 
         self.assertEqual(f.lookup(nullid), nullid)
         self.assertEqual(f.lookup(nullrev), nullid)
         self.assertEqual(f.lookup(hex(nullid)), nullid)
         self.assertEqual(f.lookup(b'%d' % nullrev), nullid)
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'badvalue')
 
         with self.assertRaises(error.LookupError):
             f.lookup(hex(nullid)[0:12])
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'-2')
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'0')
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'1')
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'11111111111111111111111111111111111111')
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(LookupError):
                 f.lookup(i)
 
         self.assertEqual(f.linkrev(nullrev), nullrev)
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(IndexError):
                 f.linkrev(i)
 
         self.assertFalse(f.iscensored(nullrev))
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(IndexError):
                 f.iscensored(i)
 
         self.assertEqual(list(f.commonancestorsheads(nullid, nullid)), [])
 
         with self.assertRaises(ValueError):
             self.assertEqual(list(f.descendants([])), [])
 
         self.assertEqual(list(f.descendants([nullrev])), [])
 
         self.assertEqual(f.heads(), [nullid])
         self.assertEqual(f.heads(nullid), [nullid])
         self.assertEqual(f.heads(None, [nullid]), [nullid])
         self.assertEqual(f.heads(nullid, [nullid]), [nullid])
 
         self.assertEqual(f.children(nullid), [])
 
         with self.assertRaises(error.LookupError):
             f.children(b'\x01' * 20)
 
     def testsinglerevision(self):
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node = f.add(b'initial', None, tr, 0, nullid, nullid)
 
         self.assertEqual(len(f), 1)
         self.assertEqual(list(f), [0])
 
         gen = iter(f)
         self.assertEqual(next(gen), 0)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         self.assertTrue(f.hasnode(node))
         self.assertFalse(f.hasnode(hex(node)))
         self.assertFalse(f.hasnode(nullrev))
         self.assertFalse(f.hasnode(nullid))
         self.assertFalse(f.hasnode(node[0:12]))
         self.assertFalse(f.hasnode(hex(node)[0:20]))
 
         self.assertEqual(list(f.revs()), [0])
         self.assertEqual(list(f.revs(start=1)), [])
         self.assertEqual(list(f.revs(start=0)), [0])
         self.assertEqual(list(f.revs(stop=0)), [0])
         self.assertEqual(list(f.revs(stop=1)), [0])
         self.assertEqual(list(f.revs(1, 1)), [])
         # TODO buggy
         self.assertEqual(list(f.revs(1, 0)), [1, 0])
         self.assertEqual(list(f.revs(2, 0)), [2, 1, 0])
 
         self.assertEqual(f.parents(node), (nullid, nullid))
         self.assertEqual(f.parentrevs(0), (nullrev, nullrev))
 
         with self.assertRaises(error.LookupError):
             f.parents(b'\x01' * 20)
 
         with self.assertRaises(IndexError):
             f.parentrevs(1)
 
         self.assertEqual(f.rev(node), 0)
 
         with self.assertRaises(error.LookupError):
             f.rev(b'\x01' * 20)
 
         self.assertEqual(f.node(0), node)
 
         with self.assertRaises(IndexError):
             f.node(1)
 
         self.assertEqual(f.lookup(node), node)
         self.assertEqual(f.lookup(0), node)
         self.assertEqual(f.lookup(-1), nullid)
         self.assertEqual(f.lookup(b'0'), node)
         self.assertEqual(f.lookup(hex(node)), node)
 
         with self.assertRaises(error.LookupError):
             f.lookup(hex(node)[0:12])
 
         with self.assertRaises(error.LookupError):
             f.lookup(-2)
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'-2')
 
         with self.assertRaises(error.LookupError):
             f.lookup(1)
 
         with self.assertRaises(error.LookupError):
             f.lookup(b'1')
 
         self.assertEqual(f.linkrev(0), 0)
 
         with self.assertRaises(IndexError):
             f.linkrev(1)
 
         self.assertFalse(f.iscensored(0))
 
         with self.assertRaises(IndexError):
             f.iscensored(1)
 
         self.assertEqual(list(f.descendants([0])), [])
 
         self.assertEqual(f.heads(), [node])
         self.assertEqual(f.heads(node), [node])
         self.assertEqual(f.heads(stop=[node]), [node])
 
         with self.assertRaises(error.LookupError):
             f.heads(stop=[b'\x01' * 20])
 
         self.assertEqual(f.children(node), [])
 
     def testmultiplerevisions(self):
         fulltext0 = b'x' * 1024
         fulltext1 = fulltext0 + b'y'
         fulltext2 = b'y' + fulltext0 + b'z'
 
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = f.add(fulltext1, None, tr, 1, node0, nullid)
             node2 = f.add(fulltext2, None, tr, 3, node1, nullid)
 
         self.assertEqual(len(f), 3)
         self.assertEqual(list(f), [0, 1, 2])
 
         gen = iter(f)
         self.assertEqual(next(gen), 0)
         self.assertEqual(next(gen), 1)
         self.assertEqual(next(gen), 2)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         self.assertEqual(list(f.revs()), [0, 1, 2])
         self.assertEqual(list(f.revs(0)), [0, 1, 2])
         self.assertEqual(list(f.revs(1)), [1, 2])
         self.assertEqual(list(f.revs(2)), [2])
         self.assertEqual(list(f.revs(3)), [])
         self.assertEqual(list(f.revs(stop=1)), [0, 1])
         self.assertEqual(list(f.revs(stop=2)), [0, 1, 2])
         self.assertEqual(list(f.revs(stop=3)), [0, 1, 2])
         self.assertEqual(list(f.revs(2, 0)), [2, 1, 0])
         self.assertEqual(list(f.revs(2, 1)), [2, 1])
         # TODO this is wrong
         self.assertEqual(list(f.revs(3, 2)), [3, 2])
 
         self.assertEqual(f.parents(node0), (nullid, nullid))
         self.assertEqual(f.parents(node1), (node0, nullid))
         self.assertEqual(f.parents(node2), (node1, nullid))
 
         self.assertEqual(f.parentrevs(0), (nullrev, nullrev))
         self.assertEqual(f.parentrevs(1), (0, nullrev))
         self.assertEqual(f.parentrevs(2), (1, nullrev))
 
         self.assertEqual(f.rev(node0), 0)
         self.assertEqual(f.rev(node1), 1)
         self.assertEqual(f.rev(node2), 2)
 
         with self.assertRaises(error.LookupError):
             f.rev(b'\x01' * 20)
 
         self.assertEqual(f.node(0), node0)
         self.assertEqual(f.node(1), node1)
         self.assertEqual(f.node(2), node2)
 
         with self.assertRaises(IndexError):
             f.node(3)
 
         self.assertEqual(f.lookup(node0), node0)
         self.assertEqual(f.lookup(0), node0)
         self.assertEqual(f.lookup(b'0'), node0)
         self.assertEqual(f.lookup(hex(node0)), node0)
 
         self.assertEqual(f.lookup(node1), node1)
         self.assertEqual(f.lookup(1), node1)
         self.assertEqual(f.lookup(b'1'), node1)
         self.assertEqual(f.lookup(hex(node1)), node1)
 
         self.assertEqual(f.linkrev(0), 0)
         self.assertEqual(f.linkrev(1), 1)
         self.assertEqual(f.linkrev(2), 3)
 
         with self.assertRaises(IndexError):
             f.linkrev(3)
 
         self.assertFalse(f.iscensored(0))
         self.assertFalse(f.iscensored(1))
         self.assertFalse(f.iscensored(2))
 
         with self.assertRaises(IndexError):
             f.iscensored(3)
 
         self.assertEqual(f.commonancestorsheads(node1, nullid), [])
         self.assertEqual(f.commonancestorsheads(node1, node0), [node0])
         self.assertEqual(f.commonancestorsheads(node1, node1), [node1])
         self.assertEqual(f.commonancestorsheads(node0, node1), [node0])
         self.assertEqual(f.commonancestorsheads(node1, node2), [node1])
         self.assertEqual(f.commonancestorsheads(node2, node1), [node1])
 
         self.assertEqual(list(f.descendants([0])), [1, 2])
         self.assertEqual(list(f.descendants([1])), [2])
         self.assertEqual(list(f.descendants([0, 1])), [1, 2])
 
         self.assertEqual(f.heads(), [node2])
         self.assertEqual(f.heads(node0), [node2])
         self.assertEqual(f.heads(node1), [node2])
         self.assertEqual(f.heads(node2), [node2])
 
         # TODO this behavior seems wonky. Is it correct? If so, the
         # docstring for heads() should be updated to reflect desired
         # behavior.
         self.assertEqual(f.heads(stop=[node1]), [node1, node2])
         self.assertEqual(f.heads(stop=[node0]), [node0, node2])
         self.assertEqual(f.heads(stop=[node1, node2]), [node1, node2])
 
         with self.assertRaises(error.LookupError):
             f.heads(stop=[b'\x01' * 20])
 
         self.assertEqual(f.children(node0), [node1])
         self.assertEqual(f.children(node1), [node2])
         self.assertEqual(f.children(node2), [])
 
     def testmultipleheads(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'0', None, tr, 0, nullid, nullid)
             node1 = f.add(b'1', None, tr, 1, node0, nullid)
             node2 = f.add(b'2', None, tr, 2, node1, nullid)
             node3 = f.add(b'3', None, tr, 3, node0, nullid)
             node4 = f.add(b'4', None, tr, 4, node3, nullid)
             node5 = f.add(b'5', None, tr, 5, node0, nullid)
 
         self.assertEqual(len(f), 6)
 
         self.assertEqual(list(f.descendants([0])), [1, 2, 3, 4, 5])
         self.assertEqual(list(f.descendants([1])), [2])
         self.assertEqual(list(f.descendants([2])), [])
         self.assertEqual(list(f.descendants([3])), [4])
         self.assertEqual(list(f.descendants([0, 1])), [1, 2, 3, 4, 5])
         self.assertEqual(list(f.descendants([1, 3])), [2, 4])
 
         self.assertEqual(f.heads(), [node2, node4, node5])
         self.assertEqual(f.heads(node0), [node2, node4, node5])
         self.assertEqual(f.heads(node1), [node2])
         self.assertEqual(f.heads(node2), [node2])
         self.assertEqual(f.heads(node3), [node4])
         self.assertEqual(f.heads(node4), [node4])
         self.assertEqual(f.heads(node5), [node5])
 
         # TODO this seems wrong.
         self.assertEqual(f.heads(stop=[node0]), [node0, node2, node4, node5])
         self.assertEqual(f.heads(stop=[node1]), [node1, node2, node4, node5])
 
         self.assertEqual(f.children(node0), [node1, node3, node5])
         self.assertEqual(f.children(node1), [node2])
         self.assertEqual(f.children(node2), [])
         self.assertEqual(f.children(node3), [node4])
         self.assertEqual(f.children(node4), [])
         self.assertEqual(f.children(node5), [])
 
 class ifiledatatests(basetestcase):
     """Generic tests for the ifiledata interface.
 
     All file storage backends for data should conform to the tests in this
     class.
 
     Use ``makeifiledatatests()`` to create an instance of this type.
     """
     def testempty(self):
         f = self._makefilefn()
 
         self.assertEqual(f.storageinfo(), {})
         self.assertEqual(f.storageinfo(revisionscount=True, trackedsize=True),
                          {'revisionscount': 0, 'trackedsize': 0})
 
         self.assertEqual(f.size(nullrev), 0)
 
         for i in range(-5, 5):
             if i == nullrev:
                 continue
 
             with self.assertRaises(IndexError):
                 f.size(i)
 
         self.assertEqual(f.revision(nullid), b'')
         self.assertEqual(f.rawdata(nullid), b'')
 
         with self.assertRaises(error.LookupError):
             f.revision(b'\x01' * 20)
 
         self.assertEqual(f.read(nullid), b'')
 
         with self.assertRaises(error.LookupError):
             f.read(b'\x01' * 20)
 
         self.assertFalse(f.renamed(nullid))
 
         with self.assertRaises(error.LookupError):
             f.read(b'\x01' * 20)
 
         self.assertTrue(f.cmp(nullid, b''))
         self.assertTrue(f.cmp(nullid, b'foo'))
 
         with self.assertRaises(error.LookupError):
             f.cmp(b'\x01' * 20, b'irrelevant')
 
         # Emitting empty list is an empty generator.
         gen = f.emitrevisions([])
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Emitting null node yields nothing.
         gen = f.emitrevisions([nullid])
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Requesting unknown node fails.
         with self.assertRaises(error.LookupError):
             list(f.emitrevisions([b'\x01' * 20]))
 
     def testsinglerevision(self):
         fulltext = b'initial'
 
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node = f.add(fulltext, None, tr, 0, nullid, nullid)
 
         self.assertEqual(f.storageinfo(), {})
         self.assertEqual(f.storageinfo(revisionscount=True, trackedsize=True),
                          {'revisionscount': 1, 'trackedsize': len(fulltext)})
 
         self.assertEqual(f.size(0), len(fulltext))
 
         with self.assertRaises(IndexError):
             f.size(1)
 
         self.assertEqual(f.revision(node), fulltext)
         self.assertEqual(f.rawdata(node), fulltext)
 
         self.assertEqual(f.read(node), fulltext)
 
         self.assertFalse(f.renamed(node))
 
         self.assertFalse(f.cmp(node, fulltext))
         self.assertTrue(f.cmp(node, fulltext + b'extra'))
 
         # Emitting a single revision works.
         gen = f.emitrevisions([node])
         rev = next(gen)
 
         self.assertEqual(rev.node, node)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertIsNone(rev.delta)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Requesting revision data works.
         gen = f.emitrevisions([node], revisiondata=True)
         rev = next(gen)
 
         self.assertEqual(rev.node, node)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertEqual(rev.revision, fulltext)
         self.assertIsNone(rev.delta)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Emitting an unknown node after a known revision results in error.
         with self.assertRaises(error.LookupError):
             list(f.emitrevisions([node, b'\x01' * 20]))
 
     def testmultiplerevisions(self):
         fulltext0 = b'x' * 1024
         fulltext1 = fulltext0 + b'y'
         fulltext2 = b'y' + fulltext0 + b'z'
 
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = f.add(fulltext1, None, tr, 1, node0, nullid)
             node2 = f.add(fulltext2, None, tr, 3, node1, nullid)
 
         self.assertEqual(f.storageinfo(), {})
         self.assertEqual(
             f.storageinfo(revisionscount=True, trackedsize=True),
             {
                 'revisionscount': 3,
                 'trackedsize': len(fulltext0) + len(fulltext1) + len(fulltext2),
             })
 
         self.assertEqual(f.size(0), len(fulltext0))
         self.assertEqual(f.size(1), len(fulltext1))
         self.assertEqual(f.size(2), len(fulltext2))
 
         with self.assertRaises(IndexError):
             f.size(3)
 
         self.assertEqual(f.revision(node0), fulltext0)
         self.assertEqual(f.rawdata(node0), fulltext0)
         self.assertEqual(f.revision(node1), fulltext1)
         self.assertEqual(f.rawdata(node1), fulltext1)
         self.assertEqual(f.revision(node2), fulltext2)
         self.assertEqual(f.rawdata(node2), fulltext2)
 
         with self.assertRaises(error.LookupError):
             f.revision(b'\x01' * 20)
 
         self.assertEqual(f.read(node0), fulltext0)
         self.assertEqual(f.read(node1), fulltext1)
         self.assertEqual(f.read(node2), fulltext2)
 
         with self.assertRaises(error.LookupError):
             f.read(b'\x01' * 20)
 
         self.assertFalse(f.renamed(node0))
         self.assertFalse(f.renamed(node1))
         self.assertFalse(f.renamed(node2))
 
         with self.assertRaises(error.LookupError):
             f.renamed(b'\x01' * 20)
 
         self.assertFalse(f.cmp(node0, fulltext0))
         self.assertFalse(f.cmp(node1, fulltext1))
         self.assertFalse(f.cmp(node2, fulltext2))
 
         self.assertTrue(f.cmp(node1, fulltext0))
         self.assertTrue(f.cmp(node2, fulltext1))
 
         with self.assertRaises(error.LookupError):
             f.cmp(b'\x01' * 20, b'irrelevant')
 
         # Nodes should be emitted in order.
         gen = f.emitrevisions([node0, node1, node2], revisiondata=True)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node0)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertEqual(rev.revision, fulltext0)
         self.assertIsNone(rev.delta)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node1)
         self.assertEqual(rev.p1node, node0)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, node0)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x04\x01' +
                          fulltext1)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node2)
         self.assertEqual(rev.p1node, node1)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, node1)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x01\x00\x00\x04\x02' +
                          fulltext2)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Request not in DAG order is reordered to be in DAG order.
         gen = f.emitrevisions([node2, node1, node0], revisiondata=True)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node0)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertEqual(rev.revision, fulltext0)
         self.assertIsNone(rev.delta)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node1)
         self.assertEqual(rev.p1node, node0)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, node0)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x04\x01' +
                          fulltext1)
 
         rev = next(gen)
 
         self.assertEqual(rev.node, node2)
         self.assertEqual(rev.p1node, node1)
         self.assertEqual(rev.p2node, nullid)
         self.assertIsNone(rev.linknode)
         self.assertEqual(rev.basenode, node1)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x01\x00\x00\x04\x02' +
                          fulltext2)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # Unrecognized nodesorder value raises ProgrammingError.
         with self.assertRaises(error.ProgrammingError):
             list(f.emitrevisions([], nodesorder='bad'))
 
         # nodesorder=storage is recognized. But we can't test it thoroughly
         # because behavior is storage-dependent.
         res = list(f.emitrevisions([node2, node1, node0],
                                          nodesorder='storage'))
         self.assertEqual(len(res), 3)
         self.assertEqual({o.node for o in res}, {node0, node1, node2})
 
         # nodesorder=nodes forces the order.
         gen = f.emitrevisions([node2, node0], nodesorder='nodes',
                               revisiondata=True)
 
         rev = next(gen)
         self.assertEqual(rev.node, node2)
         self.assertEqual(rev.p1node, node1)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertEqual(rev.revision, fulltext2)
         self.assertIsNone(rev.delta)
 
         rev = next(gen)
         self.assertEqual(rev.node, node0)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         # Delta behavior is storage dependent, so we can't easily test it.
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # assumehaveparentrevisions=False (the default) won't send a delta for
         # the first revision.
         gen = f.emitrevisions({node2, node1}, revisiondata=True)
 
         rev = next(gen)
         self.assertEqual(rev.node, node1)
         self.assertEqual(rev.p1node, node0)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertEqual(rev.revision, fulltext1)
         self.assertIsNone(rev.delta)
 
         rev = next(gen)
         self.assertEqual(rev.node, node2)
         self.assertEqual(rev.p1node, node1)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, node1)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x01\x00\x00\x04\x02' +
                          fulltext2)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         # assumehaveparentrevisions=True allows delta against initial revision.
         gen = f.emitrevisions([node2, node1],
                               revisiondata=True, assumehaveparentrevisions=True)
 
         rev = next(gen)
         self.assertEqual(rev.node, node1)
         self.assertEqual(rev.p1node, node0)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, node0)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x04\x01' +
                          fulltext1)
 
