diffhelpers: switch to policy importer

# no-check-commit

contrib/check-py3-compat.py

@@ -1,104 +1,103
 #!/usr/bin/env python
 #
 # check-py3-compat - check Python 3 compatibility of Mercurial files
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import ast
 import importlib
 import os
 import sys
 import traceback
 
 # Modules that have both Python and C implementations.
 _dualmodules = (
-    'diffhelpers.py',
     'mpatch.py',
     'parsers.py',
 )
 
 def check_compat_py2(f):
     """Check Python 3 compatibility for a file with Python 2"""
     with open(f, 'rb') as fh:
         content = fh.read()
     root = ast.parse(content)
 
     # Ignore empty files.
     if not root.body:
         return
 
     futures = set()
     haveprint = False
     for node in ast.walk(root):
         if isinstance(node, ast.ImportFrom):
             if node.module == '__future__':
                 futures |= set(n.name for n in node.names)
         elif isinstance(node, ast.Print):
             haveprint = True
 
     if 'absolute_import' not in futures:
         print('%s not using absolute_import' % f)
     if haveprint and 'print_function' not in futures:
         print('%s requires print_function' % f)
 
 def check_compat_py3(f):
     """Check Python 3 compatibility of a file with Python 3."""
     with open(f, 'rb') as fh:
         content = fh.read()
 
     try:
         ast.parse(content)
     except SyntaxError as e:
         print('%s: invalid syntax: %s' % (f, e))
         return
 
     # Try to import the module.
     # For now we only support mercurial.* and hgext.* modules because figuring
     # out module paths for things not in a package can be confusing.
     if f.startswith(('hgext/', 'mercurial/')) and not f.endswith('__init__.py'):
         assert f.endswith('.py')
         name = f.replace('/', '.')[:-3]
         if f.endswith(_dualmodules):
             name = name.replace('.pure.', '.')
         try:
             importlib.import_module(name)
         except Exception as e:
             exc_type, exc_value, tb = sys.exc_info()
             # We walk the stack and ignore frames from our custom importer,
             # import mechanisms, and stdlib modules. This kinda/sorta
             # emulates CPython behavior in import.c while also attempting
             # to pin blame on a Mercurial file.
             for frame in reversed(traceback.extract_tb(tb)):
                 if frame.name == '_call_with_frames_removed':
                     continue
                 if 'importlib' in frame.filename:
                     continue
                 if 'mercurial/__init__.py' in frame.filename:
                     continue
                 if frame.filename.startswith(sys.prefix):
                     continue
                 break
 
             if frame.filename:
                 filename = os.path.basename(frame.filename)
                 print('%s: error importing: <%s> %s (error at %s:%d)' % (
                       f, type(e).__name__, e, filename, frame.lineno))
             else:
                 print('%s: error importing module: <%s> %s (line %d)' % (
                       f, type(e).__name__, e, frame.lineno))
 
 if __name__ == '__main__':
     if sys.version_info[0] == 2:
         fn = check_compat_py2
     else:
         fn = check_compat_py3
 
     for f in sys.argv[1:]:
         fn(f)
 
     sys.exit(0)

contrib/import-checker.py

@@ -1,733 +1,732
 #!/usr/bin/env python
 
 from __future__ import absolute_import, print_function
 
 import ast
 import collections
 import os
 import re
 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
     import BaseHTTPServer
     import zlib
 
 # Whitelist of modules that symbols can be directly imported from.
 allowsymbolimports = (
     '__future__',
     'mercurial.hgweb.common',
     'mercurial.hgweb.request',
     'mercurial.i18n',
     'mercurial.node',
 )
 
 # Modules that have both Python and C implementations.
 _dualmodules = (
-    'diffhelpers.py',
     'mpatch.py',
     'parsers.py',
 )
 
 # 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, trimpure=False):
     """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('mercurial/pure/parsers.py', trimpure=True)
     'mercurial.parsers'
     >>> 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]
     if trimpure:
         return '.'.join(p for p in parts if p != 'pure')
     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 dict (or set), of which key is an absolute
     `dotted_name_of_path()`-ed source file path 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__': True, 'foo.foo1': True,
     ...              'foo.bar.__init__': True, 'foo.bar.bar1': True,
     ...              'baz.__init__': True, 'baz.baz1': True }
     >>> 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)
     """
     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 list_stdlib_modules():
     """List the modules present in the stdlib.
 
     >>> mods = set(list_stdlib_modules())
     >>> 'BaseHTTPServer' in mods
     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
     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 'builtins' # 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):
         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)
     for libpath in sys.path:
         # We want to walk everything in sys.path that starts with
         # something in stdlib_prefixes.
         if 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 ('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: dict 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.
     * Certain modules must be aliased to alternate names to avoid aliasing
       and readability problems. See `requirealias`.
     """
     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:
                     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]
             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 test(fn, lines):
     ...     for s, m, f, l in embedded(fn, "example", lines):
     ...         print("%s %s %s" % (m, f, l))
     ...         print(repr(s))
     >>> lines = [
     ...   'comment',
     ...   '  >>> from __future__ import print_function',
     ...   "  >>> ' multiline",
     ...   "  ... string'",
     ...   '  ',
     ...   'comment',
     ...   '  $ cat > foo.py <<EOF',
     ...   '  > from __future__ import print_function',
     ...   '  > EOF',
     ... ]
     >>> test("example.t", lines)
     example[2] doctest.py 2
     "from __future__ import print_function\\n' multiline\\nstring'\\n"
     example[7] foo.py 7
     'from __future__ import print_function\\n'
     """
     inlinepython = 0
     shpython = 0
     script = []
     prefix = 6
     t = ''
     n = 0
     for l in src:
         n += 1
         if not l.endswith(b'\n'):
             l += b'\n'
         if l.startswith(b'  >>> '): # python inlines
             if shpython:
                 print("%s:%d: Parse Error" % (f, n))
             if not inlinepython:
                 # We've just entered a Python block.
                 inlinepython = n
                 t = 'doctest.py'
             script.append(l[prefix:])
             continue
         if l.startswith(b'  ... '): # python inlines
             script.append(l[prefix:])
             continue
         cat = re.search(r"\$ \s*cat\s*>\s*(\S+\.py)\s*<<\s*EOF", l)
         if cat:
             if inlinepython:
                 yield ''.join(script), ("%s[%d]" %
                        (modname, inlinepython)), t, inlinepython
                 script = []
                 inlinepython = 0
             shpython = n
             t = cat.group(1)
             continue
         if shpython and l.startswith(b'  > '): # sh continuation
             if l == b'  > EOF\n':
                 yield ''.join(script), ("%s[%d]" %
                        (modname, shpython)), t, shpython
                 script = []
                 shpython = 0
             else:
                 script.append(l[4:])
             continue
         if inlinepython and l == b'  \n':
             yield ''.join(script), ("%s[%d]" %
                    (modname, inlinepython)), t, inlinepython
             script = []
             inlinepython = 0
             continue
 
 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) as src:
             yield src.read(), modname, f, 0
             py = True
     if py or f.endswith('.t'):
         with open(f) as src:
             for script, modname, t, line in embedded(f, modname, src):
                 yield script, modname, 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())
     localmods = {}
     used_imports = {}
     any_errors = False
     for source_path in argv[1:]:
         trimpure = source_path.endswith(_dualmodules)
         modname = dotted_name_of_path(source_path, trimpure=trimpure)
         localmods[modname] = source_path
     for localmodname, source_path in sorted(localmods.items()):
         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)))

contrib/wix/dist.wxs

@@ -1,35 +1,35
 <?xml version="1.0" encoding="utf-8"?>
 <Wix xmlns="http://schemas.microsoft.com/wix/2006/wi">
 
   <?include guids.wxi ?>
   <?include defines.wxi ?>
 
   <Fragment>
     <DirectoryRef Id="INSTALLDIR" FileSource="$(var.SourceDir)">
       <Component Id="distOutput" Guid="$(var.dist.guid)" Win64='$(var.IsX64)'>
         <File Name="python27.dll" KeyPath="yes" />
       </Component>
       <Directory Id="libdir" Name="lib" FileSource="$(var.SourceDir)/lib">
         <Component Id="libOutput" Guid="$(var.lib.guid)" Win64='$(var.IsX64)'>
           <File Name="library.zip" KeyPath="yes" />
           <File Name="mercurial.cext.base85.pyd" />
           <File Name="mercurial.cext.bdiff.pyd" />
-          <File Name="mercurial.diffhelpers.pyd" />
+          <File Name="mercurial.cext.diffhelpers.pyd" />
           <File Name="mercurial.mpatch.pyd" />
           <File Name="mercurial.cext.osutil.pyd" />
           <File Name="mercurial.parsers.pyd" />
           <File Name="pyexpat.pyd" />
           <File Name="bz2.pyd" />
           <File Name="select.pyd" />
           <File Name="unicodedata.pyd" />
           <File Name="_ctypes.pyd" />
           <File Name="_elementtree.pyd" />
           <File Name="_hashlib.pyd" />
           <File Name="_socket.pyd" />
           <File Name="_ssl.pyd" />
         </Component>
       </Directory>
     </DirectoryRef>
   </Fragment>
 
 </Wix>

mercurial/__init__.py

@@ -1,401 +1,400
 # __init__.py - Startup and module loading logic for Mercurial.
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import imp
 import os
 import sys
 import zipimport
 
 from . import (
     policy
 )
 
 __all__ = []
 
 modulepolicy = policy.policy
 
 # Modules that have both Python and C implementations. See also the
 # set of .py files under mercurial/pure/.
 _dualmodules = {
-    'mercurial.diffhelpers',
     'mercurial.mpatch',
     'mercurial.parsers',
 }
 
 class hgimporter(object):
     """Object that conforms to import hook interface defined in PEP-302."""
     def find_module(self, name, path=None):
         # We only care about modules that have both C and pure implementations.
         if name in _dualmodules:
             return self
         return None
 
     def load_module(self, name):
         mod = sys.modules.get(name, None)
         if mod:
             return mod
 
         mercurial = sys.modules['mercurial']
 
         # The zip importer behaves sufficiently differently from the default
         # importer to warrant its own code path.
         loader = getattr(mercurial, '__loader__', None)
         if isinstance(loader, zipimport.zipimporter):
             def ziploader(*paths):
                 """Obtain a zipimporter for a directory under the main zip."""
                 path = os.path.join(loader.archive, *paths)
                 zl = sys.path_importer_cache.get(path)
                 if not zl:
                     zl = zipimport.zipimporter(path)
                 return zl
 
             try:
                 if modulepolicy in policy.policynoc:
                     raise ImportError()
 
                 zl = ziploader('mercurial')
                 mod = zl.load_module(name)
                 # Unlike imp, ziploader doesn't expose module metadata that
                 # indicates the type of module. So just assume what we found
                 # is OK (even though it could be a pure Python module).
             except ImportError:
                 if modulepolicy == b'c':
                     raise
                 zl = ziploader('mercurial', 'pure')
                 mod = zl.load_module(name)
 
             sys.modules[name] = mod
             return mod
 
         # Unlike the default importer which searches special locations and
         # sys.path, we only look in the directory where "mercurial" was
         # imported from.
 
         # imp.find_module doesn't support submodules (modules with ".").
         # Instead you have to pass the parent package's __path__ attribute
         # as the path argument.
         stem = name.split('.')[-1]
 
         try:
             if modulepolicy in policy.policynoc:
                 raise ImportError()
 
             modinfo = imp.find_module(stem, mercurial.__path__)
 
             # The Mercurial installer used to copy files from
             # mercurial/pure/*.py to mercurial/*.py. Therefore, it's possible
             # for some installations to have .py files under mercurial/*.
             # Loading Python modules when we expected C versions could result
             # in a) poor performance b) loading a version from a previous
             # Mercurial version, potentially leading to incompatibility. Either
             # scenario is bad. So we verify that modules loaded from
             # mercurial/* are C extensions. If the current policy allows the
             # loading of .py modules, the module will be re-imported from
             # mercurial/pure/* below.
             if modinfo[2][2] != imp.C_EXTENSION:
                 raise ImportError('.py version of %s found where C '
                                   'version should exist' % name)
 
         except ImportError:
             if modulepolicy == b'c':
                 raise
 
             # Could not load the C extension and pure Python is allowed. So
             # try to load them.
             from . import pure
             modinfo = imp.find_module(stem, pure.__path__)
             if not modinfo:
                 raise ImportError('could not find mercurial module %s' %
                                   name)
 
         mod = imp.load_module(name, *modinfo)
         sys.modules[name] = mod
         return mod
 
 # Python 3 uses a custom module loader that transforms source code between
 # source file reading and compilation. This is done by registering a custom
 # finder that changes the spec for Mercurial modules to use a custom loader.
 if sys.version_info[0] >= 3:
     from . import pure
     import importlib
     import io
     import token
     import tokenize
 
     class hgpathentryfinder(importlib.abc.MetaPathFinder):
         """A sys.meta_path finder that uses a custom module loader."""
         def find_spec(self, fullname, path, target=None):
             # Only handle Mercurial-related modules.
             if not fullname.startswith(('mercurial.', 'hgext.', 'hgext3rd.')):
                 return None
             # zstd is already dual-version clean, don't try and mangle it
             if fullname.startswith('mercurial.zstd'):
                 return None
 
             # This assumes Python 3 doesn't support loading C modules.
             if fullname in _dualmodules:
                 stem = fullname.split('.')[-1]
                 fullname = 'mercurial.pure.%s' % stem
                 target = pure
                 assert len(path) == 1
                 path = [os.path.join(path[0], 'pure')]
 
             # Try to find the module using other registered finders.
             spec = None
             for finder in sys.meta_path:
                 if finder == self:
                     continue
 
                 spec = finder.find_spec(fullname, path, target=target)
                 if spec:
                     break
 
             # This is a Mercurial-related module but we couldn't find it
             # using the previously-registered finders. This likely means
             # the module doesn't exist.
             if not spec:
                 return None
 
             if (fullname.startswith('mercurial.pure.')
                 and fullname.replace('.pure.', '.') in _dualmodules):
                 spec.name = spec.name.replace('.pure.', '.')
 
             # TODO need to support loaders from alternate specs, like zip
             # loaders.
             spec.loader = hgloader(spec.name, spec.origin)
             return spec
 
     def replacetokens(tokens, fullname):
         """Transform a stream of tokens from raw to Python 3.
 
         It is called by the custom module loading machinery to rewrite
         source/tokens between source decoding and compilation.
 
         Returns a generator of possibly rewritten tokens.
 
         The input token list may be mutated as part of processing. However,
         its changes do not necessarily match the output token stream.
 
         REMEMBER TO CHANGE ``BYTECODEHEADER`` WHEN CHANGING THIS FUNCTION
         OR CACHED FILES WON'T GET INVALIDATED PROPERLY.
         """
         futureimpline = False
 
         # The following utility functions access the tokens list and i index of
         # the for i, t enumerate(tokens) loop below
         def _isop(j, *o):
             """Assert that tokens[j] is an OP with one of the given values"""
             try:
                 return tokens[j].type == token.OP and tokens[j].string in o
             except IndexError:
                 return False
 
         def _findargnofcall(n):
             """Find arg n of a call expression (start at 0)
 
             Returns index of the first token of that argument, or None if
             there is not that many arguments.
 
             Assumes that token[i + 1] is '('.
 
             """
             nested = 0
             for j in range(i + 2, len(tokens)):
                 if _isop(j, ')', ']', '}'):
                     # end of call, tuple, subscription or dict / set
                     nested -= 1
                     if nested < 0:
                         return None
                 elif n == 0:
                     # this is the starting position of arg
                     return j
                 elif _isop(j, '(', '[', '{'):
                     nested += 1
                 elif _isop(j, ',') and nested == 0:
                     n -= 1
 
             return None
 
         def _ensureunicode(j):
             """Make sure the token at j is a unicode string
 
             This rewrites a string token to include the unicode literal prefix
             so the string transformer won't add the byte prefix.
 
             Ignores tokens that are not strings. Assumes bounds checking has
             already been done.
 
