py3: stop using util.iterfile()

The Python 3 implementation is a no-op. So this is equivalent.

We still keep util.iterfile() around for backwards API compatibility to
help the Python 3 migration. It can be deleted in a future release.

Differential Revision: https://phab.mercurial-scm.org/D12347

hgext/convert/common.py

@@ -1,597 +1,597 b''
 # common.py - common code for the convert extension
 #
 #  Copyright 2005-2009 Olivia Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import base64
 import datetime
 import errno
 import os
 import pickle
 import re
 import shlex
 import subprocess
 
 from mercurial.i18n import _
 from mercurial.pycompat import open
 from mercurial import (
     encoding,
     error,
     phases,
     pycompat,
     util,
 )
 from mercurial.utils import procutil
 
 propertycache = util.propertycache
 
 
 def _encodeornone(d):
     if d is None:
         return
     return d.encode('latin1')
 
 
 class _shlexpy3proxy(object):
     def __init__(self, l):
         self._l = l
 
     def __iter__(self):
         return (_encodeornone(v) for v in self._l)
 
     def get_token(self):
         return _encodeornone(self._l.get_token())
 
     @property
     def infile(self):
         return self._l.infile or b'<unknown>'
 
     @property
     def lineno(self):
         return self._l.lineno
 
 
 def shlexer(data=None, filepath=None, wordchars=None, whitespace=None):
     if data is None:
         if pycompat.ispy3:
             data = open(filepath, b'r', encoding='latin1')
         else:
             data = open(filepath, b'r')
     else:
         if filepath is not None:
             raise error.ProgrammingError(
                 b'shlexer only accepts data or filepath, not both'
             )
         if pycompat.ispy3:
             data = data.decode('latin1')
     l = shlex.shlex(data, infile=filepath, posix=True)
     if whitespace is not None:
         l.whitespace_split = True
         if pycompat.ispy3:
             l.whitespace += whitespace.decode('latin1')
         else:
             l.whitespace += whitespace
     if wordchars is not None:
         if pycompat.ispy3:
             l.wordchars += wordchars.decode('latin1')
         else:
             l.wordchars += wordchars
     if pycompat.ispy3:
         return _shlexpy3proxy(l)
     return l
 
 
 if pycompat.ispy3:
     base64_encodebytes = base64.encodebytes
     base64_decodebytes = base64.decodebytes
 else:
     base64_encodebytes = base64.encodestring
     base64_decodebytes = base64.decodestring
 
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64_encodebytes(s)
         lines = [l.splitlines()[0] for l in pycompat.iterbytestr(lines)]
         return b''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 
 def decodeargs(s):
     s = base64_decodebytes(s)
     return pickle.loads(s)
 
 
 class MissingTool(Exception):
     pass
 
 
 def checktool(exe, name=None, abort=True):
     name = name or exe
     if not procutil.findexe(exe):
         if abort:
             exc = error.Abort
         else:
             exc = MissingTool
         raise exc(_(b'cannot find required "%s" tool') % name)
 
 
 class NoRepo(Exception):
     pass
 
 
 SKIPREV = b'SKIP'
 
 
 class commit(object):
     def __init__(
         self,
         author,
         date,
         desc,
         parents,
         branch=None,
         rev=None,
         extra=None,
         sortkey=None,
         saverev=True,
         phase=phases.draft,
         optparents=None,
         ctx=None,
     ):
         self.author = author or b'unknown'
         self.date = date or b'0 0'
         self.desc = desc
         self.parents = parents  # will be converted and used as parents
         self.optparents = optparents or []  # will be used if already converted
         self.branch = branch
         self.rev = rev
         self.extra = extra or {}
         self.sortkey = sortkey
         self.saverev = saverev
         self.phase = phase
         self.ctx = ctx  # for hg to hg conversions
 
 
 class converter_source(object):
     """Conversion source interface"""
 
     def __init__(self, ui, repotype, path=None, revs=None):
         """Initialize conversion source (or raise NoRepo("message")
         exception if path is not a valid repository)"""
         self.ui = ui
         self.path = path
         self.revs = revs
         self.repotype = repotype
 
         self.encoding = b'utf-8'
 
     def checkhexformat(self, revstr, mapname=b'splicemap'):
         """fails if revstr is not a 40 byte hex. mercurial and git both uses
         such format for their revision numbering
         """
         if not re.match(br'[0-9a-fA-F]{40,40}$', revstr):
             raise error.Abort(
                 _(b'%s entry %s is not a valid revision identifier')
                 % (mapname, revstr)
             )
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def targetfilebelongstosource(self, targetfilename):
         """Returns true if the given targetfile belongs to the source repo. This
         is useful when only a subdirectory of the target belongs to the source
         repo."""
         # For normal full repo converts, this is always True.
         return True
 
     def setrevmap(self, revmap):
         """set the map of already-converted revisions"""
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError
 
     def getfile(self, name, rev):
         """Return a pair (data, mode) where data is the file content
         as a string and mode one of '', 'x' or 'l'. rev is the
         identifier returned by a previous call to getchanges().
         Data is None if file is missing/deleted in rev.
         """
         raise NotImplementedError
 
     def getchanges(self, version, full):
         """Returns a tuple of (files, copies, cleanp2).
 
         files is a sorted list of (filename, id) tuples for all files
         changed between version and its first parent returned by
         getcommit(). If full, all files in that revision is returned.
         id is the source revision id of the file.
 
         copies is a dictionary of dest: source
 
         cleanp2 is the set of files filenames that are clean against p2.
         (Files that are clean against p1 are already not in files (unless
         full). This makes it possible to handle p2 clean files similarly.)
         """
         raise NotImplementedError
 
     def getcommit(self, version):
         """Return the commit object for version"""
         raise NotImplementedError
 
     def numcommits(self):
         """Return the number of commits in this source.
 
         If unknown, return None.
         """
         return None
 
     def gettags(self):
         """Return the tags as a dictionary of name: revision
 
         Tag names must be UTF-8 strings.
         """
         raise NotImplementedError
 
     def recode(self, s, encoding=None):
         if not encoding:
             encoding = self.encoding or b'utf-8'
 
         if isinstance(s, str):
             return s.encode("utf-8")
         try:
             return s.decode(pycompat.sysstr(encoding)).encode("utf-8")
         except UnicodeError:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except UnicodeError:
                 return s.decode(pycompat.sysstr(encoding), "replace").encode(
                     "utf-8"
                 )
 
     def getchangedfiles(self, rev, i):
         """Return the files changed by rev compared to parent[i].
 
         i is an index selecting one of the parents of rev.  The return
         value should be the list of files that are different in rev and
         this parent.
 
         If rev has no parents, i is None.
 
         This function is only needed to support --filemap
         """
         raise NotImplementedError
 
     def converted(self, rev, sinkrev):
         '''Notify the source that a revision has been converted.'''
 
     def hasnativeorder(self):
         """Return true if this source has a meaningful, native revision
         order. For instance, Mercurial revisions are store sequentially
         while there is no such global ordering with Darcs.
         """
         return False
 
     def hasnativeclose(self):
         """Return true if this source has ability to close branch."""
         return False
 
     def lookuprev(self, rev):
         """If rev is a meaningful revision reference in source, return
         the referenced identifier in the same format used by getcommit().
         return None otherwise.
         """
         return None
 
     def getbookmarks(self):
         """Return the bookmarks as a dictionary of name: revision
 
         Bookmark names are to be UTF-8 strings.
         """
         return {}
 
     def checkrevformat(self, revstr, mapname=b'splicemap'):
         """revstr is a string that describes a revision in the given
         source control system.  Return true if revstr has correct
         format.
         """
         return True
 
 
 class converter_sink(object):
     """Conversion sink (target) interface"""
 
     def __init__(self, ui, repotype, path):
         """Initialize conversion sink (or raise NoRepo("message")
         exception if path is not a valid repository)
 
         created is a list of paths to remove if a fatal error occurs
         later"""
         self.ui = ui
         self.path = path
         self.created = []
         self.repotype = repotype
 
     def revmapfile(self):
         """Path to a file that will contain lines
         source_rev_id sink_rev_id
         mapping equivalent revision identifiers for each system."""
         raise NotImplementedError
 
     def authorfile(self):
         """Path to a file that will contain lines
         srcauthor=dstauthor
         mapping equivalent authors identifiers for each system."""
         return None
 
     def putcommit(
         self, files, copies, parents, commit, source, revmap, full, cleanp2
     ):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object
         containing at a minimum the author, date, and message for this
         changeset.  'files' is a list of (path, version) tuples,
         'copies' is a dictionary mapping destinations to sources,
         'source' is the source repository, and 'revmap' is a mapfile
         of source revisions to converted revisions. Only getfile() and
         lookuprev() should be called on 'source'. 'full' means that 'files'
         is complete and all other files should be removed.
         'cleanp2' is a set of the filenames that are unchanged from p2
         (only in the common merge case where there two parents).
 
         Note that the sink repository is not told to update itself to
         a particular revision (or even what that revision would be)
         before it receives the file data.
         """
         raise NotImplementedError
 
     def puttags(self, tags):
         """Put tags into sink.
 
         tags: {tagname: sink_rev_id, ...} where tagname is an UTF-8 string.
         Return a pair (tag_revision, tag_parent_revision), or (None, None)
         if nothing was changed.
         """
         raise NotImplementedError
 
     def setbranch(self, branch, pbranches):
         """Set the current branch name. Called before the first putcommit
         on the branch.
         branch: branch name for subsequent commits
         pbranches: (converted parent revision, parent branch) tuples"""
 
     def setfilemapmode(self, active):
         """Tell the destination that we're using a filemap
 
         Some converter_sources (svn in particular) can claim that a file
         was changed in a revision, even if there was no change.  This method
         tells the destination that we're using a filemap and that it should
         filter empty revisions.
         """
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def putbookmarks(self, bookmarks):
         """Put bookmarks into sink.
 
         bookmarks: {bookmarkname: sink_rev_id, ...}
         where bookmarkname is an UTF-8 string.
         """
 
     def hascommitfrommap(self, rev):
         """Return False if a rev mentioned in a filemap is known to not be
         present."""
         raise NotImplementedError
 
     def hascommitforsplicemap(self, rev):
         """This method is for the special needs for splicemap handling and not
         for general use. Returns True if the sink contains rev, aborts on some
         special cases."""
         raise NotImplementedError
 
 
 class commandline(object):
     def __init__(self, ui, command):
         self.ui = ui
         self.command = command
 
     def prerun(self):
         pass
 
     def postrun(self):
         pass
 
     def _cmdline(self, cmd, *args, **kwargs):
         kwargs = pycompat.byteskwargs(kwargs)
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.items():
             if len(k) == 1:
                 cmdline.append(b'-' + k)
             else:
                 cmdline.append(b'--' + k.replace(b'_', b'-'))
             try:
                 if len(k) == 1:
                     cmdline.append(b'' + v)
                 else:
                     cmdline[-1] += b'=' + v
             except TypeError:
                 pass
         cmdline = [procutil.shellquote(arg) for arg in cmdline]
         if not self.ui.debugflag:
             cmdline += [b'2>', pycompat.bytestr(os.devnull)]
         cmdline = b' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         def popen(cmdline):
             p = subprocess.Popen(
                 procutil.tonativestr(cmdline),
                 shell=True,
                 bufsize=-1,
                 close_fds=procutil.closefds,
                 stdout=subprocess.PIPE,
             )
             return p
 
         return self._dorun(popen, cmd, *args, **kwargs)
 
     def _run2(self, cmd, *args, **kwargs):
         return self._dorun(procutil.popen2, cmd, *args, **kwargs)
 
     def _run3(self, cmd, *args, **kwargs):
         return self._dorun(procutil.popen3, cmd, *args, **kwargs)
 
     def _dorun(self, openfunc, cmd, *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug(b'running: %s\n' % (cmdline,))
         self.prerun()
         try:
             return openfunc(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.communicate()[0]
         self.ui.debug(output)
         return output, p.returncode
 
     def runlines(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.stdout.readlines()
         p.wait()
         self.ui.debug(b''.join(output))
         return output, p.returncode
 
     def checkexit(self, status, output=b''):
         if status:
             if output:
                 self.ui.warn(_(b'%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = procutil.explainexit(status)
             raise error.Abort(b'%s %s' % (self.command, msg))
 
     def run0(self, cmd, *args, **kwargs):
         output, status = self.run(cmd, *args, **kwargs)
         self.checkexit(status, output)
         return output
 
     def runlines0(self, cmd, *args, **kwargs):
         output, status = self.runlines(cmd, *args, **kwargs)
         self.checkexit(status, b''.join(output))
         return output
 
     @propertycache
     def argmax(self):
         # POSIX requires at least 4096 bytes for ARG_MAX
         argmax = 4096
         try:
             argmax = os.sysconf("SC_ARG_MAX")
         except (AttributeError, ValueError):
             pass
 
         # Windows shells impose their own limits on command line length,
         # down to 2047 bytes for cmd.exe under Windows NT/2k and 2500 bytes
         # for older 4nt.exe. See http://support.microsoft.com/kb/830473 for
         # details about cmd.exe limitations.
 