         # forceprevious=True forces a delta against the previous revision.
         # Special case for initial revision.
         gen = f.emitrevisions([node0], revisiondata=True,
                               deltamode=repository.CG_DELTAMODE_PREV)
 
         rev = next(gen)
         self.assertEqual(rev.node, node0)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00' +
                          fulltext0)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
         gen = f.emitrevisions([node0, node2], revisiondata=True,
                               deltamode=repository.CG_DELTAMODE_PREV)
 
         rev = next(gen)
         self.assertEqual(rev.node, node0)
         self.assertEqual(rev.p1node, nullid)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, nullid)
         self.assertIsNone(rev.baserevisionsize)
         self.assertIsNone(rev.revision)
         self.assertEqual(rev.delta,
                          b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00' +
                          fulltext0)
 
         rev = next(gen)
         self.assertEqual(rev.node, node2)
         self.assertEqual(rev.p1node, node1)
         self.assertEqual(rev.p2node, nullid)
         self.assertEqual(rev.basenode, node0)
 
         with self.assertRaises(StopIteration):
             next(gen)
 
     def testrenamed(self):
         fulltext0 = b'foo'
         fulltext1 = b'bar'
         fulltext2 = b'baz'
 
         meta1 = {
             b'copy': b'source0',
             b'copyrev': b'a' * 40,
         }
 
         meta2 = {
             b'copy': b'source1',
             b'copyrev': b'b' * 40,
         }
 
         stored1 = b''.join([
             b'\x01\ncopy: source0\n',
             b'copyrev: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\n\x01\n',
             fulltext1,
         ])
 
         stored2 = b''.join([
             b'\x01\ncopy: source1\n',
             b'copyrev: bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb\n\x01\n',
             fulltext2,
         ])
 
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = f.add(fulltext1, meta1, tr, 1, node0, nullid)
             node2 = f.add(fulltext2, meta2, tr, 2, nullid, nullid)
 
         # Metadata header isn't recognized when parent isn't nullid.
         self.assertEqual(f.size(1), len(stored1))
         self.assertEqual(f.size(2), len(fulltext2))
 
         self.assertEqual(f.revision(node1), stored1)
         self.assertEqual(f.rawdata(node1), stored1)
         self.assertEqual(f.revision(node2), stored2)
         self.assertEqual(f.rawdata(node2), stored2)
 
         self.assertEqual(f.read(node1), fulltext1)
         self.assertEqual(f.read(node2), fulltext2)
 
         # Returns False when first parent is set.
         self.assertFalse(f.renamed(node1))
         self.assertEqual(f.renamed(node2), (b'source1', b'\xbb' * 20))
 
         self.assertTrue(f.cmp(node1, fulltext1))
         self.assertTrue(f.cmp(node1, stored1))
         self.assertFalse(f.cmp(node2, fulltext2))
         self.assertTrue(f.cmp(node2, stored2))
 
     def testmetadataprefix(self):
         # Content with metadata prefix has extra prefix inserted in storage.
         fulltext0 = b'\x01\nfoo'
         stored0 = b'\x01\n\x01\n\x01\nfoo'
 
         fulltext1 = b'\x01\nbar'
         meta1 = {
             b'copy': b'source0',
             b'copyrev': b'b' * 40,
         }
         stored1 = b''.join([
             b'\x01\ncopy: source0\n',
             b'copyrev: %s\n' % (b'b' * 40),
             b'\x01\n\x01\nbar',
         ])
 
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, {}, tr, 0, nullid, nullid)
             node1 = f.add(fulltext1, meta1, tr, 1, nullid, nullid)
 
         # TODO this is buggy.
         self.assertEqual(f.size(0), len(fulltext0) + 4)
 
         self.assertEqual(f.size(1), len(fulltext1))
 
         self.assertEqual(f.revision(node0), stored0)
         self.assertEqual(f.rawdata(node0), stored0)
 
         self.assertEqual(f.revision(node1), stored1)
         self.assertEqual(f.rawdata(node1), stored1)
 
         self.assertEqual(f.read(node0), fulltext0)
         self.assertEqual(f.read(node1), fulltext1)
 
         self.assertFalse(f.cmp(node0, fulltext0))
         self.assertTrue(f.cmp(node0, stored0))
 
         self.assertFalse(f.cmp(node1, fulltext1))
         self.assertTrue(f.cmp(node1, stored0))
 
     def testbadnoderead(self):
         f = self._makefilefn()
 
         fulltext0 = b'foo\n' * 30
         fulltext1 = fulltext0 + b'bar\n'
 
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = b'\xaa' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1,
                                    rawtext=fulltext1)
 
         self.assertEqual(len(f), 2)
         self.assertEqual(f.parents(node1), (node0, nullid))
 
         # revision() raises since it performs hash verification.
         with self.assertRaises(error.StorageError):
             f.revision(node1)
 
         # rawdata() still verifies because there are no special storage
         # settings.
         with self.assertRaises(error.StorageError):
             f.rawdata(node1)
 
         # read() behaves like revision().
         with self.assertRaises(error.StorageError):
             f.read(node1)
 
         # We can't test renamed() here because some backends may not require
         # reading/validating the fulltext to return rename metadata.
 
     def testbadnoderevisionraw(self):
         # Like above except we test rawdata() first to isolate
         # revision caching behavior.
         f = self._makefilefn()
 
         fulltext0 = b'foo\n' * 30
         fulltext1 = fulltext0 + b'bar\n'
 
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = b'\xaa' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1,
                                    rawtext=fulltext1)
 
         with self.assertRaises(error.StorageError):
             f.rawdata(node1)
 
         with self.assertRaises(error.StorageError):
             f.rawdata(node1)
 
     def testbadnoderevisionraw(self):
         # Like above except we test read() first to isolate revision caching
         # behavior.
         f = self._makefilefn()
 
         fulltext0 = b'foo\n' * 30
         fulltext1 = fulltext0 + b'bar\n'
 
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = b'\xaa' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1,
                                    rawtext=fulltext1)
 
         with self.assertRaises(error.StorageError):
             f.read(node1)
 
         with self.assertRaises(error.StorageError):
             f.read(node1)
 
     def testbadnodedelta(self):
         f = self._makefilefn()
 
         fulltext0 = b'foo\n' * 31
         fulltext1 = fulltext0 + b'bar\n'
         fulltext2 = fulltext1 + b'baz\n'
 
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
             node1 = b'\xaa' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1,
                                    rawtext=fulltext1)
 
         with self.assertRaises(error.StorageError):
             f.read(node1)
 
         node2 = storageutil.hashrevisionsha1(fulltext2, node1, nullid)
 
         with self._maketransactionfn() as tr:
             delta = mdiff.textdiff(fulltext1, fulltext2)
             self._addrawrevisionfn(f, tr, node2, node1, nullid,
                                    2, delta=(1, delta))
 
         self.assertEqual(len(f), 3)
 
         # Assuming a delta is stored, we shouldn't need to validate node1 in
         # order to retrieve node2.
         self.assertEqual(f.read(node2), fulltext2)
 
     def testcensored(self):
         f = self._makefilefn()
 
         stored1 = storageutil.packmeta({
             b'censored': b'tombstone',
         }, b'')
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'foo', None, tr, 0, nullid, nullid)
 
             # The node value doesn't matter since we can't verify it.
             node1 = b'\xbb' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1, stored1,
                                    censored=True)
 
         self.assertTrue(f.iscensored(1))
 
         with self.assertRaises(error.CensoredNodeError):
             f.revision(1)
 
         with self.assertRaises(error.CensoredNodeError):
             f.rawdata(1)
 
         with self.assertRaises(error.CensoredNodeError):
             f.read(1)
 
     def testcensoredrawrevision(self):
         # Like above, except we do the rawdata() request first to
         # isolate revision caching behavior.
 
         f = self._makefilefn()
 
         stored1 = storageutil.packmeta({
             b'censored': b'tombstone',
         }, b'')
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'foo', None, tr, 0, nullid, nullid)
 
             # The node value doesn't matter since we can't verify it.
             node1 = b'\xbb' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1, stored1,
                                    censored=True)
 
         with self.assertRaises(error.CensoredNodeError):
             f.rawdata(1)
 
 class ifilemutationtests(basetestcase):
     """Generic tests for the ifilemutation interface.
 
     All file storage backends that support writing should conform to this
     interface.
 
     Use ``makeifilemutationtests()`` to create an instance of this type.
     """
     def testaddnoop(self):
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             node0 = f.add(b'foo', None, tr, 0, nullid, nullid)
             node1 = f.add(b'foo', None, tr, 0, nullid, nullid)
             # Varying by linkrev shouldn't impact hash.
             node2 = f.add(b'foo', None, tr, 1, nullid, nullid)
 
         self.assertEqual(node1, node0)
         self.assertEqual(node2, node0)
         self.assertEqual(len(f), 1)
 
     def testaddrevisionbadnode(self):
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             # Adding a revision with bad node value fails.
             with self.assertRaises(error.StorageError):
                 f.addrevision(b'foo', tr, 0, nullid, nullid, node=b'\x01' * 20)
 
     def testaddrevisionunknownflag(self):
         f = self._makefilefn()
         with self._maketransactionfn() as tr:
             for i in range(15, 0, -1):
                 if (1 << i) & ~repository.REVISION_FLAGS_KNOWN:
                     flags = 1 << i
                     break
 
             with self.assertRaises(error.StorageError):
                 f.addrevision(b'foo', tr, 0, nullid, nullid, flags=flags)
 
     def testaddgroupsimple(self):
         f = self._makefilefn()
 
         callbackargs = []
         def cb(*args, **kwargs):
             callbackargs.append((args, kwargs))
 
         def linkmapper(node):
             return 0
 
         with self._maketransactionfn() as tr:
             nodes = f.addgroup([], None, tr, addrevisioncb=cb)
 
         self.assertEqual(nodes, [])
         self.assertEqual(callbackargs, [])
         self.assertEqual(len(f), 0)
 
         fulltext0 = b'foo'
         delta0 = mdiff.trivialdiffheader(len(fulltext0)) + fulltext0
 
         with self._maketransactionfn() as tr:
             node0 = f.add(fulltext0, None, tr, 0, nullid, nullid)
 
         f = self._makefilefn()
 
         deltas = [
             (node0, nullid, nullid, nullid, nullid, delta0, 0),
         ]
 
         with self._maketransactionfn() as tr:
             nodes = f.addgroup(deltas, linkmapper, tr, addrevisioncb=cb)
 
         self.assertEqual(nodes, [
             b'\x49\xd8\xcb\xb1\x5c\xe2\x57\x92\x04\x47'
             b'\x00\x6b\x46\x97\x8b\x7a\xf9\x80\xa9\x79'])
 
         self.assertEqual(len(callbackargs), 1)
         self.assertEqual(callbackargs[0][0][1], nodes[0])
 
         self.assertEqual(list(f.revs()), [0])
         self.assertEqual(f.rev(nodes[0]), 0)
         self.assertEqual(f.node(0), nodes[0])
 
     def testaddgroupmultiple(self):
         f = self._makefilefn()
 
         fulltexts = [
             b'foo',
             b'bar',
             b'x' * 1024,
         ]
 
         nodes = []
         with self._maketransactionfn() as tr:
             for fulltext in fulltexts:
                 nodes.append(f.add(fulltext, None, tr, 0, nullid, nullid))
 
         f = self._makefilefn()
         deltas = []
         for i, fulltext in enumerate(fulltexts):
             delta = mdiff.trivialdiffheader(len(fulltext)) + fulltext
 
             deltas.append((nodes[i], nullid, nullid, nullid, nullid, delta, 0))
 
         with self._maketransactionfn() as tr:
             self.assertEqual(f.addgroup(deltas, lambda x: 0, tr), nodes)
 
         self.assertEqual(len(f), len(deltas))
         self.assertEqual(list(f.revs()), [0, 1, 2])
         self.assertEqual(f.rev(nodes[0]), 0)
         self.assertEqual(f.rev(nodes[1]), 1)
         self.assertEqual(f.rev(nodes[2]), 2)
         self.assertEqual(f.node(0), nodes[0])
         self.assertEqual(f.node(1), nodes[1])
         self.assertEqual(f.node(2), nodes[2])
 
     def testdeltaagainstcensored(self):
         # Attempt to apply a delta made against a censored revision.
         f = self._makefilefn()
 
         stored1 = storageutil.packmeta({
             b'censored': b'tombstone',
         }, b'')
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'foo\n' * 30, None, tr, 0, nullid, nullid)
 
             # The node value doesn't matter since we can't verify it.
             node1 = b'\xbb' * 20
 
             self._addrawrevisionfn(f, tr, node1, node0, nullid, 1, stored1,
                                    censored=True)
 
         delta = mdiff.textdiff(b'bar\n' * 30, (b'bar\n' * 30) + b'baz\n')
         deltas = [(b'\xcc' * 20, node1, nullid, b'\x01' * 20, node1, delta, 0)]
 
         with self._maketransactionfn() as tr:
             with self.assertRaises(error.CensoredBaseError):
                 f.addgroup(deltas, lambda x: 0, tr)
 
     def testcensorrevisionbasic(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'foo\n' * 30, None, tr, 0, nullid, nullid)
             node1 = f.add(b'foo\n' * 31, None, tr, 1, node0, nullid)
             node2 = f.add(b'foo\n' * 32, None, tr, 2, node1, nullid)
 
         with self._maketransactionfn() as tr:
             f.censorrevision(tr, node1)
 
         self.assertEqual(len(f), 3)
         self.assertEqual(list(f.revs()), [0, 1, 2])
 
         self.assertEqual(f.read(node0), b'foo\n' * 30)
         self.assertEqual(f.read(node2), b'foo\n' * 32)
 
         with self.assertRaises(error.CensoredNodeError):
             f.read(node1)
 
     def testgetstrippointnoparents(self):
         # N revisions where none have parents.
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             for rev in range(10):
                 f.add(b'%d' % rev, None, tr, rev, nullid, nullid)
 
         for rev in range(10):
             self.assertEqual(f.getstrippoint(rev), (rev, set()))
 
     def testgetstrippointlinear(self):
         # N revisions in a linear chain.
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             p1 = nullid
 
             for rev in range(10):
                 f.add(b'%d' % rev, None, tr, rev, p1, nullid)
 
         for rev in range(10):
             self.assertEqual(f.getstrippoint(rev), (rev, set()))
 
     def testgetstrippointmultipleheads(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'0', None, tr, 0, nullid, nullid)
             node1 = f.add(b'1', None, tr, 1, node0, nullid)
             f.add(b'2', None, tr, 2, node1, nullid)
             f.add(b'3', None, tr, 3, node0, nullid)
             f.add(b'4', None, tr, 4, node0, nullid)
 
         for rev in range(5):
             self.assertEqual(f.getstrippoint(rev), (rev, set()))
 
     def testgetstrippointearlierlinkrevs(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             node0 = f.add(b'0', None, tr, 0, nullid, nullid)
             f.add(b'1', None, tr, 10, node0, nullid)
             f.add(b'2', None, tr, 5, node0, nullid)
 
         self.assertEqual(f.getstrippoint(0), (0, set()))
         self.assertEqual(f.getstrippoint(1), (1, set()))
         self.assertEqual(f.getstrippoint(2), (1, set()))
         self.assertEqual(f.getstrippoint(3), (1, set()))
         self.assertEqual(f.getstrippoint(4), (1, set()))
         self.assertEqual(f.getstrippoint(5), (1, set()))
         self.assertEqual(f.getstrippoint(6), (1, {2}))
         self.assertEqual(f.getstrippoint(7), (1, {2}))
         self.assertEqual(f.getstrippoint(8), (1, {2}))
         self.assertEqual(f.getstrippoint(9), (1, {2}))
         self.assertEqual(f.getstrippoint(10), (1, {2}))
         self.assertEqual(f.getstrippoint(11), (3, set()))
 
     def teststripempty(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             f.strip(0, tr)
 
         self.assertEqual(len(f), 0)
 
     def teststripall(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             p1 = nullid
             for rev in range(10):
                 p1 = f.add(b'%d' % rev, None, tr, rev, p1, nullid)
 
         self.assertEqual(len(f), 10)
 
         with self._maketransactionfn() as tr:
             f.strip(0, tr)
 
         self.assertEqual(len(f), 0)
 
     def teststrippartial(self):
         f = self._makefilefn()
 
         with self._maketransactionfn() as tr:
             f.add(b'0', None, tr, 0, nullid, nullid)
             node1 = f.add(b'1', None, tr, 5, nullid, nullid)
             node2 = f.add(b'2', None, tr, 10, nullid, nullid)
 
         self.assertEqual(len(f), 3)
 
         with self._maketransactionfn() as tr:
             f.strip(11, tr)
 
         self.assertEqual(len(f), 3)
 
         with self._maketransactionfn() as tr:
             f.strip(10, tr)
 
         self.assertEqual(len(f), 2)
 
         with self.assertRaises(error.LookupError):
             f.rev(node2)
 
         with self._maketransactionfn() as tr:
             f.strip(6, tr)
 
         self.assertEqual(len(f), 2)
 
         with self._maketransactionfn() as tr:
             f.strip(3, tr)
 
         self.assertEqual(len(f), 1)
 
         with self.assertRaises(error.LookupError):
             f.rev(node1)
 
 def makeifileindextests(makefilefn, maketransactionfn, addrawrevisionfn):
     """Create a unittest.TestCase class suitable for testing file storage.
 
     ``makefilefn`` is a callable which receives the test case as an
     argument and returns an object implementing the ``ifilestorage`` interface.
 
     ``maketransactionfn`` is a callable which receives the test case as an
     argument and returns a transaction object.
 
     ``addrawrevisionfn`` is a callable which receives arguments describing a
     low-level revision to add. This callable allows the insertion of
     potentially bad data into the store in order to facilitate testing.
 
     Returns a type that is a ``unittest.TestCase`` that can be used for
     testing the object implementing the file storage interface. Simply
     assign the returned value to a module-level attribute and a test loader
     should find and run it automatically.
     """
     d = {
         r'_makefilefn': makefilefn,
         r'_maketransactionfn': maketransactionfn,
         r'_addrawrevisionfn': addrawrevisionfn,
     }
     return type(r'ifileindextests', (ifileindextests,), d)
 
 def makeifiledatatests(makefilefn, maketransactionfn, addrawrevisionfn):
     d = {
         r'_makefilefn': makefilefn,
         r'_maketransactionfn': maketransactionfn,
         r'_addrawrevisionfn': addrawrevisionfn,
     }
     return type(r'ifiledatatests', (ifiledatatests,), d)
 
 def makeifilemutationtests(makefilefn, maketransactionfn, addrawrevisionfn):
     d = {
         r'_makefilefn': makefilefn,
         r'_maketransactionfn': maketransactionfn,
         r'_addrawrevisionfn': addrawrevisionfn,
     }
     return type(r'ifilemutationtests', (ifilemutationtests,), d)

mercurial/utils/storageutil.py

@@ -1,486 +1,486
 # storageutil.py - Storage functionality agnostic of backend implementation.
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 import re
 import struct
 
 from ..i18n import _
 from ..node import (
     bin,
     nullid,
     nullrev,
 )
 from .. import (
     dagop,
     error,
     mdiff,
     pycompat,
-    repository,
 )
+from ..interfaces import repository
 
 _nullhash = hashlib.sha1(nullid)
 
 def hashrevisionsha1(text, p1, p2):
     """Compute the SHA-1 for revision data and its parents.
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = _nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         if p1 < p2:
             a = p1
             b = p2
         else:
             a = p2
             b = p1
         s = hashlib.sha1(a)
         s.update(b)
     s.update(text)
     return s.digest()
 
 METADATA_RE = re.compile(b'\x01\n')
 
 def parsemeta(text):
     """Parse metadata header from revision data.
 