             """
             st = tokens[j]
             if st.type == token.STRING and st.string.startswith(("'", '"')):
                 tokens[j] = st._replace(string='u%s' % st.string)
 
         for i, t in enumerate(tokens):
             # Convert most string literals to byte literals. String literals
             # in Python 2 are bytes. String literals in Python 3 are unicode.
             # Most strings in Mercurial are bytes and unicode strings are rare.
             # Rather than rewrite all string literals to use ``b''`` to indicate
             # byte strings, we apply this token transformer to insert the ``b``
             # prefix nearly everywhere.
             if t.type == token.STRING:
                 s = t.string
 
                 # Preserve docstrings as string literals. This is inconsistent
                 # with regular unprefixed strings. However, the
                 # "from __future__" parsing (which allows a module docstring to
                 # exist before it) doesn't properly handle the docstring if it
                 # is b''' prefixed, leading to a SyntaxError. We leave all
                 # docstrings as unprefixed to avoid this. This means Mercurial
                 # components touching docstrings need to handle unicode,
                 # unfortunately.
                 if s[0:3] in ("'''", '"""'):
                     yield t
                     continue
 
                 # If the first character isn't a quote, it is likely a string
                 # prefixing character (such as 'b', 'u', or 'r'. Ignore.
                 if s[0] not in ("'", '"'):
                     yield t
                     continue
 
                 # String literal. Prefix to make a b'' string.
                 yield t._replace(string='b%s' % t.string)
                 continue
 
             # Insert compatibility imports at "from __future__ import" line.
             # No '\n' should be added to preserve line numbers.
             if (t.type == token.NAME and t.string == 'import' and
                 all(u.type == token.NAME for u in tokens[i - 2:i]) and
                 [u.string for u in tokens[i - 2:i]] == ['from', '__future__']):
                 futureimpline = True
             if t.type == token.NEWLINE and futureimpline:
                 futureimpline = False
                 if fullname == 'mercurial.pycompat':
                     yield t
                     continue
                 r, c = t.start
                 l = (b'; from mercurial.pycompat import '
                      b'delattr, getattr, hasattr, setattr, xrange, '
                      b'open, unicode\n')
                 for u in tokenize.tokenize(io.BytesIO(l).readline):
                     if u.type in (tokenize.ENCODING, token.ENDMARKER):
                         continue
                     yield u._replace(
                         start=(r, c + u.start[1]), end=(r, c + u.end[1]))
                 continue
 
             # This looks like a function call.
             if t.type == token.NAME and _isop(i + 1, '('):
                 fn = t.string
 
                 # *attr() builtins don't accept byte strings to 2nd argument.
                 if (fn in ('getattr', 'setattr', 'hasattr', 'safehasattr') and
                         not _isop(i - 1, '.')):
                     arg1idx = _findargnofcall(1)
                     if arg1idx is not None:
                         _ensureunicode(arg1idx)
 
                 # .encode() and .decode() on str/bytes/unicode don't accept
                 # byte strings on Python 3.
                 elif fn in ('encode', 'decode') and _isop(i - 1, '.'):
                     for argn in range(2):
                         argidx = _findargnofcall(argn)
                         if argidx is not None:
                             _ensureunicode(argidx)
 
                 # It changes iteritems/values to items/values as they are not
                 # present in Python 3 world.
                 elif fn in ('iteritems', 'itervalues'):
                     yield t._replace(string=fn[4:])
                     continue
 
             # Emit unmodified token.
             yield t
 
     # Header to add to bytecode files. This MUST be changed when
     # ``replacetoken`` or any mechanism that changes semantics of module
     # loading is changed. Otherwise cached bytecode may get loaded without
     # the new transformation mechanisms applied.
     BYTECODEHEADER = b'HG\x00\x0a'
 
     class hgloader(importlib.machinery.SourceFileLoader):
         """Custom module loader that transforms source code.
 
         When the source code is converted to a code object, we transform
         certain patterns to be Python 3 compatible. This allows us to write code
         that is natively Python 2 and compatible with Python 3 without
         making the code excessively ugly.
 
         We do this by transforming the token stream between parse and compile.
 
         Implementing transformations invalidates caching assumptions made
         by the built-in importer. The built-in importer stores a header on
         saved bytecode files indicating the Python/bytecode version. If the
         version changes, the cached bytecode is ignored. The Mercurial
         transformations could change at any time. This means we need to check
         that cached bytecode was generated with the current transformation
         code or there could be a mismatch between cached bytecode and what
         would be generated from this class.
 
         We supplement the bytecode caching layer by wrapping ``get_data``
         and ``set_data``. These functions are called when the
         ``SourceFileLoader`` retrieves and saves bytecode cache files,
         respectively. We simply add an additional header on the file. As
         long as the version in this file is changed when semantics change,
         cached bytecode should be invalidated when transformations change.
 
         The added header has the form ``HG<VERSION>``. That is a literal
         ``HG`` with 2 binary bytes indicating the transformation version.
         """
         def get_data(self, path):
             data = super(hgloader, self).get_data(path)
 
             if not path.endswith(tuple(importlib.machinery.BYTECODE_SUFFIXES)):
                 return data
 
             # There should be a header indicating the Mercurial transformation
             # version. If it doesn't exist or doesn't match the current version,
             # we raise an OSError because that is what
             # ``SourceFileLoader.get_code()`` expects when loading bytecode
             # paths to indicate the cached file is "bad."
             if data[0:2] != b'HG':
                 raise OSError('no hg header')
             if data[0:4] != BYTECODEHEADER:
                 raise OSError('hg header version mismatch')
 
             return data[4:]
 
         def set_data(self, path, data, *args, **kwargs):
             if path.endswith(tuple(importlib.machinery.BYTECODE_SUFFIXES)):
                 data = BYTECODEHEADER + data
 
             return super(hgloader, self).set_data(path, data, *args, **kwargs)
 
         def source_to_code(self, data, path):
             """Perform token transformation before compilation."""
             buf = io.BytesIO(data)
             tokens = tokenize.tokenize(buf.readline)
             data = tokenize.untokenize(replacetokens(list(tokens), self.name))
             # Python's built-in importer strips frames from exceptions raised
             # for this code. Unfortunately, that mechanism isn't extensible
             # and our frame will be blamed for the import failure. There
             # are extremely hacky ways to do frame stripping. We haven't
             # implemented them because they are very ugly.
             return super(hgloader, self).source_to_code(data, path)
 
 # We automagically register our custom importer as a side-effect of loading.
 # This is necessary to ensure that any entry points are able to import
 # mercurial.* modules without having to perform this registration themselves.
 if sys.version_info[0] >= 3:
     _importercls = hgpathentryfinder
 else:
     _importercls = hgimporter
 if not any(isinstance(x, _importercls) for x in sys.meta_path):
     # meta_path is used before any implicit finders and before sys.path.
     sys.meta_path.insert(0, _importercls())

mercurial/patch.py

@@ -1,2741 +1,2743
 # patch.py - patch file parsing routines
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import copy
 import email
 import errno
 import hashlib
 import os
 import posixpath
 import re
 import shutil
 import tempfile
 import zlib
 
 from .i18n import _
 from .node import (
     hex,
     short,
 )
 from . import (
     copies,
-    diffhelpers,
     encoding,
     error,
     mail,
     mdiff,
     pathutil,
+    policy,
     pycompat,
     scmutil,
     similar,
     util,
     vfs as vfsmod,
 )
+
+diffhelpers = policy.importmod(r'diffhelpers')
 stringio = util.stringio
 
 gitre = re.compile(br'diff --git a/(.*) b/(.*)')
 tabsplitter = re.compile(br'(\t+|[^\t]+)')
 
 class PatchError(Exception):
     pass
 
 
 # public functions
 
 def split(stream):
     '''return an iterator of individual patches from a stream'''
     def isheader(line, inheader):
         if inheader and line[0] in (' ', '\t'):
             # continuation
             return True
         if line[0] in (' ', '-', '+'):
             # diff line - don't check for header pattern in there
             return False
         l = line.split(': ', 1)
         return len(l) == 2 and ' ' not in l[0]
 
     def chunk(lines):
         return stringio(''.join(lines))
 
     def hgsplit(stream, cur):
         inheader = True
 
         for line in stream:
             if not line.strip():
                 inheader = False
             if not inheader and line.startswith('# HG changeset patch'):
                 yield chunk(cur)
                 cur = []
                 inheader = True
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def mboxsplit(stream, cur):
         for line in stream:
             if line.startswith('From '):
                 for c in split(chunk(cur[1:])):
                     yield c
                 cur = []
 
             cur.append(line)
 
         if cur:
             for c in split(chunk(cur[1:])):
                 yield c
 
     def mimesplit(stream, cur):
         def msgfp(m):
             fp = stringio()
             g = email.Generator.Generator(fp, mangle_from_=False)
             g.flatten(m)
             fp.seek(0)
             return fp
 
         for line in stream:
             cur.append(line)
         c = chunk(cur)
 
         m = email.Parser.Parser().parse(c)
         if not m.is_multipart():
             yield msgfp(m)
         else:
             ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
             for part in m.walk():
                 ct = part.get_content_type()
                 if ct not in ok_types:
                     continue
                 yield msgfp(part)
 
     def headersplit(stream, cur):
         inheader = False
 
         for line in stream:
             if not inheader and isheader(line, inheader):
                 yield chunk(cur)
                 cur = []
                 inheader = True
             if inheader and not isheader(line, inheader):
                 inheader = False
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def remainder(cur):
         yield chunk(cur)
 
     class fiter(object):
         def __init__(self, fp):
             self.fp = fp
 
         def __iter__(self):
             return self
 
         def next(self):
             l = self.fp.readline()
             if not l:
                 raise StopIteration
             return l
 
     inheader = False
     cur = []
 
     mimeheaders = ['content-type']
 
     if not util.safehasattr(stream, 'next'):
         # http responses, for example, have readline but not next
         stream = fiter(stream)
 
     for line in stream:
         cur.append(line)
         if line.startswith('# HG changeset patch'):
             return hgsplit(stream, cur)
         elif line.startswith('From '):
             return mboxsplit(stream, cur)
         elif isheader(line, inheader):
             inheader = True
             if line.split(':', 1)[0].lower() in mimeheaders:
                 # let email parser handle this
                 return mimesplit(stream, cur)
         elif line.startswith('--- ') and inheader:
             # No evil headers seen by diff start, split by hand
             return headersplit(stream, cur)
         # Not enough info, keep reading
 
     # if we are here, we have a very plain patch
     return remainder(cur)
 
 ## Some facility for extensible patch parsing:
 # list of pairs ("header to match", "data key")
 patchheadermap = [('Date', 'date'),
                   ('Branch', 'branch'),
                   ('Node ID', 'nodeid'),
                  ]
 
 def extract(ui, fileobj):
     '''extract patch from data read from fileobj.
 
     patch can be a normal patch or contained in an email message.
 
     return a dictionary. Standard keys are:
       - filename,
       - message,
       - user,
       - date,
       - branch,
       - node,
       - p1,
       - p2.
     Any item can be missing from the dictionary. If filename is missing,
     fileobj did not contain a patch. Caller must unlink filename when done.'''
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(r'^(?:Index:[ \t]|diff[ \t]|RCS file: |'
                         r'retrieving revision [0-9]+(\.[0-9]+)*$|'
                         r'---[ \t].*?^\+\+\+[ \t]|'
                         r'\*\*\*[ \t].*?^---[ \t])', re.MULTILINE|re.DOTALL)
 
     data = {}
     fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
     tmpfp = os.fdopen(fd, pycompat.sysstr('w'))
     try:
         msg = email.Parser.Parser().parse(fileobj)
 
         subject = msg['Subject'] and mail.headdecode(msg['Subject'])
         data['user'] = msg['From'] and mail.headdecode(msg['From'])
         if not subject and not data['user']:
             # Not an email, restore parsed headers if any
             subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n'
 
         # should try to parse msg['Date']
         parents = []
 
         if subject:
             if subject.startswith('[PATCH'):
                 pend = subject.find(']')
                 if pend >= 0:
                     subject = subject[pend + 1:].lstrip()
             subject = re.sub(r'\n[ \t]+', ' ', subject)
             ui.debug('Subject: %s\n' % subject)
         if data['user']:
             ui.debug('From: %s\n' % data['user'])
         diffs_seen = 0
         ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
         message = ''
         for part in msg.walk():
             content_type = part.get_content_type()
             ui.debug('Content-Type: %s\n' % content_type)
             if content_type not in ok_types:
                 continue
             payload = part.get_payload(decode=True)
             m = diffre.search(payload)
             if m:
                 hgpatch = False
                 hgpatchheader = False
                 ignoretext = False
 
                 ui.debug('found patch at byte %d\n' % m.start(0))
                 diffs_seen += 1
                 cfp = stringio()
                 for line in payload[:m.start(0)].splitlines():
                     if line.startswith('# HG changeset patch') and not hgpatch:
                         ui.debug('patch generated by hg export\n')
                         hgpatch = True
                         hgpatchheader = True
                         # drop earlier commit message content
                         cfp.seek(0)
                         cfp.truncate()
                         subject = None
                     elif hgpatchheader:
                         if line.startswith('# User '):
                             data['user'] = line[7:]
                             ui.debug('From: %s\n' % data['user'])
                         elif line.startswith("# Parent "):
                             parents.append(line[9:].lstrip())
                         elif line.startswith("# "):
                             for header, key in patchheadermap:
                                 prefix = '# %s ' % header
                                 if line.startswith(prefix):
                                     data[key] = line[len(prefix):]
                         else:
                             hgpatchheader = False
                     elif line == '---':
                         ignoretext = True
                     if not hgpatchheader and not ignoretext:
                         cfp.write(line)
                         cfp.write('\n')
                 message = cfp.getvalue()
                 if tmpfp:
                     tmpfp.write(payload)
                     if not payload.endswith('\n'):
                         tmpfp.write('\n')
             elif not diffs_seen and message and content_type == 'text/plain':
                 message += '\n' + payload
     except: # re-raises
         tmpfp.close()
         os.unlink(tmpname)
         raise
 
     if subject and not message.startswith(subject):
         message = '%s\n%s' % (subject, message)
     data['message'] = message
     tmpfp.close()
     if parents:
         data['p1'] = parents.pop(0)
         if parents:
             data['p2'] = parents.pop(0)
 
     if diffs_seen:
         data['filename'] = tmpname
     else:
         os.unlink(tmpname)
     return data
 
 class patchmeta(object):
     """Patched file metadata
 
     'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
     or COPY.  'path' is patched file path. 'oldpath' is set to the
     origin file when 'op' is either COPY or RENAME, None otherwise. If
     file mode is changed, 'mode' is a tuple (islink, isexec) where
     'islink' is True if the file is a symlink and 'isexec' is True if
     the file is executable. Otherwise, 'mode' is None.
     """
     def __init__(self, path):
         self.path = path
         self.oldpath = None
         self.mode = None
         self.op = 'MODIFY'
         self.binary = False
 
     def setmode(self, mode):
         islink = mode & 0o20000
         isexec = mode & 0o100
         self.mode = (islink, isexec)
 
     def copy(self):
         other = patchmeta(self.path)
         other.oldpath = self.oldpath
         other.mode = self.mode
         other.op = self.op
         other.binary = self.binary
         return other
 
     def _ispatchinga(self, afile):
         if afile == '/dev/null':
             return self.op == 'ADD'
         return afile == 'a/' + (self.oldpath or self.path)
 
     def _ispatchingb(self, bfile):
         if bfile == '/dev/null':
             return self.op == 'DELETE'
         return bfile == 'b/' + self.path
 
     def ispatching(self, afile, bfile):
         return self._ispatchinga(afile) and self._ispatchingb(bfile)
 
     def __repr__(self):
         return "<patchmeta %s %r>" % (self.op, self.path)
 
 def readgitpatch(lr):
     """extract git-style metadata about patches from <patchname>"""
 