         # Since ARG_MAX is for command line _and_ environment, lower our limit
         # (and make happy Windows shells while doing this).
         return argmax // 2 - 1
 
     def _limit_arglist(self, arglist, cmd, *args, **kwargs):
         cmdlen = len(self._cmdline(cmd, *args, **kwargs))
         limit = self.argmax - cmdlen
         numbytes = 0
         fl = []
         for fn in arglist:
             b = len(fn) + 3
             if numbytes + b < limit or len(fl) == 0:
                 fl.append(fn)
                 numbytes += b
             else:
                 yield fl
                 fl = [fn]
                 numbytes = b
         if fl:
             yield fl
 
     def xargs(self, arglist, cmd, *args, **kwargs):
         for l in self._limit_arglist(arglist, cmd, *args, **kwargs):
             self.run0(cmd, *(list(args) + l), **kwargs)
 
 
 class mapfile(dict):
     def __init__(self, ui, path):
         super(mapfile, self).__init__()
         self.ui = ui
         self.path = path
         self.fp = None
         self.order = []
         self._read()
 
     def _read(self):
         if not self.path:
             return
         try:
             fp = open(self.path, b'rb')
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
-        for i, line in enumerate(util.iterfile(fp)):
+        for i, line in enumerate(fp):
             line = line.splitlines()[0].rstrip()
             if not line:
                 # Ignore blank lines
                 continue
             try:
                 key, value = line.rsplit(b' ', 1)
             except ValueError:
                 raise error.Abort(
                     _(b'syntax error in %s(%d): key/value pair expected')
                     % (self.path, i + 1)
                 )
             if key not in self:
                 self.order.append(key)
             super(mapfile, self).__setitem__(key, value)
         fp.close()
 
     def __setitem__(self, key, value):
         if self.fp is None:
             try:
                 self.fp = open(self.path, b'ab')
             except IOError as err:
                 raise error.Abort(
                     _(b'could not open map file %r: %s')
                     % (self.path, encoding.strtolocal(err.strerror))
                 )
         self.fp.write(util.tonativeeol(b'%s %s\n' % (key, value)))
         self.fp.flush()
         super(mapfile, self).__setitem__(key, value)
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None
 
 
 def makedatetimestamp(t):
     """Like dateutil.makedate() but for time t instead of current time"""
     delta = datetime.datetime.utcfromtimestamp(
         t
     ) - datetime.datetime.fromtimestamp(t)
     tz = delta.days * 86400 + delta.seconds
     return t, tz

hgext/convert/convcmd.py

@@ -1,667 +1,667 b''
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import collections
 import os
 import shutil
 
 from mercurial.i18n import _
 from mercurial.pycompat import open
 from mercurial import (
     encoding,
     error,
     hg,
     pycompat,
     scmutil,
     util,
 )
 from mercurial.utils import dateutil
 
 from . import (
     bzr,
     common,
     cvs,
     darcs,
     filemap,
     git,
     gnuarch,
     hg as hgconvert,
     monotone,
     p4,
     subversion,
 )
 
 mapfile = common.mapfile
 MissingTool = common.MissingTool
 NoRepo = common.NoRepo
 SKIPREV = common.SKIPREV
 
 bzr_source = bzr.bzr_source
 convert_cvs = cvs.convert_cvs
 convert_git = git.convert_git
 darcs_source = darcs.darcs_source
 gnuarch_source = gnuarch.gnuarch_source
 mercurial_sink = hgconvert.mercurial_sink
 mercurial_source = hgconvert.mercurial_source
 monotone_source = monotone.monotone_source
 p4_source = p4.p4_source
 svn_sink = subversion.svn_sink
 svn_source = subversion.svn_source
 
 orig_encoding = b'ascii'
 
 
 def readauthormap(ui, authorfile, authors=None):
     if authors is None:
         authors = {}
     with open(authorfile, b'rb') as afile:
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith(b'#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split(b'=', 1)
             except ValueError:
                 msg = _(b'ignoring bad line in author map file %s: %s\n')
                 ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if authors.get(srcauthor) in (None, dstauthor):
                 msg = _(b'mapping author %s to %s\n')
                 ui.debug(msg % (srcauthor, dstauthor))
                 authors[srcauthor] = dstauthor
                 continue
 
             m = _(b'overriding mapping for author %s, was %s, will be %s\n')
             ui.status(m % (srcauthor, authors[srcauthor], dstauthor))
     return authors
 
 
 def recode(s):
     if isinstance(s, str):
         return s.encode(pycompat.sysstr(orig_encoding), 'replace')
     else:
         return s.decode('utf-8').encode(
             pycompat.sysstr(orig_encoding), 'replace'
         )
 
 
 def mapbranch(branch, branchmap):
     """
     >>> bmap = {b'default': b'branch1'}
     >>> for i in [b'', None]:
     ...     mapbranch(i, bmap)
     'branch1'
     'branch1'
     >>> bmap = {b'None': b'branch2'}
     >>> for i in [b'', None]:
     ...     mapbranch(i, bmap)
     'branch2'
     'branch2'
     >>> bmap = {b'None': b'branch3', b'default': b'branch4'}
     >>> for i in [b'None', b'', None, b'default', b'branch5']:
     ...     mapbranch(i, bmap)
     'branch3'
     'branch4'
     'branch4'
     'branch4'
     'branch5'
     """
     # If branch is None or empty, this commit is coming from the source
     # repository's default branch and destined for the default branch in the
     # destination repository. For such commits, using a literal "default"
     # in branchmap below allows the user to map "default" to an alternate
     # default branch in the destination repository.
     branch = branchmap.get(branch or b'default', branch)
     # At some point we used "None" literal to denote the default branch,
     # attempt to use that for backward compatibility.
     if not branch:
         branch = branchmap.get(b'None', branch)
     return branch
 
 
 source_converters = [
     (b'cvs', convert_cvs, b'branchsort'),
     (b'git', convert_git, b'branchsort'),
     (b'svn', svn_source, b'branchsort'),
     (b'hg', mercurial_source, b'sourcesort'),
     (b'darcs', darcs_source, b'branchsort'),
     (b'mtn', monotone_source, b'branchsort'),
     (b'gnuarch', gnuarch_source, b'branchsort'),
     (b'bzr', bzr_source, b'branchsort'),
     (b'p4', p4_source, b'branchsort'),
 ]
 
 sink_converters = [
     (b'hg', mercurial_sink),
     (b'svn', svn_sink),
 ]
 
 
 def convertsource(ui, path, type, revs):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise error.Abort(_(b'%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, name, path, revs), sortmode
         except (NoRepo, MissingTool) as inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write(b"%s\n" % pycompat.bytestr(inst.args[0]))
     raise error.Abort(_(b'%s: missing or unsupported repository') % path)
 
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise error.Abort(_(b'%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, name, path)
         except NoRepo as inst:
             ui.note(_(b"convert: %s\n") % inst)
         except MissingTool as inst:
             raise error.Abort(b'%s\n' % inst)
     raise error.Abort(_(b'%s: unknown repository type') % path)
 
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.progress = ui.makeprogress(
             _(b'getting files'), unit=_(b'files'), total=filecount
         )
 
     def getfile(self, file, rev):
         self.progress.increment(item=file)
         return self.source.getfile(file, rev)
 
     def targetfilebelongstosource(self, targetfilename):
         return self.source.targetfilebelongstosource(targetfilename)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.progress.complete()
 
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get(b'authormap'):
             self.readauthormap(opts.get(b'authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = self.parsesplicemap(opts.get(b'splicemap'))
         self.branchmap = mapfile(ui, opts.get(b'branchmap'))
 
     def parsesplicemap(self, path):
         """check and validate the splicemap format and
         return a child/parents dictionary.
         Format checking has two parts.
         1. generic format which is same across all source types
         2. specific format checking which may be different for
            different source type.  This logic is implemented in
            checkrevformat function in source files like
            hg.py, subversion.py etc.
         """
 
         if not path:
             return {}
         m = {}
         try:
             fp = open(path, b'rb')
-            for i, line in enumerate(util.iterfile(fp)):
+            for i, line in enumerate(fp):
                 line = line.splitlines()[0].rstrip()
                 if not line:
                     # Ignore blank lines
                     continue
                 # split line
                 lex = common.shlexer(data=line, whitespace=b',')
                 line = list(lex)
                 # check number of parents
                 if not (2 <= len(line) <= 3):
                     raise error.Abort(
                         _(
                             b'syntax error in %s(%d): child parent1'
                             b'[,parent2] expected'
                         )
                         % (path, i + 1)
                     )
                 for part in line:
                     self.source.checkrevformat(part)
                 child, p1, p2 = line[0], line[1:2], line[2:]
                 if p1 == p2:
                     m[child] = p1
                 else:
                     m[child] = p1 + p2
         # if file does not exist or error reading, exit
         except IOError:
             raise error.Abort(
                 _(b'splicemap file not found or error reading %s:') % path
             )
         return m
 
     def walktree(self, heads):
         """Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset."""
         visit = list(heads)
         known = set()
         parents = {}
         numcommits = self.source.numcommits()
         progress = self.ui.makeprogress(
             _(b'scanning'), unit=_(b'revisions'), total=numcommits
         )
         while visit:
             n = visit.pop(0)
             if n in known:
                 continue
             if n in self.map:
                 m = self.map[n]
                 if m == SKIPREV or self.dest.hascommitfrommap(m):
                     continue
             known.add(n)
             progress.update(len(known))
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         progress.complete()
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in sorted(splicemap):
             if c not in parents:
                 if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(
                         _(
                             b'splice map revision %s is not being '
                             b'converted, ignoring\n'
                         )
                         % c
                     )
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise error.Abort(_(b'unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         """Return an ordering such that every uncommitted changeset is
         preceded by all its uncommitted ancestors."""
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = collections.deque(sorted(parents))
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.popleft()
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
 
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
 
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
 
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
 
             return picknext
 
         def makeclosesorter():
             """Close order sort."""
             keyfn = lambda n: (
                 b'close' not in self.commitcache[n].extra,
                 self.commitcache[n].sortkey,
             )
 