     Returns a 2-tuple of (metadata, offset), where both can be None if there
     is no metadata.
     """
     # text can be buffer, so we can't use .startswith or .index
     if text[:2] != b'\x01\n':
         return None, None
     s = METADATA_RE.search(text, 2).start()
     mtext = text[2:s]
     meta = {}
     for l in mtext.splitlines():
         k, v = l.split(b': ', 1)
         meta[k] = v
     return meta, s + 2
 
 def packmeta(meta, text):
     """Add metadata to fulltext to produce revision text."""
     keys = sorted(meta)
     metatext = b''.join(b'%s: %s\n' % (k, meta[k]) for k in keys)
     return b'\x01\n%s\x01\n%s' % (metatext, text)
 
 def iscensoredtext(text):
     meta = parsemeta(text)[0]
     return meta and b'censored' in meta
 
 def filtermetadata(text):
     """Extract just the revision data from source text.
 
     Returns ``text`` unless it has a metadata header, in which case we return
     a new buffer without hte metadata.
     """
     if not text.startswith(b'\x01\n'):
         return text
 
     offset = text.index(b'\x01\n', 2)
     return text[offset + 2:]
 
 def filerevisioncopied(store, node):
     """Resolve file revision copy metadata.
 
     Returns ``False`` if the file has no copy metadata. Otherwise a
     2-tuple of the source filename and node.
     """
     if store.parents(node)[0] != nullid:
         return False
 
     meta = parsemeta(store.revision(node))[0]
 
     # copy and copyrev occur in pairs. In rare cases due to old bugs,
     # one can occur without the other. So ensure both are present to flag
     # as a copy.
     if meta and b'copy' in meta and b'copyrev' in meta:
         return meta[b'copy'], bin(meta[b'copyrev'])
 
     return False
 
 def filedataequivalent(store, node, filedata):
     """Determines whether file data is equivalent to a stored node.
 
     Returns True if the passed file data would hash to the same value
     as a stored revision and False otherwise.
 
     When a stored revision is censored, filedata must be empty to have
     equivalence.
 
     When a stored revision has copy metadata, it is ignored as part
     of the compare.
     """
 
     if filedata.startswith(b'\x01\n'):
         revisiontext = b'\x01\n\x01\n' + filedata
     else:
         revisiontext = filedata
 
     p1, p2 = store.parents(node)
 
     computednode = hashrevisionsha1(revisiontext, p1, p2)
 
     if computednode == node:
         return True
 
     # Censored files compare against the empty file.
     if store.iscensored(store.rev(node)):
         return filedata == b''
 
     # Renaming a file produces a different hash, even if the data
     # remains unchanged. Check if that's the case.
     if store.renamed(node):
         return store.read(node) == filedata
 
     return False
 
 def iterrevs(storelen, start=0, stop=None):
     """Iterate over revision numbers in a store."""
     step = 1
 
     if stop is not None:
         if start > stop:
             step = -1
         stop += step
         if stop > storelen:
             stop = storelen
     else:
         stop = storelen
 
     return pycompat.xrange(start, stop, step)
 
 def fileidlookup(store, fileid, identifier):
     """Resolve the file node for a value.
 
     ``store`` is an object implementing the ``ifileindex`` interface.
 
     ``fileid`` can be:
 
     * A 20 byte binary node.
     * An integer revision number
     * A 40 byte hex node.
     * A bytes that can be parsed as an integer representing a revision number.
 
     ``identifier`` is used to populate ``error.LookupError`` with an identifier
     for the store.
 
     Raises ``error.LookupError`` on failure.
     """
     if isinstance(fileid, int):
         try:
             return store.node(fileid)
         except IndexError:
             raise error.LookupError('%d' % fileid, identifier,
                                     _('no match found'))
 
     if len(fileid) == 20:
         try:
             store.rev(fileid)
             return fileid
         except error.LookupError:
             pass
 
     if len(fileid) == 40:
         try:
             rawnode = bin(fileid)
             store.rev(rawnode)
             return rawnode
         except TypeError:
             pass
 
     try:
         rev = int(fileid)
 
         if b'%d' % rev != fileid:
             raise ValueError
 
         try:
             return store.node(rev)
         except (IndexError, TypeError):
             pass
     except (ValueError, OverflowError):
         pass
 
     raise error.LookupError(fileid, identifier, _('no match found'))
 
 def resolvestripinfo(minlinkrev, tiprev, headrevs, linkrevfn, parentrevsfn):
     """Resolve information needed to strip revisions.
 
     Finds the minimum revision number that must be stripped in order to
     strip ``minlinkrev``.
 
     Returns a 2-tuple of the minimum revision number to do that and a set
     of all revision numbers that have linkrevs that would be broken
     by that strip.
 
     ``tiprev`` is the current tip-most revision. It is ``len(store) - 1``.
     ``headrevs`` is an iterable of head revisions.
     ``linkrevfn`` is a callable that receives a revision and returns a linked
     revision.
     ``parentrevsfn`` is a callable that receives a revision number and returns
     an iterable of its parent revision numbers.
     """
     brokenrevs = set()
     strippoint = tiprev + 1
 
     heads = {}
     futurelargelinkrevs = set()
     for head in headrevs:
         headlinkrev = linkrevfn(head)
         heads[head] = headlinkrev
         if headlinkrev >= minlinkrev:
             futurelargelinkrevs.add(headlinkrev)
 
     # This algorithm involves walking down the rev graph, starting at the
     # heads. Since the revs are topologically sorted according to linkrev,
     # once all head linkrevs are below the minlink, we know there are
     # no more revs that could have a linkrev greater than minlink.
     # So we can stop walking.
     while futurelargelinkrevs:
         strippoint -= 1
         linkrev = heads.pop(strippoint)
 
         if linkrev < minlinkrev:
             brokenrevs.add(strippoint)
         else:
             futurelargelinkrevs.remove(linkrev)
 
         for p in parentrevsfn(strippoint):
             if p != nullrev:
                 plinkrev = linkrevfn(p)
                 heads[p] = plinkrev
                 if plinkrev >= minlinkrev:
                     futurelargelinkrevs.add(plinkrev)
 
     return strippoint, brokenrevs
 
 def emitrevisions(store, nodes, nodesorder, resultcls, deltaparentfn=None,
                   candeltafn=None, rawsizefn=None, revdifffn=None, flagsfn=None,
                   deltamode=repository.CG_DELTAMODE_STD,
                   revisiondata=False, assumehaveparentrevisions=False):
     """Generic implementation of ifiledata.emitrevisions().
 
     Emitting revision data is subtly complex. This function attempts to
     encapsulate all the logic for doing so in a backend-agnostic way.
 
     ``store``
        Object conforming to ``ifilestorage`` interface.
 
     ``nodes``
        List of revision nodes whose data to emit.
 
     ``resultcls``
        A type implementing the ``irevisiondelta`` interface that will be
        constructed and returned.
 
     ``deltaparentfn`` (optional)
        Callable receiving a revision number and returning the revision number
        of a revision that the internal delta is stored against. This delta
        will be preferred over computing a new arbitrary delta.
 
        If not defined, a delta will always be computed from raw revision
        data.
 
     ``candeltafn`` (optional)
        Callable receiving a pair of revision numbers that returns a bool
        indicating whether a delta between them can be produced.
 
        If not defined, it is assumed that any two revisions can delta with
        each other.
 
     ``rawsizefn`` (optional)
        Callable receiving a revision number and returning the length of the
        ``store.rawdata(rev)``.
 
        If not defined, ``len(store.rawdata(rev))`` will be called.
 
     ``revdifffn`` (optional)
        Callable receiving a pair of revision numbers that returns a delta
        between them.
 
        If not defined, a delta will be computed by invoking mdiff code
        on ``store.revision()`` results.
 
        Defining this function allows a precomputed or stored delta to be
        used without having to compute on.
 
     ``flagsfn`` (optional)
        Callable receiving a revision number and returns the integer flags
        value for it. If not defined, flags value will be 0.
 
     ``deltamode``
        constaint on delta to be sent:
        * CG_DELTAMODE_STD  - normal mode, try to reuse storage deltas,
        * CG_DELTAMODE_PREV - only delta against "prev",
        * CG_DELTAMODE_FULL - only issue full snapshot.
 
        Whether to send fulltext revisions instead of deltas, if allowed.
 
     ``nodesorder``
     ``revisiondata``
     ``assumehaveparentrevisions``
     """
 
     fnode = store.node
     frev = store.rev
 
     if nodesorder == 'nodes':
         revs = [frev(n) for n in nodes]
     elif nodesorder == 'linear':
         revs = set(frev(n) for n in nodes)
         revs = dagop.linearize(revs, store.parentrevs)
     else: # storage and default
         revs = sorted(frev(n) for n in nodes)
 
     prevrev = None
 
     if deltamode == repository.CG_DELTAMODE_PREV or assumehaveparentrevisions:
         prevrev = store.parentrevs(revs[0])[0]
 
     # Set of revs available to delta against.
     available = set()
 
     for rev in revs:
         if rev == nullrev:
             continue
 
         node = fnode(rev)
         p1rev, p2rev = store.parentrevs(rev)
 
         if deltaparentfn:
             deltaparentrev = deltaparentfn(rev)
         else:
             deltaparentrev = nullrev
 
         # Forced delta against previous mode.
         if deltamode == repository.CG_DELTAMODE_PREV:
             baserev = prevrev
 
         # We're instructed to send fulltext. Honor that.
         elif deltamode == repository.CG_DELTAMODE_FULL:
             baserev = nullrev
         # We're instructed to use p1. Honor that
         elif deltamode == repository.CG_DELTAMODE_P1:
             baserev = p1rev
 
         # There is a delta in storage. We try to use that because it
         # amounts to effectively copying data from storage and is
         # therefore the fastest.
         elif deltaparentrev != nullrev:
             # Base revision was already emitted in this group. We can
             # always safely use the delta.
             if deltaparentrev in available:
                 baserev = deltaparentrev
 
             # Base revision is a parent that hasn't been emitted already.
             # Use it if we can assume the receiver has the parent revision.
             elif (assumehaveparentrevisions
                   and deltaparentrev in (p1rev, p2rev)):
                 baserev = deltaparentrev
 
             # No guarantee the receiver has the delta parent. Send delta
             # against last revision (if possible), which in the common case
             # should be similar enough to this revision that the delta is
             # reasonable.
             elif prevrev is not None:
                 baserev = prevrev
             else:
                 baserev = nullrev
 
         # Storage has a fulltext revision.
 
         # Let's use the previous revision, which is as good a guess as any.
         # There is definitely room to improve this logic.
         elif prevrev is not None:
             baserev = prevrev
         else:
             baserev = nullrev
 
         # But we can't actually use our chosen delta base for whatever
         # reason. Reset to fulltext.
         if baserev != nullrev and (candeltafn and not candeltafn(baserev, rev)):
             baserev = nullrev
 
         revision = None
         delta = None
         baserevisionsize = None
 
         if revisiondata:
             if store.iscensored(baserev) or store.iscensored(rev):
                 try:
                     revision = store.rawdata(node)
                 except error.CensoredNodeError as e:
                     revision = e.tombstone
 
                 if baserev != nullrev:
                     if rawsizefn:
                         baserevisionsize = rawsizefn(baserev)
                     else:
                         baserevisionsize = len(store.rawdata(baserev))
 
             elif (baserev == nullrev
                     and deltamode != repository.CG_DELTAMODE_PREV):
                 revision = store.rawdata(node)
                 available.add(rev)
             else:
                 if revdifffn:
                     delta = revdifffn(baserev, rev)
                 else:
                     delta = mdiff.textdiff(store.rawdata(baserev),
                                            store.rawdata(rev))
 
                 available.add(rev)
 
         yield resultcls(
             node=node,
             p1node=fnode(p1rev),
             p2node=fnode(p2rev),
             basenode=fnode(baserev),
             flags=flagsfn(rev) if flagsfn else 0,
             baserevisionsize=baserevisionsize,
             revision=revision,
             delta=delta)
 
         prevrev = rev
 
 def deltaiscensored(delta, baserev, baselenfn):
     """Determine if a delta represents censored revision data.
 
     ``baserev`` is the base revision this delta is encoded against.
     ``baselenfn`` is a callable receiving a revision number that resolves the
     length of the revision fulltext.
 
     Returns a bool indicating if the result of the delta represents a censored
     revision.
     """
     # Fragile heuristic: unless new file meta keys are added alphabetically
     # preceding "censored", all censored revisions are prefixed by
     # "\1\ncensored:". A delta producing such a censored revision must be a
     # full-replacement delta, so we inspect the first and only patch in the
     # delta for this prefix.
     hlen = struct.calcsize(">lll")
     if len(delta) <= hlen:
         return False
 
     oldlen = baselenfn(baserev)
     newlen = len(delta) - hlen
     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
         return False
 
     add = "\1\ncensored:"
     addlen = len(add)
     return newlen >= addlen and delta[hlen:hlen + addlen] == add

mercurial/wireprotov1peer.py

@@ -1,624 +1,626
 # wireprotov1peer.py - Client-side functionality for wire protocol version 1.
 #
 # Copyright 2005-2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 import sys
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
 )
 from . import (
     bundle2,
     changegroup as changegroupmod,
     encoding,
     error,
     pushkey as pushkeymod,
     pycompat,
-    repository,
     util,
     wireprototypes,
 )
+from .interfaces import (
+    repository,
+)
 from .utils import (
     interfaceutil,
 )
 
 urlreq = util.urlreq
 
 def batchable(f):
     '''annotation for batchable methods
 
     Such methods must implement a coroutine as follows:
 
     @batchable
     def sample(self, one, two=None):
         # Build list of encoded arguments suitable for your wire protocol:
         encargs = [('one', encode(one),), ('two', encode(two),)]
         # Create future for injection of encoded result:
         encresref = future()
         # Return encoded arguments and future:
         yield encargs, encresref
         # Assuming the future to be filled with the result from the batched
         # request now. Decode it:
         yield decode(encresref.value)
 
     The decorator returns a function which wraps this coroutine as a plain
     method, but adds the original method as an attribute called "batchable",
     which is used by remotebatch to split the call into separate encoding and
     decoding phases.
     '''
     def plain(*args, **opts):
         batchable = f(*args, **opts)
         encargsorres, encresref = next(batchable)
         if not encresref:
             return encargsorres # a local result in this case
         self = args[0]
         cmd = pycompat.bytesurl(f.__name__)  # ensure cmd is ascii bytestr
         encresref.set(self._submitone(cmd, encargsorres))
         return next(batchable)
     setattr(plain, 'batchable', f)
     setattr(plain, '__name__', f.__name__)
     return plain
 
 class future(object):
     '''placeholder for a value to be set later'''
     def set(self, value):
         if util.safehasattr(self, 'value'):
             raise error.RepoError("future is already set")
         self.value = value
 
 def encodebatchcmds(req):
     """Return a ``cmds`` argument value for the ``batch`` command."""
     escapearg = wireprototypes.escapebatcharg
 
     cmds = []
     for op, argsdict in req:
         # Old servers didn't properly unescape argument names. So prevent
         # the sending of argument names that may not be decoded properly by
         # servers.
         assert all(escapearg(k) == k for k in argsdict)
 
         args = ','.join('%s=%s' % (escapearg(k), escapearg(v))
                         for k, v in argsdict.iteritems())
         cmds.append('%s %s' % (op, args))
 
     return ';'.join(cmds)
 
 class unsentfuture(pycompat.futures.Future):
     """A Future variation to represent an unsent command.
 
     Because we buffer commands and don't submit them immediately, calling
     ``result()`` on an unsent future could deadlock. Futures for buffered
     commands are represented by this type, which wraps ``result()`` to
     call ``sendcommands()``.
     """
 
     def result(self, timeout=None):
         if self.done():
             return pycompat.futures.Future.result(self, timeout)
 
         self._peerexecutor.sendcommands()
 
         # This looks like it will infinitely recurse. However,
         # sendcommands() should modify __class__. This call serves as a check
         # on that.
         return self.result(timeout)
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class peerexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
         self._calls = []
         self._futures = weakref.WeakSet()
         self._responseexecutor = None
         self._responsef = None
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalee, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError('callcommand() cannot be used '
                                          'after commands are sent')
 
         if self._closed:
             raise error.ProgrammingError('callcommand() cannot be used '
                                          'after close()')
 
         # Commands are dispatched through methods on the peer.
         fn = getattr(self._peer, pycompat.sysstr(command), None)
 
         if not fn:
             raise error.ProgrammingError(
                 'cannot call command %s: method of same name not available '
                 'on peer' % command)
 
         # Commands are either batchable or they aren't. If a command
         # isn't batchable, we send it immediately because the executor
         # can no longer accept new commands after a non-batchable command.
         # If a command is batchable, we queue it for later. But we have
         # to account for the case of a non-batchable command arriving after
         # a batchable one and refuse to service it.
 
         def addcall():
             f = pycompat.futures.Future()
             self._futures.add(f)
             self._calls.append((command, args, fn, f))
             return f
 
         if getattr(fn, 'batchable', False):
             f = addcall()
 
             # But since we don't issue it immediately, we wrap its result()
             # to trigger sending so we avoid deadlocks.
             f.__class__ = unsentfuture
             f._peerexecutor = self
         else:
             if self._calls:
                 raise error.ProgrammingError(
                     '%s is not batchable and cannot be called on a command '
                     'executor along with other commands' % command)
 
             f = addcall()
 
             # Non-batchable commands can never coexist with another command
             # in this executor. So send the command immediately.
             self.sendcommands()
 
         return f
 
     def sendcommands(self):
         if self._sent:
             return
 
         if not self._calls:
             return
 
         self._sent = True
 
         # Unhack any future types so caller seens a clean type and to break
         # cycle between us and futures.
         for f in self._futures:
             if isinstance(f, unsentfuture):
                 f.__class__ = pycompat.futures.Future
                 f._peerexecutor = None
 
         calls = self._calls
         # Mainly to destroy references to futures.
         self._calls = None
 
         # Simple case of a single command. We call it synchronously.
         if len(calls) == 1:
             command, args, fn, f = calls[0]
 
             # Future was cancelled. Ignore it.
             if not f.set_running_or_notify_cancel():
                 return
 
             try:
                 result = fn(**pycompat.strkwargs(args))
             except Exception:
                 pycompat.future_set_exception_info(f, sys.exc_info()[1:])
             else:
                 f.set_result(result)
 
             return
 
         # Batch commands are a bit harder. First, we have to deal with the
         # @batchable coroutine. That's a bit annoying. Furthermore, we also
         # need to preserve streaming. i.e. it should be possible for the
         # futures to resolve as data is coming in off the wire without having
         # to wait for the final byte of the final response. We do this by
         # spinning up a thread to read the responses.
 
         requests = []
         states = []
 
         for command, args, fn, f in calls:
             # Future was cancelled. Ignore it.
             if not f.set_running_or_notify_cancel():
                 continue
 
             try:
                 batchable = fn.batchable(fn.__self__,
                                          **pycompat.strkwargs(args))
             except Exception:
                 pycompat.future_set_exception_info(f, sys.exc_info()[1:])
                 return
 
             # Encoded arguments and future holding remote result.
             try:
                 encargsorres, fremote = next(batchable)
             except Exception:
                 pycompat.future_set_exception_info(f, sys.exc_info()[1:])
                 return
 
             if not fremote:
                 f.set_result(encargsorres)
             else:
                 requests.append((command, encargsorres))
                 states.append((command, f, batchable, fremote))
 
         if not requests:
             return
 
         # This will emit responses in order they were executed.
         wireresults = self._peer._submitbatch(requests)
 
         # The use of a thread pool executor here is a bit weird for something
         # that only spins up a single thread. However, thread management is
         # hard and it is easy to encounter race conditions, deadlocks, etc.
         # concurrent.futures already solves these problems and its thread pool
         # executor has minimal overhead. So we use it.
         self._responseexecutor = pycompat.futures.ThreadPoolExecutor(1)
         self._responsef = self._responseexecutor.submit(self._readbatchresponse,
                                                         states, wireresults)
 
     def close(self):
         self.sendcommands()
 
         if self._closed:
             return
 
         self._closed = True
 
         if not self._responsef:
             return
 
         # We need to wait on our in-flight response and then shut down the
         # executor once we have a result.
         try:
             self._responsef.result()
         finally:
             self._responseexecutor.shutdown(wait=True)
             self._responsef = None
             self._responseexecutor = None
 
             # If any of our futures are still in progress, mark them as
             # errored. Otherwise a result() could wait indefinitely.
             for f in self._futures:
                 if not f.done():
                     f.set_exception(error.ResponseError(
                         _('unfulfilled batch command response')))
 
             self._futures = None
 
     def _readbatchresponse(self, states, wireresults):
         # Executes in a thread to read data off the wire.
 
         for command, f, batchable, fremote in states:
             # Grab raw result off the wire and teach the internal future
             # about it.
             remoteresult = next(wireresults)
             fremote.set(remoteresult)
 
             # And ask the coroutine to decode that value.
             try:
                 result = next(batchable)
             except Exception:
                 pycompat.future_set_exception_info(f, sys.exc_info()[1:])
             else:
                 f.set_result(result)
 
 @interfaceutil.implementer(repository.ipeercommands,
                            repository.ipeerlegacycommands)
 class wirepeer(repository.peer):
     """Client-side interface for communicating with a peer repository.
 