     # Filter patch for git information
     gp = None
     gitpatches = []
     for line in lr:
         line = line.rstrip(' \r\n')
         if line.startswith('diff --git a/'):
             m = gitre.match(line)
             if m:
                 if gp:
                     gitpatches.append(gp)
                 dst = m.group(2)
                 gp = patchmeta(dst)
         elif gp:
             if line.startswith('--- '):
                 gitpatches.append(gp)
                 gp = None
                 continue
             if line.startswith('rename from '):
                 gp.op = 'RENAME'
                 gp.oldpath = line[12:]
             elif line.startswith('rename to '):
                 gp.path = line[10:]
             elif line.startswith('copy from '):
                 gp.op = 'COPY'
                 gp.oldpath = line[10:]
             elif line.startswith('copy to '):
                 gp.path = line[8:]
             elif line.startswith('deleted file'):
                 gp.op = 'DELETE'
             elif line.startswith('new file mode '):
                 gp.op = 'ADD'
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('new mode '):
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('GIT binary patch'):
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     return gitpatches
 
 class linereader(object):
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp):
         self.fp = fp
         self.buf = []
 
     def push(self, line):
         if line is not None:
             self.buf.append(line)
 
     def readline(self):
         if self.buf:
             l = self.buf[0]
             del self.buf[0]
             return l
         return self.fp.readline()
 
     def __iter__(self):
         return iter(self.readline, '')
 
 class abstractbackend(object):
     def __init__(self, ui):
         self.ui = ui
 
     def getfile(self, fname):
         """Return target file data and flags as a (data, (islink,
         isexec)) tuple. Data is None if file is missing/deleted.
         """
         raise NotImplementedError
 
     def setfile(self, fname, data, mode, copysource):
         """Write data to target file fname and set its mode. mode is a
         (islink, isexec) tuple. If data is None, the file content should
         be left unchanged. If the file is modified after being copied,
         copysource is set to the original file name.
         """
         raise NotImplementedError
 
     def unlink(self, fname):
         """Unlink target file."""
         raise NotImplementedError
 
     def writerej(self, fname, failed, total, lines):
         """Write rejected lines for fname. total is the number of hunks
         which failed to apply and total the total number of hunks for this
         files.
         """
         pass
 
     def exists(self, fname):
         raise NotImplementedError
 
 class fsbackend(abstractbackend):
     def __init__(self, ui, basedir):
         super(fsbackend, self).__init__(ui)
         self.opener = vfsmod.vfs(basedir)
 
     def _join(self, f):
         return os.path.join(self.opener.base, f)
 
     def getfile(self, fname):
         if self.opener.islink(fname):
             return (self.opener.readlink(fname), (True, False))
 
         isexec = False
         try:
             isexec = self.opener.lstat(fname).st_mode & 0o100 != 0
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
         try:
             return (self.opener.read(fname), (False, isexec))
         except IOError as e:
             if e.errno != errno.ENOENT:
                 raise
             return None, None
 
     def setfile(self, fname, data, mode, copysource):
         islink, isexec = mode
         if data is None:
             self.opener.setflags(fname, islink, isexec)
             return
         if islink:
             self.opener.symlink(data, fname)
         else:
             self.opener.write(fname, data)
             if isexec:
                 self.opener.setflags(fname, False, True)
 
     def unlink(self, fname):
         self.opener.unlinkpath(fname, ignoremissing=True)
 
     def writerej(self, fname, failed, total, lines):
         fname = fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
             (failed, total, fname))
         fp = self.opener(fname, 'w')
         fp.writelines(lines)
         fp.close()
 
     def exists(self, fname):
         return self.opener.lexists(fname)
 
 class workingbackend(fsbackend):
     def __init__(self, ui, repo, similarity):
         super(workingbackend, self).__init__(ui, repo.root)
         self.repo = repo
         self.similarity = similarity
         self.removed = set()
         self.changed = set()
         self.copied = []
 
     def _checkknown(self, fname):
         if self.repo.dirstate[fname] == '?' and self.exists(fname):
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def setfile(self, fname, data, mode, copysource):
         self._checkknown(fname)
         super(workingbackend, self).setfile(fname, data, mode, copysource)
         if copysource is not None:
             self.copied.append((copysource, fname))
         self.changed.add(fname)
 
     def unlink(self, fname):
         self._checkknown(fname)
         super(workingbackend, self).unlink(fname)
         self.removed.add(fname)
         self.changed.add(fname)
 
     def close(self):
         wctx = self.repo[None]
         changed = set(self.changed)
         for src, dst in self.copied:
             scmutil.dirstatecopy(self.ui, self.repo, wctx, src, dst)
         if self.removed:
             wctx.forget(sorted(self.removed))
             for f in self.removed:
                 if f not in self.repo.dirstate:
                     # File was deleted and no longer belongs to the
                     # dirstate, it was probably marked added then
                     # deleted, and should not be considered by
                     # marktouched().
                     changed.discard(f)
         if changed:
             scmutil.marktouched(self.repo, changed, self.similarity)
         return sorted(self.changed)
 
 class filestore(object):
     def __init__(self, maxsize=None):
         self.opener = None
         self.files = {}
         self.created = 0
         self.maxsize = maxsize
         if self.maxsize is None:
             self.maxsize = 4*(2**20)
         self.size = 0
         self.data = {}
 
     def setfile(self, fname, data, mode, copied=None):
         if self.maxsize < 0 or (len(data) + self.size) <= self.maxsize:
             self.data[fname] = (data, mode, copied)
             self.size += len(data)
         else:
             if self.opener is None:
                 root = tempfile.mkdtemp(prefix='hg-patch-')
                 self.opener = vfsmod.vfs(root)
             # Avoid filename issues with these simple names
             fn = str(self.created)
             self.opener.write(fn, data)
             self.created += 1
             self.files[fname] = (fn, mode, copied)
 
     def getfile(self, fname):
         if fname in self.data:
             return self.data[fname]
         if not self.opener or fname not in self.files:
             return None, None, None
         fn, mode, copied = self.files[fname]
         return self.opener.read(fn), mode, copied
 
     def close(self):
         if self.opener:
             shutil.rmtree(self.opener.base)
 
 class repobackend(abstractbackend):
     def __init__(self, ui, repo, ctx, store):
         super(repobackend, self).__init__(ui)
         self.repo = repo
         self.ctx = ctx
         self.store = store
         self.changed = set()
         self.removed = set()
         self.copied = {}
 
     def _checkknown(self, fname):
         if fname not in self.ctx:
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def getfile(self, fname):
         try:
             fctx = self.ctx[fname]
         except error.LookupError:
             return None, None
         flags = fctx.flags()
         return fctx.data(), ('l' in flags, 'x' in flags)
 
     def setfile(self, fname, data, mode, copysource):
         if copysource:
             self._checkknown(copysource)
         if data is None:
             data = self.ctx[fname].data()
         self.store.setfile(fname, data, mode, copysource)
         self.changed.add(fname)
         if copysource:
             self.copied[fname] = copysource
 
     def unlink(self, fname):
         self._checkknown(fname)
         self.removed.add(fname)
 
     def exists(self, fname):
         return fname in self.ctx
 
     def close(self):
         return self.changed | self.removed
 
 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
 unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
 contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
 eolmodes = ['strict', 'crlf', 'lf', 'auto']
 
 class patchfile(object):
     def __init__(self, ui, gp, backend, store, eolmode='strict'):
         self.fname = gp.path
         self.eolmode = eolmode
         self.eol = None
         self.backend = backend
         self.ui = ui
         self.lines = []
         self.exists = False
         self.missing = True
         self.mode = gp.mode
         self.copysource = gp.oldpath
         self.create = gp.op in ('ADD', 'COPY', 'RENAME')
         self.remove = gp.op == 'DELETE'
         if self.copysource is None:
             data, mode = backend.getfile(self.fname)
         else:
             data, mode = store.getfile(self.copysource)[:2]
         if data is not None:
             self.exists = self.copysource is None or backend.exists(self.fname)
             self.missing = False
             if data:
                 self.lines = mdiff.splitnewlines(data)
             if self.mode is None:
                 self.mode = mode
             if self.lines:
                 # Normalize line endings
                 if self.lines[0].endswith('\r\n'):
                     self.eol = '\r\n'
                 elif self.lines[0].endswith('\n'):
                     self.eol = '\n'
                 if eolmode != 'strict':
                     nlines = []
                     for l in self.lines:
                         if l.endswith('\r\n'):
                             l = l[:-2] + '\n'
                         nlines.append(l)
                     self.lines = nlines
         else:
             if self.create:
                 self.missing = False
             if self.mode is None:
                 self.mode = (False, False)
         if self.missing:
             self.ui.warn(_("unable to find '%s' for patching\n") % self.fname)
             self.ui.warn(_("(use '--prefix' to apply patch relative to the "
                            "current directory)\n"))
 
         self.hash = {}
         self.dirty = 0
         self.offset = 0
         self.skew = 0
         self.rej = []
         self.fileprinted = False
         self.printfile(False)
         self.hunks = 0
 
     def writelines(self, fname, lines, mode):
         if self.eolmode == 'auto':
             eol = self.eol
         elif self.eolmode == 'crlf':
             eol = '\r\n'
         else:
             eol = '\n'
 
         if self.eolmode != 'strict' and eol and eol != '\n':
             rawlines = []
             for l in lines:
                 if l and l[-1] == '\n':
                     l = l[:-1] + eol
                 rawlines.append(l)
             lines = rawlines
 
         self.backend.setfile(fname, ''.join(lines), mode, self.copysource)
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _("patching file %s\n") % self.fname
         if warn:
             self.ui.warn(s)
         else:
             self.ui.note(s)
 
 
     def findlines(self, l, linenum):
         # looks through the hash and finds candidate lines.  The
         # result is a list of line numbers sorted based on distance
         # from linenum
 
         cand = self.hash.get(l, [])
         if len(cand) > 1:
             # resort our list of potentials forward then back.
             cand.sort(key=lambda x: abs(x - linenum))
         return cand
 
     def write_rej(self):
         # our rejects are a little different from patch(1).  This always
         # creates rejects in the same form as the original patch.  A file
         # header is inserted so that you can run the reject through patch again
         # without having to type the filename.
         if not self.rej:
             return
         base = os.path.basename(self.fname)
         lines = ["--- %s\n+++ %s\n" % (base, base)]
         for x in self.rej:
             for l in x.hunk:
                 lines.append(l)
                 if l[-1:] != '\n':
                     lines.append("\n\ No newline at end of file\n")
         self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)
 
     def apply(self, h):
         if not h.complete():
             raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                             (h.number, h.desc, len(h.a), h.lena, len(h.b),
                             h.lenb))
 
         self.hunks += 1
 
         if self.missing:
             self.rej.append(h)
             return -1
 
         if self.exists and self.create:
             if self.copysource:
                 self.ui.warn(_("cannot create %s: destination already "
                                "exists\n") % self.fname)
             else:
                 self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 l = h.new(self.lines)
                 self.lines[:] = l
                 self.offset += len(l)
                 self.dirty = True
             return 0
 
         horig = h
         if (self.eolmode in ('crlf', 'lf')
             or self.eolmode == 'auto' and self.eol):
             # If new eols are going to be normalized, then normalize
             # hunk data before patching. Otherwise, preserve input
             # line-endings.
             h = h.getnormalized()
 
         # fast case first, no offsets, no fuzz
         old, oldstart, new, newstart = h.fuzzit(0, False)
         oldstart += self.offset
         orig_start = oldstart
         # if there's skew we want to emit the "(offset %d lines)" even
         # when the hunk cleanly applies at start + skew, so skip the
         # fast case code
         if (self.skew == 0 and
             diffhelpers.testhunk(old, self.lines, oldstart) == 0):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[oldstart:oldstart + len(old)] = new
                 self.offset += len(new) - len(old)
                 self.dirty = True
             return 0
 
         # ok, we couldn't match the hunk. Lets look for offsets and fuzz it
         self.hash = {}
         for x, s in enumerate(self.lines):
             self.hash.setdefault(s, []).append(x)
 
         for fuzzlen in xrange(self.ui.configint("patch", "fuzz", 2) + 1):
             for toponly in [True, False]:
                 old, oldstart, new, newstart = h.fuzzit(fuzzlen, toponly)
                 oldstart = oldstart + self.offset + self.skew
                 oldstart = min(oldstart, len(self.lines))
                 if old:
                     cand = self.findlines(old[0][1:], oldstart)
                 else:
                     # Only adding lines with no or fuzzed context, just
                     # take the skew in account
                     cand = [oldstart]
 
                 for l in cand:
                     if not old or diffhelpers.testhunk(old, self.lines, l) == 0:
                         self.lines[l : l + len(old)] = new
                         self.offset += len(new) - len(old)
                         self.skew = l - orig_start
                         self.dirty = True
                         offset = l - orig_start - fuzzlen
                         if fuzzlen:
                             msg = _("Hunk #%d succeeded at %d "
                                     "with fuzz %d "
                                     "(offset %d lines).\n")
                             self.printfile(True)
                             self.ui.warn(msg %
                                 (h.number, l + 1, fuzzlen, offset))
                         else:
                             msg = _("Hunk #%d succeeded at %d "
                                     "(offset %d lines).\n")
                             self.ui.note(msg % (h.number, l + 1, offset))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
         self.rej.append(horig)
         return -1
 
     def close(self):
         if self.dirty:
             self.writelines(self.fname, self.lines, self.mode)
         self.write_rej()
         return len(self.rej)
 
 class header(object):
     """patch header
     """
     diffgit_re = re.compile('diff --git a/(.*) b/(.*)$')
     diff_re = re.compile('diff -r .* (.*)$')
     allhunks_re = re.compile('(?:index|deleted file) ')
     pretty_re = re.compile('(?:new file|deleted file) ')
     special_re = re.compile('(?:index|deleted|copy|rename) ')
     newfile_re = re.compile('(?:new file)')
 
     def __init__(self, header):
         self.header = header
         self.hunks = []
 
     def binary(self):
         return any(h.startswith('index ') for h in self.header)
 
     def pretty(self, fp):
         for h in self.header:
             if h.startswith('index '):
                 fp.write(_('this modifies a binary file (all or nothing)\n'))
                 break
             if self.pretty_re.match(h):
                 fp.write(h)
                 if self.binary():
                     fp.write(_('this is a binary file\n'))
                 break
             if h.startswith('---'):
                 fp.write(_('%d hunks, %d lines changed\n') %
                          (len(self.hunks),
                           sum([max(h.added, h.removed) for h in self.hunks])))
                 break
             fp.write(h)
 
     def write(self, fp):
         fp.write(''.join(self.header))
 
     def allhunks(self):
         return any(self.allhunks_re.match(h) for h in self.header)
 
     def files(self):
         match = self.diffgit_re.match(self.header[0])
         if match:
             fromfile, tofile = match.groups()
             if fromfile == tofile:
                 return [fromfile]
             return [fromfile, tofile]
         else:
             return self.diff_re.match(self.header[0]).groups()
 
     def filename(self):
         return self.files()[-1]
 
     def __repr__(self):
         return '<header %s>' % (' '.join(map(repr, self.files())))
 
     def isnewfile(self):
         return any(self.newfile_re.match(h) for h in self.header)
 
     def special(self):
         # Special files are shown only at the header level and not at the hunk
         # level for example a file that has been deleted is a special file.
         # The user cannot change the content of the operation, in the case of
         # the deleted file he has to take the deletion or not take it, he
         # cannot take some of it.
         # Newly added files are special if they are empty, they are not special
         # if they have some content as we want to be able to change it
         nocontent = len(self.header) == 2
         emptynewfile = self.isnewfile() and nocontent
         return emptynewfile or \
                 any(self.special_re.match(h) for h in self.header)
 
 class recordhunk(object):
     """patch hunk
 
     XXX shouldn't we merge this with the other hunk class?
     """
     maxcontext = 3
 
     def __init__(self, header, fromline, toline, proc, before, hunk, after):
         def trimcontext(number, lines):
             delta = len(lines) - self.maxcontext
             if False and delta > 0:
                 return number + delta, lines[:self.maxcontext]
             return number, lines
 
         self.header = header
         self.fromline, self.before = trimcontext(fromline, before)
         self.toline, self.after = trimcontext(toline, after)
         self.proc = proc
         self.hunk = hunk
         self.added, self.removed = self.countchanges(self.hunk)
 
     def __eq__(self, v):
         if not isinstance(v, recordhunk):
             return False
 
         return ((v.hunk == self.hunk) and
                 (v.proc == self.proc) and
                 (self.fromline == v.fromline) and
                 (self.header.files() == v.header.files()))
 
     def __hash__(self):
         return hash((tuple(self.hunk),
             tuple(self.header.files()),
             self.fromline,
             self.proc))
 
     def countchanges(self, hunk):
         """hunk -> (n+,n-)"""
         add = len([h for h in hunk if h[0] == '+'])
         rem = len([h for h in hunk if h[0] == '-'])
         return add, rem
 
     def write(self, fp):
         delta = len(self.before) + len(self.after)
         if self.after and self.after[-1] == '\\ No newline at end of file\n':
             delta -= 1
         fromlen = delta + self.removed
         tolen = delta + self.added
         fp.write('@@ -%d,%d +%d,%d @@%s\n' %
                  (self.fromline, fromlen, self.toline, tolen,
                   self.proc and (' ' + self.proc)))
         fp.write(''.join(self.before + self.hunk + self.after))
 
     pretty = write
 
     def filename(self):
         return self.header.filename()
 
     def __repr__(self):
         return '<hunk %r@%d>' % (self.filename(), self.fromline)
 
 def filterpatch(ui, headers, operation=None):
     """Interactively filter patch chunks into applied-only chunks"""
     if operation is None:
         operation = 'record'
     messages = {
         'multiple': {
             'discard': _("discard change %d/%d to '%s'?"),
             'record': _("record change %d/%d to '%s'?"),
             'revert': _("revert change %d/%d to '%s'?"),
         }[operation],
         'single': {
             'discard': _("discard this change to '%s'?"),
             'record': _("record this change to '%s'?"),
             'revert': _("revert this change to '%s'?"),
         }[operation],
         'help': {
             'discard': _('[Ynesfdaq?]'
                          '$$ &Yes, discard this change'
                          '$$ &No, skip this change'
                          '$$ &Edit this change manually'
                          '$$ &Skip remaining changes to this file'
                          '$$ Discard remaining changes to this &file'
                          '$$ &Done, skip remaining changes and files'
                          '$$ Discard &all changes to all remaining files'
                          '$$ &Quit, discarding no changes'
                          '$$ &? (display help)'),
             'record': _('[Ynesfdaq?]'
                         '$$ &Yes, record this change'
                         '$$ &No, skip this change'
                         '$$ &Edit this change manually'
                         '$$ &Skip remaining changes to this file'
                         '$$ Record remaining changes to this &file'
                         '$$ &Done, skip remaining changes and files'
                         '$$ Record &all changes to all remaining files'
                         '$$ &Quit, recording no changes'
                         '$$ &? (display help)'),
             'revert': _('[Ynesfdaq?]'
                         '$$ &Yes, revert this change'
                         '$$ &No, skip this change'
                         '$$ &Edit this change manually'
                         '$$ &Skip remaining changes to this file'
                         '$$ Revert remaining changes to this &file'
                         '$$ &Done, skip remaining changes and files'
                         '$$ Revert &all changes to all remaining files'
                         '$$ &Quit, reverting no changes'
                         '$$ &? (display help)')
         }[operation]
     }
 
     def prompt(skipfile, skipall, query, chunk):
         """prompt query, and process base inputs
 