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
 
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
 
             def getdate(n):
                 if n not in dates:
                     dates[n] = dateutil.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == b'branchsort':
             picknext = makebranchsorter()
         elif sortmode == b'datesort':
             picknext = makedatesorter()
         elif sortmode == b'sourcesort':
             picknext = makesourcesorter()
         elif sortmode == b'closesort':
             picknext = makeclosesorter()
         else:
             raise error.Abort(_(b'unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise error.Abort(
                         _(b'cycle detected between %s and %s')
                         % (recode(c), recode(n))
                     )
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise error.Abort(_(b"not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_(b'writing author map file %s\n') % authorfile)
             ofile = open(authorfile, b'wb+')
             for author in self.authors:
                 ofile.write(
                     util.tonativeeol(
                         b"%s=%s\n" % (author, self.authors[author])
                     )
                 )
             ofile.close()
 
     def readauthormap(self, authorfile):
         self.authors = readauthormap(self.ui, authorfile, self.authors)
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         commit.branch = mapbranch(commit.branch, self.branchmap)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         full = self.opts.get(b'full')
         changes = self.source.getchanges(rev, full)
         if isinstance(changes, bytes):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies, cleanp2 = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append(
                     (self.map[prev], self.commitcache[prev].branch)
                 )
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(
                 _(b'spliced in %s as parents of %s\n')
                 % (_(b' and ').join(parents), rev)
             )
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
             parents.extend(
                 self.map[x] for x in commit.optparents if x in self.map
             )
         if len(pbranches) != 2:
             cleanp2 = set()
         if len(parents) < 3:
             source = progresssource(self.ui, self.source, len(files))
         else:
             # For an octopus merge, we end up traversing the list of
             # changed files N-1 times. This tweak to the number of
             # files makes it so the progress bar doesn't overflow
             # itself.
             source = progresssource(
                 self.ui, self.source, len(files) * (len(parents) - 1)
             )
         newnode = self.dest.putcommit(
             files, copies, parents, commit, source, self.map, full, cleanp2
         )
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_(b"scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_(b"sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_(b"converting...\n"))
             progress = self.ui.makeprogress(
                 _(b'converting'), unit=_(b'revisions'), total=len(t)
             )
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if b"\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status(b"%d %s\n" % (num, recode(desc)))
                 self.ui.note(_(b"source: %s\n") % recode(c))
                 progress.update(i)
                 self.copy(c)
             progress.complete()
 
             if not self.ui.configbool(b'convert', b'skiptags'):
                 tags = self.source.gettags()
                 ctags = {}
                 for k in tags:
                     v = tags[k]
                     if self.map.get(v, SKIPREV) != SKIPREV:
                         ctags[k] = self.map[v]
 
                 if c and ctags:
                     nrev, tagsparent = self.dest.puttags(ctags)
                     if nrev and tagsparent:
                         # write another hash correspondence to override the
                         # previous one so we don't end up with extra tag heads
                         tagsparents = [
                             e for e in self.map.items() if e[1] == tagsparent
                         ]
                         if tagsparents:
                             self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     opts = pycompat.byteskwargs(opts)
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = b'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get(b'authormap'):
         opts[b'authormap'] = opts.get(b'authors')
 
     if not dest:
         dest = hg.defaultdest(src) + b"-hg"
         ui.status(_(b"assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get(b'dest_type'))
     destc = scmutil.wrapconvertsink(destc)
 
     try:
         srcc, defaultsort = convertsource(
             ui, src, opts.get(b'source_type'), opts.get(b'rev')
         )
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = (b'branchsort', b'datesort', b'sourcesort', b'closesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise error.Abort(_(b'more than one sort mode specified'))
     if sortmode:
         sortmode = sortmode[0]
     else:
         sortmode = defaultsort
 
     if sortmode == b'sourcesort' and not srcc.hasnativeorder():
         raise error.Abort(
             _(b'--sourcesort is not supported by this data source')
         )
     if sortmode == b'closesort' and not srcc.hasnativeclose():
         raise error.Abort(
             _(b'--closesort is not supported by this data source')
         )
 
     fmap = opts.get(b'filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         revmapfile = destc.revmapfile()
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)

mercurial/match.py

@@ -1,1655 +1,1655 b''
 # match.py - filename matching
 #
 #  Copyright 2008, 2009 Olivia Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import bisect
 import copy
 import itertools
 import os
 import re
 
 from .i18n import _
 from .pycompat import open
 from . import (
     encoding,
     error,
     pathutil,
     policy,
     pycompat,
     util,
 )
 from .utils import stringutil
 
 rustmod = policy.importrust('dirstate')
 
 allpatternkinds = (
     b're',
     b'glob',
     b'path',
     b'relglob',
     b'relpath',
     b'relre',
     b'rootglob',
     b'listfile',
     b'listfile0',
     b'set',
     b'include',
     b'subinclude',
     b'rootfilesin',
 )
 cwdrelativepatternkinds = (b'relpath', b'glob')
 
 propertycache = util.propertycache
 
 
 def _rematcher(regex):
     """compile the regexp with the best available regexp engine and return a
     matcher function"""
     m = util.re.compile(regex)
     try:
         # slightly faster, provided by facebook's re2 bindings
         return m.test_match
     except AttributeError:
         return m.match
 
 
 def _expandsets(cwd, kindpats, ctx=None, listsubrepos=False, badfn=None):
     '''Returns the kindpats list with the 'set' patterns expanded to matchers'''
     matchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == b'set':
             if ctx is None:
                 raise error.ProgrammingError(
                     b"fileset expression with no context"
                 )
             matchers.append(ctx.matchfileset(cwd, pat, badfn=badfn))
 
             if listsubrepos:
                 for subpath in ctx.substate:
                     sm = ctx.sub(subpath).matchfileset(cwd, pat, badfn=badfn)
                     pm = prefixdirmatcher(subpath, sm, badfn=badfn)
                     matchers.append(pm)
 
             continue
         other.append((kind, pat, source))
     return matchers, other
 
 
 def _expandsubinclude(kindpats, root):
     """Returns the list of subinclude matcher args and the kindpats without the
     subincludes in it."""
     relmatchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == b'subinclude':
             sourceroot = pathutil.dirname(util.normpath(source))
             pat = util.pconvert(pat)
             path = pathutil.join(sourceroot, pat)
 
             newroot = pathutil.dirname(path)
             matcherargs = (newroot, b'', [], [b'include:%s' % path])
 
             prefix = pathutil.canonpath(root, root, newroot)
             if prefix:
                 prefix += b'/'
             relmatchers.append((prefix, matcherargs))
         else:
             other.append((kind, pat, source))
 
     return relmatchers, other
 
 
 def _kindpatsalwaysmatch(kindpats):
     """Checks whether the kindspats match everything, as e.g.
     'relpath:.' does.
     """
     for kind, pat, source in kindpats:
         if pat != b'' or kind not in [b'relpath', b'glob']:
             return False
     return True
 
 
 def _buildkindpatsmatcher(
     matchercls,
     root,
     cwd,
     kindpats,
     ctx=None,
     listsubrepos=False,
     badfn=None,
 ):
     matchers = []
     fms, kindpats = _expandsets(
         cwd,
         kindpats,
         ctx=ctx,
         listsubrepos=listsubrepos,
         badfn=badfn,
     )
     if kindpats:
         m = matchercls(root, kindpats, badfn=badfn)
         matchers.append(m)
     if fms:
         matchers.extend(fms)
     if not matchers:
         return nevermatcher(badfn=badfn)
     if len(matchers) == 1:
         return matchers[0]
     return unionmatcher(matchers)
 
 
 def match(
     root,
     cwd,
     patterns=None,
     include=None,
     exclude=None,
     default=b'glob',
     auditor=None,
     ctx=None,
     listsubrepos=False,
     warn=None,
     badfn=None,
     icasefs=False,
 ):
     r"""build an object to match a set of file patterns
 
     arguments:
     root - the canonical root of the tree you're matching against
     cwd - the current working directory, if relevant
     patterns - patterns to find
     include - patterns to include (unless they are excluded)
     exclude - patterns to exclude (even if they are included)
     default - if a pattern in patterns has no explicit type, assume this one
     auditor - optional path auditor
     ctx - optional changecontext
     listsubrepos - if True, recurse into subrepositories
     warn - optional function used for printing warnings
     badfn - optional bad() callback for this matcher instead of the default
     icasefs - make a matcher for wdir on case insensitive filesystems, which
         normalizes the given patterns to the case in the filesystem
 
     a pattern is one of:
     'glob:<glob>' - a glob relative to cwd
     're:<regexp>' - a regular expression
     'path:<path>' - a path relative to repository root, which is matched
                     recursively
     'rootfilesin:<path>' - a path relative to repository root, which is
                     matched non-recursively (will not match subdirectories)
     'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
     'relpath:<path>' - a path relative to cwd
     'relre:<regexp>' - a regexp that needn't match the start of a name
     'set:<fileset>' - a fileset expression
     'include:<path>' - a file of patterns to read and include
     'subinclude:<path>' - a file of patterns to match against files under
                           the same directory
     '<something>' - a pattern of the specified default type
 
     >>> def _match(root, *args, **kwargs):
     ...     return match(util.localpath(root), *args, **kwargs)
 
     Usually a patternmatcher is returned:
     >>> _match(b'/foo', b'.', [b're:.*\.c$', b'path:foo/a', b'*.py'])
     <patternmatcher patterns='.*\\.c$|foo/a(?:/|$)|[^/]*\\.py$'>
 
     Combining 'patterns' with 'include' (resp. 'exclude') gives an
     intersectionmatcher (resp. a differencematcher):
     >>> type(_match(b'/foo', b'.', [b're:.*\.c$'], include=[b'path:lib']))
     <class 'mercurial.match.intersectionmatcher'>
     >>> type(_match(b'/foo', b'.', [b're:.*\.c$'], exclude=[b'path:build']))
     <class 'mercurial.match.differencematcher'>
 
     Notice that, if 'patterns' is empty, an alwaysmatcher is returned:
     >>> _match(b'/foo', b'.', [])
     <alwaysmatcher>
 
     The 'default' argument determines which kind of pattern is assumed if a
     pattern has no prefix:
     >>> _match(b'/foo', b'.', [b'.*\.c$'], default=b're')
     <patternmatcher patterns='.*\\.c$'>
     >>> _match(b'/foo', b'.', [b'main.py'], default=b'relpath')
     <patternmatcher patterns='main\\.py(?:/|$)'>
     >>> _match(b'/foo', b'.', [b'main.py'], default=b're')
     <patternmatcher patterns='main.py'>
 
     The primary use of matchers is to check whether a value (usually a file
     name) matches againset one of the patterns given at initialization. There
     are two ways of doing this check.
 