     Methods commonly call wire protocol commands of the same name.
 
     See also httppeer.py and sshpeer.py for protocol-specific
     implementations of this interface.
     """
     def commandexecutor(self):
         return peerexecutor(self)
 
     # Begin of ipeercommands interface.
 
     def clonebundles(self):
         self.requirecap('clonebundles', _('clone bundles'))
         return self._call('clonebundles')
 
     @batchable
     def lookup(self, key):
         self.requirecap('lookup', _('look up remote revision'))
         f = future()
         yield {'key': encoding.fromlocal(key)}, f
         d = f.value
         success, data = d[:-1].split(" ", 1)
         if int(success):
             yield bin(data)
         else:
             self._abort(error.RepoError(data))
 
     @batchable
     def heads(self):
         f = future()
         yield {}, f
         d = f.value
         try:
             yield wireprototypes.decodelist(d[:-1])
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def known(self, nodes):
         f = future()
         yield {'nodes': wireprototypes.encodelist(nodes)}, f
         d = f.value
         try:
             yield [bool(int(b)) for b in pycompat.iterbytestr(d)]
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def branchmap(self):
         f = future()
         yield {}, f
         d = f.value
         try:
             branchmap = {}
             for branchpart in d.splitlines():
                 branchname, branchheads = branchpart.split(' ', 1)
                 branchname = encoding.tolocal(urlreq.unquote(branchname))
                 branchheads = wireprototypes.decodelist(branchheads)
                 branchmap[branchname] = branchheads
             yield branchmap
         except TypeError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     @batchable
     def listkeys(self, namespace):
         if not self.capable('pushkey'):
             yield {}, None
         f = future()
         self.ui.debug('preparing listkeys for "%s"\n' % namespace)
         yield {'namespace': encoding.fromlocal(namespace)}, f
         d = f.value
         self.ui.debug('received listkey for "%s": %i bytes\n'
                       % (namespace, len(d)))
         yield pushkeymod.decodekeys(d)
 
     @batchable
     def pushkey(self, namespace, key, old, new):
         if not self.capable('pushkey'):
             yield False, None
         f = future()
         self.ui.debug('preparing pushkey for "%s:%s"\n' % (namespace, key))
         yield {'namespace': encoding.fromlocal(namespace),
                'key': encoding.fromlocal(key),
                'old': encoding.fromlocal(old),
                'new': encoding.fromlocal(new)}, f
         d = f.value
         d, output = d.split('\n', 1)
         try:
             d = bool(int(d))
         except ValueError:
             raise error.ResponseError(
                 _('push failed (unexpected response):'), d)
         for l in output.splitlines(True):
             self.ui.status(_('remote: '), l)
         yield d
 
     def stream_out(self):
         return self._callstream('stream_out')
 
     def getbundle(self, source, **kwargs):
         kwargs = pycompat.byteskwargs(kwargs)
         self.requirecap('getbundle', _('look up remote changes'))
         opts = {}
         bundlecaps = kwargs.get('bundlecaps') or set()
         for key, value in kwargs.iteritems():
             if value is None:
                 continue
             keytype = wireprototypes.GETBUNDLE_ARGUMENTS.get(key)
             if keytype is None:
                 raise error.ProgrammingError(
                     'Unexpectedly None keytype for key %s' % key)
             elif keytype == 'nodes':
                 value = wireprototypes.encodelist(value)
             elif keytype == 'csv':
                 value = ','.join(value)
             elif keytype == 'scsv':
                 value = ','.join(sorted(value))
             elif keytype == 'boolean':
                 value = '%i' % bool(value)
             elif keytype != 'plain':
                 raise KeyError('unknown getbundle option type %s'
                                % keytype)
             opts[key] = value
         f = self._callcompressable("getbundle", **pycompat.strkwargs(opts))
         if any((cap.startswith('HG2') for cap in bundlecaps)):
             return bundle2.getunbundler(self.ui, f)
         else:
             return changegroupmod.cg1unpacker(f, 'UN')
 
     def unbundle(self, bundle, heads, url):
         '''Send cg (a readable file-like object representing the
         changegroup to push, typically a chunkbuffer object) to the
         remote server as a bundle.
 
         When pushing a bundle10 stream, return an integer indicating the
         result of the push (see changegroup.apply()).
 
         When pushing a bundle20 stream, return a bundle20 stream.
 
         `url` is the url the client thinks it's pushing to, which is
         visible to hooks.
         '''
 
         if heads != ['force'] and self.capable('unbundlehash'):
             heads = wireprototypes.encodelist(
                 ['hashed', hashlib.sha1(''.join(sorted(heads))).digest()])
         else:
             heads = wireprototypes.encodelist(heads)
 
         if util.safehasattr(bundle, 'deltaheader'):
             # this a bundle10, do the old style call sequence
             ret, output = self._callpush("unbundle", bundle, heads=heads)
             if ret == "":
                 raise error.ResponseError(
                     _('push failed:'), output)
             try:
                 ret = int(ret)
             except ValueError:
                 raise error.ResponseError(
                     _('push failed (unexpected response):'), ret)
 
             for l in output.splitlines(True):
                 self.ui.status(_('remote: '), l)
         else:
             # bundle2 push. Send a stream, fetch a stream.
             stream = self._calltwowaystream('unbundle', bundle, heads=heads)
             ret = bundle2.getunbundler(self.ui, stream)
         return ret
 
     # End of ipeercommands interface.
 
     # Begin of ipeerlegacycommands interface.
 
     def branches(self, nodes):
         n = wireprototypes.encodelist(nodes)
         d = self._call("branches", nodes=n)
         try:
             br = [tuple(wireprototypes.decodelist(b)) for b in d.splitlines()]
             return br
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), d))
 
     def between(self, pairs):
         batch = 8 # avoid giant requests
         r = []
         for i in pycompat.xrange(0, len(pairs), batch):
             n = " ".join([wireprototypes.encodelist(p, '-')
                           for p in pairs[i:i + batch]])
             d = self._call("between", pairs=n)
             try:
                 r.extend(l and wireprototypes.decodelist(l) or []
                          for l in d.splitlines())
             except ValueError:
                 self._abort(error.ResponseError(_("unexpected response:"), d))
         return r
 
     def changegroup(self, nodes, source):
         n = wireprototypes.encodelist(nodes)
         f = self._callcompressable("changegroup", roots=n)
         return changegroupmod.cg1unpacker(f, 'UN')
 
     def changegroupsubset(self, bases, heads, source):
         self.requirecap('changegroupsubset', _('look up remote changes'))
         bases = wireprototypes.encodelist(bases)
         heads = wireprototypes.encodelist(heads)
         f = self._callcompressable("changegroupsubset",
                                    bases=bases, heads=heads)
         return changegroupmod.cg1unpacker(f, 'UN')
 
     # End of ipeerlegacycommands interface.
 
     def _submitbatch(self, req):
         """run batch request <req> on the server
 
         Returns an iterator of the raw responses from the server.
         """
         ui = self.ui
         if ui.debugflag and ui.configbool('devel', 'debug.peer-request'):
             ui.debug('devel-peer-request: batched-content\n')
             for op, args in req:
                 msg = 'devel-peer-request:    - %s (%d arguments)\n'
                 ui.debug(msg % (op, len(args)))
 
         unescapearg = wireprototypes.unescapebatcharg
 
         rsp = self._callstream("batch", cmds=encodebatchcmds(req))
         chunk = rsp.read(1024)
         work = [chunk]
         while chunk:
             while ';' not in chunk and chunk:
                 chunk = rsp.read(1024)
                 work.append(chunk)
             merged = ''.join(work)
             while ';' in merged:
                 one, merged = merged.split(';', 1)
                 yield unescapearg(one)
             chunk = rsp.read(1024)
             work = [merged, chunk]
         yield unescapearg(''.join(work))
 
     def _submitone(self, op, args):
         return self._call(op, **pycompat.strkwargs(args))
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         # don't pass optional arguments left at their default value
         opts = {}
         if three is not None:
             opts[r'three'] = three
         if four is not None:
             opts[r'four'] = four
         return self._call('debugwireargs', one=one, two=two, **opts)
 
     def _call(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a simple string.
 
         returns the server reply as a string."""
         raise NotImplementedError()
 
     def _callstream(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a stream. Note that if the
         command doesn't return a stream, _callstream behaves
         differently for ssh and http peers.
 
         returns the server reply as a file like object.
         """
         raise NotImplementedError()
 
     def _callcompressable(self, cmd, **args):
         """execute <cmd> on the server
 
         The command is expected to return a stream.
 
         The stream may have been compressed in some implementations. This
         function takes care of the decompression. This is the only difference
         with _callstream.
 
         returns the server reply as a file like object.
         """
         raise NotImplementedError()
 
     def _callpush(self, cmd, fp, **args):
         """execute a <cmd> on server
 
         The command is expected to be related to a push. Push has a special
         return method.
 
         returns the server reply as a (ret, output) tuple. ret is either
         empty (error) or a stringified int.
         """
         raise NotImplementedError()
 
     def _calltwowaystream(self, cmd, fp, **args):
         """execute <cmd> on server
 
         The command will send a stream to the server and get a stream in reply.
         """
         raise NotImplementedError()
 
     def _abort(self, exception):
         """clearly abort the wire protocol connection and raise the exception
         """
         raise NotImplementedError()

setup.py

@@ -1,1512 +1,1513
 #
 # This is the mercurial setup script.
 #
 # 'python setup.py install', or
 # 'python setup.py --help' for more options
 
 import os
 
 supportedpy = '~= 2.7'
 if os.environ.get('HGALLOWPYTHON3', ''):
     # Mercurial will never work on Python 3 before 3.5 due to a lack
     # of % formatting on bytestrings, and can't work on 3.6.0 or 3.6.1
     # due to a bug in % formatting in bytestrings.
     # We cannot support Python 3.5.0, 3.5.1, 3.5.2 because of bug in
     # codecs.escape_encode() where it raises SystemError on empty bytestring
     # bug link: https://bugs.python.org/issue25270
     #
     # TODO: when we actually work on Python 3, use this string as the
     # actual supportedpy string.
     supportedpy = ','.join([
         '>=2.7',
         '!=3.0.*',
         '!=3.1.*',
         '!=3.2.*',
         '!=3.3.*',
         '!=3.4.*',
         '!=3.5.0',
         '!=3.5.1',
         '!=3.5.2',
         '!=3.6.0',
         '!=3.6.1',
     ])
 
 import sys, platform
 import sysconfig
 if sys.version_info[0] >= 3:
     printf = eval('print')
     libdir_escape = 'unicode_escape'
     def sysstr(s):
         return s.decode('latin-1')
 else:
     libdir_escape = 'string_escape'
     def printf(*args, **kwargs):
         f = kwargs.get('file', sys.stdout)
         end = kwargs.get('end', '\n')
         f.write(b' '.join(args) + end)
     def sysstr(s):
         return s
 
 # Attempt to guide users to a modern pip - this means that 2.6 users
 # should have a chance of getting a 4.2 release, and when we ratchet
 # the version requirement forward again hopefully everyone will get
 # something that works for them.
 if sys.version_info < (2, 7, 0, 'final'):
     pip_message = ('This may be due to an out of date pip. '
                    'Make sure you have pip >= 9.0.1.')
     try:
         import pip
         pip_version = tuple([int(x) for x in pip.__version__.split('.')[:3]])
         if pip_version < (9, 0, 1) :
             pip_message = (
                 'Your pip version is out of date, please install '
                 'pip >= 9.0.1. pip {} detected.'.format(pip.__version__))
         else:
             # pip is new enough - it must be something else
             pip_message = ''
     except Exception:
         pass
     error = """
 Mercurial does not support Python older than 2.7.
 Python {py} detected.
 {pip}
 """.format(py=sys.version_info, pip=pip_message)
     printf(error, file=sys.stderr)
     sys.exit(1)
 
 # We don't yet officially support Python 3. But we want to allow developers to
 # hack on. Detect and disallow running on Python 3 by default. But provide a
 # backdoor to enable working on Python 3.
 if sys.version_info[0] != 2:
     badpython = True
 
     # Allow Python 3 from source checkouts.
     if os.path.isdir('.hg') or 'HGPYTHON3' in os.environ:
         badpython = False
 
     if badpython:
         error = """
 Python {py} detected.
 
 Mercurial currently has beta support for Python 3 and use of Python 2.7 is
 recommended for the best experience.
 
 Please re-run with Python 2.7 for a faster, less buggy experience.
 
 If you would like to beta test Mercurial with Python 3, this error can
 be suppressed by defining the HGPYTHON3 environment variable when invoking
 this command. No special environment variables or configuration changes are
 necessary to run `hg` with Python 3.
 
 See https://www.mercurial-scm.org/wiki/Python3 for more on Mercurial's
 Python 3 support.
 """.format(py='.'.join('%d' % x for x in sys.version_info[0:2]))
 
         printf(error, file=sys.stderr)
         sys.exit(1)
 
 if sys.version_info[0] >= 3:
     DYLIB_SUFFIX = sysconfig.get_config_vars()['EXT_SUFFIX']
 else:
     # deprecated in Python 3
     DYLIB_SUFFIX = sysconfig.get_config_vars()['SO']
 
 # Solaris Python packaging brain damage
 try:
     import hashlib
     sha = hashlib.sha1()
 except ImportError:
     try:
         import sha
         sha.sha # silence unused import warning
     except ImportError:
         raise SystemExit(
             "Couldn't import standard hashlib (incomplete Python install).")
 
 try:
     import zlib
     zlib.compressobj # silence unused import warning
 except ImportError:
     raise SystemExit(
         "Couldn't import standard zlib (incomplete Python install).")
 
 # The base IronPython distribution (as of 2.7.1) doesn't support bz2
 isironpython = False
 try:
     isironpython = (platform.python_implementation()
                     .lower().find("ironpython") != -1)
 except AttributeError:
     pass
 
 if isironpython:
     sys.stderr.write("warning: IronPython detected (no bz2 support)\n")
 else:
     try:
         import bz2
         bz2.BZ2Compressor # silence unused import warning
     except ImportError:
         raise SystemExit(
             "Couldn't import standard bz2 (incomplete Python install).")
 
 ispypy = "PyPy" in sys.version
 
 hgrustext = os.environ.get('HGWITHRUSTEXT')
 # TODO record it for proper rebuild upon changes
 # (see mercurial/__modulepolicy__.py)
 if hgrustext != 'cpython' and hgrustext is not None:
     hgrustext = 'direct-ffi'
 
 import ctypes
 import errno
 import stat, subprocess, time
 import re
 import shutil
 import tempfile
 from distutils import log
 # We have issues with setuptools on some platforms and builders. Until
 # those are resolved, setuptools is opt-in except for platforms where
 # we don't have issues.
 issetuptools = (os.name == 'nt' or 'FORCE_SETUPTOOLS' in os.environ)
 if issetuptools:
     from setuptools import setup
 else:
     from distutils.core import setup
 from distutils.ccompiler import new_compiler
 from distutils.core import Command, Extension
 from distutils.dist import Distribution
 from distutils.command.build import build
 from distutils.command.build_ext import build_ext
 from distutils.command.build_py import build_py
 from distutils.command.build_scripts import build_scripts
 from distutils.command.install import install
 from distutils.command.install_lib import install_lib
 from distutils.command.install_scripts import install_scripts
 from distutils.spawn import spawn, find_executable
 from distutils import file_util
 from distutils.errors import (
     CCompilerError,
     DistutilsError,
     DistutilsExecError,
 )
 from distutils.sysconfig import get_python_inc, get_config_var
 from distutils.version import StrictVersion
 
 # Explain to distutils.StrictVersion how our release candidates are versionned
 StrictVersion.version_re = re.compile(r'^(\d+)\.(\d+)(\.(\d+))?-?(rc(\d+))?$')
 
 def write_if_changed(path, content):
     """Write content to a file iff the content hasn't changed."""
     if os.path.exists(path):
         with open(path, 'rb') as fh:
             current = fh.read()
     else:
         current = b''
 
     if current != content:
         with open(path, 'wb') as fh:
             fh.write(content)
 
 scripts = ['hg']
 if os.name == 'nt':
     # We remove hg.bat if we are able to build hg.exe.
     scripts.append('contrib/win32/hg.bat')
 
 def cancompile(cc, code):
     tmpdir = tempfile.mkdtemp(prefix='hg-install-')
     devnull = oldstderr = None
     try:
         fname = os.path.join(tmpdir, 'testcomp.c')
         f = open(fname, 'w')
         f.write(code)
         f.close()
         # Redirect stderr to /dev/null to hide any error messages
         # from the compiler.
         # This will have to be changed if we ever have to check
         # for a function on Windows.
         devnull = open('/dev/null', 'w')
         oldstderr = os.dup(sys.stderr.fileno())
         os.dup2(devnull.fileno(), sys.stderr.fileno())
         objects = cc.compile([fname], output_dir=tmpdir)
         cc.link_executable(objects, os.path.join(tmpdir, "a.out"))
         return True
     except Exception:
         return False
     finally:
         if oldstderr is not None:
             os.dup2(oldstderr, sys.stderr.fileno())
         if devnull is not None:
             devnull.close()
         shutil.rmtree(tmpdir)
 
 # simplified version of distutils.ccompiler.CCompiler.has_function
 # that actually removes its temporary files.
 def hasfunction(cc, funcname):
     code = 'int main(void) { %s(); }\n' % funcname
     return cancompile(cc, code)
 
 def hasheader(cc, headername):
     code = '#include <%s>\nint main(void) { return 0; }\n' % headername
     return cancompile(cc, code)
 
 # py2exe needs to be installed to work
 try:
     import py2exe
     py2exe.Distribution # silence unused import warning
     py2exeloaded = True
     # import py2exe's patched Distribution class
     from distutils.core import Distribution
 except ImportError:
     py2exeloaded = False
 
 def runcmd(cmd, env, cwd=None):
     p = subprocess.Popen(cmd, stdout=subprocess.PIPE,
                          stderr=subprocess.PIPE, env=env, cwd=cwd)
     out, err = p.communicate()
     return p.returncode, out, err
 
 class hgcommand(object):
     def __init__(self, cmd, env):
         self.cmd = cmd
         self.env = env
 
     def run(self, args):
         cmd = self.cmd + args
         returncode, out, err = runcmd(cmd, self.env)
         err = filterhgerr(err)
         if err or returncode != 0:
             printf("stderr from '%s':" % (' '.join(cmd)), file=sys.stderr)
             printf(err, file=sys.stderr)
             return ''
         return out
 
 def filterhgerr(err):
     # If root is executing setup.py, but the repository is owned by
     # another user (as in "sudo python setup.py install") we will get
     # trust warnings since the .hg/hgrc file is untrusted. That is
     # fine, we don't want to load it anyway.  Python may warn about
     # a missing __init__.py in mercurial/locale, we also ignore that.
     err = [e for e in err.splitlines()
            if (not e.startswith(b'not trusting file')
                and not e.startswith(b'warning: Not importing')
                and not e.startswith(b'obsolete feature not enabled')
                and not e.startswith(b'*** failed to import extension')
                and not e.startswith(b'devel-warn:')
                and not (e.startswith(b'(third party extension')
                         and e.endswith(b'or newer of Mercurial; disabling)')))]
     return b'\n'.join(b'  ' + e for e in err)
 
 def findhg():
     """Try to figure out how we should invoke hg for examining the local
     repository contents.
 