         - y/n for the rest of file
         - y/n for the rest
         - ? (help)
         - q (quit)
 
         Return True/False and possibly updated skipfile and skipall.
         """
         newpatches = None
         if skipall is not None:
             return skipall, skipfile, skipall, newpatches
         if skipfile is not None:
             return skipfile, skipfile, skipall, newpatches
         while True:
             resps = messages['help']
             r = ui.promptchoice("%s %s" % (query, resps))
             ui.write("\n")
             if r == 8: # ?
                 for c, t in ui.extractchoices(resps)[1]:
                     ui.write('%s - %s\n' % (c, encoding.lower(t)))
                 continue
             elif r == 0: # yes
                 ret = True
             elif r == 1: # no
                 ret = False
             elif r == 2: # Edit patch
                 if chunk is None:
                     ui.write(_('cannot edit patch for whole file'))
                     ui.write("\n")
                     continue
                 if chunk.header.binary():
                     ui.write(_('cannot edit patch for binary file'))
                     ui.write("\n")
                     continue
                 # Patch comment based on the Git one (based on comment at end of
                 # https://mercurial-scm.org/wiki/RecordExtension)
                 phelp = '---' + _("""
 To remove '-' lines, make them ' ' lines (context).
 To remove '+' lines, delete them.
 Lines starting with # will be removed from the patch.
 
 If the patch applies cleanly, the edited hunk will immediately be
 added to the record list. If it does not apply cleanly, a rejects
 file will be generated: you can use that when you try again. If
 all lines of the hunk are removed, then the edit is aborted and
 the hunk is left unchanged.
 """)
                 (patchfd, patchfn) = tempfile.mkstemp(prefix="hg-editor-",
                         suffix=".diff", text=True)
                 ncpatchfp = None
                 try:
                     # Write the initial patch
                     f = os.fdopen(patchfd, pycompat.sysstr("w"))
                     chunk.header.write(f)
                     chunk.write(f)
                     f.write('\n'.join(['# ' + i for i in phelp.splitlines()]))
                     f.close()
                     # Start the editor and wait for it to complete
                     editor = ui.geteditor()
                     ret = ui.system("%s \"%s\"" % (editor, patchfn),
                                     environ={'HGUSER': ui.username()},
                                     blockedtag='filterpatch')
                     if ret != 0:
                         ui.warn(_("editor exited with exit code %d\n") % ret)
                         continue
                     # Remove comment lines
                     patchfp = open(patchfn)
                     ncpatchfp = stringio()
                     for line in util.iterfile(patchfp):
                         if not line.startswith('#'):
                             ncpatchfp.write(line)
                     patchfp.close()
                     ncpatchfp.seek(0)
                     newpatches = parsepatch(ncpatchfp)
                 finally:
                     os.unlink(patchfn)
                     del ncpatchfp
                 # Signal that the chunk shouldn't be applied as-is, but
                 # provide the new patch to be used instead.
                 ret = False
             elif r == 3: # Skip
                 ret = skipfile = False
             elif r == 4: # file (Record remaining)
                 ret = skipfile = True
             elif r == 5: # done, skip remaining
                 ret = skipall = False
             elif r == 6: # all
                 ret = skipall = True
             elif r == 7: # quit
                 raise error.Abort(_('user quit'))
             return ret, skipfile, skipall, newpatches
 
     seen = set()
     applied = {}        # 'filename' -> [] of chunks
     skipfile, skipall = None, None
     pos, total = 1, sum(len(h.hunks) for h in headers)
     for h in headers:
         pos += len(h.hunks)
         skipfile = None
         fixoffset = 0
         hdr = ''.join(h.header)
         if hdr in seen:
             continue
         seen.add(hdr)
         if skipall is None:
             h.pretty(ui)
         msg = (_('examine changes to %s?') %
                _(' and ').join("'%s'" % f for f in h.files()))
         r, skipfile, skipall, np = prompt(skipfile, skipall, msg, None)
         if not r:
             continue
         applied[h.filename()] = [h]
         if h.allhunks():
             applied[h.filename()] += h.hunks
             continue
         for i, chunk in enumerate(h.hunks):
             if skipfile is None and skipall is None:
                 chunk.pretty(ui)
             if total == 1:
                 msg = messages['single'] % chunk.filename()
             else:
                 idx = pos - len(h.hunks) + i
                 msg = messages['multiple'] % (idx, total, chunk.filename())
             r, skipfile, skipall, newpatches = prompt(skipfile,
                     skipall, msg, chunk)
             if r:
                 if fixoffset:
                     chunk = copy.copy(chunk)
                     chunk.toline += fixoffset
                 applied[chunk.filename()].append(chunk)
             elif newpatches is not None:
                 for newpatch in newpatches:
                     for newhunk in newpatch.hunks:
                         if fixoffset:
                             newhunk.toline += fixoffset
                         applied[newhunk.filename()].append(newhunk)
             else:
                 fixoffset += chunk.removed - chunk.added
     return (sum([h for h in applied.itervalues()
                if h[0].special() or len(h) > 1], []), {})
 class hunk(object):
     def __init__(self, desc, num, lr, context):
         self.number = num
         self.desc = desc
         self.hunk = [desc]
         self.a = []
         self.b = []
         self.starta = self.lena = None
         self.startb = self.lenb = None
         if lr is not None:
             if context:
                 self.read_context_hunk(lr)
             else:
                 self.read_unified_hunk(lr)
 
     def getnormalized(self):
         """Return a copy with line endings normalized to LF."""
 
         def normalize(lines):
             nlines = []
             for line in lines:
                 if line.endswith('\r\n'):
                     line = line[:-2] + '\n'
                 nlines.append(line)
             return nlines
 
         # Dummy object, it is rebuilt manually
         nh = hunk(self.desc, self.number, None, None)
         nh.number = self.number
         nh.desc = self.desc
         nh.hunk = self.hunk
         nh.a = normalize(self.a)
         nh.b = normalize(self.b)
         nh.starta = self.starta
         nh.startb = self.startb
         nh.lena = self.lena
         nh.lenb = self.lenb
         return nh
 
     def read_unified_hunk(self, lr):
         m = unidesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, self.lena, self.startb, self.lenb = m.groups()
         if self.lena is None:
             self.lena = 1
         else:
             self.lena = int(self.lena)
         if self.lenb is None:
             self.lenb = 1
         else:
             self.lenb = int(self.lenb)
         self.starta = int(self.starta)
         self.startb = int(self.startb)
         diffhelpers.addlines(lr, self.hunk, self.lena, self.lenb, self.a,
                              self.b)
         # if we hit eof before finishing out the hunk, the last line will
         # be zero length.  Lets try to fix it up.
         while len(self.hunk[-1]) == 0:
             del self.hunk[-1]
             del self.a[-1]
             del self.b[-1]
             self.lena -= 1
             self.lenb -= 1
         self._fixnewline(lr)
 
     def read_context_hunk(self, lr):
         self.desc = lr.readline()
         m = contextdesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, aend = m.groups()
         self.starta = int(self.starta)
         if aend is None:
             aend = self.starta
         self.lena = int(aend) - self.starta
         if self.starta:
             self.lena += 1
         for x in xrange(self.lena):
             l = lr.readline()
             if l.startswith('---'):
                 # lines addition, old block is empty
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('- ') or l.startswith('! '):
                 u = '-' + s
             elif l.startswith('  '):
                 u = ' ' + s
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith('\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.startb, bend = m.groups()
         self.startb = int(self.startb)
         if bend is None:
             bend = self.startb
         self.lenb = int(bend) - self.startb
         if self.startb:
             self.lenb += 1
         hunki = 1
         for x in xrange(self.lenb):
             l = lr.readline()
             if l.startswith('\ '):
                 # XXX: the only way to hit this is with an invalid line range.
                 # The no-eol marker is not counted in the line range, but I
                 # guess there are diff(1) out there which behave differently.
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki - 1] = s
                 continue
             if not l:
                 # line deletions, new block is empty and we hit EOF
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('+ ') or l.startswith('! '):
                 u = '+' + s
             elif l.startswith('  '):
                 u = ' ' + s
             elif len(self.b) == 0:
                 # line deletions, new block is empty
                 lr.push(l)
                 break
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = ""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith('-'):
                     continue
                 else:
                     self.hunk.insert(hunki - 1, u)
                     break
 
         if not self.a:
             # this happens when lines were only added to the hunk
             for x in self.hunk:
                 if x.startswith('-') or x.startswith(' '):
                     self.a.append(x)
         if not self.b:
             # this happens when lines were only deleted from the hunk
             for x in self.hunk:
                 if x.startswith('+') or x.startswith(' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                              self.startb, self.lenb)
         self.hunk[0] = self.desc
         self._fixnewline(lr)
 
     def _fixnewline(self, lr):
         l = lr.readline()
         if l.startswith('\ '):
             diffhelpers.fix_newline(self.hunk, self.a, self.b)
         else:
             lr.push(l)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def _fuzzit(self, old, new, fuzz, toponly):
         # this removes context lines from the top and bottom of list 'l'.  It
         # checks the hunk to make sure only context lines are removed, and then
         # returns a new shortened list of lines.
         fuzz = min(fuzz, len(old))
         if fuzz:
             top = 0
             bot = 0
             hlen = len(self.hunk)
             for x in xrange(hlen - 1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x + 1][0] == ' ':
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in xrange(hlen - 1):
                     if self.hunk[hlen - bot - 1][0] == ' ':
                         bot += 1
                     else:
                         break
 
             bot = min(fuzz, bot)
             top = min(fuzz, top)
             return old[top:len(old) - bot], new[top:len(new) - bot], top
         return old, new, 0
 
     def fuzzit(self, fuzz, toponly):
         old, new, top = self._fuzzit(self.a, self.b, fuzz, toponly)
         oldstart = self.starta + top
         newstart = self.startb + top
         # zero length hunk ranges already have their start decremented
         if self.lena and oldstart > 0:
             oldstart -= 1
         if self.lenb and newstart > 0:
             newstart -= 1
         return old, oldstart, new, newstart
 
 class binhunk(object):
     'A binary patch file.'
     def __init__(self, lr, fname):
         self.text = None
         self.delta = False
         self.hunk = ['GIT binary patch\n']
         self._fname = fname
         self._read(lr)
 
     def complete(self):
         return self.text is not None
 
     def new(self, lines):
         if self.delta:
             return [applybindelta(self.text, ''.join(lines))]
         return [self.text]
 
     def _read(self, lr):
         def getline(lr, hunk):
             l = lr.readline()
             hunk.append(l)
             return l.rstrip('\r\n')
 
         size = 0
         while True:
             line = getline(lr, self.hunk)
             if not line:
                 raise PatchError(_('could not extract "%s" binary data')
                                  % self._fname)
             if line.startswith('literal '):
                 size = int(line[8:].rstrip())
                 break
             if line.startswith('delta '):
                 size = int(line[6:].rstrip())
                 self.delta = True
                 break
         dec = []
         line = getline(lr, self.hunk)
         while len(line) > 1:
             l = line[0]
             if l <= 'Z' and l >= 'A':
                 l = ord(l) - ord('A') + 1
             else:
                 l = ord(l) - ord('a') + 27
             try:
                 dec.append(util.b85decode(line[1:])[:l])
             except ValueError as e:
                 raise PatchError(_('could not decode "%s" binary patch: %s')
                                  % (self._fname, str(e)))
             line = getline(lr, self.hunk)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('"%s" length is %d bytes, should be %d')
                              % (self._fname, len(text), size))
         self.text = text
 
 def parsefilename(str):
     # --- filename \t|space stuff
     s = str[4:].rstrip('\r\n')
     i = s.find('\t')
     if i < 0:
         i = s.find(' ')
         if i < 0:
             return s
     return s[:i]
 
 def reversehunks(hunks):
     '''reverse the signs in the hunks given as argument
 
     This function operates on hunks coming out of patch.filterpatch, that is
     a list of the form: [header1, hunk1, hunk2, header2...]. Example usage:
 
     >>> rawpatch = """diff --git a/folder1/g b/folder1/g
     ... --- a/folder1/g
     ... +++ b/folder1/g
     ... @@ -1,7 +1,7 @@
     ... +firstline
     ...  c
     ...  1
     ...  2
     ... + 3
     ... -4
     ...  5
     ...  d
     ... +lastline"""
     >>> hunks = parsepatch(rawpatch)
     >>> hunkscomingfromfilterpatch = []
     >>> for h in hunks:
     ...     hunkscomingfromfilterpatch.append(h)
     ...     hunkscomingfromfilterpatch.extend(h.hunks)
 
     >>> reversedhunks = reversehunks(hunkscomingfromfilterpatch)
     >>> from . import util
     >>> fp = util.stringio()
     >>> for c in reversedhunks:
     ...      c.write(fp)
     >>> fp.seek(0)
     >>> reversedpatch = fp.read()
     >>> print reversedpatch
     diff --git a/folder1/g b/folder1/g
     --- a/folder1/g
     +++ b/folder1/g
     @@ -1,4 +1,3 @@
     -firstline
      c
      1
      2
     @@ -1,6 +2,6 @@
      c
      1
      2
     - 3
     +4
      5
      d
     @@ -5,3 +6,2 @@
      5
      d
     -lastline
 
     '''
 
     from . import crecord as crecordmod
     newhunks = []
     for c in hunks:
         if isinstance(c, crecordmod.uihunk):
             # curses hunks encapsulate the record hunk in _hunk
             c = c._hunk
         if isinstance(c, recordhunk):
             for j, line in enumerate(c.hunk):
                 if line.startswith("-"):
                     c.hunk[j] = "+" + c.hunk[j][1:]
                 elif line.startswith("+"):
                     c.hunk[j] = "-" + c.hunk[j][1:]
             c.added, c.removed = c.removed, c.added
         newhunks.append(c)
     return newhunks
 
 def parsepatch(originalchunks):
     """patch -> [] of headers -> [] of hunks """
     class parser(object):
         """patch parsing state machine"""
         def __init__(self):
             self.fromline = 0
             self.toline = 0
             self.proc = ''
             self.header = None
             self.context = []
             self.before = []
             self.hunk = []
             self.headers = []
 
         def addrange(self, limits):
             fromstart, fromend, tostart, toend, proc = limits
             self.fromline = int(fromstart)
             self.toline = int(tostart)
             self.proc = proc
 
         def addcontext(self, context):
             if self.hunk:
                 h = recordhunk(self.header, self.fromline, self.toline,
                         self.proc, self.before, self.hunk, context)
                 self.header.hunks.append(h)
                 self.fromline += len(self.before) + h.removed
                 self.toline += len(self.before) + h.added
                 self.before = []
                 self.hunk = []
             self.context = context
 
         def addhunk(self, hunk):
             if self.context:
                 self.before = self.context
                 self.context = []
             self.hunk = hunk
 
         def newfile(self, hdr):
             self.addcontext([])
             h = header(hdr)
             self.headers.append(h)
             self.header = h
 
         def addother(self, line):
             pass # 'other' lines are ignored
 
         def finished(self):
             self.addcontext([])
             return self.headers
 
         transitions = {
             'file': {'context': addcontext,
                      'file': newfile,
                      'hunk': addhunk,
                      'range': addrange},
             'context': {'file': newfile,
                         'hunk': addhunk,
                         'range': addrange,
                         'other': addother},
             'hunk': {'context': addcontext,
                      'file': newfile,
                      'range': addrange},
             'range': {'context': addcontext,
                       'hunk': addhunk},
             'other': {'other': addother},
             }
 
     p = parser()
     fp = stringio()
     fp.write(''.join(originalchunks))
     fp.seek(0)
 
     state = 'context'
     for newstate, data in scanpatch(fp):
         try:
             p.transitions[state][newstate](p, data)
         except KeyError:
             raise PatchError('unhandled transition: %s -> %s' %
                                    (state, newstate))
         state = newstate
     del fp
     return p.finished()
 
 def pathtransform(path, strip, prefix):
     '''turn a path from a patch into a path suitable for the repository
 
     prefix, if not empty, is expected to be normalized with a / at the end.
 