     >>> m = _match(b'/foo', b'', [b're:.*\.c$', b'relpath:a'])
 
     1. Calling the matcher with a file name returns True if any pattern
     matches that file name:
     >>> m(b'a')
     True
     >>> m(b'main.c')
     True
     >>> m(b'test.py')
     False
 
     2. Using the exact() method only returns True if the file name matches one
     of the exact patterns (i.e. not re: or glob: patterns):
     >>> m.exact(b'a')
     True
     >>> m.exact(b'main.c')
     False
     """
     assert os.path.isabs(root)
     cwd = os.path.join(root, util.localpath(cwd))
     normalize = _donormalize
     if icasefs:
         dirstate = ctx.repo().dirstate
         dsnormalize = dirstate.normalize
 
         def normalize(patterns, default, root, cwd, auditor, warn):
             kp = _donormalize(patterns, default, root, cwd, auditor, warn)
             kindpats = []
             for kind, pats, source in kp:
                 if kind not in (b're', b'relre'):  # regex can't be normalized
                     p = pats
                     pats = dsnormalize(pats)
 
                     # Preserve the original to handle a case only rename.
                     if p != pats and p in dirstate:
                         kindpats.append((kind, p, source))
 
                 kindpats.append((kind, pats, source))
             return kindpats
 
     if patterns:
         kindpats = normalize(patterns, default, root, cwd, auditor, warn)
         if _kindpatsalwaysmatch(kindpats):
             m = alwaysmatcher(badfn)
         else:
             m = _buildkindpatsmatcher(
                 patternmatcher,
                 root,
                 cwd,
                 kindpats,
                 ctx=ctx,
                 listsubrepos=listsubrepos,
                 badfn=badfn,
             )
     else:
         # It's a little strange that no patterns means to match everything.
         # Consider changing this to match nothing (probably using nevermatcher).
         m = alwaysmatcher(badfn)
 
     if include:
         kindpats = normalize(include, b'glob', root, cwd, auditor, warn)
         im = _buildkindpatsmatcher(
             includematcher,
             root,
             cwd,
             kindpats,
             ctx=ctx,
             listsubrepos=listsubrepos,
             badfn=None,
         )
         m = intersectmatchers(m, im)
     if exclude:
         kindpats = normalize(exclude, b'glob', root, cwd, auditor, warn)
         em = _buildkindpatsmatcher(
             includematcher,
             root,
             cwd,
             kindpats,
             ctx=ctx,
             listsubrepos=listsubrepos,
             badfn=None,
         )
         m = differencematcher(m, em)
     return m
 
 
 def exact(files, badfn=None):
     return exactmatcher(files, badfn=badfn)
 
 
 def always(badfn=None):
     return alwaysmatcher(badfn)
 
 
 def never(badfn=None):
     return nevermatcher(badfn)
 
 
 def badmatch(match, badfn):
     """Make a copy of the given matcher, replacing its bad method with the given
     one.
     """
     m = copy.copy(match)
     m.bad = badfn
     return m
 
 
 def _donormalize(patterns, default, root, cwd, auditor=None, warn=None):
     """Convert 'kind:pat' from the patterns list to tuples with kind and
     normalized and rooted patterns and with listfiles expanded."""
     kindpats = []
     for kind, pat in [_patsplit(p, default) for p in patterns]:
         if kind in cwdrelativepatternkinds:
             pat = pathutil.canonpath(root, cwd, pat, auditor=auditor)
         elif kind in (b'relglob', b'path', b'rootfilesin', b'rootglob'):
             pat = util.normpath(pat)
         elif kind in (b'listfile', b'listfile0'):
             try:
                 files = util.readfile(pat)
                 if kind == b'listfile0':
                     files = files.split(b'\0')
                 else:
                     files = files.splitlines()
                 files = [f for f in files if f]
             except EnvironmentError:
                 raise error.Abort(_(b"unable to read file list (%s)") % pat)
             for k, p, source in _donormalize(
                 files, default, root, cwd, auditor, warn
             ):
                 kindpats.append((k, p, pat))
             continue
         elif kind == b'include':
             try:
                 fullpath = os.path.join(root, util.localpath(pat))
                 includepats = readpatternfile(fullpath, warn)
                 for k, p, source in _donormalize(
                     includepats, default, root, cwd, auditor, warn
                 ):
                     kindpats.append((k, p, source or pat))
             except error.Abort as inst:
                 raise error.Abort(
                     b'%s: %s'
                     % (
                         pat,
                         inst.message,
                     )  # pytype: disable=unsupported-operands
                 )
             except IOError as inst:
                 if warn:
                     warn(
                         _(b"skipping unreadable pattern file '%s': %s\n")
                         % (pat, stringutil.forcebytestr(inst.strerror))
                     )
             continue
         # else: re or relre - which cannot be normalized
         kindpats.append((kind, pat, b''))
     return kindpats
 
 
 class basematcher(object):
     def __init__(self, badfn=None):
         if badfn is not None:
             self.bad = badfn
 
     def __call__(self, fn):
         return self.matchfn(fn)
 
     # Callbacks related to how the matcher is used by dirstate.walk.
     # Subscribers to these events must monkeypatch the matcher object.
     def bad(self, f, msg):
         """Callback from dirstate.walk for each explicit file that can't be
         found/accessed, with an error message."""
 
     # If an traversedir is set, it will be called when a directory discovered
     # by recursive traversal is visited.
     traversedir = None
 
     @propertycache
     def _files(self):
         return []
 
     def files(self):
         """Explicitly listed files or patterns or roots:
         if no patterns or .always(): empty list,
         if exact: list exact files,
         if not .anypats(): list all files and dirs,
         else: optimal roots"""
         return self._files
 
     @propertycache
     def _fileset(self):
         return set(self._files)
 
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fileset
 
     def matchfn(self, f):
         return False
 
     def visitdir(self, dir):
         """Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories. This is
         based on the match's primary, included, and excluded patterns.
 
         Returns the string 'all' if the given directory and all subdirectories
         should be visited. Otherwise returns True or False indicating whether
         the given directory should be visited.
         """
         return True
 
     def visitchildrenset(self, dir):
         """Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories, and
         potentially lists which subdirectories of that directory should be
         visited. This is based on the match's primary, included, and excluded
         patterns.
 
         This function is very similar to 'visitdir', and the following mapping
         can be applied:
 
              visitdir | visitchildrenlist
             ----------+-------------------
              False    | set()
              'all'    | 'all'
              True     | 'this' OR non-empty set of subdirs -or files- to visit
 
         Example:
           Assume matchers ['path:foo/bar', 'rootfilesin:qux'], we would return
           the following values (assuming the implementation of visitchildrenset
           is capable of recognizing this; some implementations are not).
 
           '' -> {'foo', 'qux'}
           'baz' -> set()
           'foo' -> {'bar'}
           # Ideally this would be 'all', but since the prefix nature of matchers
           # is applied to the entire matcher, we have to downgrade this to
           # 'this' due to the non-prefix 'rootfilesin'-kind matcher being mixed
           # in.
           'foo/bar' -> 'this'
           'qux' -> 'this'
 
         Important:
           Most matchers do not know if they're representing files or
           directories. They see ['path:dir/f'] and don't know whether 'f' is a
           file or a directory, so visitchildrenset('dir') for most matchers will
           return {'f'}, but if the matcher knows it's a file (like exactmatcher
           does), it may return 'this'. Do not rely on the return being a set
           indicating that there are no files in this dir to investigate (or
           equivalently that if there are files to investigate in 'dir' that it
           will always return 'this').
         """
         return b'this'
 
     def always(self):
         """Matcher will match everything and .files() will be empty --
         optimization might be possible."""
         return False
 
     def isexact(self):
         """Matcher will match exactly the list of files in .files() --
         optimization might be possible."""
         return False
 
     def prefix(self):
         """Matcher will match the paths in .files() recursively --
         optimization might be possible."""
         return False
 
     def anypats(self):
         """None of .always(), .isexact(), and .prefix() is true --
         optimizations will be difficult."""
         return not self.always() and not self.isexact() and not self.prefix()
 
 
 class alwaysmatcher(basematcher):
     '''Matches everything.'''
 
     def __init__(self, badfn=None):
         super(alwaysmatcher, self).__init__(badfn)
 
     def always(self):
         return True
 
     def matchfn(self, f):
         return True
 
     def visitdir(self, dir):
         return b'all'
 
     def visitchildrenset(self, dir):
         return b'all'
 
     def __repr__(self):
         return r'<alwaysmatcher>'
 
 
 class nevermatcher(basematcher):
     '''Matches nothing.'''
 
     def __init__(self, badfn=None):
         super(nevermatcher, self).__init__(badfn)
 
     # It's a little weird to say that the nevermatcher is an exact matcher
     # or a prefix matcher, but it seems to make sense to let callers take
     # fast paths based on either. There will be no exact matches, nor any
     # prefixes (files() returns []), so fast paths iterating over them should
     # be efficient (and correct).
     def isexact(self):
         return True
 
     def prefix(self):
         return True
 
     def visitdir(self, dir):
         return False
 
     def visitchildrenset(self, dir):
         return set()
 
     def __repr__(self):
         return r'<nevermatcher>'
 
 
 class predicatematcher(basematcher):
     """A matcher adapter for a simple boolean function"""
 
     def __init__(self, predfn, predrepr=None, badfn=None):
         super(predicatematcher, self).__init__(badfn)
         self.matchfn = predfn
         self._predrepr = predrepr
 
     @encoding.strmethod
     def __repr__(self):
         s = stringutil.buildrepr(self._predrepr) or pycompat.byterepr(
             self.matchfn
         )
         return b'<predicatenmatcher pred=%s>' % s
 
 
 def path_or_parents_in_set(path, prefix_set):
     """Returns True if `path` (or any parent of `path`) is in `prefix_set`."""
     l = len(prefix_set)
     if l == 0:
         return False
     if path in prefix_set:
         return True
     # If there's more than 5 paths in prefix_set, it's *probably* quicker to
     # "walk up" the directory hierarchy instead, with the assumption that most
     # directory hierarchies are relatively shallow and hash lookup is cheap.
     if l > 5:
         return any(
             parentdir in prefix_set for parentdir in pathutil.finddirs(path)
         )
 
     # FIXME: Ideally we'd never get to this point if this is the case - we'd
     # recognize ourselves as an 'always' matcher and skip this.
     if b'' in prefix_set:
         return True
 
     sl = ord(b'/')
 
     # We already checked that path isn't in prefix_set exactly, so
     # `path[len(pf)] should never raise IndexError.
     return any(path.startswith(pf) and path[len(pf)] == sl for pf in prefix_set)
 
 
 class patternmatcher(basematcher):
     r"""Matches a set of (kind, pat, source) against a 'root' directory.
 
     >>> kindpats = [
     ...     (b're', br'.*\.c$', b''),
     ...     (b'path', b'foo/a', b''),
     ...     (b'relpath', b'b', b''),
     ...     (b'glob', b'*.h', b''),
     ... ]
     >>> m = patternmatcher(b'foo', kindpats)
     >>> m(b'main.c')  # matches re:.*\.c$
     True
     >>> m(b'b.txt')
     False
     >>> m(b'foo/a')  # matches path:foo/a
     True
     >>> m(b'a')  # does not match path:b, since 'root' is 'foo'
     False
     >>> m(b'b')  # matches relpath:b, since 'root' is 'foo'
     True
     >>> m(b'lib.h')  # matches glob:*.h
     True
 
     >>> m.files()
     ['', 'foo/a', 'b', '']
     >>> m.exact(b'foo/a')
     True
     >>> m.exact(b'b')
     True
     >>> m.exact(b'lib.h')  # exact matches are for (rel)path kinds
     False
     """
 
     def __init__(self, root, kindpats, badfn=None):
         super(patternmatcher, self).__init__(badfn)
 
         self._files = _explicitfiles(kindpats)
         self._prefix = _prefix(kindpats)
         self._pats, self.matchfn = _buildmatch(kindpats, b'$', root)
 
     @propertycache
     def _dirs(self):
         return set(pathutil.dirs(self._fileset))
 
     def visitdir(self, dir):
         if self._prefix and dir in self._fileset:
             return b'all'
         return dir in self._dirs or path_or_parents_in_set(dir, self._fileset)
 
     def visitchildrenset(self, dir):
         ret = self.visitdir(dir)
         if ret is True:
             return b'this'
         elif not ret:
             return set()
         assert ret == b'all'
         return b'all'
 
     def prefix(self):
         return self._prefix
 
     @encoding.strmethod
     def __repr__(self):
         return b'<patternmatcher patterns=%r>' % pycompat.bytestr(self._pats)
 
