flagutil: create a `mercurial.revlogutils.flagutil` module

The flagprocessings logic is duplicated in 2 extra places, and usually in a less
robust flavor. This is a maintenance nightmare that I would like to see cleaned
up. To do so I am creating a `flagutil` module to move flag processings related
code and make it easily reusable by other code.

mercurial/revlogutils/flagutil.py

@@ -0,0 +1,31 b''
+# flagutils.py - code to deal with revlog flags and their processors
+#
+# Copyright 2016 Remi Chaintron <[e-mail]>
+# Copyright 2016-2019 Pierre-Yves David <[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 .constants import (
+    REVIDX_DEFAULT_FLAGS,
+    REVIDX_ELLIPSIS,
+    REVIDX_EXTSTORED,
+    REVIDX_FLAGS_ORDER,
+    REVIDX_ISCENSORED,
+    REVIDX_KNOWN_FLAGS,
+    REVIDX_RAWTEXT_CHANGING_FLAGS,
+)
+
+# blanked usage of all the name to prevent pyflakes constraints
+# We need these name available in the module for extensions.
+REVIDX_ISCENSORED
+REVIDX_ELLIPSIS
+REVIDX_EXTSTORED
+REVIDX_DEFAULT_FLAGS
+REVIDX_FLAGS_ORDER
+REVIDX_KNOWN_FLAGS
+REVIDX_RAWTEXT_CHANGING_FLAGS
+
+

contrib/import-checker.py

@@ -1,747 +1,748 b''
 #!/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.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)))

mercurial/revlog.py

@@ -1,2702 +1,2704 b''
 # 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,
-    REVIDX_DEFAULT_FLAGS,
-    REVIDX_ELLIPSIS,
-    REVIDX_EXTSTORED,
-    REVIDX_FLAGS_ORDER,
-    REVIDX_ISCENSORED,
-    REVIDX_KNOWN_FLAGS,
-    REVIDX_RAWTEXT_CHANGING_FLAGS,
     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_KNOWN_FLAGS,
+    REVIDX_RAWTEXT_CHANGING_FLAGS,
+)
 from .thirdparty import (
     attr,
 )
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     repository,
     templatefilters,
     util,
 )
 from .revlogutils import (
     deltas as deltautil,
 )
 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_KNOWN_FLAGS
 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
 
 # Store flag processors (cf. 'addflagprocessor()' to register)
 _flagprocessors = {
     REVIDX_ISCENSORED: None,
 }
 
 # 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 addflagprocessor(flag, processor):
     """Register a flag processor on a revision data flag.
 
     Invariant:
     - Flags need to be defined in REVIDX_KNOWN_FLAGS and REVIDX_FLAGS_ORDER,
       and REVIDX_RAWTEXT_CHANGING_FLAGS if they can alter rawtext.
     - Only one flag processor can be registered on a specific flag.
     - flagprocessors must be 3-tuples of functions (read, write, raw) with the
       following signatures:
           - (read)  f(self, rawtext) -> text, bool
           - (write) f(self, text) -> rawtext, bool
           - (raw)   f(self, rawtext) -> bool
       "text" is presented to the user. "rawtext" is stored in revlog data, not
       directly visible to the user.
       The boolean returned by these transforms is used to determine whether
       the returned text can be used for hash integrity checking. For example,
       if "write" returns False, then "text" is used to generate hash. If
       "write" returns True, that basically means "rawtext" returned by "write"
       should be used to generate hash. Usually, "write" and "read" return
       different booleans. And "raw" returns a same boolean as "write".
 
       Note: The 'raw' transform is used for changegroup generation and in some
       debug commands. In this case the transform only indicates whether the
       contents can be used for hash integrity checks.
     """
     _insertflagprocessor(flag, processor, _flagprocessors)
 
 def _insertflagprocessor(flag, processor, flagprocessors):
     if not flag & REVIDX_KNOWN_FLAGS:
         msg = _("cannot register processor on unknown flag '%#x'.") % (flag)
         raise error.ProgrammingError(msg)
     if flag not in REVIDX_FLAGS_ORDER:
         msg = _("flag '%#x' undefined in REVIDX_FLAGS_ORDER.") % (flag)
         raise error.ProgrammingError(msg)
     if flag in flagprocessors:
         msg = _("cannot register multiple processors on flag '%#x'.") % (flag)
         raise error.Abort(msg)
     flagprocessors[flag] = processor
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     if (type & ~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(_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():
             _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.revision(rev, raw=True)
         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 & (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.revision(rev1, raw=True),
                               self.revision(rev2, raw=True))
 
     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):
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         cachedrev = None
         flags = None
         rawtext = None
         if node == nullid:
             return ""
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 # _cache only stores rawtext
                 if raw:
                     return self._revisioncache[2]
                 # duplicated, but good for perf
                 if rev is None:
                     rev = self.rev(node)
                 if flags is None:
                     flags = self.flags(rev)
                 # no extra flags set, no flag processor runs, text = rawtext
                 if flags == REVIDX_DEFAULT_FLAGS:
                     return self._revisioncache[2]
                 # rawtext is reusable. need to run flag processor
                 rawtext = self._revisioncache[2]
 
             cachedrev = self._revisioncache[1]
 
         # look up what we need to read
         if rawtext is None:
             if rev is None:
                 rev = self.rev(node)
 
             chain, stopped = self._deltachain(rev, stoprev=cachedrev)
             if stopped:
                 rawtext = self._revisioncache[2]
 
             # drop cache to save memory
             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 rawtext is None:
                 rawtext = bytes(bins[0])
                 bins = bins[1:]
 
             rawtext = mdiff.patches(rawtext, bins)
             self._revisioncache = (node, rev, rawtext)
 
         if flags is None:
             if rev is None:
                 rev = self.rev(node)
             flags = self.flags(rev)
 
         text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
 
         return text
 
     def rawdata(self, nodeorrev, _df=None, raw=False):
         """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 & ~REVIDX_KNOWN_FLAGS:
             raise error.RevlogError(_("incompatible revision flag '%#x'") %
                                     (flags & ~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.revision(rev, raw=True)
 
 
                 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.revision(rev, raw=True)
 
             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 "revision(rev, raw=True)". "text"
             # mentioned below is "revision(rev, raw=False)".
             #
             # 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 revlog.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.revision(node, raw=True))
 
                 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