     Returns (stripped components, path in repository).
 
     >>> pathtransform('a/b/c', 0, '')
     ('', 'a/b/c')
     >>> pathtransform('   a/b/c   ', 0, '')
     ('', '   a/b/c')
     >>> pathtransform('   a/b/c   ', 2, '')
     ('a/b/', 'c')
     >>> pathtransform('a/b/c', 0, 'd/e/')
     ('', 'd/e/a/b/c')
     >>> pathtransform('   a//b/c   ', 2, 'd/e/')
     ('a//b/', 'd/e/c')
     >>> pathtransform('a/b/c', 3, '')
     Traceback (most recent call last):
     PatchError: unable to strip away 1 of 3 dirs from a/b/c
     '''
     pathlen = len(path)
     i = 0
     if strip == 0:
         return '', prefix + path.rstrip()
     count = strip
     while count > 0:
         i = path.find('/', i)
         if i == -1:
             raise PatchError(_("unable to strip away %d of %d dirs from %s") %
                              (count, strip, path))
         i += 1
         # consume '//' in the path
         while i < pathlen - 1 and path[i] == '/':
             i += 1
         count -= 1
     return path[:i].lstrip(), prefix + path[i:].rstrip()
 
 def makepatchmeta(backend, afile_orig, bfile_orig, hunk, strip, prefix):
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     create = nulla and hunk.starta == 0 and hunk.lena == 0
     remove = nullb and hunk.startb == 0 and hunk.lenb == 0
     abase, afile = pathtransform(afile_orig, strip, prefix)
     gooda = not nulla and backend.exists(afile)
     bbase, bfile = pathtransform(bfile_orig, strip, prefix)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = not nullb and backend.exists(bfile)
     missing = not goodb and not gooda and not create
 
     # some diff programs apparently produce patches where the afile is
     # not /dev/null, but afile starts with bfile
     abasedir = afile[:afile.rfind('/') + 1]
     bbasedir = bfile[:bfile.rfind('/') + 1]
     if (missing and abasedir == bbasedir and afile.startswith(bfile)
         and hunk.starta == 0 and hunk.lena == 0):
         create = True
         missing = False
 
     # If afile is "a/b/foo" and bfile is "a/b/foo.orig" we assume the
     # diff is between a file and its backup. In this case, the original
     # file should be patched (see original mpatch code).
     isbackup = (abase == bbase and bfile.startswith(afile))
     fname = None
     if not missing:
         if gooda and goodb:
             if isbackup:
                 fname = afile
             else:
                 fname = bfile
         elif gooda:
             fname = afile
 
     if not fname:
         if not nullb:
             if isbackup:
                 fname = afile
             else:
                 fname = bfile
         elif not nulla:
             fname = afile
         else:
             raise PatchError(_("undefined source and destination files"))
 
     gp = patchmeta(fname)
     if create:
         gp.op = 'ADD'
     elif remove:
         gp.op = 'DELETE'
     return gp
 
 def scanpatch(fp):
     """like patch.iterhunks, but yield different events
 
     - ('file',    [header_lines + fromfile + tofile])
     - ('context', [context_lines])
     - ('hunk',    [hunk_lines])
     - ('range',   (-start,len, +start,len, proc))
     """
     lines_re = re.compile(r'@@ -(\d+),(\d+) \+(\d+),(\d+) @@\s*(.*)')
     lr = linereader(fp)
 
     def scanwhile(first, p):
         """scan lr while predicate holds"""
         lines = [first]
         for line in iter(lr.readline, ''):
             if p(line):
                 lines.append(line)
             else:
                 lr.push(line)
                 break
         return lines
 
     for line in iter(lr.readline, ''):
         if line.startswith('diff --git a/') or line.startswith('diff -r '):
             def notheader(line):
                 s = line.split(None, 1)
                 return not s or s[0] not in ('---', 'diff')
             header = scanwhile(line, notheader)
             fromfile = lr.readline()
             if fromfile.startswith('---'):
                 tofile = lr.readline()
                 header += [fromfile, tofile]
             else:
                 lr.push(fromfile)
             yield 'file', header
         elif line[0] == ' ':
             yield 'context', scanwhile(line, lambda l: l[0] in ' \\')
         elif line[0] in '-+':
             yield 'hunk', scanwhile(line, lambda l: l[0] in '-+\\')
         else:
             m = lines_re.match(line)
             if m:
                 yield 'range', m.groups()
             else:
                 yield 'other', line
 
 def scangitpatch(lr, firstline):
     """
     Git patches can emit:
     - rename a to b
     - change b
     - copy a to c
     - change c
 
     We cannot apply this sequence as-is, the renamed 'a' could not be
     found for it would have been renamed already. And we cannot copy
     from 'b' instead because 'b' would have been changed already. So
     we scan the git patch for copy and rename commands so we can
     perform the copies ahead of time.
     """
     pos = 0
     try:
         pos = lr.fp.tell()
         fp = lr.fp
     except IOError:
         fp = stringio(lr.fp.read())
     gitlr = linereader(fp)
     gitlr.push(firstline)
     gitpatches = readgitpatch(gitlr)
     fp.seek(pos)
     return gitpatches
 
 def iterhunks(fp):
     """Read a patch and yield the following events:
     - ("file", afile, bfile, firsthunk): select a new target file.
     - ("hunk", hunk): a new hunk is ready to be applied, follows a
     "file" event.
     - ("git", gitchanges): current diff is in git format, gitchanges
     maps filenames to gitpatch records. Unique event.
     """
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
     emitfile = newfile = False
     gitpatches = None
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
 
     for x in iter(lr.readline, ''):
         if state == BFILE and (
             (not context and x[0] == '@')
             or (context is not False and x.startswith('***************'))
             or x.startswith('GIT binary patch')):
             gp = None
             if (gitpatches and
                 gitpatches[-1].ispatching(afile, bfile)):
                 gp = gitpatches.pop()
             if x.startswith('GIT binary patch'):
                 h = binhunk(lr, gp.path)
             else:
                 if context is None and x.startswith('***************'):
                     context = True
                 h = hunk(x, hunknum + 1, lr, context)
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', (afile, bfile, h, gp and gp.copy() or None)
             yield 'hunk', h
         elif x.startswith('diff --git a/'):
             m = gitre.match(x.rstrip(' \r\n'))
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = scangitpatch(lr, x)
                 yield 'git', [g.copy() for g in gitpatches
                               if g.op in ('COPY', 'RENAME')]
                 gitpatches.reverse()
             afile = 'a/' + m.group(1)
             bfile = 'b/' + m.group(2)
             while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
                 yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
             if not gitpatches:
                 raise PatchError(_('failed to synchronize metadata for "%s"')
                                  % afile[2:])
             gp = gitpatches[-1]
             newfile = True
         elif x.startswith('---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith('+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith('***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith('---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith("***************"):
                 lr.push(l2)
                 continue
             newfile = True
             context = True
             afile = parsefilename(x)
             bfile = parsefilename(l2)
 
         if newfile:
             newfile = False
             emitfile = True
             state = BFILE
             hunknum = 0
 
     while gitpatches:
         gp = gitpatches.pop()
         yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
 
 def applybindelta(binchunk, data):
     """Apply a binary delta hunk
     The algorithm used is the algorithm from git's patch-delta.c
     """
     def deltahead(binchunk):
         i = 0
         for c in binchunk:
             i += 1
             if not (ord(c) & 0x80):
                 return i
         return i
     out = ""
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     i = 0
     while i < len(binchunk):
         cmd = ord(binchunk[i])
         i += 1
         if (cmd & 0x80):
             offset = 0
             size = 0
             if (cmd & 0x01):
                 offset = ord(binchunk[i])
                 i += 1
             if (cmd & 0x02):
                 offset |= ord(binchunk[i]) << 8
                 i += 1
             if (cmd & 0x04):
                 offset |= ord(binchunk[i]) << 16
                 i += 1
             if (cmd & 0x08):
                 offset |= ord(binchunk[i]) << 24
                 i += 1
             if (cmd & 0x10):
                 size = ord(binchunk[i])
                 i += 1
             if (cmd & 0x20):
                 size |= ord(binchunk[i]) << 8
                 i += 1
             if (cmd & 0x40):
                 size |= ord(binchunk[i]) << 16
                 i += 1
             if size == 0:
                 size = 0x10000
             offset_end = offset + size
             out += data[offset:offset_end]
         elif cmd != 0:
             offset_end = i + cmd
             out += binchunk[i:offset_end]
             i += cmd
         else:
             raise PatchError(_('unexpected delta opcode 0'))
     return out
 
 def applydiff(ui, fp, backend, store, strip=1, prefix='', eolmode='strict'):
     """Reads a patch from fp and tries to apply it.
 
     Returns 0 for a clean patch, -1 if any rejects were found and 1 if
     there was any fuzz.
 
     If 'eolmode' is 'strict', the patch content and patched file are
     read in binary mode. Otherwise, line endings are ignored when
     patching then normalized according to 'eolmode'.
     """
     return _applydiff(ui, fp, patchfile, backend, store, strip=strip,
                       prefix=prefix, eolmode=eolmode)
 
 def _applydiff(ui, fp, patcher, backend, store, strip=1, prefix='',
                eolmode='strict'):
 
     if prefix:
         prefix = pathutil.canonpath(backend.repo.root, backend.repo.getcwd(),
                                     prefix)
         if prefix != '':
             prefix += '/'
     def pstrip(p):
         return pathtransform(p, strip - 1, prefix)[1]
 
     rejects = 0
     err = 0
     current_file = None
 
     for state, values in iterhunks(fp):
         if state == 'hunk':
             if not current_file:
                 continue
             ret = current_file.apply(values)
             if ret > 0:
                 err = 1
         elif state == 'file':
             if current_file:
                 rejects += current_file.close()
                 current_file = None
             afile, bfile, first_hunk, gp = values
             if gp:
                 gp.path = pstrip(gp.path)
                 if gp.oldpath:
                     gp.oldpath = pstrip(gp.oldpath)
             else:
                 gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                    prefix)
             if gp.op == 'RENAME':
                 backend.unlink(gp.oldpath)
             if not first_hunk:
                 if gp.op == 'DELETE':
                     backend.unlink(gp.path)
                     continue
                 data, mode = None, None
                 if gp.op in ('RENAME', 'COPY'):
                     data, mode = store.getfile(gp.oldpath)[:2]
                     if data is None:
                         # This means that the old path does not exist
                         raise PatchError(_("source file '%s' does not exist")
                                            % gp.oldpath)
                 if gp.mode:
                     mode = gp.mode
                     if gp.op == 'ADD':
                         # Added files without content have no hunk and
                         # must be created
                         data = ''
                 if data or mode:
                     if (gp.op in ('ADD', 'RENAME', 'COPY')
                         and backend.exists(gp.path)):
                         raise PatchError(_("cannot create %s: destination "
                                            "already exists") % gp.path)
                     backend.setfile(gp.path, data, mode, gp.oldpath)
                 continue
             try:
                 current_file = patcher(ui, gp, backend, store,
                                        eolmode=eolmode)
             except PatchError as inst:
                 ui.warn(str(inst) + '\n')
                 current_file = None
                 rejects += 1
                 continue
         elif state == 'git':
             for gp in values:
                 path = pstrip(gp.oldpath)
                 data, mode = backend.getfile(path)
                 if data is None:
                     # The error ignored here will trigger a getfile()
                     # error in a place more appropriate for error
                     # handling, and will not interrupt the patching
                     # process.
                     pass
                 else:
                     store.setfile(path, data, mode)
         else:
             raise error.Abort(_('unsupported parser state: %s') % state)
 
     if current_file:
         rejects += current_file.close()
 
     if rejects:
         return -1
     return err
 
 def _externalpatch(ui, repo, patcher, patchname, strip, files,
                    similarity):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     args = []
     cwd = repo.root
     if cwd:
         args.append('-d %s' % util.shellquote(cwd))
     fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                        util.shellquote(patchname)))
     try:
         for line in util.iterfile(fp):
             line = line.rstrip()
             ui.note(line + '\n')
             if line.startswith('patching file '):
                 pf = util.parsepatchoutput(line)
                 printed_file = False
                 files.add(pf)
             elif line.find('with fuzz') >= 0:
                 fuzz = True
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
             elif line.find('saving rejects to file') >= 0:
                 ui.warn(line + '\n')
             elif line.find('FAILED') >= 0:
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
     finally:
         if files:
             scmutil.marktouched(repo, files, similarity)
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          util.explainexit(code)[0])
     return fuzz
 
 def patchbackend(ui, backend, patchobj, strip, prefix, files=None,
                  eolmode='strict'):
     if files is None:
         files = set()
     if eolmode is None:
         eolmode = ui.config('patch', 'eol', 'strict')
     if eolmode.lower() not in eolmodes:
         raise error.Abort(_('unsupported line endings type: %s') % eolmode)
     eolmode = eolmode.lower()
 
     store = filestore()
     try:
         fp = open(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     try:
         ret = applydiff(ui, fp, backend, store, strip=strip, prefix=prefix,
                         eolmode=eolmode)
     finally:
         if fp != patchobj:
             fp.close()
         files.update(backend.close())
         store.close()
     if ret < 0:
         raise PatchError(_('patch failed to apply'))
     return ret > 0
 
 def internalpatch(ui, repo, patchobj, strip, prefix='', files=None,
                   eolmode='strict', similarity=0):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
     backend = workingbackend(ui, repo, similarity)
     return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)
 
 def patchrepo(ui, repo, ctx, store, patchobj, strip, prefix, files=None,
               eolmode='strict'):
     backend = repobackend(ui, repo, ctx, store)
     return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)
 
 def patch(ui, repo, patchname, strip=1, prefix='', files=None, eolmode='strict',
           similarity=0):
     """Apply <patchname> to the working directory.
 
     'eolmode' specifies how end of lines should be handled. It can be:
     - 'strict': inputs are read in binary mode, EOLs are preserved
     - 'crlf': EOLs are ignored when patching and reset to CRLF
     - 'lf': EOLs are ignored when patching and reset to LF
     - None: get it from user settings, default to 'strict'
     'eolmode' is ignored when using an external patcher program.
 