     Returns an hgcommand object."""
     # By default, prefer the "hg" command in the user's path.  This was
     # presumably the hg command that the user used to create this repository.
     #
     # This repository may require extensions or other settings that would not
     # be enabled by running the hg script directly from this local repository.
     hgenv = os.environ.copy()
     # Use HGPLAIN to disable hgrc settings that would change output formatting,
     # and disable localization for the same reasons.
     hgenv['HGPLAIN'] = '1'
     hgenv['LANGUAGE'] = 'C'
     hgcmd = ['hg']
     # Run a simple "hg log" command just to see if using hg from the user's
     # path works and can successfully interact with this repository.  Windows
     # gives precedence to hg.exe in the current directory, so fall back to the
     # python invocation of local hg, where pythonXY.dll can always be found.
     check_cmd = ['log', '-r.', '-Ttest']
     if os.name != 'nt':
         try:
             retcode, out, err = runcmd(hgcmd + check_cmd, hgenv)
         except EnvironmentError:
             retcode = -1
         if retcode == 0 and not filterhgerr(err):
             return hgcommand(hgcmd, hgenv)
 
     # Fall back to trying the local hg installation.
     hgenv = localhgenv()
     hgcmd = [sys.executable, 'hg']
     try:
         retcode, out, err = runcmd(hgcmd + check_cmd, hgenv)
     except EnvironmentError:
         retcode = -1
     if retcode == 0 and not filterhgerr(err):
         return hgcommand(hgcmd, hgenv)
 
     raise SystemExit('Unable to find a working hg binary to extract the '
                      'version from the repository tags')
 
 def localhgenv():
     """Get an environment dictionary to use for invoking or importing
     mercurial from the local repository."""
     # Execute hg out of this directory with a custom environment which takes
     # care to not use any hgrc files and do no localization.
     env = {'HGMODULEPOLICY': 'py',
            'HGRCPATH': '',
            'LANGUAGE': 'C',
            'PATH': ''} # make pypi modules that use os.environ['PATH'] happy
     if 'LD_LIBRARY_PATH' in os.environ:
         env['LD_LIBRARY_PATH'] = os.environ['LD_LIBRARY_PATH']
     if 'SystemRoot' in os.environ:
         # SystemRoot is required by Windows to load various DLLs.  See:
         # https://bugs.python.org/issue13524#msg148850
         env['SystemRoot'] = os.environ['SystemRoot']
     return env
 
 version = ''
 
 if os.path.isdir('.hg'):
     hg = findhg()
     cmd = ['log', '-r', '.', '--template', '{tags}\n']
     numerictags = [t for t in sysstr(hg.run(cmd)).split() if t[0:1].isdigit()]
     hgid = sysstr(hg.run(['id', '-i'])).strip()
     if not hgid:
         # Bail out if hg is having problems interacting with this repository,
         # rather than falling through and producing a bogus version number.
         # Continuing with an invalid version number will break extensions
         # that define minimumhgversion.
         raise SystemExit('Unable to determine hg version from local repository')
     if numerictags: # tag(s) found
         version = numerictags[-1]
         if hgid.endswith('+'): # propagate the dirty status to the tag
             version += '+'
     else: # no tag found
         ltagcmd = ['parents', '--template', '{latesttag}']
         ltag = sysstr(hg.run(ltagcmd))
         changessincecmd = ['log', '-T', 'x\n', '-r', "only(.,'%s')" % ltag]
         changessince = len(hg.run(changessincecmd).splitlines())
         version = '%s+%s-%s' % (ltag, changessince, hgid)
     if version.endswith('+'):
         version += time.strftime('%Y%m%d')
 elif os.path.exists('.hg_archival.txt'):
     kw = dict([[t.strip() for t in l.split(':', 1)]
                for l in open('.hg_archival.txt')])
     if 'tag' in kw:
         version = kw['tag']
     elif 'latesttag' in kw:
         if 'changessincelatesttag' in kw:
             version = '%(latesttag)s+%(changessincelatesttag)s-%(node).12s' % kw
         else:
             version = '%(latesttag)s+%(latesttagdistance)s-%(node).12s' % kw
     else:
         version = kw.get('node', '')[:12]
 
 if version:
     versionb = version
     if not isinstance(versionb, bytes):
         versionb = versionb.encode('ascii')
 
     write_if_changed('mercurial/__version__.py', b''.join([
         b'# this file is autogenerated by setup.py\n'
         b'version = b"%s"\n' % versionb,
     ]))
 
 try:
     oldpolicy = os.environ.get('HGMODULEPOLICY', None)
     os.environ['HGMODULEPOLICY'] = 'py'
     from mercurial import __version__
     version = __version__.version
 except ImportError:
     version = b'unknown'
 finally:
     if oldpolicy is None:
         del os.environ['HGMODULEPOLICY']
     else:
         os.environ['HGMODULEPOLICY'] = oldpolicy
 
 class hgbuild(build):
     # Insert hgbuildmo first so that files in mercurial/locale/ are found
     # when build_py is run next.
     sub_commands = [('build_mo', None)] + build.sub_commands
 
 class hgbuildmo(build):
 
     description = "build translations (.mo files)"
 
     def run(self):
         if not find_executable('msgfmt'):
             self.warn("could not find msgfmt executable, no translations "
                      "will be built")
             return
 
         podir = 'i18n'
         if not os.path.isdir(podir):
             self.warn("could not find %s/ directory" % podir)
             return
 
         join = os.path.join
         for po in os.listdir(podir):
             if not po.endswith('.po'):
                 continue
             pofile = join(podir, po)
             modir = join('locale', po[:-3], 'LC_MESSAGES')
             mofile = join(modir, 'hg.mo')
             mobuildfile = join('mercurial', mofile)
             cmd = ['msgfmt', '-v', '-o', mobuildfile, pofile]
             if sys.platform != 'sunos5':
                 # msgfmt on Solaris does not know about -c
                 cmd.append('-c')
             self.mkpath(join('mercurial', modir))
             self.make_file([pofile], mobuildfile, spawn, (cmd,))
 
 
 class hgdist(Distribution):
     pure = False
     rust = hgrustext is not None
     cffi = ispypy
 
     global_options = Distribution.global_options + [
         ('pure', None, "use pure (slow) Python code instead of C extensions"),
         ('rust', None, "use Rust extensions additionally to C extensions"),
     ]
 
     def has_ext_modules(self):
         # self.ext_modules is emptied in hgbuildpy.finalize_options which is
         # too late for some cases
         return not self.pure and Distribution.has_ext_modules(self)
 
 # This is ugly as a one-liner. So use a variable.
 buildextnegops = dict(getattr(build_ext, 'negative_options', {}))
 buildextnegops['no-zstd'] = 'zstd'
 buildextnegops['no-rust'] = 'rust'
 
 class hgbuildext(build_ext):
     user_options = build_ext.user_options + [
         ('zstd', None, 'compile zstd bindings [default]'),
         ('no-zstd', None, 'do not compile zstd bindings'),
         ('rust', None,
          'compile Rust extensions if they are in use '
          '(requires Cargo) [default]'),
         ('no-rust', None, 'do not compile Rust extensions'),
     ]
 
     boolean_options = build_ext.boolean_options + ['zstd', 'rust']
     negative_opt = buildextnegops
 
     def initialize_options(self):
         self.zstd = True
         self.rust = True
 
         return build_ext.initialize_options(self)
 
     def build_extensions(self):
         ruststandalones = [e for e in self.extensions
                            if isinstance(e, RustStandaloneExtension)]
         self.extensions = [e for e in self.extensions
                            if e not in ruststandalones]
         # Filter out zstd if disabled via argument.
         if not self.zstd:
             self.extensions = [e for e in self.extensions
                                if e.name != 'mercurial.zstd']
 
         # Build Rust standalon extensions if it'll be used
         # and its build is not explictely disabled (for external build
         # as Linux distributions would do)
         if self.distribution.rust and self.rust and hgrustext != 'direct-ffi':
             for rustext in ruststandalones:
                 rustext.build('' if self.inplace else self.build_lib)
 
         return build_ext.build_extensions(self)
 
     def build_extension(self, ext):
         if (self.distribution.rust and self.rust
             and isinstance(ext, RustExtension)):
                 ext.rustbuild()
         try:
             build_ext.build_extension(self, ext)
         except CCompilerError:
             if not getattr(ext, 'optional', False):
                 raise
             log.warn("Failed to build optional extension '%s' (skipping)",
                      ext.name)
 
 class hgbuildscripts(build_scripts):
     def run(self):
         if os.name != 'nt' or self.distribution.pure:
             return build_scripts.run(self)
 
         exebuilt = False
         try:
             self.run_command('build_hgexe')
             exebuilt = True
         except (DistutilsError, CCompilerError):
             log.warn('failed to build optional hg.exe')
 
         if exebuilt:
             # Copying hg.exe to the scripts build directory ensures it is
             # installed by the install_scripts command.
             hgexecommand = self.get_finalized_command('build_hgexe')
             dest = os.path.join(self.build_dir, 'hg.exe')
             self.mkpath(self.build_dir)
             self.copy_file(hgexecommand.hgexepath, dest)
 
             # Remove hg.bat because it is redundant with hg.exe.
             self.scripts.remove('contrib/win32/hg.bat')
 
         return build_scripts.run(self)
 
 class hgbuildpy(build_py):
     def finalize_options(self):
         build_py.finalize_options(self)
 
         if self.distribution.pure:
             self.distribution.ext_modules = []
         elif self.distribution.cffi:
             from mercurial.cffi import (
                 bdiffbuild,
                 mpatchbuild,
             )
             exts = [mpatchbuild.ffi.distutils_extension(),
                     bdiffbuild.ffi.distutils_extension()]
             # cffi modules go here
             if sys.platform == 'darwin':
                 from mercurial.cffi import osutilbuild
                 exts.append(osutilbuild.ffi.distutils_extension())
             self.distribution.ext_modules = exts
         else:
             h = os.path.join(get_python_inc(), 'Python.h')
             if not os.path.exists(h):
                 raise SystemExit('Python headers are required to build '
                                  'Mercurial but weren\'t found in %s' % h)
 
     def run(self):
         basepath = os.path.join(self.build_lib, 'mercurial')
         self.mkpath(basepath)
 
         rust = self.distribution.rust
         if self.distribution.pure:
             modulepolicy = 'py'
         elif self.build_lib == '.':
             # in-place build should run without rebuilding and Rust extensions
             modulepolicy = 'rust+c-allow' if rust else 'allow'
         else:
             modulepolicy = 'rust+c' if rust else 'c'
 
         content = b''.join([
             b'# this file is autogenerated by setup.py\n',
             b'modulepolicy = b"%s"\n' % modulepolicy.encode('ascii'),
         ])
         write_if_changed(os.path.join(basepath, '__modulepolicy__.py'),
                          content)
 
         build_py.run(self)
 
 class buildhgextindex(Command):
     description = 'generate prebuilt index of hgext (for frozen package)'
     user_options = []
     _indexfilename = 'hgext/__index__.py'
 
     def initialize_options(self):
         pass
 
     def finalize_options(self):
         pass
 
     def run(self):
         if os.path.exists(self._indexfilename):
             with open(self._indexfilename, 'w') as f:
                 f.write('# empty\n')
 
         # here no extension enabled, disabled() lists up everything
         code = ('import pprint; from mercurial import extensions; '
                 'pprint.pprint(extensions.disabled())')
         returncode, out, err = runcmd([sys.executable, '-c', code],
                                       localhgenv())
         if err or returncode != 0:
             raise DistutilsExecError(err)
 
         with open(self._indexfilename, 'wb') as f:
             f.write(b'# this file is autogenerated by setup.py\n')
             f.write(b'docs = ')
             f.write(out)
 
 class buildhgexe(build_ext):
     description = 'compile hg.exe from mercurial/exewrapper.c'
     user_options = build_ext.user_options + [
         ('long-paths-support', None, 'enable support for long paths on '
                                      'Windows (off by default and '
                                      'experimental)'),
     ]
 
     LONG_PATHS_MANIFEST = """
     <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
     <assembly xmlns="urn:schemas-microsoft-com:asm.v1" manifestVersion="1.0">
         <application>
             <windowsSettings
             xmlns:ws2="http://schemas.microsoft.com/SMI/2016/WindowsSettings">
                 <ws2:longPathAware>true</ws2:longPathAware>
             </windowsSettings>
         </application>
     </assembly>"""
 
     def initialize_options(self):
         build_ext.initialize_options(self)
         self.long_paths_support = False
 
     def build_extensions(self):
         if os.name != 'nt':
             return
         if isinstance(self.compiler, HackedMingw32CCompiler):
             self.compiler.compiler_so = self.compiler.compiler # no -mdll
             self.compiler.dll_libraries = [] # no -lmsrvc90
 
         # Different Python installs can have different Python library
         # names. e.g. the official CPython distribution uses pythonXY.dll
         # and MinGW uses libpythonX.Y.dll.
         _kernel32 = ctypes.windll.kernel32
         _kernel32.GetModuleFileNameA.argtypes = [ctypes.c_void_p,
                                                  ctypes.c_void_p,
                                                  ctypes.c_ulong]
         _kernel32.GetModuleFileNameA.restype = ctypes.c_ulong
         size = 1000
         buf = ctypes.create_string_buffer(size + 1)
         filelen = _kernel32.GetModuleFileNameA(sys.dllhandle, ctypes.byref(buf),
                                                size)
 
         if filelen > 0 and filelen != size:
             dllbasename = os.path.basename(buf.value)
             if not dllbasename.lower().endswith(b'.dll'):
                 raise SystemExit('Python DLL does not end with .dll: %s' %
                                  dllbasename)
             pythonlib = dllbasename[:-4]
         else:
             log.warn('could not determine Python DLL filename; '
                      'assuming pythonXY')
 
             hv = sys.hexversion
             pythonlib = 'python%d%d' % (hv >> 24, (hv >> 16) & 0xff)
 
         log.info('using %s as Python library name' % pythonlib)
         with open('mercurial/hgpythonlib.h', 'wb') as f:
             f.write(b'/* this file is autogenerated by setup.py */\n')
             f.write(b'#define HGPYTHONLIB "%s"\n' % pythonlib)
 
         macros = None
         if sys.version_info[0] >= 3:
             macros = [('_UNICODE', None), ('UNICODE', None)]
 
         objects = self.compiler.compile(['mercurial/exewrapper.c'],
                                          output_dir=self.build_temp,
                                          macros=macros)
         dir = os.path.dirname(self.get_ext_fullpath('dummy'))
         self.hgtarget = os.path.join(dir, 'hg')
         self.compiler.link_executable(objects, self.hgtarget,
                                       libraries=[],
                                       output_dir=self.build_temp)
         if self.long_paths_support:
             self.addlongpathsmanifest()
 
     def addlongpathsmanifest(self):
         r"""Add manifest pieces so that hg.exe understands long paths
 
         This is an EXPERIMENTAL feature, use with care.
         To enable long paths support, one needs to do two things:
         - build Mercurial with --long-paths-support option
         - change HKLM\SYSTEM\CurrentControlSet\Control\FileSystem\
                  LongPathsEnabled to have value 1.
 
         Please ignore 'warning 81010002: Unrecognized Element "longPathAware"';
         it happens because Mercurial uses mt.exe circa 2008, which is not
         yet aware of long paths support in the manifest (I think so at least).
         This does not stop mt.exe from embedding/merging the XML properly.
 
         Why resource #1 should be used for .exe manifests? I don't know and
         wasn't able to find an explanation for mortals. But it seems to work.
         """
         exefname = self.compiler.executable_filename(self.hgtarget)
         fdauto, manfname = tempfile.mkstemp(suffix='.hg.exe.manifest')
         os.close(fdauto)
         with open(manfname, 'w') as f:
             f.write(self.LONG_PATHS_MANIFEST)
         log.info("long paths manifest is written to '%s'" % manfname)
         inputresource = '-inputresource:%s;#1' % exefname
         outputresource = '-outputresource:%s;#1' % exefname
         log.info("running mt.exe to update hg.exe's manifest in-place")
         # supplying both -manifest and -inputresource to mt.exe makes
         # it merge the embedded and supplied manifests in the -outputresource
         self.spawn(['mt.exe', '-nologo', '-manifest', manfname,
                     inputresource, outputresource])
         log.info("done updating hg.exe's manifest")
         os.remove(manfname)
 
     @property
     def hgexepath(self):
         dir = os.path.dirname(self.get_ext_fullpath('dummy'))
         return os.path.join(self.build_temp, dir, 'hg.exe')
 
 class hgbuilddoc(Command):
     description = 'build documentation'
     user_options = [
         ('man', None, 'generate man pages'),
         ('html', None, 'generate html pages'),
     ]
 
     def initialize_options(self):
         self.man = None
         self.html = None
 
     def finalize_options(self):
         # If --man or --html are set, only generate what we're told to.
         # Otherwise generate everything.
         have_subset = self.man is not None or self.html is not None
 
         if have_subset:
             self.man = True if self.man else False
             self.html = True if self.html else False
         else:
             self.man = True
             self.html = True
 
     def run(self):
         def normalizecrlf(p):
             with open(p, 'rb') as fh:
                 orig = fh.read()
 
             if b'\r\n' not in orig:
                 return
 
             log.info('normalizing %s to LF line endings' % p)
             with open(p, 'wb') as fh:
                 fh.write(orig.replace(b'\r\n', b'\n'))
 
         def gentxt(root):
             txt = 'doc/%s.txt' % root
             log.info('generating %s' % txt)
             res, out, err = runcmd(
                 [sys.executable, 'gendoc.py', root],
                 os.environ,
                 cwd='doc')
             if res:
                 raise SystemExit('error running gendoc.py: %s' %
                                  '\n'.join([out, err]))
 
             with open(txt, 'wb') as fh:
                 fh.write(out)
 
         def gengendoc(root):
             gendoc = 'doc/%s.gendoc.txt' % root
 
             log.info('generating %s' % gendoc)
             res, out, err = runcmd(
                 [sys.executable, 'gendoc.py', '%s.gendoc' % root],
                 os.environ,
                 cwd='doc')
             if res:
                 raise SystemExit('error running gendoc: %s' %
                                  '\n'.join([out, err]))
 
             with open(gendoc, 'wb') as fh:
                 fh.write(out)
 
         def genman(root):
             log.info('generating doc/%s' % root)
             res, out, err = runcmd(
                 [sys.executable, 'runrst', 'hgmanpage', '--halt', 'warning',
                  '--strip-elements-with-class', 'htmlonly',
                  '%s.txt' % root, root],
                 os.environ,
                 cwd='doc')
             if res:
                 raise SystemExit('error running runrst: %s' %
                                  '\n'.join([out, err]))
 
             normalizecrlf('doc/%s' % root)
 
         def genhtml(root):
             log.info('generating doc/%s.html' % root)
             res, out, err = runcmd(
                 [sys.executable, 'runrst', 'html', '--halt', 'warning',
                  '--link-stylesheet', '--stylesheet-path', 'style.css',
                  '%s.txt' % root, '%s.html' % root],
                 os.environ,
                 cwd='doc')
             if res:
                 raise SystemExit('error running runrst: %s' %
                                  '\n'.join([out, err]))
 
             normalizecrlf('doc/%s.html' % root)
 
         # This logic is duplicated in doc/Makefile.
         sources = set(f for f in os.listdir('mercurial/help')
                       if re.search(r'[0-9]\.txt$', f))
 
         # common.txt is a one-off.
         gentxt('common')
 
         for source in sorted(sources):
             assert source[-4:] == '.txt'
             root = source[:-4]
 
             gentxt(root)
             gengendoc(root)
 
             if self.man:
                 genman(root)
             if self.html:
                 genhtml(root)
 
 class hginstall(install):
 
     user_options = install.user_options + [
         ('old-and-unmanageable', None,
          'noop, present for eggless setuptools compat'),
         ('single-version-externally-managed', None,
          'noop, present for eggless setuptools compat'),
     ]
 
     # Also helps setuptools not be sad while we refuse to create eggs.
     single_version_externally_managed = True
 
     def get_sub_commands(self):
         # Screen out egg related commands to prevent egg generation.  But allow
         # mercurial.egg-info generation, since that is part of modern
         # packaging.
         excl = set(['bdist_egg'])
         return filter(lambda x: x not in excl, install.get_sub_commands(self))
 
 class hginstalllib(install_lib):
     '''
     This is a specialization of install_lib that replaces the copy_file used
     there so that it supports setting the mode of files after copying them,
     instead of just preserving the mode that the files originally had.  If your
     system has a umask of something like 027, preserving the permissions when
     copying will lead to a broken install.
 