 
 # This is basically a reimplementation of pathutil.dirs that stores the
 # children instead of just a count of them, plus a small optional optimization
 # to avoid some directories we don't need.
 class _dirchildren(object):
     def __init__(self, paths, onlyinclude=None):
         self._dirs = {}
         self._onlyinclude = onlyinclude or []
         addpath = self.addpath
         for f in paths:
             addpath(f)
 
     def addpath(self, path):
         if path == b'':
             return
         dirs = self._dirs
         findsplitdirs = _dirchildren._findsplitdirs
         for d, b in findsplitdirs(path):
             if d not in self._onlyinclude:
                 continue
             dirs.setdefault(d, set()).add(b)
 
     @staticmethod
     def _findsplitdirs(path):
         # yields (dirname, basename) tuples, walking back to the root.  This is
         # very similar to pathutil.finddirs, except:
         #  - produces a (dirname, basename) tuple, not just 'dirname'
         # Unlike manifest._splittopdir, this does not suffix `dirname` with a
         # slash.
         oldpos = len(path)
         pos = path.rfind(b'/')
         while pos != -1:
             yield path[:pos], path[pos + 1 : oldpos]
             oldpos = pos
             pos = path.rfind(b'/', 0, pos)
         yield b'', path[:oldpos]
 
     def get(self, path):
         return self._dirs.get(path, set())
 
 
 class includematcher(basematcher):
     def __init__(self, root, kindpats, badfn=None):
         super(includematcher, self).__init__(badfn)
         if rustmod is not None:
             # We need to pass the patterns to Rust because they can contain
             # patterns from the user interface
             self._kindpats = kindpats
         self._pats, self.matchfn = _buildmatch(kindpats, b'(?:/|$)', root)
         self._prefix = _prefix(kindpats)
         roots, dirs, parents = _rootsdirsandparents(kindpats)
         # roots are directories which are recursively included.
         self._roots = set(roots)
         # dirs are directories which are non-recursively included.
         self._dirs = set(dirs)
         # parents are directories which are non-recursively included because
         # they are needed to get to items in _dirs or _roots.
         self._parents = parents
 
     def visitdir(self, dir):
         if self._prefix and dir in self._roots:
             return b'all'
         return (
             dir in self._dirs
             or dir in self._parents
             or path_or_parents_in_set(dir, self._roots)
         )
 
     @propertycache
     def _allparentschildren(self):
         # It may seem odd that we add dirs, roots, and parents, and then
         # restrict to only parents. This is to catch the case of:
         #   dirs = ['foo/bar']
         #   parents = ['foo']
         # if we asked for the children of 'foo', but had only added
         # self._parents, we wouldn't be able to respond ['bar'].
         return _dirchildren(
             itertools.chain(self._dirs, self._roots, self._parents),
             onlyinclude=self._parents,
         )
 
     def visitchildrenset(self, dir):
         if self._prefix and dir in self._roots:
             return b'all'
         # Note: this does *not* include the 'dir in self._parents' case from
         # visitdir, that's handled below.
         if (
             b'' in self._roots
             or dir in self._dirs
             or path_or_parents_in_set(dir, self._roots)
         ):
             return b'this'
 
         if dir in self._parents:
             return self._allparentschildren.get(dir) or set()
         return set()
 
     @encoding.strmethod
     def __repr__(self):
         return b'<includematcher includes=%r>' % pycompat.bytestr(self._pats)
 
 
 class exactmatcher(basematcher):
     r"""Matches the input files exactly. They are interpreted as paths, not
     patterns (so no kind-prefixes).
 
     >>> m = exactmatcher([b'a.txt', br're:.*\.c$'])
     >>> m(b'a.txt')
     True
     >>> m(b'b.txt')
     False
 
     Input files that would be matched are exactly those returned by .files()
     >>> m.files()
     ['a.txt', 're:.*\\.c$']
 
     So pattern 're:.*\.c$' is not considered as a regex, but as a file name
     >>> m(b'main.c')
     False
     >>> m(br're:.*\.c$')
     True
     """
 
     def __init__(self, files, badfn=None):
         super(exactmatcher, self).__init__(badfn)
 
         if isinstance(files, list):
             self._files = files
         else:
             self._files = list(files)
 
     matchfn = basematcher.exact
 
     @propertycache
     def _dirs(self):
         return set(pathutil.dirs(self._fileset))
 
     def visitdir(self, dir):
         return dir in self._dirs
 
     @propertycache
     def _visitchildrenset_candidates(self):
         """A memoized set of candidates for visitchildrenset."""
         return self._fileset | self._dirs - {b''}
 
     @propertycache
     def _sorted_visitchildrenset_candidates(self):
         """A memoized sorted list of candidates for visitchildrenset."""
         return sorted(self._visitchildrenset_candidates)
 
     def visitchildrenset(self, dir):
         if not self._fileset or dir not in self._dirs:
             return set()
 
         if dir == b'':
             candidates = self._visitchildrenset_candidates
         else:
             candidates = self._sorted_visitchildrenset_candidates
             d = dir + b'/'
             # Use bisect to find the first element potentially starting with d
             # (i.e. >= d). This should always find at least one element (we'll
             # assert later if this is not the case).
             first = bisect.bisect_left(candidates, d)
             # We need a representation of the first element that is > d that
             # does not start with d, so since we added a `/` on the end of dir,
             # we'll add whatever comes after slash (we could probably assume
             # that `0` is after `/`, but let's not) to the end of dir instead.
             dnext = dir + encoding.strtolocal(chr(ord(b'/') + 1))
             # Use bisect to find the first element >= d_next
             last = bisect.bisect_left(candidates, dnext, lo=first)
             dlen = len(d)
             candidates = {c[dlen:] for c in candidates[first:last]}
         # self._dirs includes all of the directories, recursively, so if
         # we're attempting to match foo/bar/baz.txt, it'll have '', 'foo',
         # 'foo/bar' in it. Thus we can safely ignore a candidate that has a
         # '/' in it, indicating a it's for a subdir-of-a-subdir; the
         # immediate subdir will be in there without a slash.
         ret = {c for c in candidates if b'/' not in c}
         # We really do not expect ret to be empty, since that would imply that
         # there's something in _dirs that didn't have a file in _fileset.
         assert ret
         return ret
 
     def isexact(self):
         return True
 
     @encoding.strmethod
     def __repr__(self):
         return b'<exactmatcher files=%r>' % self._files
 
 
 class differencematcher(basematcher):
     """Composes two matchers by matching if the first matches and the second
     does not.
 
     The second matcher's non-matching-attributes (bad, traversedir) are ignored.
     """
 
     def __init__(self, m1, m2):
         super(differencematcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.traversedir = m1.traversedir
 
     def matchfn(self, f):
         return self._m1(f) and not self._m2(f)
 
     @propertycache
     def _files(self):
         if self.isexact():
             return [f for f in self._m1.files() if self(f)]
         # If m1 is not an exact matcher, we can't easily figure out the set of
         # files, because its files() are not always files. For example, if
         # m1 is "path:dir" and m2 is "rootfileins:.", we don't
         # want to remove "dir" from the set even though it would match m2,
         # because the "dir" in m1 may not be a file.
         return self._m1.files()
 
     def visitdir(self, dir):
         if self._m2.visitdir(dir) == b'all':
             return False
         elif not self._m2.visitdir(dir):
             # m2 does not match dir, we can return 'all' here if possible
             return self._m1.visitdir(dir)
         return bool(self._m1.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m2_set = self._m2.visitchildrenset(dir)
         if m2_set == b'all':
             return set()
         m1_set = self._m1.visitchildrenset(dir)
         # Possible values for m1: 'all', 'this', set(...), set()
         # Possible values for m2:        'this', set(...), set()
         # If m2 has nothing under here that we care about, return m1, even if
         # it's 'all'. This is a change in behavior from visitdir, which would
         # return True, not 'all', for some reason.
         if not m2_set:
             return m1_set
         if m1_set in [b'all', b'this']:
             # Never return 'all' here if m2_set is any kind of non-empty (either
             # 'this' or set(foo)), since m2 might return set() for a
             # subdirectory.
             return b'this'
         # Possible values for m1:         set(...), set()
         # Possible values for m2: 'this', set(...)
         # We ignore m2's set results. They're possibly incorrect:
         #  m1 = path:dir/subdir, m2=rootfilesin:dir, visitchildrenset(''):
         #    m1 returns {'dir'}, m2 returns {'dir'}, if we subtracted we'd
         #    return set(), which is *not* correct, we still need to visit 'dir'!
         return m1_set
 
     def isexact(self):
         return self._m1.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return b'<differencematcher m1=%r, m2=%r>' % (self._m1, self._m2)
 
 
 def intersectmatchers(m1, m2):
     """Composes two matchers by matching if both of them match.
 
     The second matcher's non-matching-attributes (bad, traversedir) are ignored.
     """
     if m1 is None or m2 is None:
         return m1 or m2
     if m1.always():
         m = copy.copy(m2)
         # TODO: Consider encapsulating these things in a class so there's only
         # one thing to copy from m1.
         m.bad = m1.bad
         m.traversedir = m1.traversedir
         return m
     if m2.always():
         m = copy.copy(m1)
         return m
     return intersectionmatcher(m1, m2)
 
 
 class intersectionmatcher(basematcher):
     def __init__(self, m1, m2):
         super(intersectionmatcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.traversedir = m1.traversedir
 
     @propertycache
     def _files(self):
         if self.isexact():
             m1, m2 = self._m1, self._m2
             if not m1.isexact():
                 m1, m2 = m2, m1
             return [f for f in m1.files() if m2(f)]
         # It neither m1 nor m2 is an exact matcher, we can't easily intersect
         # the set of files, because their files() are not always files. For
         # example, if intersecting a matcher "-I glob:foo.txt" with matcher of
         # "path:dir2", we don't want to remove "dir2" from the set.
         return self._m1.files() + self._m2.files()
 
     def matchfn(self, f):
         return self._m1(f) and self._m2(f)
 
     def visitdir(self, dir):
         visit1 = self._m1.visitdir(dir)
         if visit1 == b'all':
             return self._m2.visitdir(dir)
         # bool() because visit1=True + visit2='all' should not be 'all'
         return bool(visit1 and self._m2.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m1_set = self._m1.visitchildrenset(dir)
         if not m1_set:
             return set()
         m2_set = self._m2.visitchildrenset(dir)
         if not m2_set:
             return set()
 
         if m1_set == b'all':
             return m2_set
         elif m2_set == b'all':
             return m1_set
 
         if m1_set == b'this' or m2_set == b'this':
             return b'this'
 
         assert isinstance(m1_set, set) and isinstance(m2_set, set)
         return m1_set.intersection(m2_set)
 
     def always(self):
         return self._m1.always() and self._m2.always()
 
     def isexact(self):
         return self._m1.isexact() or self._m2.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return b'<intersectionmatcher m1=%r, m2=%r>' % (self._m1, self._m2)
 
 
 class subdirmatcher(basematcher):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> from . import pycompat
     >>> m1 = match(util.localpath(b'/root'), b'', [b'a.txt', b'sub/b.txt'], auditor=lambda name: None)
     >>> m2 = subdirmatcher(b'sub', m1)
     >>> m2(b'a.txt')
     False
     >>> m2(b'b.txt')
     True
     >>> m2.matchfn(b'a.txt')
     False
     >>> m2.matchfn(b'b.txt')
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact(b'b.txt')
     True
     >>> def bad(f, msg):
     ...     print(pycompat.sysstr(b"%s: %s" % (f, msg)))
     >>> m1.bad = bad
     >>> m2.bad(b'x.txt', b'No such file')
     sub/x.txt: No such file
     """
 
     def __init__(self, path, matcher):
         super(subdirmatcher, self).__init__()
         self._path = path
         self._matcher = matcher
         self._always = matcher.always()
 
         self._files = [
             f[len(path) + 1 :]
             for f in matcher._files
             if f.startswith(path + b"/")
         ]
 
         # If the parent repo had a path to this subrepo and the matcher is
         # a prefix matcher, this submatcher always matches.
         if matcher.prefix():
             self._always = any(f == path for f in matcher._files)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + b"/" + f, msg)
 
     def matchfn(self, f):
         # Some information is lost in the superclass's constructor, so we
         # can not accurately create the matching function for the subdirectory
         # from the inputs. Instead, we override matchfn() and visitdir() to
         # call the original matcher with the subdirectory path prepended.
         return self._matcher.matchfn(self._path + b"/" + f)
 
     def visitdir(self, dir):
         if dir == b'':
             dir = self._path
         else:
             dir = self._path + b"/" + dir
         return self._matcher.visitdir(dir)
 
     def visitchildrenset(self, dir):
         if dir == b'':
             dir = self._path
         else:
             dir = self._path + b"/" + dir
         return self._matcher.visitchildrenset(dir)
 
     def always(self):
         return self._always
 
     def prefix(self):
         return self._matcher.prefix() and not self._always
 
     @encoding.strmethod
     def __repr__(self):
         return b'<subdirmatcher path=%r, matcher=%r>' % (
             self._path,
             self._matcher,
         )
 
 
 class prefixdirmatcher(basematcher):
     """Adapt a matcher to work on a parent directory.
 