     Returns whether patch was applied with fuzz factor.
     """
     patcher = ui.config('ui', 'patch')
     if files is None:
         files = set()
     if patcher:
         return _externalpatch(ui, repo, patcher, patchname, strip,
                               files, similarity)
     return internalpatch(ui, repo, patchname, strip, prefix, files, eolmode,
                          similarity)
 
 def changedfiles(ui, repo, patchpath, strip=1):
     backend = fsbackend(ui, repo.root)
     with open(patchpath, 'rb') as fp:
         changed = set()
         for state, values in iterhunks(fp):
             if state == 'file':
                 afile, bfile, first_hunk, gp = values
                 if gp:
                     gp.path = pathtransform(gp.path, strip - 1, '')[1]
                     if gp.oldpath:
                         gp.oldpath = pathtransform(gp.oldpath, strip - 1, '')[1]
                 else:
                     gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                        '')
                 changed.add(gp.path)
                 if gp.op == 'RENAME':
                     changed.add(gp.oldpath)
             elif state not in ('hunk', 'git'):
                 raise error.Abort(_('unsupported parser state: %s') % state)
         return changed
 
 class GitDiffRequired(Exception):
     pass
 
 def diffallopts(ui, opts=None, untrusted=False, section='diff'):
     '''return diffopts with all features supported and parsed'''
     return difffeatureopts(ui, opts=opts, untrusted=untrusted, section=section,
                            git=True, whitespace=True, formatchanging=True)
 
 diffopts = diffallopts
 
 def difffeatureopts(ui, opts=None, untrusted=False, section='diff', git=False,
                     whitespace=False, formatchanging=False):
     '''return diffopts with only opted-in features parsed
 
     Features:
     - git: git-style diffs
     - whitespace: whitespace options like ignoreblanklines and ignorews
     - formatchanging: options that will likely break or cause correctness issues
       with most diff parsers
     '''
     def get(key, name=None, getter=ui.configbool, forceplain=None):
         if opts:
             v = opts.get(key)
             # diffopts flags are either None-default (which is passed
             # through unchanged, so we can identify unset values), or
             # some other falsey default (eg --unified, which defaults
             # to an empty string). We only want to override the config
             # entries from hgrc with command line values if they
             # appear to have been set, which is any truthy value,
             # True, or False.
             if v or isinstance(v, bool):
                 return v
         if forceplain is not None and ui.plain():
             return forceplain
         return getter(section, name or key, None, untrusted=untrusted)
 
     # core options, expected to be understood by every diff parser
     buildopts = {
         'nodates': get('nodates'),
         'showfunc': get('show_function', 'showfunc'),
         'context': get('unified', getter=ui.config),
     }
 
     if git:
         buildopts['git'] = get('git')
 
         # since this is in the experimental section, we need to call
         # ui.configbool directory
         buildopts['showsimilarity'] = ui.configbool('experimental',
                                                     'extendedheader.similarity')
 
         # need to inspect the ui object instead of using get() since we want to
         # test for an int
         hconf = ui.config('experimental', 'extendedheader.index')
         if hconf is not None:
             hlen = None
             try:
                 # the hash config could be an integer (for length of hash) or a
                 # word (e.g. short, full, none)
                 hlen = int(hconf)
                 if hlen < 0 or hlen > 40:
                     msg = _("invalid length for extendedheader.index: '%d'\n")
                     ui.warn(msg % hlen)
             except ValueError:
                 # default value
                 if hconf == 'short' or hconf == '':
                     hlen = 12
                 elif hconf == 'full':
                     hlen = 40
                 elif hconf != 'none':
                     msg = _("invalid value for extendedheader.index: '%s'\n")
                     ui.warn(msg % hconf)
             finally:
                 buildopts['index'] = hlen
 
     if whitespace:
         buildopts['ignorews'] = get('ignore_all_space', 'ignorews')
         buildopts['ignorewsamount'] = get('ignore_space_change',
                                           'ignorewsamount')
         buildopts['ignoreblanklines'] = get('ignore_blank_lines',
                                             'ignoreblanklines')
     if formatchanging:
         buildopts['text'] = opts and opts.get('text')
         binary = None if opts is None else opts.get('binary')
         buildopts['nobinary'] = (not binary if binary is not None
                                  else get('nobinary', forceplain=False))
         buildopts['noprefix'] = get('noprefix', forceplain=False)
 
     return mdiff.diffopts(**pycompat.strkwargs(buildopts))
 
 def diff(repo, node1=None, node2=None, match=None, changes=None,
          opts=None, losedatafn=None, prefix='', relroot='', copy=None):
     '''yields diff of changes to files between two nodes, or node and
     working directory.
 
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.
 
     losedatafn(**kwarg) is a callable run when opts.upgrade=True and
     every time some change cannot be represented with the current
     patch format. Return False to upgrade to git patch format, True to
     accept the loss or raise an exception to abort the diff. It is
     called with the name of current file being diffed as 'fn'. If set
     to None, patches will always be upgraded to git format when
     necessary.
 
     prefix is a filename prefix that is prepended to all filenames on
     display (used for subrepos).
 
     relroot, if not empty, must be normalized with a trailing /. Any match
     patterns that fall outside it will be ignored.
 
     copy, if not empty, should contain mappings {dst@y: src@x} of copy
     information.'''
     for header, hunks in diffhunks(repo, node1=node1, node2=node2, match=match,
                                    changes=changes, opts=opts,
                                    losedatafn=losedatafn, prefix=prefix,
                                    relroot=relroot, copy=copy):
         text = ''.join(sum((list(hlines) for hrange, hlines in hunks), []))
         if header and (text or len(header) > 1):
             yield '\n'.join(header) + '\n'
         if text:
             yield text
 
 def diffhunks(repo, node1=None, node2=None, match=None, changes=None,
               opts=None, losedatafn=None, prefix='', relroot='', copy=None):
     """Yield diff of changes to files in the form of (`header`, `hunks`) tuples
     where `header` is a list of diff headers and `hunks` is an iterable of
     (`hunkrange`, `hunklines`) tuples.
 
     See diff() for the meaning of parameters.
     """
 
     if opts is None:
         opts = mdiff.defaultopts
 
     if not node1 and not node2:
         node1 = repo.dirstate.p1()
 
     def lrugetfilectx():
         cache = {}
         order = collections.deque()
         def getfilectx(f, ctx):
             fctx = ctx.filectx(f, filelog=cache.get(f))
             if f not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[f] = fctx.filelog()
             else:
                 order.remove(f)
             order.append(f)
             return fctx
         return getfilectx
     getfilectx = lrugetfilectx()
 
     ctx1 = repo[node1]
     ctx2 = repo[node2]
 
     relfiltered = False
     if relroot != '' and match.always():
         # as a special case, create a new matcher with just the relroot
         pats = [relroot]
         match = scmutil.match(ctx2, pats, default='path')
         relfiltered = True
 
     if not changes:
         changes = repo.status(ctx1, ctx2, match=match)
     modified, added, removed = changes[:3]
 
     if not modified and not added and not removed:
         return []
 
     if repo.ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     revs = [hexfunc(node) for node in [ctx1.node(), ctx2.node()] if node]
 
     if copy is None:
         copy = {}
         if opts.git or opts.upgrade:
             copy = copies.pathcopies(ctx1, ctx2, match=match)
 
     if relroot is not None:
         if not relfiltered:
             # XXX this would ideally be done in the matcher, but that is
             # generally meant to 'or' patterns, not 'and' them. In this case we
             # need to 'and' all the patterns from the matcher with relroot.
             def filterrel(l):
                 return [f for f in l if f.startswith(relroot)]
             modified = filterrel(modified)
             added = filterrel(added)
             removed = filterrel(removed)
             relfiltered = True
         # filter out copies where either side isn't inside the relative root
         copy = dict(((dst, src) for (dst, src) in copy.iteritems()
                      if dst.startswith(relroot)
                      and src.startswith(relroot)))
 
     modifiedset = set(modified)
     addedset = set(added)
     removedset = set(removed)
     for f in modified:
         if f not in ctx1:
             # Fix up added, since merged-in additions appear as
             # modifications during merges
             modifiedset.remove(f)
             addedset.add(f)
     for f in removed:
         if f not in ctx1:
             # Merged-in additions that are then removed are reported as removed.
             # They are not in ctx1, so We don't want to show them in the diff.
             removedset.remove(f)
     modified = sorted(modifiedset)
     added = sorted(addedset)
     removed = sorted(removedset)
     for dst, src in copy.items():
         if src not in ctx1:
             # Files merged in during a merge and then copied/renamed are
             # reported as copies. We want to show them in the diff as additions.
             del copy[dst]
 
     def difffn(opts, losedata):
         return trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
                        copy, getfilectx, opts, losedata, prefix, relroot)
     if opts.upgrade and not opts.git:
         try:
             def losedata(fn):
                 if not losedatafn or not losedatafn(fn=fn):
                     raise GitDiffRequired
             # Buffer the whole output until we are sure it can be generated
             return list(difffn(opts.copy(git=False), losedata))
         except GitDiffRequired:
             return difffn(opts.copy(git=True), None)
     else:
         return difffn(opts, None)
 
 def difflabel(func, *args, **kw):
     '''yields 2-tuples of (output, label) based on the output of func()'''
     headprefixes = [('diff', 'diff.diffline'),
                     ('copy', 'diff.extended'),
                     ('rename', 'diff.extended'),
                     ('old', 'diff.extended'),
                     ('new', 'diff.extended'),
                     ('deleted', 'diff.extended'),
                     ('index', 'diff.extended'),
                     ('similarity', 'diff.extended'),
                     ('---', 'diff.file_a'),
                     ('+++', 'diff.file_b')]
     textprefixes = [('@', 'diff.hunk'),
                     ('-', 'diff.deleted'),
                     ('+', 'diff.inserted')]
     head = False
     for chunk in func(*args, **kw):
         lines = chunk.split('\n')
         for i, line in enumerate(lines):
             if i != 0:
                 yield ('\n', '')
             if head:
                 if line.startswith('@'):
                     head = False
             else:
                 if line and line[0] not in ' +-@\\':
                     head = True
             stripline = line
             diffline = False
             if not head and line and line[0] in '+-':
                 # highlight tabs and trailing whitespace, but only in
                 # changed lines
                 stripline = line.rstrip()
                 diffline = True
 
             prefixes = textprefixes
             if head:
                 prefixes = headprefixes
             for prefix, label in prefixes:
                 if stripline.startswith(prefix):
                     if diffline:
                         for token in tabsplitter.findall(stripline):
                             if '\t' == token[0]:
                                 yield (token, 'diff.tab')
                             else:
                                 yield (token, label)
                     else:
                         yield (stripline, label)
                     break
             else:
                 yield (line, '')
             if line != stripline:
                 yield (line[len(stripline):], 'diff.trailingwhitespace')
 
 def diffui(*args, **kw):
     '''like diff(), but yields 2-tuples of (output, label) for ui.write()'''
     return difflabel(diff, *args, **kw)
 
 def _filepairs(modified, added, removed, copy, opts):
     '''generates tuples (f1, f2, copyop), where f1 is the name of the file
     before and f2 is the the name after. For added files, f1 will be None,
     and for removed files, f2 will be None. copyop may be set to None, 'copy'
     or 'rename' (the latter two only if opts.git is set).'''
     gone = set()
 
     copyto = dict([(v, k) for k, v in copy.items()])
 
     addedset, removedset = set(added), set(removed)
 
     for f in sorted(modified + added + removed):
         copyop = None
         f1, f2 = f, f
         if f in addedset:
             f1 = None
             if f in copy:
                 if opts.git:
                     f1 = copy[f]
                     if f1 in removedset and f1 not in gone:
                         copyop = 'rename'
                         gone.add(f1)
                     else:
                         copyop = 'copy'
         elif f in removedset:
             f2 = None
             if opts.git:
                 # have we already reported a copy above?
                 if (f in copyto and copyto[f] in addedset
                     and copy[copyto[f]] == f):
                     continue
         yield f1, f2, copyop
 
 def trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
             copy, getfilectx, opts, losedatafn, prefix, relroot):
     '''given input data, generate a diff and yield it in blocks
 
     If generating a diff would lose data like flags or binary data and
     losedatafn is not None, it will be called.
 
     relroot is removed and prefix is added to every path in the diff output.
 
     If relroot is not empty, this function expects every path in modified,
     added, removed and copy to start with it.'''
 
     def gitindex(text):
         if not text:
             text = ""
         l = len(text)
         s = hashlib.sha1('blob %d\0' % l)
         s.update(text)
         return s.hexdigest()
 
     if opts.noprefix:
         aprefix = bprefix = ''
     else:
         aprefix = 'a/'
         bprefix = 'b/'
 
     def diffline(f, revs):
         revinfo = ' '.join(["-r %s" % rev for rev in revs])
         return 'diff %s %s' % (revinfo, f)
 
     def isempty(fctx):
         return fctx is None or fctx.size() == 0
 
     date1 = util.datestr(ctx1.date())
     date2 = util.datestr(ctx2.date())
 
     gitmode = {'l': '120000', 'x': '100755', '': '100644'}
 
     if relroot != '' and (repo.ui.configbool('devel', 'all')
                           or repo.ui.configbool('devel', 'check-relroot')):
         for f in modified + added + removed + copy.keys() + copy.values():
             if f is not None and not f.startswith(relroot):
                 raise AssertionError(
                     "file %s doesn't start with relroot %s" % (f, relroot))
 
     for f1, f2, copyop in _filepairs(modified, added, removed, copy, opts):
         content1 = None
         content2 = None
         fctx1 = None
         fctx2 = None
         flag1 = None
         flag2 = None
         if f1:
             fctx1 = getfilectx(f1, ctx1)
             if opts.git or losedatafn:
                 flag1 = ctx1.flags(f1)
         if f2:
             fctx2 = getfilectx(f2, ctx2)
             if opts.git or losedatafn:
                 flag2 = ctx2.flags(f2)
         # if binary is True, output "summary" or "base85", but not "text diff"
         binary = not opts.text and any(f.isbinary()
                                        for f in [fctx1, fctx2] if f is not None)
 
         if losedatafn and not opts.git:
             if (binary or
                 # copy/rename
                 f2 in copy or
                 # empty file creation
                 (not f1 and isempty(fctx2)) or
                 # empty file deletion
                 (isempty(fctx1) and not f2) or
                 # create with flags
                 (not f1 and flag2) or
                 # change flags
                 (f1 and f2 and flag1 != flag2)):
                 losedatafn(f2 or f1)
 
         path1 = f1 or f2
         path2 = f2 or f1
         path1 = posixpath.join(prefix, path1[len(relroot):])
         path2 = posixpath.join(prefix, path2[len(relroot):])
         header = []
         if opts.git:
             header.append('diff --git %s%s %s%s' %
                           (aprefix, path1, bprefix, path2))
             if not f1: # added
                 header.append('new file mode %s' % gitmode[flag2])
             elif not f2: # removed
                 header.append('deleted file mode %s' % gitmode[flag1])
             else:  # modified/copied/renamed
                 mode1, mode2 = gitmode[flag1], gitmode[flag2]
                 if mode1 != mode2:
                     header.append('old mode %s' % mode1)
                     header.append('new mode %s' % mode2)
                 if copyop is not None:
                     if opts.showsimilarity:
                         sim = similar.score(ctx1[path1], ctx2[path2]) * 100
                         header.append('similarity index %d%%' % sim)
                     header.append('%s from %s' % (copyop, path1))
                     header.append('%s to %s' % (copyop, path2))
         elif revs and not repo.ui.quiet:
             header.append(diffline(path1, revs))
 
         #  fctx.is  | diffopts                | what to   | is fctx.data()
         #  binary() | text nobinary git index | output?   | outputted?
         # ------------------------------------|----------------------------
         #  yes      | no   no       no  *     | summary   | no
         #  yes      | no   no       yes *     | base85    | yes
         #  yes      | no   yes      no  *     | summary   | no
         #  yes      | no   yes      yes 0     | summary   | no
         #  yes      | no   yes      yes >0    | summary   | semi [1]
         #  yes      | yes  *        *   *     | text diff | yes
         #  no       | *    *        *   *     | text diff | yes
         # [1]: hash(fctx.data()) is outputted. so fctx.data() cannot be faked
         if binary and (not opts.git or (opts.git and opts.nobinary and not
                                         opts.index)):
             # fast path: no binary content will be displayed, content1 and
             # content2 are only used for equivalent test. cmp() could have a
             # fast path.
             if fctx1 is not None:
                 content1 = b'\0'
             if fctx2 is not None:
                 if fctx1 is not None and not fctx1.cmp(fctx2):
                     content2 = b'\0' # not different
                 else:
                     content2 = b'\0\0'
         else:
             # normal path: load contents
             if fctx1 is not None:
                 content1 = fctx1.data()
             if fctx2 is not None:
                 content2 = fctx2.data()
 
         if binary and opts.git and not opts.nobinary:
             text = mdiff.b85diff(content1, content2)
             if text:
                 header.append('index %s..%s' %
                               (gitindex(content1), gitindex(content2)))
             hunks = (None, [text]),
         else:
             if opts.git and opts.index > 0:
                 flag = flag1
                 if flag is None:
                     flag = flag2
                 header.append('index %s..%s %s' %
                               (gitindex(content1)[0:opts.index],
                                gitindex(content2)[0:opts.index],
                                gitmode[flag]))
 
             uheaders, hunks = mdiff.unidiff(content1, date1,
                                             content2, date2,
                                             path1, path2, opts=opts)
             header.extend(uheaders)
         yield header, hunks
 
 def diffstatsum(stats):
     maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
     for f, a, r, b in stats:
         maxfile = max(maxfile, encoding.colwidth(f))
         maxtotal = max(maxtotal, a + r)
         addtotal += a
         removetotal += r
         binary = binary or b
 
     return maxfile, maxtotal, addtotal, removetotal, binary
 
 def diffstatdata(lines):
     diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$')
 
     results = []
     filename, adds, removes, isbinary = None, 0, 0, False
 
     def addresult():
         if filename:
             results.append((filename, adds, removes, isbinary))
 