     Note that just passing keep_permissions=False to copy_file would be
     insufficient, as it might still be applying a umask.
     '''
 
     def run(self):
         realcopyfile = file_util.copy_file
         def copyfileandsetmode(*args, **kwargs):
             src, dst = args[0], args[1]
             dst, copied = realcopyfile(*args, **kwargs)
             if copied:
                 st = os.stat(src)
                 # Persist executable bit (apply it to group and other if user
                 # has it)
                 if st[stat.ST_MODE] & stat.S_IXUSR:
                     setmode = int('0755', 8)
                 else:
                     setmode = int('0644', 8)
                 m = stat.S_IMODE(st[stat.ST_MODE])
                 m = (m & ~int('0777', 8)) | setmode
                 os.chmod(dst, m)
         file_util.copy_file = copyfileandsetmode
         try:
             install_lib.run(self)
         finally:
             file_util.copy_file = realcopyfile
 
 class hginstallscripts(install_scripts):
     '''
     This is a specialization of install_scripts that replaces the @LIBDIR@ with
     the configured directory for modules. If possible, the path is made relative
     to the directory for scripts.
     '''
 
     def initialize_options(self):
         install_scripts.initialize_options(self)
 
         self.install_lib = None
 
     def finalize_options(self):
         install_scripts.finalize_options(self)
         self.set_undefined_options('install',
                                    ('install_lib', 'install_lib'))
 
     def run(self):
         install_scripts.run(self)
 
         # It only makes sense to replace @LIBDIR@ with the install path if
         # the install path is known. For wheels, the logic below calculates
         # the libdir to be "../..". This is because the internal layout of a
         # wheel archive looks like:
         #
         #   mercurial-3.6.1.data/scripts/hg
         #   mercurial/__init__.py
         #
         # When installing wheels, the subdirectories of the "<pkg>.data"
         # directory are translated to system local paths and files therein
         # are copied in place. The mercurial/* files are installed into the
         # site-packages directory. However, the site-packages directory
         # isn't known until wheel install time. This means we have no clue
         # at wheel generation time what the installed site-packages directory
         # will be. And, wheels don't appear to provide the ability to register
         # custom code to run during wheel installation. This all means that
         # we can't reliably set the libdir in wheels: the default behavior
         # of looking in sys.path must do.
 
         if (os.path.splitdrive(self.install_dir)[0] !=
             os.path.splitdrive(self.install_lib)[0]):
             # can't make relative paths from one drive to another, so use an
             # absolute path instead
             libdir = self.install_lib
         else:
             common = os.path.commonprefix((self.install_dir, self.install_lib))
             rest = self.install_dir[len(common):]
             uplevel = len([n for n in os.path.split(rest) if n])
 
             libdir = uplevel * ('..' + os.sep) + self.install_lib[len(common):]
 
         for outfile in self.outfiles:
             with open(outfile, 'rb') as fp:
                 data = fp.read()
 
             # skip binary files
             if b'\0' in data:
                 continue
 
             # During local installs, the shebang will be rewritten to the final
             # install path. During wheel packaging, the shebang has a special
             # value.
             if data.startswith(b'#!python'):
                 log.info('not rewriting @LIBDIR@ in %s because install path '
                          'not known' % outfile)
                 continue
 
             data = data.replace(b'@LIBDIR@', libdir.encode(libdir_escape))
             with open(outfile, 'wb') as fp:
                 fp.write(data)
 
 # virtualenv installs custom distutils/__init__.py and
 # distutils/distutils.cfg files which essentially proxy back to the
 # "real" distutils in the main Python install. The presence of this
 # directory causes py2exe to pick up the "hacked" distutils package
 # from the virtualenv and "import distutils" will fail from the py2exe
 # build because the "real" distutils files can't be located.
 #
 # We work around this by monkeypatching the py2exe code finding Python
 # modules to replace the found virtualenv distutils modules with the
 # original versions via filesystem scanning. This is a bit hacky. But
 # it allows us to use virtualenvs for py2exe packaging, which is more
 # deterministic and reproducible.
 #
 # It's worth noting that the common StackOverflow suggestions for this
 # problem involve copying the original distutils files into the
 # virtualenv or into the staging directory after setup() is invoked.
 # The former is very brittle and can easily break setup(). Our hacking
 # of the found modules routine has a similar result as copying the files
 # manually. But it makes fewer assumptions about how py2exe works and
 # is less brittle.
 
 # This only catches virtualenvs made with virtualenv (as opposed to
 # venv, which is likely what Python 3 uses).
 py2exehacked = py2exeloaded and getattr(sys, 'real_prefix', None) is not None
 
 if py2exehacked:
     from distutils.command.py2exe import py2exe as buildpy2exe
     from py2exe.mf import Module as py2exemodule
 
     class hgbuildpy2exe(buildpy2exe):
         def find_needed_modules(self, mf, files, modules):
             res = buildpy2exe.find_needed_modules(self, mf, files, modules)
 
             # Replace virtualenv's distutils modules with the real ones.
             modules = {}
             for k, v in res.modules.items():
                 if k != 'distutils' and not k.startswith('distutils.'):
                     modules[k] = v
 
             res.modules = modules
 
             import opcode
             distutilsreal = os.path.join(os.path.dirname(opcode.__file__),
                                          'distutils')
 
             for root, dirs, files in os.walk(distutilsreal):
                 for f in sorted(files):
                     if not f.endswith('.py'):
                         continue
 
                     full = os.path.join(root, f)
 
                     parents = ['distutils']
 
                     if root != distutilsreal:
                         rel = os.path.relpath(root, distutilsreal)
                         parents.extend(p for p in rel.split(os.sep))
 
                     modname = '%s.%s' % ('.'.join(parents), f[:-3])
 
                     if modname.startswith('distutils.tests.'):
                         continue
 
                     if modname.endswith('.__init__'):
                         modname = modname[:-len('.__init__')]
                         path = os.path.dirname(full)
                     else:
                         path = None
 
                     res.modules[modname] = py2exemodule(modname, full,
                                                         path=path)
 
             if 'distutils' not in res.modules:
                 raise SystemExit('could not find distutils modules')
 
             return res
 
 cmdclass = {'build': hgbuild,
             'build_doc': hgbuilddoc,
             'build_mo': hgbuildmo,
             'build_ext': hgbuildext,
             'build_py': hgbuildpy,
             'build_scripts': hgbuildscripts,
             'build_hgextindex': buildhgextindex,
             'install': hginstall,
             'install_lib': hginstalllib,
             'install_scripts': hginstallscripts,
             'build_hgexe': buildhgexe,
             }
 
 if py2exehacked:
     cmdclass['py2exe'] = hgbuildpy2exe
 
 packages = ['mercurial',
             'mercurial.cext',
             'mercurial.cffi',
             'mercurial.hgweb',
+            'mercurial.interfaces',
             'mercurial.pure',
             'mercurial.thirdparty',
             'mercurial.thirdparty.attr',
             'mercurial.thirdparty.zope',
             'mercurial.thirdparty.zope.interface',
             'mercurial.utils',
             'mercurial.revlogutils',
             'mercurial.testing',
             'hgext', 'hgext.convert', 'hgext.fsmonitor',
             'hgext.fastannotate',
             'hgext.fsmonitor.pywatchman',
             'hgext.highlight',
             'hgext.infinitepush',
             'hgext.largefiles', 'hgext.lfs', 'hgext.narrow',
             'hgext.remotefilelog',
             'hgext.zeroconf', 'hgext3rd',
             'hgdemandimport']
 if sys.version_info[0] == 2:
     packages.extend(['mercurial.thirdparty.concurrent',
                      'mercurial.thirdparty.concurrent.futures'])
 
 if 'HG_PY2EXE_EXTRA_INSTALL_PACKAGES' in os.environ:
     # py2exe can't cope with namespace packages very well, so we have to
     # install any hgext3rd.* extensions that we want in the final py2exe
     # image here. This is gross, but you gotta do what you gotta do.
     packages.extend(os.environ['HG_PY2EXE_EXTRA_INSTALL_PACKAGES'].split(' '))
 
 common_depends = ['mercurial/bitmanipulation.h',
                   'mercurial/compat.h',
                   'mercurial/cext/util.h']
 common_include_dirs = ['mercurial']
 
 osutil_cflags = []
 osutil_ldflags = []
 
 # platform specific macros
 for plat, func in [('bsd', 'setproctitle')]:
     if re.search(plat, sys.platform) and hasfunction(new_compiler(), func):
         osutil_cflags.append('-DHAVE_%s' % func.upper())
 
 for plat, macro, code in [
     ('bsd|darwin', 'BSD_STATFS', '''
      #include <sys/param.h>
      #include <sys/mount.h>
      int main() { struct statfs s; return sizeof(s.f_fstypename); }
      '''),
     ('linux', 'LINUX_STATFS', '''
      #include <linux/magic.h>
      #include <sys/vfs.h>
      int main() { struct statfs s; return sizeof(s.f_type); }
      '''),
 ]:
     if re.search(plat, sys.platform) and cancompile(new_compiler(), code):
         osutil_cflags.append('-DHAVE_%s' % macro)
 
 if sys.platform == 'darwin':
     osutil_ldflags += ['-framework', 'ApplicationServices']
 
 xdiff_srcs = [
     'mercurial/thirdparty/xdiff/xdiffi.c',
     'mercurial/thirdparty/xdiff/xprepare.c',
     'mercurial/thirdparty/xdiff/xutils.c',
 ]
 
 xdiff_headers = [
     'mercurial/thirdparty/xdiff/xdiff.h',
     'mercurial/thirdparty/xdiff/xdiffi.h',
     'mercurial/thirdparty/xdiff/xinclude.h',
     'mercurial/thirdparty/xdiff/xmacros.h',
     'mercurial/thirdparty/xdiff/xprepare.h',
     'mercurial/thirdparty/xdiff/xtypes.h',
     'mercurial/thirdparty/xdiff/xutils.h',
 ]
 
 class RustCompilationError(CCompilerError):
     """Exception class for Rust compilation errors."""
 
 class RustExtension(Extension):
     """Base classes for concrete Rust Extension classes.
     """
 
     rusttargetdir = os.path.join('rust', 'target', 'release')
 
     def __init__(self, mpath, sources, rustlibname, subcrate,
                  py3_features=None, **kw):
         Extension.__init__(self, mpath, sources, **kw)
         srcdir = self.rustsrcdir = os.path.join('rust', subcrate)
         self.py3_features = py3_features
 
         # adding Rust source and control files to depends so that the extension
         # gets rebuilt if they've changed
         self.depends.append(os.path.join(srcdir, 'Cargo.toml'))
         cargo_lock = os.path.join(srcdir, 'Cargo.lock')
         if os.path.exists(cargo_lock):
             self.depends.append(cargo_lock)
         for dirpath, subdir, fnames in os.walk(os.path.join(srcdir, 'src')):
             self.depends.extend(os.path.join(dirpath, fname)
                                 for fname in fnames
                                 if os.path.splitext(fname)[1] == '.rs')
 
     @staticmethod
     def rustdylibsuffix():
         """Return the suffix for shared libraries produced by rustc.
 
         See also: https://doc.rust-lang.org/reference/linkage.html
         """
         if sys.platform == 'darwin':
             return '.dylib'
         elif os.name == 'nt':
             return '.dll'
         else:
             return '.so'
 
     def rustbuild(self):
         env = os.environ.copy()
         if 'HGTEST_RESTOREENV' in env:
             # Mercurial tests change HOME to a temporary directory,
             # but, if installed with rustup, the Rust toolchain needs
             # HOME to be correct (otherwise the 'no default toolchain'
             # error message is issued and the build fails).
             # This happens currently with test-hghave.t, which does
             # invoke this build.
 
             # Unix only fix (os.path.expanduser not really reliable if
             # HOME is shadowed like this)
             import pwd
             env['HOME'] = pwd.getpwuid(os.getuid()).pw_dir
 
         cargocmd = ['cargo', 'rustc', '-vv', '--release']
         if sys.version_info[0] == 3 and self.py3_features is not None:
             cargocmd.extend(('--features', self.py3_features,
                              '--no-default-features'))
         cargocmd.append('--')
         if sys.platform == 'darwin':
             cargocmd.extend(("-C", "link-arg=-undefined",
                              "-C", "link-arg=dynamic_lookup"))
         try:
             subprocess.check_call(cargocmd, env=env, cwd=self.rustsrcdir)
         except OSError as exc:
             if exc.errno == errno.ENOENT:
                 raise RustCompilationError("Cargo not found")
             elif exc.errno == errno.EACCES:
                 raise RustCompilationError(
                     "Cargo found, but permisssion to execute it is denied")
             else:
                 raise
         except subprocess.CalledProcessError:
             raise RustCompilationError(
                 "Cargo failed. Working directory: %r, "
                 "command: %r, environment: %r"
                 % (self.rustsrcdir, cargocmd, env))
 
 class RustEnhancedExtension(RustExtension):
     """A C Extension, conditionally enhanced with Rust code.
 
     If the HGRUSTEXT environment variable is set to something else
     than 'cpython', the Rust sources get compiled and linked within the
     C target shared library object.
     """
 
     def __init__(self, mpath, sources, rustlibname, subcrate, **kw):
         RustExtension.__init__(self, mpath, sources, rustlibname, subcrate,
                                **kw)
         if hgrustext != 'direct-ffi':
             return
         self.extra_compile_args.append('-DWITH_RUST')
         self.libraries.append(rustlibname)
         self.library_dirs.append(self.rusttargetdir)
 
     def rustbuild(self):
         if hgrustext == 'direct-ffi':
             RustExtension.rustbuild(self)
 
 class RustStandaloneExtension(RustExtension):
 
     def __init__(self, pydottedname, rustcrate, dylibname, **kw):
         RustExtension.__init__(self, pydottedname, [], dylibname, rustcrate,
                                **kw)
         self.dylibname = dylibname
 
     def build(self, target_dir):
         self.rustbuild()
         target = [target_dir]
         target.extend(self.name.split('.'))
         target[-1] += DYLIB_SUFFIX
         shutil.copy2(os.path.join(self.rusttargetdir,
                                   self.dylibname + self.rustdylibsuffix()),
                      os.path.join(*target))
 
 
 extmodules = [
     Extension('mercurial.cext.base85', ['mercurial/cext/base85.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     Extension('mercurial.cext.bdiff', ['mercurial/bdiff.c',
                                        'mercurial/cext/bdiff.c'] + xdiff_srcs,
               include_dirs=common_include_dirs,
               depends=common_depends + ['mercurial/bdiff.h'] + xdiff_headers),
     Extension('mercurial.cext.mpatch', ['mercurial/mpatch.c',
                                         'mercurial/cext/mpatch.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     RustEnhancedExtension(
         'mercurial.cext.parsers', ['mercurial/cext/charencode.c',
                                    'mercurial/cext/dirs.c',
                                    'mercurial/cext/manifest.c',
                                    'mercurial/cext/parsers.c',
                                    'mercurial/cext/pathencode.c',
                                    'mercurial/cext/revlog.c'],
         'hgdirectffi',
         'hg-direct-ffi',
         include_dirs=common_include_dirs,
         depends=common_depends + ['mercurial/cext/charencode.h',
                                   'mercurial/cext/revlog.h',
                                   'rust/hg-core/src/ancestors.rs',
                                   'rust/hg-core/src/lib.rs']),
     Extension('mercurial.cext.osutil', ['mercurial/cext/osutil.c'],
               include_dirs=common_include_dirs,
               extra_compile_args=osutil_cflags,
               extra_link_args=osutil_ldflags,
               depends=common_depends),
     Extension(
         'mercurial.thirdparty.zope.interface._zope_interface_coptimizations', [
         'mercurial/thirdparty/zope/interface/_zope_interface_coptimizations.c',
         ]),
     Extension('hgext.fsmonitor.pywatchman.bser',
               ['hgext/fsmonitor/pywatchman/bser.c']),
     RustStandaloneExtension('mercurial.rustext', 'hg-cpython', 'librusthg',
                             py3_features='python3'),
     ]
 
 
 sys.path.insert(0, 'contrib/python-zstandard')
 import setup_zstd
 extmodules.append(setup_zstd.get_c_extension(
     name='mercurial.zstd',
     root=os.path.abspath(os.path.dirname(__file__))))
 
 try:
     from distutils import cygwinccompiler
 
     # the -mno-cygwin option has been deprecated for years
     mingw32compilerclass = cygwinccompiler.Mingw32CCompiler
 
     class HackedMingw32CCompiler(cygwinccompiler.Mingw32CCompiler):
         def __init__(self, *args, **kwargs):
             mingw32compilerclass.__init__(self, *args, **kwargs)
             for i in 'compiler compiler_so linker_exe linker_so'.split():
                 try:
                     getattr(self, i).remove('-mno-cygwin')
                 except ValueError:
                     pass
 
     cygwinccompiler.Mingw32CCompiler = HackedMingw32CCompiler
 except ImportError:
     # the cygwinccompiler package is not available on some Python
     # distributions like the ones from the optware project for Synology
     # DiskStation boxes
     class HackedMingw32CCompiler(object):
         pass
 
 if os.name == 'nt':
     # Allow compiler/linker flags to be added to Visual Studio builds.  Passing
     # extra_link_args to distutils.extensions.Extension() doesn't have any
     # effect.
     from distutils import msvccompiler
 
     msvccompilerclass = msvccompiler.MSVCCompiler
 
     class HackedMSVCCompiler(msvccompiler.MSVCCompiler):
         def initialize(self):
             msvccompilerclass.initialize(self)
             # "warning LNK4197: export 'func' specified multiple times"
             self.ldflags_shared.append('/ignore:4197')
             self.ldflags_shared_debug.append('/ignore:4197')
 
     msvccompiler.MSVCCompiler = HackedMSVCCompiler
 
 packagedata = {'mercurial': ['locale/*/LC_MESSAGES/hg.mo',
                              'help/*.txt',
                              'help/internals/*.txt',
                              'default.d/*.rc',
                              'dummycert.pem']}
 
 def ordinarypath(p):
     return p and p[0] != '.' and p[-1] != '~'
 
 for root in ('templates',):
     for curdir, dirs, files in os.walk(os.path.join('mercurial', root)):
         curdir = curdir.split(os.sep, 1)[1]
         dirs[:] = filter(ordinarypath, dirs)
         for f in filter(ordinarypath, files):
             f = os.path.join(curdir, f)
             packagedata['mercurial'].append(f)
 
 datafiles = []
 