     The matcher's non-matching-attributes (bad, traversedir) are ignored.
 
     The prefix path should usually be the relative path from the root of
     this matcher to the root of the wrapped matcher.
 
     >>> m1 = match(util.localpath(b'/root/d/e'), b'f', [b'../a.txt', b'b.txt'], auditor=lambda name: None)
     >>> m2 = prefixdirmatcher(b'd/e', m1)
     >>> m2(b'a.txt')
     False
     >>> m2(b'd/e/a.txt')
     True
     >>> m2(b'd/e/b.txt')
     False
     >>> m2.files()
     ['d/e/a.txt', 'd/e/f/b.txt']
     >>> m2.exact(b'd/e/a.txt')
     True
     >>> m2.visitdir(b'd')
     True
     >>> m2.visitdir(b'd/e')
     True
     >>> m2.visitdir(b'd/e/f')
     True
     >>> m2.visitdir(b'd/e/g')
     False
     >>> m2.visitdir(b'd/ef')
     False
     """
 
     def __init__(self, path, matcher, badfn=None):
         super(prefixdirmatcher, self).__init__(badfn)
         if not path:
             raise error.ProgrammingError(b'prefix path must not be empty')
         self._path = path
         self._pathprefix = path + b'/'
         self._matcher = matcher
 
     @propertycache
     def _files(self):
         return [self._pathprefix + f for f in self._matcher._files]
 
     def matchfn(self, f):
         if not f.startswith(self._pathprefix):
             return False
         return self._matcher.matchfn(f[len(self._pathprefix) :])
 
     @propertycache
     def _pathdirs(self):
         return set(pathutil.finddirs(self._path))
 
     def visitdir(self, dir):
         if dir == self._path:
             return self._matcher.visitdir(b'')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitdir(dir[len(self._pathprefix) :])
         return dir in self._pathdirs
 
     def visitchildrenset(self, dir):
         if dir == self._path:
             return self._matcher.visitchildrenset(b'')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitchildrenset(dir[len(self._pathprefix) :])
         if dir in self._pathdirs:
             return b'this'
         return set()
 
     def isexact(self):
         return self._matcher.isexact()
 
     def prefix(self):
         return self._matcher.prefix()
 
     @encoding.strmethod
     def __repr__(self):
         return b'<prefixdirmatcher path=%r, matcher=%r>' % (
             pycompat.bytestr(self._path),
             self._matcher,
         )
 
 
 class unionmatcher(basematcher):
     """A matcher that is the union of several matchers.
 
     The non-matching-attributes (bad, traversedir) are taken from the first
     matcher.
     """
 
     def __init__(self, matchers):
         m1 = matchers[0]
         super(unionmatcher, self).__init__()
         self.traversedir = m1.traversedir
         self._matchers = matchers
 
     def matchfn(self, f):
         for match in self._matchers:
             if match(f):
                 return True
         return False
 
     def visitdir(self, dir):
         r = False
         for m in self._matchers:
             v = m.visitdir(dir)
             if v == b'all':
                 return v
             r |= v
         return r
 
     def visitchildrenset(self, dir):
         r = set()
         this = False
         for m in self._matchers:
             v = m.visitchildrenset(dir)
             if not v:
                 continue
             if v == b'all':
                 return v
             if this or v == b'this':
                 this = True
                 # don't break, we might have an 'all' in here.
                 continue
             assert isinstance(v, set)
             r = r.union(v)
         if this:
             return b'this'
         return r
 
     @encoding.strmethod
     def __repr__(self):
         return b'<unionmatcher matchers=%r>' % self._matchers
 
 
 def patkind(pattern, default=None):
     r"""If pattern is 'kind:pat' with a known kind, return kind.
 
     >>> patkind(br're:.*\.c$')
     're'
     >>> patkind(b'glob:*.c')
     'glob'
     >>> patkind(b'relpath:test.py')
     'relpath'
     >>> patkind(b'main.py')
     >>> patkind(b'main.py', default=b're')
     're'
     """
     return _patsplit(pattern, default)[0]
 
 
 def _patsplit(pattern, default):
     """Split a string into the optional pattern kind prefix and the actual
     pattern."""
     if b':' in pattern:
         kind, pat = pattern.split(b':', 1)
         if kind in allpatternkinds:
             return kind, pat
     return default, pattern
 
 
 def _globre(pat):
     r"""Convert an extended glob string to a regexp string.
 
     >>> from . import pycompat
     >>> def bprint(s):
     ...     print(pycompat.sysstr(s))
     >>> bprint(_globre(br'?'))
     .
     >>> bprint(_globre(br'*'))
     [^/]*
     >>> bprint(_globre(br'**'))
     .*
     >>> bprint(_globre(br'**/a'))
     (?:.*/)?a
     >>> bprint(_globre(br'a/**/b'))
     a/(?:.*/)?b
     >>> bprint(_globre(br'[a*?!^][^b][!c]'))
     [a*?!^][\^b][^c]
     >>> bprint(_globre(br'{a,b}'))
     (?:a|b)
     >>> bprint(_globre(br'.\*\?'))
     \.\*\?
     """
     i, n = 0, len(pat)
     res = b''
     group = 0
     escape = util.stringutil.regexbytesescapemap.get
 
     def peek():
         return i < n and pat[i : i + 1]
 
     while i < n:
         c = pat[i : i + 1]
         i += 1
         if c not in b'*?[{},\\':
             res += escape(c, c)
         elif c == b'*':
             if peek() == b'*':
                 i += 1
                 if peek() == b'/':
                     i += 1
                     res += b'(?:.*/)?'
                 else:
                     res += b'.*'
             else:
                 res += b'[^/]*'
         elif c == b'?':
             res += b'.'
         elif c == b'[':
             j = i
             if j < n and pat[j : j + 1] in b'!]':
                 j += 1
             while j < n and pat[j : j + 1] != b']':
                 j += 1
             if j >= n:
                 res += b'\\['
             else:
                 stuff = pat[i:j].replace(b'\\', b'\\\\')
                 i = j + 1
                 if stuff[0:1] == b'!':
                     stuff = b'^' + stuff[1:]
                 elif stuff[0:1] == b'^':
                     stuff = b'\\' + stuff
                 res = b'%s[%s]' % (res, stuff)
         elif c == b'{':
             group += 1
             res += b'(?:'
         elif c == b'}' and group:
             res += b')'
             group -= 1
         elif c == b',' and group:
             res += b'|'
         elif c == b'\\':
             p = peek()
             if p:
                 i += 1
                 res += escape(p, p)
             else:
                 res += escape(c, c)
         else:
             res += escape(c, c)
     return res
 
 
 def _regex(kind, pat, globsuffix):
     """Convert a (normalized) pattern of any kind into a
     regular expression.
     globsuffix is appended to the regexp of globs."""
     if not pat and kind in (b'glob', b'relpath'):
         return b''
     if kind == b're':
         return pat
     if kind in (b'path', b'relpath'):
         if pat == b'.':
             return b''
         return util.stringutil.reescape(pat) + b'(?:/|$)'
     if kind == b'rootfilesin':
         if pat == b'.':
             escaped = b''
         else:
             # Pattern is a directory name.
             escaped = util.stringutil.reescape(pat) + b'/'
         # Anything after the pattern must be a non-directory.
         return escaped + b'[^/]+$'
     if kind == b'relglob':
         globre = _globre(pat)
         if globre.startswith(b'[^/]*'):
             # When pat has the form *XYZ (common), make the returned regex more
             # legible by returning the regex for **XYZ instead of **/*XYZ.
             return b'.*' + globre[len(b'[^/]*') :] + globsuffix
         return b'(?:|.*/)' + globre + globsuffix
     if kind == b'relre':
         if pat.startswith(b'^'):
             return pat
         return b'.*' + pat
     if kind in (b'glob', b'rootglob'):
         return _globre(pat) + globsuffix
     raise error.ProgrammingError(b'not a regex pattern: %s:%s' % (kind, pat))
 
 
 def _buildmatch(kindpats, globsuffix, root):
     """Return regexp string and a matcher function for kindpats.
     globsuffix is appended to the regexp of globs."""
     matchfuncs = []
 
     subincludes, kindpats = _expandsubinclude(kindpats, root)
     if subincludes:
         submatchers = {}
 
         def matchsubinclude(f):
             for prefix, matcherargs in subincludes:
                 if f.startswith(prefix):
                     mf = submatchers.get(prefix)
                     if mf is None:
                         mf = match(*matcherargs)
                         submatchers[prefix] = mf
 
                     if mf(f[len(prefix) :]):
                         return True
             return False
 
         matchfuncs.append(matchsubinclude)
 
     regex = b''
     if kindpats:
         if all(k == b'rootfilesin' for k, p, s in kindpats):
             dirs = {p for k, p, s in kindpats}
 
             def mf(f):
                 i = f.rfind(b'/')
                 if i >= 0:
                     dir = f[:i]
                 else:
                     dir = b'.'
                 return dir in dirs
 
             regex = b'rootfilesin: %s' % stringutil.pprint(list(sorted(dirs)))
             matchfuncs.append(mf)
         else:
             regex, mf = _buildregexmatch(kindpats, globsuffix)
             matchfuncs.append(mf)
 
     if len(matchfuncs) == 1:
         return regex, matchfuncs[0]
     else:
         return regex, lambda f: any(mf(f) for mf in matchfuncs)
 
 
 MAX_RE_SIZE = 20000
 
 
 def _joinregexes(regexps):
     """gather multiple regular expressions into a single one"""
     return b'|'.join(regexps)
 
 
 def _buildregexmatch(kindpats, globsuffix):
     """Build a match function from a list of kinds and kindpats,
     return regexp string and a matcher function.
 