     # inheader is used to track if a line is in the
     # header portion of the diff.  This helps properly account
     # for lines that start with '--' or '++'
     inheader = False
 
     for line in lines:
         if line.startswith('diff'):
             addresult()
             # starting a new file diff
             # set numbers to 0 and reset inheader
             inheader = True
             adds, removes, isbinary = 0, 0, False
             if line.startswith('diff --git a/'):
                 filename = gitre.search(line).group(2)
             elif line.startswith('diff -r'):
                 # format: "diff -r ... -r ... filename"
                 filename = diffre.search(line).group(1)
         elif line.startswith('@@'):
             inheader = False
         elif line.startswith('+') and not inheader:
             adds += 1
         elif line.startswith('-') and not inheader:
             removes += 1
         elif (line.startswith('GIT binary patch') or
               line.startswith('Binary file')):
             isbinary = True
     addresult()
     return results
 
 def diffstat(lines, width=80):
     output = []
     stats = diffstatdata(lines)
     maxname, maxtotal, totaladds, totalremoves, hasbinary = diffstatsum(stats)
 
     countwidth = len(str(maxtotal))
     if hasbinary and countwidth < 3:
         countwidth = 3
     graphwidth = width - countwidth - maxname - 6
     if graphwidth < 10:
         graphwidth = 10
 
     def scale(i):
         if maxtotal <= graphwidth:
             return i
         # If diffstat runs out of room it doesn't print anything,
         # which isn't very useful, so always print at least one + or -
         # if there were at least some changes.
         return max(i * graphwidth // maxtotal, int(bool(i)))
 
     for filename, adds, removes, isbinary in stats:
         if isbinary:
             count = 'Bin'
         else:
             count = adds + removes
         pluses = '+' * scale(adds)
         minuses = '-' * scale(removes)
         output.append(' %s%s |  %*s %s%s\n' %
                       (filename, ' ' * (maxname - encoding.colwidth(filename)),
                        countwidth, count, pluses, minuses))
 
     if stats:
         output.append(_(' %d files changed, %d insertions(+), '
                         '%d deletions(-)\n')
                       % (len(stats), totaladds, totalremoves))
 
     return ''.join(output)
 
 def diffstatui(*args, **kw):
     '''like diffstat(), but yields 2-tuples of (output, label) for
     ui.write()
     '''
 
     for line in diffstat(*args, **kw).splitlines():
         if line and line[-1] in '+-':
             name, graph = line.rsplit(' ', 1)
             yield (name + ' ', '')
             m = re.search(r'\++', graph)
             if m:
                 yield (m.group(0), 'diffstat.inserted')
             m = re.search(r'-+', graph)
             if m:
                 yield (m.group(0), 'diffstat.deleted')
         else:
             yield (line, '')
         yield ('\n', '')

setup.py

@@ -1,802 +1,802
 #
 # This is the mercurial setup script.
 #
 # 'python setup.py install', or
 # 'python setup.py --help' for more options
 
 import sys, platform
 if sys.version_info < (2, 7, 0, 'final'):
     raise SystemExit('Mercurial requires Python 2.7 or later.')
 
 if sys.version_info[0] >= 3:
     printf = eval('print')
     libdir_escape = 'unicode_escape'
 else:
     libdir_escape = 'string_escape'
     def printf(*args, **kwargs):
         f = kwargs.get('file', sys.stdout)
         end = kwargs.get('end', '\n')
         f.write(b' '.join(args) + end)
 
 # Solaris Python packaging brain damage
 try:
     import hashlib
     sha = hashlib.sha1()
 except ImportError:
     try:
         import sha
         sha.sha # silence unused import warning
     except ImportError:
         raise SystemExit(
             "Couldn't import standard hashlib (incomplete Python install).")
 
 try:
     import zlib
     zlib.compressobj # silence unused import warning
 except ImportError:
     raise SystemExit(
         "Couldn't import standard zlib (incomplete Python install).")
 
 # The base IronPython distribution (as of 2.7.1) doesn't support bz2
 isironpython = False
 try:
     isironpython = (platform.python_implementation()
                     .lower().find("ironpython") != -1)
 except AttributeError:
     pass
 
 if isironpython:
     sys.stderr.write("warning: IronPython detected (no bz2 support)\n")
 else:
     try:
         import bz2
         bz2.BZ2Compressor # silence unused import warning
     except ImportError:
         raise SystemExit(
             "Couldn't import standard bz2 (incomplete Python install).")
 
 ispypy = "PyPy" in sys.version
 
 import ctypes
 import os, stat, subprocess, time
 import re
 import shutil
 import tempfile
 from distutils import log
 # We have issues with setuptools on some platforms and builders. Until
 # those are resolved, setuptools is opt-in except for platforms where
 # we don't have issues.
 if os.name == 'nt' or 'FORCE_SETUPTOOLS' in os.environ:
     from setuptools import setup
 else:
     from distutils.core import setup
 from distutils.ccompiler import new_compiler
 from distutils.core import Command, Extension
 from distutils.dist import Distribution
 from distutils.command.build import build
 from distutils.command.build_ext import build_ext
 from distutils.command.build_py import build_py
 from distutils.command.build_scripts import build_scripts
 from distutils.command.install_lib import install_lib
 from distutils.command.install_scripts import install_scripts
 from distutils.spawn import spawn, find_executable
 from distutils import file_util
 from distutils.errors import (
     CCompilerError,
     DistutilsError,
     DistutilsExecError,
 )
 from distutils.sysconfig import get_python_inc, get_config_var
 from distutils.version import StrictVersion
 
 scripts = ['hg']
 if os.name == 'nt':
     # We remove hg.bat if we are able to build hg.exe.
     scripts.append('contrib/win32/hg.bat')
 
 def cancompile(cc, code):
     tmpdir = tempfile.mkdtemp(prefix='hg-install-')
     devnull = oldstderr = None
     try:
         fname = os.path.join(tmpdir, 'testcomp.c')
         f = open(fname, 'w')
         f.write(code)
         f.close()
         # Redirect stderr to /dev/null to hide any error messages
         # from the compiler.
         # This will have to be changed if we ever have to check
         # for a function on Windows.
         devnull = open('/dev/null', 'w')
         oldstderr = os.dup(sys.stderr.fileno())
         os.dup2(devnull.fileno(), sys.stderr.fileno())
         objects = cc.compile([fname], output_dir=tmpdir)
         cc.link_executable(objects, os.path.join(tmpdir, "a.out"))
         return True
     except Exception:
         return False
     finally:
         if oldstderr is not None:
             os.dup2(oldstderr, sys.stderr.fileno())
         if devnull is not None:
             devnull.close()
         shutil.rmtree(tmpdir)
 
 # simplified version of distutils.ccompiler.CCompiler.has_function
 # that actually removes its temporary files.
 def hasfunction(cc, funcname):
     code = 'int main(void) { %s(); }\n' % funcname
     return cancompile(cc, code)
 
 def hasheader(cc, headername):
     code = '#include <%s>\nint main(void) { return 0; }\n' % headername
     return cancompile(cc, code)
 
 # py2exe needs to be installed to work
 try:
     import py2exe
     py2exe.Distribution # silence unused import warning
     py2exeloaded = True
     # import py2exe's patched Distribution class
     from distutils.core import Distribution
 except ImportError:
     py2exeloaded = False
 
 def runcmd(cmd, env):
     if (sys.platform == 'plan9'
        and (sys.version_info[0] == 2 and sys.version_info[1] < 7)):
         # subprocess kludge to work around issues in half-baked Python
         # ports, notably bichued/python:
         _, out, err = os.popen3(cmd)
         return str(out), str(err)
     else:
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE,
                              stderr=subprocess.PIPE, env=env)
         out, err = p.communicate()
         return out, err
 
 def runhg(cmd, env):
     out, err = runcmd(cmd, env)
     # If root is executing setup.py, but the repository is owned by
     # another user (as in "sudo python setup.py install") we will get
     # trust warnings since the .hg/hgrc file is untrusted. That is
     # fine, we don't want to load it anyway.  Python may warn about
     # a missing __init__.py in mercurial/locale, we also ignore that.
     err = [e for e in err.splitlines()
            if not e.startswith(b'not trusting file') \
               and not e.startswith(b'warning: Not importing') \
               and not e.startswith(b'obsolete feature not enabled')]
     if err:
         printf("stderr from '%s':" % (' '.join(cmd)), file=sys.stderr)
         printf(b'\n'.join([b'  ' + e for e in err]), file=sys.stderr)
         return ''
     return out
 
 version = ''
 
 # Execute hg out of this directory with a custom environment which takes care
 # to not use any hgrc files and do no localization.
 env = {'HGMODULEPOLICY': 'py',
        'HGRCPATH': '',
        'LANGUAGE': 'C',
        'PATH': ''} # make pypi modules that use os.environ['PATH'] happy
 if 'LD_LIBRARY_PATH' in os.environ:
     env['LD_LIBRARY_PATH'] = os.environ['LD_LIBRARY_PATH']
 if 'SystemRoot' in os.environ:
     # Copy SystemRoot into the custom environment for Python 2.6
     # under Windows. Otherwise, the subprocess will fail with
     # error 0xc0150004. See: http://bugs.python.org/issue3440
     env['SystemRoot'] = os.environ['SystemRoot']
 
 if os.path.isdir('.hg'):
     cmd = [sys.executable, 'hg', 'log', '-r', '.', '--template', '{tags}\n']
     numerictags = [t for t in runhg(cmd, env).split() if t[0].isdigit()]
     hgid = runhg([sys.executable, 'hg', 'id', '-i'], env).strip()
     if numerictags: # tag(s) found
         version = numerictags[-1]
         if hgid.endswith('+'): # propagate the dirty status to the tag
             version += '+'
     else: # no tag found
         ltagcmd = [sys.executable, 'hg', 'parents', '--template',
                    '{latesttag}']
         ltag = runhg(ltagcmd, env)
         changessincecmd = [sys.executable, 'hg', 'log', '-T', 'x\n', '-r',
                            "only(.,'%s')" % ltag]
         changessince = len(runhg(changessincecmd, env).splitlines())
         version = '%s+%s-%s' % (ltag, changessince, hgid)
     if version.endswith('+'):
         version += time.strftime('%Y%m%d')
 elif os.path.exists('.hg_archival.txt'):
     kw = dict([[t.strip() for t in l.split(':', 1)]
                for l in open('.hg_archival.txt')])
     if 'tag' in kw:
         version = kw['tag']
     elif 'latesttag' in kw:
         if 'changessincelatesttag' in kw:
             version = '%(latesttag)s+%(changessincelatesttag)s-%(node).12s' % kw
         else:
             version = '%(latesttag)s+%(latesttagdistance)s-%(node).12s' % kw
     else:
         version = kw.get('node', '')[:12]
 
 if version:
     with open("mercurial/__version__.py", "w") as f:
         f.write('# this file is autogenerated by setup.py\n')
         f.write('version = "%s"\n' % version)
 
 try:
     oldpolicy = os.environ.get('HGMODULEPOLICY', None)
     os.environ['HGMODULEPOLICY'] = 'py'
     from mercurial import __version__
     version = __version__.version
 except ImportError:
     version = 'unknown'
 finally:
     if oldpolicy is None:
         del os.environ['HGMODULEPOLICY']
     else:
         os.environ['HGMODULEPOLICY'] = oldpolicy
 
 class hgbuild(build):
     # Insert hgbuildmo first so that files in mercurial/locale/ are found
     # when build_py is run next.
     sub_commands = [('build_mo', None)] + build.sub_commands
 
 class hgbuildmo(build):
 
     description = "build translations (.mo files)"
 
     def run(self):
         if not find_executable('msgfmt'):
             self.warn("could not find msgfmt executable, no translations "
                      "will be built")
             return
 
         podir = 'i18n'
         if not os.path.isdir(podir):
             self.warn("could not find %s/ directory" % podir)
             return
 
         join = os.path.join
         for po in os.listdir(podir):
             if not po.endswith('.po'):
                 continue
             pofile = join(podir, po)
             modir = join('locale', po[:-3], 'LC_MESSAGES')
             mofile = join(modir, 'hg.mo')
             mobuildfile = join('mercurial', mofile)
             cmd = ['msgfmt', '-v', '-o', mobuildfile, pofile]
             if sys.platform != 'sunos5':
                 # msgfmt on Solaris does not know about -c
                 cmd.append('-c')
             self.mkpath(join('mercurial', modir))
             self.make_file([pofile], mobuildfile, spawn, (cmd,))
 
 
 class hgdist(Distribution):
     pure = False
     cffi = ispypy
 
     global_options = Distribution.global_options + \
                      [('pure', None, "use pure (slow) Python "
                         "code instead of C extensions"),
                      ]
 
     def has_ext_modules(self):
         # self.ext_modules is emptied in hgbuildpy.finalize_options which is
         # too late for some cases
         return not self.pure and Distribution.has_ext_modules(self)
 
 # This is ugly as a one-liner. So use a variable.
 buildextnegops = dict(getattr(build_ext, 'negative_options', {}))
 buildextnegops['no-zstd'] = 'zstd'
 
 class hgbuildext(build_ext):
     user_options = build_ext.user_options + [
         ('zstd', None, 'compile zstd bindings [default]'),
         ('no-zstd', None, 'do not compile zstd bindings'),
     ]
 
     boolean_options = build_ext.boolean_options + ['zstd']
     negative_opt = buildextnegops
 
     def initialize_options(self):
         self.zstd = True
         return build_ext.initialize_options(self)
 
     def build_extensions(self):
         # Filter out zstd if disabled via argument.
         if not self.zstd:
             self.extensions = [e for e in self.extensions
                                if e.name != 'mercurial.zstd']
 
         return build_ext.build_extensions(self)
 
     def build_extension(self, ext):
         try:
             build_ext.build_extension(self, ext)
         except CCompilerError:
             if not getattr(ext, 'optional', False):
                 raise
             log.warn("Failed to build optional extension '%s' (skipping)",
                      ext.name)
 
 class hgbuildscripts(build_scripts):
     def run(self):
         if os.name != 'nt' or self.distribution.pure:
             return build_scripts.run(self)
 
         exebuilt = False
         try:
             self.run_command('build_hgexe')
             exebuilt = True
         except (DistutilsError, CCompilerError):
             log.warn('failed to build optional hg.exe')
 
         if exebuilt:
             # Copying hg.exe to the scripts build directory ensures it is
             # installed by the install_scripts command.
             hgexecommand = self.get_finalized_command('build_hgexe')
             dest = os.path.join(self.build_dir, 'hg.exe')
             self.mkpath(self.build_dir)
             self.copy_file(hgexecommand.hgexepath, dest)
 