 # distutils expects version to be str/unicode. Converting it to
 # unicode on Python 2 still works because it won't contain any
 # non-ascii bytes and will be implicitly converted back to bytes
 # when operated on.
 assert isinstance(version, bytes)
 setupversion = version.decode('ascii')
 
 extra = {}
 
 py2exepackages = [
     'hgdemandimport',
     'hgext3rd',
     'hgext',
     'email',
     # implicitly imported per module policy
     # (cffi wouldn't be used as a frozen exe)
     'mercurial.cext',
     #'mercurial.cffi',
     'mercurial.pure',
 ]
 
 py2exeexcludes = []
 py2exedllexcludes = ['crypt32.dll']
 
 if issetuptools:
     extra['python_requires'] = supportedpy
 
 if py2exeloaded:
     extra['console'] = [
         {'script':'hg',
          'copyright':'Copyright (C) 2005-2019 Matt Mackall and others',
          'product_version':version}]
     # Sub command of 'build' because 'py2exe' does not handle sub_commands.
     # Need to override hgbuild because it has a private copy of
     # build.sub_commands.
     hgbuild.sub_commands.insert(0, ('build_hgextindex', None))
     # put dlls in sub directory so that they won't pollute PATH
     extra['zipfile'] = 'lib/library.zip'
 
     # We allow some configuration to be supplemented via environment
     # variables. This is better than setup.cfg files because it allows
     # supplementing configs instead of replacing them.
     extrapackages = os.environ.get('HG_PY2EXE_EXTRA_PACKAGES')
     if extrapackages:
         py2exepackages.extend(extrapackages.split(' '))
 
     excludes = os.environ.get('HG_PY2EXE_EXTRA_EXCLUDES')
     if excludes:
         py2exeexcludes.extend(excludes.split(' '))
 
     dllexcludes = os.environ.get('HG_PY2EXE_EXTRA_DLL_EXCLUDES')
     if dllexcludes:
         py2exedllexcludes.extend(dllexcludes.split(' '))
 
 if os.name == 'nt':
     # Windows binary file versions for exe/dll files must have the
     # form W.X.Y.Z, where W,X,Y,Z are numbers in the range 0..65535
     setupversion = setupversion.split(r'+', 1)[0]
 
 if sys.platform == 'darwin' and os.path.exists('/usr/bin/xcodebuild'):
     version = runcmd(['/usr/bin/xcodebuild', '-version'], {})[1].splitlines()
     if version:
         version = version[0]
         if sys.version_info[0] == 3:
             version = version.decode('utf-8')
         xcode4 = (version.startswith('Xcode') and
                   StrictVersion(version.split()[1]) >= StrictVersion('4.0'))
         xcode51 = re.match(r'^Xcode\s+5\.1', version) is not None
     else:
         # xcodebuild returns empty on OS X Lion with XCode 4.3 not
         # installed, but instead with only command-line tools. Assume
         # that only happens on >= Lion, thus no PPC support.
         xcode4 = True
         xcode51 = False
 
     # XCode 4.0 dropped support for ppc architecture, which is hardcoded in
     # distutils.sysconfig
     if xcode4:
         os.environ['ARCHFLAGS'] = ''
 
     # XCode 5.1 changes clang such that it now fails to compile if the
     # -mno-fused-madd flag is passed, but the version of Python shipped with
     # OS X 10.9 Mavericks includes this flag. This causes problems in all
     # C extension modules, and a bug has been filed upstream at
     # http://bugs.python.org/issue21244. We also need to patch this here
     # so Mercurial can continue to compile in the meantime.
     if xcode51:
         cflags = get_config_var('CFLAGS')
         if cflags and re.search(r'-mno-fused-madd\b', cflags) is not None:
             os.environ['CFLAGS'] = (
                 os.environ.get('CFLAGS', '') + ' -Qunused-arguments')
 
 setup(name='mercurial',
       version=setupversion,
       author='Matt Mackall and many others',
       author_email='[e-mail]',
       url='https://mercurial-scm.org/',
       download_url='https://mercurial-scm.org/release/',
       description=('Fast scalable distributed SCM (revision control, version '
                    'control) system'),
       long_description=('Mercurial is a distributed SCM tool written in Python.'
                         ' It is used by a number of large projects that require'
                         ' fast, reliable distributed revision control, such as '
                         'Mozilla.'),
       license='GNU GPLv2 or any later version',
       classifiers=[
           'Development Status :: 6 - Mature',
           'Environment :: Console',
           'Intended Audience :: Developers',
           'Intended Audience :: System Administrators',
           'License :: OSI Approved :: GNU General Public License (GPL)',
           'Natural Language :: Danish',
           'Natural Language :: English',
           'Natural Language :: German',
           'Natural Language :: Italian',
           'Natural Language :: Japanese',
           'Natural Language :: Portuguese (Brazilian)',
           'Operating System :: Microsoft :: Windows',
           'Operating System :: OS Independent',
           'Operating System :: POSIX',
           'Programming Language :: C',
           'Programming Language :: Python',
           'Topic :: Software Development :: Version Control',
       ],
       scripts=scripts,
       packages=packages,
       ext_modules=extmodules,
       data_files=datafiles,
       package_data=packagedata,
       cmdclass=cmdclass,
       distclass=hgdist,
       options={
           'py2exe': {
               'bundle_files': 3,
               'dll_excludes': py2exedllexcludes,
               'excludes': py2exeexcludes,
               'packages': py2exepackages,
           },
           'bdist_mpkg': {
               'zipdist': False,
               'license': 'COPYING',
               'readme': 'contrib/packaging/macosx/Readme.html',
               'welcome': 'contrib/packaging/macosx/Welcome.html',
           },
       },
       **extra)

tests/notcapable

@@ -1,24 +1,25
 # Disable the $CAP wire protocol capability.
 
 if test -z "$CAP"
 then
     echo "CAP environment variable not set."
 fi
 
 cat > notcapable-$CAP.py << EOF
-from mercurial import extensions, localrepo, repository
+from mercurial import extensions, localrepo
+from mercurial.interfaces import repository
 def extsetup(ui):
     extensions.wrapfunction(repository.peer, 'capable', wrapcapable)
     extensions.wrapfunction(localrepo.localrepository, 'peer', wrappeer)
 def wrapcapable(orig, self, name, *args, **kwargs):
     if name in b'$CAP'.split(b' '):
         return False
     return orig(self, name, *args, **kwargs)
 def wrappeer(orig, self):
     # Since we're disabling some newer features, we need to make sure local
     # repos add in the legacy features again.
     return localrepo.locallegacypeer(self)
 EOF
 
 echo '[extensions]' >> $HGRCPATH
 echo "notcapable-$CAP = `pwd`/notcapable-$CAP.py" >> $HGRCPATH

tests/pullext.py

@@ -1,50 +1,52
 # pullext.py - Simple extension to test pulling
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     commands,
     error,
     extensions,
     localrepo,
+)
+from mercurial.interfaces import (
     repository,
 )
 
 def clonecommand(orig, ui, repo, *args, **kwargs):
     if kwargs.get(r'include') or kwargs.get(r'exclude'):
         kwargs[r'narrow'] = True
 
     if kwargs.get(r'depth'):
         try:
             kwargs[r'depth'] = int(kwargs[r'depth'])
         except ValueError:
             raise error.Abort(_('--depth must be an integer'))
 
     return orig(ui, repo, *args, **kwargs)
 
 def featuresetup(ui, features):
     features.add(repository.NARROW_REQUIREMENT)
 
 def extsetup(ui):
     entry = extensions.wrapcommand(commands.table, b'clone', clonecommand)
 
     hasinclude = any(x[1] == b'include' for x in entry[1])
     hasdepth = any(x[1] == b'depth' for x in entry[1])
 
     if not hasinclude:
         entry[1].append((b'', b'include', [],
                          _(b'pattern of file/directory to clone')))
         entry[1].append((b'', b'exclude', [],
                          _(b'pattern of file/directory to not clone')))
 
     if not hasdepth:
         entry[1].append((b'', b'depth', b'',
                          _(b'ancestry depth of changesets to fetch')))
 
     localrepo.featuresetupfuncs.add(featuresetup)

tests/simplestorerepo.py

@@ -1,711 +1,713
 # simplestorerepo.py - Extension that swaps in alternate repository storage.
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # To use this with the test suite:
 #
 #   $ HGREPOFEATURES="simplestore" ./run-tests.py \
 #       --extra-config-opt extensions.simplestore=`pwd`/simplestorerepo.py
 
 from __future__ import absolute_import
 
 import stat
 
 from mercurial.i18n import _
 from mercurial.node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from mercurial.thirdparty import (
     attr,
 )
 from mercurial import (
     ancestor,
     bundlerepo,
     error,
     extensions,
     localrepo,
     mdiff,
     pycompat,
-    repository,
     revlog,
     store,
     verify,
 )
+from mercurial.interfaces import (
+    repository,
+)
 from mercurial.utils import (
     cborutil,
     interfaceutil,
     storageutil,
 )
 from mercurial.revlogutils import (
     flagutil,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 REQUIREMENT = 'testonly-simplestore'
 
 def validatenode(node):
     if isinstance(node, int):
         raise ValueError('expected node; got int')
 
     if len(node) != 20:
         raise ValueError('expected 20 byte node')
 
 def validaterev(rev):
     if not isinstance(rev, int):
         raise ValueError('expected int')
 
 class simplestoreerror(error.StorageError):
     pass
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class simplestorerevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     linknode = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class simplefilestoreproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.ifilestorage)
 class filestorage(object):
     """Implements storage for a tracked path.
 
     Data is stored in the VFS in a directory corresponding to the tracked
     path.
 
     Index data is stored in an ``index`` file using CBOR.
 
     Fulltext data is stored in files having names of the node.
     """
 
     def __init__(self, svfs, path):
         self._svfs = svfs
         self._path = path
 
         self._storepath = b'/'.join([b'data', path])
         self._indexpath = b'/'.join([self._storepath, b'index'])
 
         indexdata = self._svfs.tryread(self._indexpath)
         if indexdata:
             indexdata = cborutil.decodeall(indexdata)
 
         self._indexdata = indexdata or []
         self._indexbynode = {}
         self._indexbyrev = {}
         self._index = []
         self._refreshindex()
 
     def _refreshindex(self):
         self._indexbynode.clear()
         self._indexbyrev.clear()
         self._index = []
 
         for i, entry in enumerate(self._indexdata):
             self._indexbynode[entry[b'node']] = entry
             self._indexbyrev[i] = entry
 
         self._indexbynode[nullid] = {
             b'node': nullid,
             b'p1': nullid,
             b'p2': nullid,
             b'linkrev': nullrev,
             b'flags': 0,
         }
 
         self._indexbyrev[nullrev] = {
             b'node': nullid,
             b'p1': nullid,
             b'p2': nullid,
             b'linkrev': nullrev,
             b'flags': 0,
         }
 
         for i, entry in enumerate(self._indexdata):
             p1rev, p2rev = self.parentrevs(self.rev(entry[b'node']))
 
             # start, length, rawsize, chainbase, linkrev, p1, p2, node
             self._index.append((0, 0, 0, -1, entry[b'linkrev'], p1rev, p2rev,
                                 entry[b'node']))
 
         self._index.append((0, 0, 0, -1, -1, -1, -1, nullid))
 
     def __len__(self):
         return len(self._indexdata)
 
     def __iter__(self):
         return iter(range(len(self)))
 
     def revs(self, start=0, stop=None):
         step = 1
         if stop is not None:
             if start > stop:
                 step = -1
 
             stop += step
         else:
             stop = len(self)
 
         return range(start, stop, step)
 
     def parents(self, node):
         validatenode(node)
 
         if node not in self._indexbynode:
             raise KeyError('unknown node')
 
         entry = self._indexbynode[node]
 
         return entry[b'p1'], entry[b'p2']
 
     def parentrevs(self, rev):
         p1, p2 = self.parents(self._indexbyrev[rev][b'node'])
         return self.rev(p1), self.rev(p2)
 
     def rev(self, node):
         validatenode(node)
 
         try:
             self._indexbynode[node]
         except KeyError:
             raise error.LookupError(node, self._indexpath, _('no node'))
 
         for rev, entry in self._indexbyrev.items():
             if entry[b'node'] == node:
                 return rev
 
         raise error.ProgrammingError('this should not occur')
 
     def node(self, rev):
         validaterev(rev)
 
         return self._indexbyrev[rev][b'node']
 
     def hasnode(self, node):
         validatenode(node)
         return node in self._indexbynode
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         raise NotImplementedError('TODO')
 
     def lookup(self, node):
         if isinstance(node, int):
             return self.node(node)
 
         if len(node) == 20:
             self.rev(node)
             return node
 
         try:
             rev = int(node)
             if '%d' % rev != node:
                 raise ValueError
 
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
 
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
 
         if len(node) == 40:
             try:
                 rawnode = bin(node)
                 self.rev(rawnode)
                 return rawnode
             except TypeError:
                 pass
 
         raise error.LookupError(node, self._path, _('invalid lookup input'))
 
     def linkrev(self, rev):
         validaterev(rev)
 
         return self._indexbyrev[rev][b'linkrev']
 
     def _flags(self, rev):
         validaterev(rev)
 
         return self._indexbyrev[rev][b'flags']
 
     def _candelta(self, baserev, rev):
         validaterev(baserev)
         validaterev(rev)
 
         if ((self._flags(baserev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS)
             or (self._flags(rev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS)):
             return False
 
         return True
 
     def _processflags(self, text, flags, operation, raw=False):
         if flags == 0:
             return text, True
 
         if flags & ~flagutil.REVIDX_KNOWN_FLAGS:
             raise simplestoreerror(_("incompatible revision flag '%#x'") %
                                    (flags & ~flagutil.REVIDX_KNOWN_FLAGS))
 
         validatehash = True
         # Depending on the operation (read or write), the order might be
         # reversed due to non-commutative transforms.
         orderedflags = revlog.REVIDX_FLAGS_ORDER
         if operation == 'write':
             orderedflags = reversed(orderedflags)
 
         for flag in orderedflags:
             # If a flagprocessor has been registered for a known flag, apply the
             # related operation transform and update result tuple.
             if flag & flags:
                 vhash = True
 
                 if flag not in revlog._flagprocessors:
                     message = _("missing processor for flag '%#x'") % (flag)
                     raise simplestoreerror(message)
 
                 processor = revlog._flagprocessors[flag]
                 if processor is not None:
                     readtransform, writetransform, rawtransform = processor
 
                     if raw:
                         vhash = rawtransform(self, text)
                     elif operation == 'read':
                         text, vhash = readtransform(self, text)
                     else:  # write operation
                         text, vhash = writetransform(self, text)
                 validatehash = validatehash and vhash
 
         return text, validatehash
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         if p1 is None and p2 is None:
             p1, p2 = self.parents(node)
         if node != storageutil.hashrevisionsha1(text, p1, p2):
             raise simplestoreerror(_("integrity check failed on %s") %
                 self._path)
 
     def revision(self, nodeorrev, raw=False):
         if isinstance(nodeorrev, int):
             node = self.node(nodeorrev)
         else:
             node = nodeorrev
         validatenode(node)
 
         if node == nullid:
             return b''
 
         rev = self.rev(node)
         flags = self._flags(rev)
 
         path = b'/'.join([self._storepath, hex(node)])
         rawtext = self._svfs.read(path)
 
         text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
 
         return text
 
     def rawdata(self, nodeorrev):
         return self.revision(raw=True)
 
     def read(self, node):
         validatenode(node)
 
         revision = self.revision(node)
 
         if not revision.startswith(b'\1\n'):
             return revision
 
         start = revision.index(b'\1\n', 2)
         return revision[start + 2:]
 
     def renamed(self, node):
         validatenode(node)
 
         if self.parents(node)[0] != nullid:
             return False
 
         fulltext = self.revision(node)
         m = storageutil.parsemeta(fulltext)[0]
 
         if m and 'copy' in m:
             return m['copy'], bin(m['copyrev'])
 
         return False
 
     def cmp(self, node, text):
         validatenode(node)
 
         t = text
 
         if text.startswith(b'\1\n'):
             t = b'\1\n\1\n' + text
 
         p1, p2 = self.parents(node)
 
         if storageutil.hashrevisionsha1(t, p1, p2) == node:
             return False
 
         if self.iscensored(self.rev(node)):
             return text != b''
 
         if self.renamed(node):
             t2 = self.read(node)
             return t2 != text
 
         return True
 
     def size(self, rev):
         validaterev(rev)
 
         node = self._indexbyrev[rev][b'node']
 
         if self.renamed(node):
             return len(self.read(node))
 
         if self.iscensored(rev):
             return 0
 
         return len(self.revision(node))
 
     def iscensored(self, rev):
         validaterev(rev)
 
         return self._flags(rev) & repository.REVISION_FLAG_CENSORED
 
     def commonancestorsheads(self, a, b):
         validatenode(a)
         validatenode(b)
 
         a = self.rev(a)
         b = self.rev(b)
 
         ancestors = ancestor.commonancestorsheads(self.parentrevs, a, b)
         return pycompat.maplist(self.node, ancestors)
 
     def descendants(self, revs):
         # This is a copy of revlog.descendants()
         first = min(revs)
         if first == nullrev:
             for i in self:
                 yield i
             return
 
         seen = set(revs)
         for i in self.revs(start=first + 1):
             for x in self.parentrevs(i):
                 if x != nullrev and x in seen:
                     seen.add(i)
                     yield i
                     break
 
     # Required by verify.
     def files(self):
         entries = self._svfs.listdir(self._storepath)
 
         # Strip out undo.backup.* files created as part of transaction
         # recording.
         entries = [f for f in entries if not f.startswith('undo.backup.')]
 