     Test too large input
     >>> _buildregexmatch([
     ...     (b'relglob', b'?' * MAX_RE_SIZE, b'')
     ... ], b'$')
     Traceback (most recent call last):
     ...
     Abort: matcher pattern is too long (20009 bytes)
     """
     try:
         allgroups = []
         regexps = [_regex(k, p, globsuffix) for (k, p, s) in kindpats]
         fullregexp = _joinregexes(regexps)
 
         startidx = 0
         groupsize = 0
         for idx, r in enumerate(regexps):
             piecesize = len(r)
             if piecesize > MAX_RE_SIZE:
                 msg = _(b"matcher pattern is too long (%d bytes)") % piecesize
                 raise error.Abort(msg)
             elif (groupsize + piecesize) > MAX_RE_SIZE:
                 group = regexps[startidx:idx]
                 allgroups.append(_joinregexes(group))
                 startidx = idx
                 groupsize = 0
             groupsize += piecesize + 1
 
         if startidx == 0:
             matcher = _rematcher(fullregexp)
             func = lambda s: bool(matcher(s))
         else:
             group = regexps[startidx:]
             allgroups.append(_joinregexes(group))
             allmatchers = [_rematcher(g) for g in allgroups]
             func = lambda s: any(m(s) for m in allmatchers)
         return fullregexp, func
     except re.error:
         for k, p, s in kindpats:
             try:
                 _rematcher(_regex(k, p, globsuffix))
             except re.error:
                 if s:
                     raise error.Abort(
                         _(b"%s: invalid pattern (%s): %s") % (s, k, p)
                     )
                 else:
                     raise error.Abort(_(b"invalid pattern (%s): %s") % (k, p))
         raise error.Abort(_(b"invalid pattern"))
 
 
 def _patternrootsanddirs(kindpats):
     """Returns roots and directories corresponding to each pattern.
 
     This calculates the roots and directories exactly matching the patterns and
     returns a tuple of (roots, dirs) for each. It does not return other
     directories which may also need to be considered, like the parent
     directories.
     """
     r = []
     d = []
     for kind, pat, source in kindpats:
         if kind in (b'glob', b'rootglob'):  # find the non-glob prefix
             root = []
             for p in pat.split(b'/'):
                 if b'[' in p or b'{' in p or b'*' in p or b'?' in p:
                     break
                 root.append(p)
             r.append(b'/'.join(root))
         elif kind in (b'relpath', b'path'):
             if pat == b'.':
                 pat = b''
             r.append(pat)
         elif kind in (b'rootfilesin',):
             if pat == b'.':
                 pat = b''
             d.append(pat)
         else:  # relglob, re, relre
             r.append(b'')
     return r, d
 
 
 def _roots(kindpats):
     '''Returns root directories to match recursively from the given patterns.'''
     roots, dirs = _patternrootsanddirs(kindpats)
     return roots
 
 
 def _rootsdirsandparents(kindpats):
     """Returns roots and exact directories from patterns.
 
     `roots` are directories to match recursively, `dirs` should
     be matched non-recursively, and `parents` are the implicitly required
     directories to walk to items in either roots or dirs.
 
     Returns a tuple of (roots, dirs, parents).
 
     >>> r = _rootsdirsandparents(
     ...     [(b'glob', b'g/h/*', b''), (b'glob', b'g/h', b''),
     ...      (b'glob', b'g*', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['g/h', 'g/h', ''], []) ['', 'g']
     >>> r = _rootsdirsandparents(
     ...     [(b'rootfilesin', b'g/h', b''), (b'rootfilesin', b'', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     ([], ['g/h', '']) ['', 'g']
     >>> r = _rootsdirsandparents(
     ...     [(b'relpath', b'r', b''), (b'path', b'p/p', b''),
     ...      (b'path', b'', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['r', 'p/p', ''], []) ['', 'p']
     >>> r = _rootsdirsandparents(
     ...     [(b'relglob', b'rg*', b''), (b're', b're/', b''),
     ...      (b'relre', b'rr', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['', '', ''], []) ['']
     """
     r, d = _patternrootsanddirs(kindpats)
 
     p = set()
     # Add the parents as non-recursive/exact directories, since they must be
     # scanned to get to either the roots or the other exact directories.
     p.update(pathutil.dirs(d))
     p.update(pathutil.dirs(r))
 
     # FIXME: all uses of this function convert these to sets, do so before
     # returning.
     # FIXME: all uses of this function do not need anything in 'roots' and
     # 'dirs' to also be in 'parents', consider removing them before returning.
     return r, d, p
 
 
 def _explicitfiles(kindpats):
     """Returns the potential explicit filenames from the patterns.
 
     >>> _explicitfiles([(b'path', b'foo/bar', b'')])
     ['foo/bar']
     >>> _explicitfiles([(b'rootfilesin', b'foo/bar', b'')])
     []
     """
     # Keep only the pattern kinds where one can specify filenames (vs only
     # directory names).
     filable = [kp for kp in kindpats if kp[0] not in (b'rootfilesin',)]
     return _roots(filable)
 
 
 def _prefix(kindpats):
     '''Whether all the patterns match a prefix (i.e. recursively)'''
     for kind, pat, source in kindpats:
         if kind not in (b'path', b'relpath'):
             return False
     return True
 
 
 _commentre = None
 
 
 def readpatternfile(filepath, warn, sourceinfo=False):
     """parse a pattern file, returning a list of
     patterns. These patterns should be given to compile()
     to be validated and converted into a match function.
 
     trailing white space is dropped.
     the escape character is backslash.
     comments start with #.
     empty lines are skipped.
 
     lines can be of the following formats:
 
     syntax: regexp # defaults following lines to non-rooted regexps
     syntax: glob   # defaults following lines to non-rooted globs
     re:pattern     # non-rooted regular expression
     glob:pattern   # non-rooted glob
     rootglob:pat   # rooted glob (same root as ^ in regexps)
     pattern        # pattern of the current default type
 
     if sourceinfo is set, returns a list of tuples:
     (pattern, lineno, originalline).
     This is useful to debug ignore patterns.
     """
 
     syntaxes = {
         b're': b'relre:',
         b'regexp': b'relre:',
         b'glob': b'relglob:',
         b'rootglob': b'rootglob:',
         b'include': b'include',
         b'subinclude': b'subinclude',
     }
     syntax = b'relre:'
     patterns = []
 
     fp = open(filepath, b'rb')
-    for lineno, line in enumerate(util.iterfile(fp), start=1):
+    for lineno, line in enumerate(fp, start=1):
         if b"#" in line:
             global _commentre
             if not _commentre:
                 _commentre = util.re.compile(br'((?:^|[^\\])(?:\\\\)*)#.*')
             # remove comments prefixed by an even number of escapes
             m = _commentre.search(line)
             if m:
                 line = line[: m.end(1)]
             # fixup properly escaped comments that survived the above
             line = line.replace(b"\\#", b"#")
         line = line.rstrip()
         if not line:
             continue
 
         if line.startswith(b'syntax:'):
             s = line[7:].strip()
             try:
                 syntax = syntaxes[s]
             except KeyError:
                 if warn:
                     warn(
                         _(b"%s: ignoring invalid syntax '%s'\n") % (filepath, s)
                     )
             continue
 
         linesyntax = syntax
         for s, rels in syntaxes.items():
             if line.startswith(rels):
                 linesyntax = rels
                 line = line[len(rels) :]
                 break
             elif line.startswith(s + b':'):
                 linesyntax = rels
                 line = line[len(s) + 1 :]
                 break
         if sourceinfo:
             patterns.append((linesyntax + line, lineno, line))
         else:
             patterns.append(linesyntax + line)
     fp.close()
     return patterns

mercurial/patch.py

@@ -1,3261 +1,3261 b''
 # 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.
 
 
 import collections
 import contextlib
 import copy
 import errno
 import os
 import re
 import shutil
 import zlib
 
 from .i18n import _
 from .node import (
     hex,
     sha1nodeconstants,
     short,
 )
 from .pycompat import open
 from . import (
     copies,
     diffhelper,
     diffutil,
     encoding,
     error,
     mail,
     mdiff,
     pathutil,
     pycompat,
     scmutil,
     similar,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     dateutil,
     hashutil,
     procutil,
     stringutil,
 )
 
 stringio = util.stringio
 
 gitre = re.compile(br'diff --git a/(.*) b/(.*)')
 tabsplitter = re.compile(br'(\t+|[^\t]+)')
 wordsplitter = re.compile(
     br'(\t+| +|[a-zA-Z0-9_\x80-\xff]+|[^ \ta-zA-Z0-9_\x80-\xff])'
 )
 
 PatchError = error.PatchError
 PatchParseError = error.PatchParseError
 PatchApplicationError = error.PatchApplicationError
 
 # public functions
 
 
 def split(stream):
     '''return an iterator of individual patches from a stream'''
 
     def isheader(line, inheader):
         if inheader and line.startswith((b' ', b'\t')):
             # continuation
             return True
         if line.startswith((b' ', b'-', b'+')):
             # diff line - don't check for header pattern in there
             return False
         l = line.split(b': ', 1)
         return len(l) == 2 and b' ' not in l[0]
 
     def chunk(lines):
         return stringio(b''.join(lines))
 
     def hgsplit(stream, cur):
         inheader = True
 
         for line in stream:
             if not line.strip():
                 inheader = False
             if not inheader and line.startswith(b'# 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(b'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()
             # pytype: disable=wrong-arg-types
             g = mail.Generator(fp, mangle_from_=False)
             # pytype: enable=wrong-arg-types
             g.flatten(m)
             fp.seek(0)
             return fp
 
         for line in stream:
             cur.append(line)
         c = chunk(cur)
 
         m = mail.parse(c)
         if not m.is_multipart():
             yield msgfp(m)
         else:
             ok_types = (b'text/plain', b'text/x-diff', b'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
 
         __next__ = next
 
     inheader = False
     cur = []
 
     mimeheaders = [b'content-type']
 
     if not util.safehasattr(stream, b'next'):
         # http responses, for example, have readline but not next
         stream = fiter(stream)
 
     for line in stream:
         cur.append(line)
         if line.startswith(b'# HG changeset patch'):
             return hgsplit(stream, cur)
         elif line.startswith(b'From '):
             return mboxsplit(stream, cur)
         elif isheader(line, inheader):
             inheader = True
             if line.split(b':', 1)[0].lower() in mimeheaders:
                 # let email parser handle this
                 return mimesplit(stream, cur)
         elif line.startswith(b'--- ') 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 = [
     (b'Date', b'date'),
     (b'Branch', b'branch'),
     (b'Node ID', b'nodeid'),
 ]
 
 
 @contextlib.contextmanager
 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."""
 
     fd, tmpname = pycompat.mkstemp(prefix=b'hg-patch-')
     tmpfp = os.fdopen(fd, 'wb')
     try:
         yield _extract(ui, fileobj, tmpname, tmpfp)
     finally:
         tmpfp.close()
         os.unlink(tmpname)
 
 
 def _extract(ui, fileobj, tmpname, tmpfp):
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(
         br'^(?:Index:[ \t]|diff[ \t]-|RCS file: |'
         br'retrieving revision [0-9]+(\.[0-9]+)*$|'
         br'---[ \t].*?^\+\+\+[ \t]|'
         br'\*\*\*[ \t].*?^---[ \t])',
         re.MULTILINE | re.DOTALL,
     )
 
     data = {}
 
     msg = mail.parse(fileobj)
 
     subject = msg['Subject'] and mail.headdecode(msg['Subject'])
     data[b'user'] = msg['From'] and mail.headdecode(msg['From'])
     if not subject and not data[b'user']:
         # Not an email, restore parsed headers if any
         subject = (
             b'\n'.join(
                 b': '.join(map(encoding.strtolocal, h)) for h in msg.items()
             )
             + b'\n'
         )
 