             # Remove hg.bat because it is redundant with hg.exe.
             self.scripts.remove('contrib/win32/hg.bat')
 
         return build_scripts.run(self)
 
 class hgbuildpy(build_py):
     def finalize_options(self):
         build_py.finalize_options(self)
 
         if self.distribution.pure:
             self.distribution.ext_modules = []
         elif self.distribution.cffi:
             from mercurial.cffi import (
                 bdiff,
                 mpatch,
             )
             exts = [mpatch.ffi.distutils_extension(),
                     bdiff.ffi.distutils_extension()]
             # cffi modules go here
             if sys.platform == 'darwin':
                 from mercurial.cffi import osutil
                 exts.append(osutil.ffi.distutils_extension())
             self.distribution.ext_modules = exts
         else:
             h = os.path.join(get_python_inc(), 'Python.h')
             if not os.path.exists(h):
                 raise SystemExit('Python headers are required to build '
                                  'Mercurial but weren\'t found in %s' % h)
 
     def run(self):
         if self.distribution.pure:
             modulepolicy = 'py'
         elif self.build_lib == '.':
             # in-place build should run without rebuilding C extensions
             modulepolicy = 'allow'
         else:
             modulepolicy = 'c'
         with open("mercurial/__modulepolicy__.py", "w") as f:
             f.write('# this file is autogenerated by setup.py\n')
             f.write('modulepolicy = b"%s"\n' % modulepolicy)
 
         build_py.run(self)
 
 class buildhgextindex(Command):
     description = 'generate prebuilt index of hgext (for frozen package)'
     user_options = []
     _indexfilename = 'hgext/__index__.py'
 
     def initialize_options(self):
         pass
 
     def finalize_options(self):
         pass
 
     def run(self):
         if os.path.exists(self._indexfilename):
             with open(self._indexfilename, 'w') as f:
                 f.write('# empty\n')
 
         # here no extension enabled, disabled() lists up everything
         code = ('import pprint; from mercurial import extensions; '
                 'pprint.pprint(extensions.disabled())')
         out, err = runcmd([sys.executable, '-c', code], env)
         if err:
             raise DistutilsExecError(err)
 
         with open(self._indexfilename, 'w') as f:
             f.write('# this file is autogenerated by setup.py\n')
             f.write('docs = ')
             f.write(out)
 
 class buildhgexe(build_ext):
     description = 'compile hg.exe from mercurial/exewrapper.c'
 
     def build_extensions(self):
         if os.name != 'nt':
             return
         if isinstance(self.compiler, HackedMingw32CCompiler):
             self.compiler.compiler_so = self.compiler.compiler # no -mdll
             self.compiler.dll_libraries = [] # no -lmsrvc90
 
         # Different Python installs can have different Python library
         # names. e.g. the official CPython distribution uses pythonXY.dll
         # and MinGW uses libpythonX.Y.dll.
         _kernel32 = ctypes.windll.kernel32
         _kernel32.GetModuleFileNameA.argtypes = [ctypes.c_void_p,
                                                  ctypes.c_void_p,
                                                  ctypes.c_ulong]
         _kernel32.GetModuleFileNameA.restype = ctypes.c_ulong
         size = 1000
         buf = ctypes.create_string_buffer(size + 1)
         filelen = _kernel32.GetModuleFileNameA(sys.dllhandle, ctypes.byref(buf),
                                                size)
 
         if filelen > 0 and filelen != size:
             dllbasename = os.path.basename(buf.value)
             if not dllbasename.lower().endswith('.dll'):
                 raise SystemExit('Python DLL does not end with .dll: %s' %
                                  dllbasename)
             pythonlib = dllbasename[:-4]
         else:
             log.warn('could not determine Python DLL filename; '
                      'assuming pythonXY')
 
             hv = sys.hexversion
             pythonlib = 'python%d%d' % (hv >> 24, (hv >> 16) & 0xff)
 
         log.info('using %s as Python library name' % pythonlib)
         with open('mercurial/hgpythonlib.h', 'wb') as f:
             f.write('/* this file is autogenerated by setup.py */\n')
             f.write('#define HGPYTHONLIB "%s"\n' % pythonlib)
         objects = self.compiler.compile(['mercurial/exewrapper.c'],
                                          output_dir=self.build_temp)
         dir = os.path.dirname(self.get_ext_fullpath('dummy'))
         target = os.path.join(dir, 'hg')
         self.compiler.link_executable(objects, target,
                                       libraries=[],
                                       output_dir=self.build_temp)
 
     @property
     def hgexepath(self):
         dir = os.path.dirname(self.get_ext_fullpath('dummy'))
         return os.path.join(self.build_temp, dir, 'hg.exe')
 
 class hginstalllib(install_lib):
     '''
     This is a specialization of install_lib that replaces the copy_file used
     there so that it supports setting the mode of files after copying them,
     instead of just preserving the mode that the files originally had.  If your
     system has a umask of something like 027, preserving the permissions when
     copying will lead to a broken install.
 
     Note that just passing keep_permissions=False to copy_file would be
     insufficient, as it might still be applying a umask.
     '''
 
     def run(self):
         realcopyfile = file_util.copy_file
         def copyfileandsetmode(*args, **kwargs):
             src, dst = args[0], args[1]
             dst, copied = realcopyfile(*args, **kwargs)
             if copied:
                 st = os.stat(src)
                 # Persist executable bit (apply it to group and other if user
                 # has it)
                 if st[stat.ST_MODE] & stat.S_IXUSR:
                     setmode = int('0755', 8)
                 else:
                     setmode = int('0644', 8)
                 m = stat.S_IMODE(st[stat.ST_MODE])
                 m = (m & ~int('0777', 8)) | setmode
                 os.chmod(dst, m)
         file_util.copy_file = copyfileandsetmode
         try:
             install_lib.run(self)
         finally:
             file_util.copy_file = realcopyfile
 
 class hginstallscripts(install_scripts):
     '''
     This is a specialization of install_scripts that replaces the @LIBDIR@ with
     the configured directory for modules. If possible, the path is made relative
     to the directory for scripts.
     '''
 
     def initialize_options(self):
         install_scripts.initialize_options(self)
 
         self.install_lib = None
 
     def finalize_options(self):
         install_scripts.finalize_options(self)
         self.set_undefined_options('install',
                                    ('install_lib', 'install_lib'))
 
     def run(self):
         install_scripts.run(self)
 
         # It only makes sense to replace @LIBDIR@ with the install path if
         # the install path is known. For wheels, the logic below calculates
         # the libdir to be "../..". This is because the internal layout of a
         # wheel archive looks like:
         #
         #   mercurial-3.6.1.data/scripts/hg
         #   mercurial/__init__.py
         #
         # When installing wheels, the subdirectories of the "<pkg>.data"
         # directory are translated to system local paths and files therein
         # are copied in place. The mercurial/* files are installed into the
         # site-packages directory. However, the site-packages directory
         # isn't known until wheel install time. This means we have no clue
         # at wheel generation time what the installed site-packages directory
         # will be. And, wheels don't appear to provide the ability to register
         # custom code to run during wheel installation. This all means that
         # we can't reliably set the libdir in wheels: the default behavior
         # of looking in sys.path must do.
 
         if (os.path.splitdrive(self.install_dir)[0] !=
             os.path.splitdrive(self.install_lib)[0]):
             # can't make relative paths from one drive to another, so use an
             # absolute path instead
             libdir = self.install_lib
         else:
             common = os.path.commonprefix((self.install_dir, self.install_lib))
             rest = self.install_dir[len(common):]
             uplevel = len([n for n in os.path.split(rest) if n])
 
             libdir = uplevel * ('..' + os.sep) + self.install_lib[len(common):]
 
         for outfile in self.outfiles:
             with open(outfile, 'rb') as fp:
                 data = fp.read()
 
             # skip binary files
             if b'\0' in data:
                 continue
 
             # During local installs, the shebang will be rewritten to the final
             # install path. During wheel packaging, the shebang has a special
             # value.
             if data.startswith(b'#!python'):
                 log.info('not rewriting @LIBDIR@ in %s because install path '
                          'not known' % outfile)
                 continue
 
             data = data.replace(b'@LIBDIR@', libdir.encode(libdir_escape))
             with open(outfile, 'wb') as fp:
                 fp.write(data)
 
 cmdclass = {'build': hgbuild,
             'build_mo': hgbuildmo,
             'build_ext': hgbuildext,
             'build_py': hgbuildpy,
             'build_scripts': hgbuildscripts,
             'build_hgextindex': buildhgextindex,
             'install_lib': hginstalllib,
             'install_scripts': hginstallscripts,
             'build_hgexe': buildhgexe,
             }
 
 packages = ['mercurial',
             'mercurial.cext',
             'mercurial.hgweb',
             'mercurial.httpclient',
             'mercurial.pure',
             'hgext', 'hgext.convert', 'hgext.fsmonitor',
             'hgext.fsmonitor.pywatchman', 'hgext.highlight',
             'hgext.largefiles', 'hgext.zeroconf', 'hgext3rd']
 
 common_depends = ['mercurial/bitmanipulation.h',
                   'mercurial/compat.h',
                   'mercurial/util.h']
 common_include_dirs = ['mercurial']
 
 osutil_cflags = []
 osutil_ldflags = []
 
 # platform specific macros
 for plat, func in [('bsd', 'setproctitle')]:
     if re.search(plat, sys.platform) and hasfunction(new_compiler(), func):
         osutil_cflags.append('-DHAVE_%s' % func.upper())
 
 for plat, macro, code in [
     ('bsd|darwin', 'BSD_STATFS', '''
      #include <sys/param.h>
      #include <sys/mount.h>
      int main() { struct statfs s; return sizeof(s.f_fstypename); }
      '''),
     ('linux', 'LINUX_STATFS', '''
      #include <linux/magic.h>
      #include <sys/vfs.h>
      int main() { struct statfs s; return sizeof(s.f_type); }
      '''),
 ]:
     if re.search(plat, sys.platform) and cancompile(new_compiler(), code):
         osutil_cflags.append('-DHAVE_%s' % macro)
 
 if sys.platform == 'darwin':
     osutil_ldflags += ['-framework', 'ApplicationServices']
 
 extmodules = [
     Extension('mercurial.cext.base85', ['mercurial/cext/base85.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     Extension('mercurial.cext.bdiff', ['mercurial/bdiff.c',
                                        'mercurial/cext/bdiff.c'],
               include_dirs=common_include_dirs,
               depends=common_depends + ['mercurial/bdiff.h']),
-    Extension('mercurial.diffhelpers', ['mercurial/diffhelpers.c'],
+    Extension('mercurial.cext.diffhelpers', ['mercurial/cext/diffhelpers.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     Extension('mercurial.mpatch', ['mercurial/mpatch.c',
                                    'mercurial/mpatch_module.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     Extension('mercurial.parsers', ['mercurial/dirs.c',
                                     'mercurial/manifest.c',
                                     'mercurial/parsers.c',
                                     'mercurial/pathencode.c'],
               include_dirs=common_include_dirs,
               depends=common_depends),
     Extension('mercurial.cext.osutil', ['mercurial/cext/osutil.c'],
               include_dirs=common_include_dirs,
               extra_compile_args=osutil_cflags,
               extra_link_args=osutil_ldflags,
               depends=common_depends),
     Extension('hgext.fsmonitor.pywatchman.bser',
               ['hgext/fsmonitor/pywatchman/bser.c']),
     ]
 
 sys.path.insert(0, 'contrib/python-zstandard')
 import setup_zstd
 extmodules.append(setup_zstd.get_c_extension(name='mercurial.zstd'))
 
 try:
     from distutils import cygwinccompiler
 
     # the -mno-cygwin option has been deprecated for years
     compiler = cygwinccompiler.Mingw32CCompiler
 
     class HackedMingw32CCompiler(cygwinccompiler.Mingw32CCompiler):
         def __init__(self, *args, **kwargs):
             compiler.__init__(self, *args, **kwargs)
             for i in 'compiler compiler_so linker_exe linker_so'.split():
                 try:
                     getattr(self, i).remove('-mno-cygwin')
                 except ValueError:
                     pass
 
     cygwinccompiler.Mingw32CCompiler = HackedMingw32CCompiler
 except ImportError:
     # the cygwinccompiler package is not available on some Python
     # distributions like the ones from the optware project for Synology
     # DiskStation boxes
     class HackedMingw32CCompiler(object):
         pass
 
 packagedata = {'mercurial': ['locale/*/LC_MESSAGES/hg.mo',
                              'help/*.txt',
                              'help/internals/*.txt',
                              'default.d/*.rc',
                              'dummycert.pem']}
 
 def ordinarypath(p):
     return p and p[0] != '.' and p[-1] != '~'
 
 for root in ('templates',):
     for curdir, dirs, files in os.walk(os.path.join('mercurial', root)):
         curdir = curdir.split(os.sep, 1)[1]
         dirs[:] = filter(ordinarypath, dirs)
         for f in filter(ordinarypath, files):
             f = os.path.join(curdir, f)
             packagedata['mercurial'].append(f)
 
 datafiles = []
 
 # distutils expects version to be str/unicode. Converting it to
 # unicode on Python 2 still works because it won't contain any
 # non-ascii bytes and will be implicitly converted back to bytes
 # when operated on.
 assert isinstance(version, bytes)
 setupversion = version.decode('ascii')
 
 extra = {}
 
 if py2exeloaded:
     extra['console'] = [
         {'script':'hg',
          'copyright':'Copyright (C) 2005-2017 Matt Mackall and others',
          'product_version':version}]
     # sub command of 'build' because 'py2exe' does not handle sub_commands
     build.sub_commands.insert(0, ('build_hgextindex', None))
     # put dlls in sub directory so that they won't pollute PATH
     extra['zipfile'] = 'lib/library.zip'
 
 if os.name == 'nt':
     # Windows binary file versions for exe/dll files must have the
     # form W.X.Y.Z, where W,X,Y,Z are numbers in the range 0..65535
     setupversion = version.split('+', 1)[0]
 
 if sys.platform == 'darwin' and os.path.exists('/usr/bin/xcodebuild'):
     version = runcmd(['/usr/bin/xcodebuild', '-version'], {})[0].splitlines()
     if version:
         version = version[0]
         if sys.version_info[0] == 3:
             version = version.decode('utf-8')
         xcode4 = (version.startswith('Xcode') and
                   StrictVersion(version.split()[1]) >= StrictVersion('4.0'))
         xcode51 = re.match(r'^Xcode\s+5\.1', version) is not None
     else:
         # xcodebuild returns empty on OS X Lion with XCode 4.3 not
         # installed, but instead with only command-line tools. Assume
         # that only happens on >= Lion, thus no PPC support.
         xcode4 = True
         xcode51 = False
 
     # XCode 4.0 dropped support for ppc architecture, which is hardcoded in
     # distutils.sysconfig
     if xcode4:
         os.environ['ARCHFLAGS'] = ''
 
     # XCode 5.1 changes clang such that it now fails to compile if the
     # -mno-fused-madd flag is passed, but the version of Python shipped with
     # OS X 10.9 Mavericks includes this flag. This causes problems in all
     # C extension modules, and a bug has been filed upstream at
     # http://bugs.python.org/issue21244. We also need to patch this here
     # so Mercurial can continue to compile in the meantime.
     if xcode51:
         cflags = get_config_var('CFLAGS')
         if cflags and re.search(r'-mno-fused-madd\b', cflags) is not None:
             os.environ['CFLAGS'] = (
                 os.environ.get('CFLAGS', '') + ' -Qunused-arguments')
 
 setup(name='mercurial',
       version=setupversion,
       author='Matt Mackall and many others',
       author_email='[e-mail]',
       url='https://mercurial-scm.org/',
       download_url='https://mercurial-scm.org/release/',
       description=('Fast scalable distributed SCM (revision control, version '
                    'control) system'),
       long_description=('Mercurial is a distributed SCM tool written in Python.'
                         ' It is used by a number of large projects that require'
                         ' fast, reliable distributed revision control, such as '
                         'Mozilla.'),
       license='GNU GPLv2 or any later version',
       classifiers=[
           'Development Status :: 6 - Mature',
           'Environment :: Console',
           'Intended Audience :: Developers',
           'Intended Audience :: System Administrators',
           'License :: OSI Approved :: GNU General Public License (GPL)',
           'Natural Language :: Danish',
           'Natural Language :: English',
           'Natural Language :: German',
           'Natural Language :: Italian',
           'Natural Language :: Japanese',
           'Natural Language :: Portuguese (Brazilian)',
           'Operating System :: Microsoft :: Windows',
           'Operating System :: OS Independent',
           'Operating System :: POSIX',
           'Programming Language :: C',
           'Programming Language :: Python',
           'Topic :: Software Development :: Version Control',
       ],
       scripts=scripts,
       packages=packages,
       ext_modules=extmodules,
       data_files=datafiles,
       package_data=packagedata,
       cmdclass=cmdclass,
       distclass=hgdist,
       options={'py2exe': {'packages': ['hgext', 'email']},
                'bdist_mpkg': {'zipdist': False,
                               'license': 'COPYING',
                               'readme': 'contrib/macosx/Readme.html',
                               'welcome': 'contrib/macosx/Welcome.html',
                               },
                },
       **extra)