         return [b'/'.join((self._storepath, f)) for f in entries]
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         # TODO do a real implementation of this
         return {
             'exclusivefiles': [],
             'sharedfiles': [],
             'revisionscount': len(self),
             'trackedsize': 0,
             'storedsize': None,
         }
 
     def verifyintegrity(self, state):
         state['skipread'] = set()
         for rev in self:
             node = self.node(rev)
             try:
                 self.revision(node)
             except Exception as e:
                 yield simplefilestoreproblem(
                     error='unpacking %s: %s' % (node, e),
                     node=node)
                 state['skipread'].add(node)
 
     def emitrevisions(self, nodes, nodesorder=None, revisiondata=False,
                       assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         # TODO this will probably break on some ordering options.
         nodes = [n for n in nodes if n != nullid]
         if not nodes:
             return
         for delta in storageutil.emitrevisions(
                 self, nodes, nodesorder, simplestorerevisiondelta,
                 revisiondata=revisiondata,
                 assumehaveparentrevisions=assumehaveparentrevisions,
                 deltamode=deltamode):
             yield delta
 
     def add(self, text, meta, transaction, linkrev, p1, p2):
         if meta or text.startswith(b'\1\n'):
             text = storageutil.packmeta(meta, text)
 
         return self.addrevision(text, transaction, linkrev, p1, p2)
 
     def addrevision(self, text, transaction, linkrev, p1, p2, node=None,
                     flags=revlog.REVIDX_DEFAULT_FLAGS, cachedelta=None):
         validatenode(p1)
         validatenode(p2)
 
         if flags:
             node = node or storageutil.hashrevisionsha1(text, p1, p2)
 
         rawtext, validatehash = self._processflags(text, flags, 'write')
 
         node = node or storageutil.hashrevisionsha1(text, p1, p2)
 
         if node in self._indexbynode:
             return node
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self._addrawrevision(node, rawtext, transaction, linkrev, p1, p2,
                                     flags)
 
     def _addrawrevision(self, node, rawtext, transaction, link, p1, p2, flags):
         transaction.addbackup(self._indexpath)
 
         path = b'/'.join([self._storepath, hex(node)])
 
         self._svfs.write(path, rawtext)
 
         self._indexdata.append({
             b'node': node,
             b'p1': p1,
             b'p2': p2,
             b'linkrev': link,
             b'flags': flags,
         })
 
         self._reflectindexupdate()
 
         return node
 
     def _reflectindexupdate(self):
         self._refreshindex()
         self._svfs.write(self._indexpath,
                          ''.join(cborutil.streamencode(self._indexdata)))
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None,
                  maybemissingparents=False):
         if maybemissingparents:
             raise error.Abort(_('simple store does not support missing parents '
                                 'write mode'))
 
         nodes = []
 
         transaction.addbackup(self._indexpath)
 
         for node, p1, p2, linknode, deltabase, delta, flags in deltas:
             linkrev = linkmapper(linknode)
             flags = flags or revlog.REVIDX_DEFAULT_FLAGS
 
             nodes.append(node)
 
             if node in self._indexbynode:
                 continue
 
             # Need to resolve the fulltext from the delta base.
             if deltabase == nullid:
                 text = mdiff.patch(b'', delta)
             else:
                 text = mdiff.patch(self.revision(deltabase), delta)
 
             self._addrawrevision(node, text, transaction, linkrev, p1, p2,
                                  flags)
 
             if addrevisioncb:
                 addrevisioncb(self, node)
         return nodes
 
     def _headrevs(self):
         # Assume all revisions are heads by default.
         revishead = {rev: True for rev in self._indexbyrev}
 
         for rev, entry in self._indexbyrev.items():
             # Unset head flag for all seen parents.
             revishead[self.rev(entry[b'p1'])] = False
             revishead[self.rev(entry[b'p2'])] = False
 
         return [rev for rev, ishead in sorted(revishead.items())
                 if ishead]
 
     def heads(self, start=None, stop=None):
         # This is copied from revlog.py.
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self._headrevs()]
 
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = set([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = {startrev}
         heads = {startrev}
 
         parentrevs = self.parentrevs
         for r in self.revs(start=startrev + 1):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable.add(r)
                     heads.add(r)
                 if p in heads and p not in stoprevs:
                     heads.remove(p)
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         validatenode(node)
 
         # This is a copy of revlog.children().
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def getstrippoint(self, minlink):
         return storageutil.resolvestripinfo(
             minlink, len(self) - 1, self._headrevs(), self.linkrev,
             self.parentrevs)
 
     def strip(self, minlink, transaction):
         if not len(self):
             return
 
         rev, _ignored = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # Purge index data starting at the requested revision.
         self._indexdata[rev:] = []
         self._reflectindexupdate()
 
 def issimplestorefile(f, kind, st):
     if kind != stat.S_IFREG:
         return False
 
     if store.isrevlog(f, kind, st):
         return False
 
     # Ignore transaction undo files.
     if f.startswith('undo.'):
         return False
 
     # Otherwise assume it belongs to the simple store.
     return True
 
 class simplestore(store.encodedstore):
     def datafiles(self):
         for x in super(simplestore, self).datafiles():
             yield x
 
         # Supplement with non-revlog files.
         extrafiles = self._walk('data', True, filefilter=issimplestorefile)
 
         for unencoded, encoded, size in extrafiles:
             try:
                 unencoded = store.decodefilename(unencoded)
             except KeyError:
                 unencoded = None
 
             yield unencoded, encoded, size
 
 def reposetup(ui, repo):
     if not repo.local():
         return
 
     if isinstance(repo, bundlerepo.bundlerepository):
         raise error.Abort(_('cannot use simple store with bundlerepo'))
 
     class simplestorerepo(repo.__class__):
         def file(self, f):
             return filestorage(self.svfs, f)
 
     repo.__class__ = simplestorerepo
 
 def featuresetup(ui, supported):
     supported.add(REQUIREMENT)
 
 def newreporequirements(orig, ui, createopts):
     """Modifies default requirements for new repos to use the simple store."""
     requirements = orig(ui, createopts)
 
     # These requirements are only used to affect creation of the store
     # object. We have our own store. So we can remove them.
     # TODO do this once we feel like taking the test hit.
     #if 'fncache' in requirements:
     #    requirements.remove('fncache')
     #if 'dotencode' in requirements:
     #    requirements.remove('dotencode')
 
     requirements.add(REQUIREMENT)
 
     return requirements
 
 def makestore(orig, requirements, path, vfstype):
     if REQUIREMENT not in requirements:
         return orig(requirements, path, vfstype)
 
     return simplestore(path, vfstype)
 
 def verifierinit(orig, self, *args, **kwargs):
     orig(self, *args, **kwargs)
 
     # We don't care that files in the store don't align with what is
     # advertised. So suppress these warnings.
     self.warnorphanstorefiles = False
 
 def extsetup(ui):
     localrepo.featuresetupfuncs.add(featuresetup)
 
     extensions.wrapfunction(localrepo, 'newreporequirements',
                             newreporequirements)
     extensions.wrapfunction(localrepo, 'makestore', makestore)
     extensions.wrapfunction(verify.verifier, '__init__', verifierinit)

tests/test-check-interfaces.py

@@ -1,233 +1,235
 # Test that certain objects conform to well-defined interfaces.
 
 from __future__ import absolute_import, print_function
 
 from mercurial import encoding
 encoding.environ[b'HGREALINTERFACES'] = b'1'
 
 import os
 import subprocess
 import sys
 
 # Only run if tests are run in a repo
 if subprocess.call(['python', '%s/hghave' % os.environ['TESTDIR'],
                     'test-repo']):
     sys.exit(80)
 
+from mercurial.interfaces import (
+    repository,
+)
 from mercurial.thirdparty.zope import (
     interface as zi,
 )
 from mercurial.thirdparty.zope.interface import (
     verify as ziverify,
 )
 from mercurial import (
     bundlerepo,
     filelog,
     httppeer,
     localrepo,
     manifest,
     pycompat,
-    repository,
     revlog,
     sshpeer,
     statichttprepo,
     ui as uimod,
     unionrepo,
     vfs as vfsmod,
     wireprotoserver,
     wireprototypes,
     wireprotov1peer,
     wireprotov2server,
 )
 
 testdir = os.path.dirname(__file__)
 rootdir = pycompat.fsencode(os.path.normpath(os.path.join(testdir, '..')))
 
 sys.path[0:0] = [testdir]
 import simplestorerepo
 del sys.path[0]
 
 def checkzobject(o, allowextra=False):
     """Verify an object with a zope interface."""
     ifaces = zi.providedBy(o)
     if not ifaces:
         print('%r does not provide any zope interfaces' % o)
         return
 
     # Run zope.interface's built-in verification routine. This verifies that
     # everything that is supposed to be present is present.
     for iface in ifaces:
         ziverify.verifyObject(iface, o)
 
     if allowextra:
         return
 
     # Now verify that the object provides no extra public attributes that
     # aren't declared as part of interfaces.
     allowed = set()
     for iface in ifaces:
         allowed |= set(iface.names(all=True))
 
     public = {a for a in dir(o) if not a.startswith('_')}
 
     for attr in sorted(public - allowed):
         print('public attribute not declared in interfaces: %s.%s' % (
             o.__class__.__name__, attr))
 
 # Facilitates testing localpeer.
 class dummyrepo(object):
     def __init__(self):
         self.ui = uimod.ui()
     def filtered(self, name):
         pass
     def _restrictcapabilities(self, caps):
         pass
 
 class dummyopener(object):
     handlers = []
 
 # Facilitates testing sshpeer without requiring a server.
 class badpeer(httppeer.httppeer):
     def __init__(self):
         super(badpeer, self).__init__(None, None, None, dummyopener(), None,
                                       None)
         self.badattribute = True
 
     def badmethod(self):
         pass
 
 class dummypipe(object):
     def close(self):
         pass
 
 def main():
     ui = uimod.ui()
     # Needed so we can open a local repo with obsstore without a warning.
     ui.setconfig(b'experimental', b'evolution.createmarkers', True)
 
     checkzobject(badpeer())
 
     ziverify.verifyClass(repository.ipeerbase, httppeer.httppeer)
     checkzobject(httppeer.httppeer(None, None, None, dummyopener(), None, None))
 
     ziverify.verifyClass(repository.ipeerv2, httppeer.httpv2peer)
     checkzobject(httppeer.httpv2peer(None, b'', b'', None, None, None))
 
     ziverify.verifyClass(repository.ipeerbase,
                          localrepo.localpeer)
     checkzobject(localrepo.localpeer(dummyrepo()))
 
     ziverify.verifyClass(repository.ipeercommandexecutor,
                          localrepo.localcommandexecutor)
     checkzobject(localrepo.localcommandexecutor(None))
 
     ziverify.verifyClass(repository.ipeercommandexecutor,
                          wireprotov1peer.peerexecutor)
     checkzobject(wireprotov1peer.peerexecutor(None))
 
     ziverify.verifyClass(repository.ipeerbase, sshpeer.sshv1peer)
     checkzobject(sshpeer.sshv1peer(ui, b'ssh://localhost/foo', b'', dummypipe(),
                                    dummypipe(), None, None))
 
     ziverify.verifyClass(repository.ipeerbase, sshpeer.sshv2peer)
     checkzobject(sshpeer.sshv2peer(ui, b'ssh://localhost/foo', b'', dummypipe(),
                                    dummypipe(), None, None))
 
     ziverify.verifyClass(repository.ipeerbase, bundlerepo.bundlepeer)
     checkzobject(bundlerepo.bundlepeer(dummyrepo()))
 
     ziverify.verifyClass(repository.ipeerbase, statichttprepo.statichttppeer)
     checkzobject(statichttprepo.statichttppeer(dummyrepo()))
 
     ziverify.verifyClass(repository.ipeerbase, unionrepo.unionpeer)
     checkzobject(unionrepo.unionpeer(dummyrepo()))
 
     ziverify.verifyClass(repository.ilocalrepositorymain,
                          localrepo.localrepository)
     ziverify.verifyClass(repository.ilocalrepositoryfilestorage,
                          localrepo.revlogfilestorage)
     repo = localrepo.makelocalrepository(ui, rootdir)
     checkzobject(repo)
 
     ziverify.verifyClass(wireprototypes.baseprotocolhandler,
                          wireprotoserver.sshv1protocolhandler)
     ziverify.verifyClass(wireprototypes.baseprotocolhandler,
                          wireprotoserver.sshv2protocolhandler)
     ziverify.verifyClass(wireprototypes.baseprotocolhandler,
                          wireprotoserver.httpv1protocolhandler)
     ziverify.verifyClass(wireprototypes.baseprotocolhandler,
                          wireprotov2server.httpv2protocolhandler)
 
     sshv1 = wireprotoserver.sshv1protocolhandler(None, None, None)
     checkzobject(sshv1)
     sshv2 = wireprotoserver.sshv2protocolhandler(None, None, None)
     checkzobject(sshv2)
 
     httpv1 = wireprotoserver.httpv1protocolhandler(None, None, None)
     checkzobject(httpv1)
     httpv2 = wireprotov2server.httpv2protocolhandler(None, None)
     checkzobject(httpv2)
 
     ziverify.verifyClass(repository.ifilestorage, filelog.filelog)
     ziverify.verifyClass(repository.imanifestdict, manifest.manifestdict)
     ziverify.verifyClass(repository.imanifestrevisionstored,
                          manifest.manifestctx)
     ziverify.verifyClass(repository.imanifestrevisionwritable,
                          manifest.memmanifestctx)
     ziverify.verifyClass(repository.imanifestrevisionstored,
                          manifest.treemanifestctx)
     ziverify.verifyClass(repository.imanifestrevisionwritable,
                          manifest.memtreemanifestctx)
     ziverify.verifyClass(repository.imanifestlog, manifest.manifestlog)
     ziverify.verifyClass(repository.imanifeststorage, manifest.manifestrevlog)
 
     ziverify.verifyClass(repository.irevisiondelta,
                          simplestorerepo.simplestorerevisiondelta)
     ziverify.verifyClass(repository.ifilestorage, simplestorerepo.filestorage)
     ziverify.verifyClass(repository.iverifyproblem,
                          simplestorerepo.simplefilestoreproblem)
 
     vfs = vfsmod.vfs(b'.')
     fl = filelog.filelog(vfs, b'dummy.i')
     checkzobject(fl, allowextra=True)
 
     # Conforms to imanifestlog.
     ml = manifest.manifestlog(vfs, repo, manifest.manifestrevlog(repo.svfs),
                               repo.narrowmatch())
     checkzobject(ml)
     checkzobject(repo.manifestlog)
 
     # Conforms to imanifestrevision.
     mctx = ml[repo[0].manifestnode()]
     checkzobject(mctx)
 
     # Conforms to imanifestrevisionwritable.
     checkzobject(mctx.new())
     checkzobject(mctx.copy())
 
     # Conforms to imanifestdict.
     checkzobject(mctx.read())
 
     mrl = manifest.manifestrevlog(vfs)
     checkzobject(mrl)
 
     ziverify.verifyClass(repository.irevisiondelta,
                          revlog.revlogrevisiondelta)
 
     rd = revlog.revlogrevisiondelta(
         node=b'',
         p1node=b'',
         p2node=b'',
         basenode=b'',
         linknode=b'',
         flags=b'',
         baserevisionsize=None,
         revision=b'',
         delta=None)
     checkzobject(rd)
 
     ziverify.verifyClass(repository.iverifyproblem,
                          revlog.revlogproblem)
     checkzobject(revlog.revlogproblem())
 
 main()

tests/wireprotosimplecache.py

@@ -1,193 +1,195
 # wireprotosimplecache.py - Extension providing in-memory wire protocol cache
 #
 # Copyright 2018 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from mercurial import (
     extensions,
     registrar,
-    repository,
     util,
     wireprotoserver,
     wireprototypes,
     wireprotov2server,
 )
+from mercurial.interfaces import (
+    repository,
+)
 from mercurial.utils import (
     interfaceutil,
     stringutil,
 )
 
 CACHE = None
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem(b'simplecache', b'cacheapi',
            default=False)
 configitem(b'simplecache', b'cacheobjects',
            default=False)
 configitem(b'simplecache', b'redirectsfile',
            default=None)
 
 # API handler that makes cached keys available.
 def handlecacherequest(rctx, req, res, checkperm, urlparts):
     if rctx.repo.ui.configbool(b'simplecache', b'cacheobjects'):
         res.status = b'500 Internal Server Error'
         res.setbodybytes(b'cacheobjects not supported for api server')
         return
 
     if not urlparts:
         res.status = b'200 OK'
         res.headers[b'Content-Type'] = b'text/plain'
         res.setbodybytes(b'simple cache server')
         return
 
     key = b'/'.join(urlparts)
 
     if key not in CACHE:
         res.status = b'404 Not Found'
         res.headers[b'Content-Type'] = b'text/plain'
         res.setbodybytes(b'key not found in cache')
         return
 
     res.status = b'200 OK'
     res.headers[b'Content-Type'] = b'application/mercurial-cbor'
     res.setbodybytes(CACHE[key])
 
 def cachedescriptor(req, repo):
     return {}
 
 wireprotoserver.API_HANDLERS[b'simplecache'] = {
     b'config': (b'simplecache', b'cacheapi'),
     b'handler': handlecacherequest,
     b'apidescriptor': cachedescriptor,
 }
 
 @interfaceutil.implementer(repository.iwireprotocolcommandcacher)
 class memorycacher(object):
     def __init__(self, ui, command, encodefn, redirecttargets, redirecthashes,
                  req):
         self.ui = ui
         self.encodefn = encodefn
         self.redirecttargets = redirecttargets
         self.redirecthashes = redirecthashes
         self.req = req
         self.key = None
         self.cacheobjects = ui.configbool(b'simplecache', b'cacheobjects')
         self.cacheapi = ui.configbool(b'simplecache', b'cacheapi')
         self.buffered = []
 
         ui.log(b'simplecache', b'cacher constructed for %s\n', command)
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         if exctype:
             self.ui.log(b'simplecache', b'cacher exiting due to error\n')
 
     def adjustcachekeystate(self, state):
         # Needed in order to make tests deterministic. Don't copy this
         # pattern for production caches!
         del state[b'repo']
 
     def setcachekey(self, key):
         self.key = key
         return True
 
     def lookup(self):
         if self.key not in CACHE:
             self.ui.log(b'simplecache', b'cache miss for %s\n', self.key)
             return None
 
         entry = CACHE[self.key]
         self.ui.log(b'simplecache', b'cache hit for %s\n', self.key)
 
         redirectable = True
 
         if not self.cacheapi:
             redirectable = False
         elif not self.redirecttargets:
             redirectable = False
         else:
             clienttargets = set(self.redirecttargets)
             ourtargets = set(t[b'name'] for t in loadredirecttargets(self.ui))
 
             # We only ever redirect to a single target (for now). So we don't
             # need to store which target matched.
             if not clienttargets & ourtargets:
                 redirectable = False
 
         if redirectable:
             paths = self.req.dispatchparts[:-3]
             paths.append(b'simplecache')
             paths.append(self.key)
 
             url = b'%s/%s' % (self.req.baseurl, b'/'.join(paths))
 
             #url = b'http://example.com/%s' % self.key
             self.ui.log(b'simplecache', b'sending content redirect for %s to '
                                         b'%s\n', self.key, url)
             response = wireprototypes.alternatelocationresponse(
                 url=url,
                 mediatype=b'application/mercurial-cbor')
 
             return {b'objs': [response]}
 
         if self.cacheobjects:
             return {
                 b'objs': entry,
             }
         else:
             return {
                 b'objs': [wireprototypes.encodedresponse(entry)],
             }
 
     def onobject(self, obj):
         if self.cacheobjects:
             self.buffered.append(obj)
         else:
             self.buffered.extend(self.encodefn(obj))
 
         yield obj
 
     def onfinished(self):
         self.ui.log(b'simplecache', b'storing cache entry for %s\n', self.key)
         if self.cacheobjects:
             CACHE[self.key] = self.buffered
         else:
             CACHE[self.key] = b''.join(self.buffered)
 
         return []
 
 def makeresponsecacher(orig, repo, proto, command, args, objencoderfn,
                        redirecttargets, redirecthashes):
     return memorycacher(repo.ui, command, objencoderfn, redirecttargets,
                         redirecthashes, proto._req)
 
 def loadredirecttargets(ui):
     path = ui.config(b'simplecache', b'redirectsfile')
     if not path:
         return []
 
     with open(path, 'rb') as fh:
         s = fh.read()
 
     return stringutil.evalpythonliteral(s)
 
 def getadvertisedredirecttargets(orig, repo, proto):
     return loadredirecttargets(repo.ui)
 
 def extsetup(ui):
     global CACHE
 
     CACHE = util.lrucachedict(10000)
 
     extensions.wrapfunction(wireprotov2server, b'makeresponsecacher',
                             makeresponsecacher)
     extensions.wrapfunction(wireprotov2server, b'getadvertisedredirecttargets',
                             getadvertisedredirecttargets)