     # should try to parse msg['Date']
     parents = []
 
     nodeid = msg['X-Mercurial-Node']
     if nodeid:
         data[b'nodeid'] = nodeid = mail.headdecode(nodeid)
         ui.debug(b'Node ID: %s\n' % nodeid)
 
     if subject:
         if subject.startswith(b'[PATCH'):
             pend = subject.find(b']')
             if pend >= 0:
                 subject = subject[pend + 1 :].lstrip()
         subject = re.sub(br'\n[ \t]+', b' ', subject)
         ui.debug(b'Subject: %s\n' % subject)
     if data[b'user']:
         ui.debug(b'From: %s\n' % data[b'user'])
     diffs_seen = 0
     ok_types = (b'text/plain', b'text/x-diff', b'text/x-patch')
     message = b''
     for part in msg.walk():
         content_type = pycompat.bytestr(part.get_content_type())
         ui.debug(b'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(b'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(b'# HG changeset patch') and not hgpatch:
                     ui.debug(b'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(b'# User '):
                         data[b'user'] = line[7:]
                         ui.debug(b'From: %s\n' % data[b'user'])
                     elif line.startswith(b"# Parent "):
                         parents.append(line[9:].lstrip())
                     elif line.startswith(b"# "):
                         for header, key in patchheadermap:
                             prefix = b'# %s ' % header
                             if line.startswith(prefix):
                                 data[key] = line[len(prefix) :]
                                 ui.debug(b'%s: %s\n' % (header, data[key]))
                     else:
                         hgpatchheader = False
                 elif line == b'---':
                     ignoretext = True
                 if not hgpatchheader and not ignoretext:
                     cfp.write(line)
                     cfp.write(b'\n')
             message = cfp.getvalue()
             if tmpfp:
                 tmpfp.write(payload)
                 if not payload.endswith(b'\n'):
                     tmpfp.write(b'\n')
         elif not diffs_seen and message and content_type == b'text/plain':
             message += b'\n' + payload
 
     if subject and not message.startswith(subject):
         message = b'%s\n%s' % (subject, message)
     data[b'message'] = message
     tmpfp.close()
     if parents:
         data[b'p1'] = parents.pop(0)
         if parents:
             data[b'p2'] = parents.pop(0)
 
     if diffs_seen:
         data[b'filename'] = 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 = b'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 == b'/dev/null':
             return self.op == b'ADD'
         return afile == b'a/' + (self.oldpath or self.path)
 
     def _ispatchingb(self, bfile):
         if bfile == b'/dev/null':
             return self.op == b'DELETE'
         return bfile == b'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(b'\r\n')
         if line.startswith(b'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(b'--- '):
                 gitpatches.append(gp)
                 gp = None
                 continue
             if line.startswith(b'rename from '):
                 gp.op = b'RENAME'
                 gp.oldpath = line[12:]
             elif line.startswith(b'rename to '):
                 gp.path = line[10:]
             elif line.startswith(b'copy from '):
                 gp.op = b'COPY'
                 gp.oldpath = line[10:]
             elif line.startswith(b'copy to '):
                 gp.path = line[8:]
             elif line.startswith(b'deleted file'):
                 gp.op = b'DELETE'
             elif line.startswith(b'new file mode '):
                 gp.op = b'ADD'
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith(b'new mode '):
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith(b'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, b'')
 
 
 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.
         """
 
     def exists(self, fname):
         raise NotImplementedError
 
     def close(self):
         raise NotImplementedError
 
 
 class fsbackend(abstractbackend):
     def __init__(self, ui, basedir):
         super(fsbackend, self).__init__(ui)
         self.opener = vfsmod.vfs(basedir)
 
     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):
         rmdir = self.ui.configbool(b'experimental', b'removeemptydirs')
         self.opener.unlinkpath(fname, ignoremissing=True, rmdir=rmdir)
 
     def writerej(self, fname, failed, total, lines):
         fname = fname + b".rej"
         self.ui.warn(
             _(b"%d out of %d hunks FAILED -- saving rejects to file %s\n")
             % (failed, total, fname)
         )
         fp = self.opener(fname, b'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 not self.repo.dirstate.get_entry(fname).any_tracked and self.exists(
             fname
         ):
             raise PatchApplicationError(
                 _(b'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 = pycompat.mkdtemp(prefix=b'hg-patch-')
                 self.opener = vfsmod.vfs(root)
             # Avoid filename issues with these simple names
             fn = b'%d' % 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 PatchApplicationError(
                 _(b'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(), (b'l' in flags, b'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(br'@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
 contextdesc = re.compile(br'(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
 eolmodes = [b'strict', b'crlf', b'lf', b'auto']
 
 
 class patchfile(object):
     def __init__(self, ui, gp, backend, store, eolmode=b'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 (b'ADD', b'COPY', b'RENAME')
         self.remove = gp.op == b'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(b'\r\n'):
                     self.eol = b'\r\n'
                 elif self.lines[0].endswith(b'\n'):
                     self.eol = b'\n'
                 if eolmode != b'strict':
                     nlines = []
                     for l in self.lines:
                         if l.endswith(b'\r\n'):
                             l = l[:-2] + b'\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(_(b"unable to find '%s' for patching\n") % self.fname)
             self.ui.warn(
                 _(
                     b"(use '--prefix' to apply patch relative to the "
                     b"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 == b'auto':
             eol = self.eol
         elif self.eolmode == b'crlf':
             eol = b'\r\n'
         else:
             eol = b'\n'
 
         if self.eolmode != b'strict' and eol and eol != b'\n':
             rawlines = []
             for l in lines:
                 if l and l.endswith(b'\n'):
                     l = l[:-1] + eol
                 rawlines.append(l)
             lines = rawlines
 
         self.backend.setfile(fname, b''.join(lines), mode, self.copysource)
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _(b"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 = [b"--- %s\n+++ %s\n" % (base, base)]
         for x in self.rej:
             for l in x.hunk:
                 lines.append(l)
                 if l[-1:] != b'\n':
                     lines.append(b'\n' + diffhelper.MISSING_NEWLINE_MARKER)
         self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)
 
     def apply(self, h):
         if not h.complete():
             raise PatchParseError(
                 _(b"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(
                     _(b"cannot create %s: destination already exists\n")
                     % self.fname
                 )
             else:
                 self.ui.warn(_(b"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 (b'crlf', b'lf')
             or self.eolmode == b'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 diffhelper.testhunk(old, self.lines, oldstart):
             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 pycompat.xrange(
             self.ui.configint(b"patch", b"fuzz") + 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 diffhelper.testhunk(old, self.lines, l):
                         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 = _(
                                 b"Hunk #%d succeeded at %d "
                                 b"with fuzz %d "
                                 b"(offset %d lines).\n"
                             )
                             self.printfile(True)
                             self.ui.warn(
                                 msg % (h.number, l + 1, fuzzlen, offset)
                             )
                         else:
                             msg = _(
                                 b"Hunk #%d succeeded at %d "
                                 b"(offset %d lines).\n"
                             )
                             self.ui.note(msg % (h.number, l + 1, offset))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_(b"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(b'diff --git a/(.*) b/(.*)$')
     diff_re = re.compile(b'diff -r .* (.*)$')
     allhunks_re = re.compile(b'(?:index|deleted file) ')
     pretty_re = re.compile(b'(?:new file|deleted file) ')
     special_re = re.compile(b'(?:index|deleted|copy|rename|new mode) ')
     newfile_re = re.compile(b'(?:new file|copy to|rename to)')
 
     def __init__(self, header):
         self.header = header
         self.hunks = []
 
     def binary(self):
         return any(h.startswith(b'index ') for h in self.header)
 
     def pretty(self, fp):
         for h in self.header:
             if h.startswith(b'index '):
                 fp.write(_(b'this modifies a binary file (all or nothing)\n'))
                 break
             if self.pretty_re.match(h):
                 fp.write(h)
                 if self.binary():
                     fp.write(_(b'this is a binary file\n'))
                 break
             if h.startswith(b'---'):
                 fp.write(
                     _(b'%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(b''.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(pycompat.rapply(pycompat.fsdecode, 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?
     """
 
     def __init__(
         self,
         header,
         fromline,
         toline,
         proc,
         before,
         hunk,
         after,
         maxcontext=None,
     ):
         def trimcontext(lines, reverse=False):
             if maxcontext is not None:
                 delta = len(lines) - maxcontext
                 if delta > 0:
                     if reverse:
                         return delta, lines[delta:]
                     else:
                         return delta, lines[:maxcontext]
             return 0, lines
 
         self.header = header
         trimedbefore, self.before = trimcontext(before, True)
         self.fromline = fromline + trimedbefore
         self.toline = toline + trimedbefore
         _trimedafter, self.after = trimcontext(after, False)
         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.startswith(b'+')])
         rem = len([h for h in hunk if h.startswith(b'-')])
         return add, rem
 
     def reversehunk(self):
         """return another recordhunk which is the reverse of the hunk
 
         If this hunk is diff(A, B), the returned hunk is diff(B, A). To do
         that, swap fromline/toline and +/- signs while keep other things
         unchanged.
         """
         m = {b'+': b'-', b'-': b'+', b'\\': b'\\'}
         hunk = [b'%s%s' % (m[l[0:1]], l[1:]) for l in self.hunk]
         return recordhunk(
             self.header,
             self.toline,
             self.fromline,
             self.proc,
             self.before,
             hunk,
             self.after,
         )
 
     def write(self, fp):
         delta = len(self.before) + len(self.after)
         if self.after and self.after[-1] == diffhelper.MISSING_NEWLINE_MARKER:
             delta -= 1
         fromlen = delta + self.removed
         tolen = delta + self.added
         fp.write(
             b'@@ -%d,%d +%d,%d @@%s\n'
             % (
                 self.fromline,
                 fromlen,
                 self.toline,
                 tolen,
                 self.proc and (b' ' + self.proc),
             )
         )
         fp.write(b''.join(self.before + self.hunk + self.after))
 
     pretty = write
 
     def filename(self):
         return self.header.filename()
 
     @encoding.strmethod
     def __repr__(self):
         return b'<hunk %r@%d>' % (self.filename(), self.fromline)
 
 
 def getmessages():
     return {
         b'multiple': {
             b'apply': _(b"apply change %d/%d to '%s'?"),
             b'discard': _(b"discard change %d/%d to '%s'?"),
             b'keep': _(b"keep change %d/%d to '%s'?"),
             b'record': _(b"record change %d/%d to '%s'?"),
         },
         b'single': {
             b'apply': _(b"apply this change to '%s'?"),
             b'discard': _(b"discard this change to '%s'?"),
             b'keep': _(b"keep this change to '%s'?"),
             b'record': _(b"record this change to '%s'?"),
         },
         b'help': {
             b'apply': _(
                 b'[Ynesfdaq?]'
                 b'$$ &Yes, apply this change'
                 b'$$ &No, skip this change'
                 b'$$ &Edit this change manually'
                 b'$$ &Skip remaining changes to this file'
                 b'$$ Apply remaining changes to this &file'
                 b'$$ &Done, skip remaining changes and files'
                 b'$$ Apply &all changes to all remaining files'
                 b'$$ &Quit, applying no changes'
                 b'$$ &? (display help)'
             ),
             b'discard': _(
                 b'[Ynesfdaq?]'
                 b'$$ &Yes, discard this change'
                 b'$$ &No, skip this change'
                 b'$$ &Edit this change manually'
                 b'$$ &Skip remaining changes to this file'
                 b'$$ Discard remaining changes to this &file'
                 b'$$ &Done, skip remaining changes and files'
                 b'$$ Discard &all changes to all remaining files'
                 b'$$ &Quit, discarding no changes'
                 b'$$ &? (display help)'
             ),
             b'keep': _(
                 b'[Ynesfdaq?]'
                 b'$$ &Yes, keep this change'
                 b'$$ &No, skip this change'
                 b'$$ &Edit this change manually'
                 b'$$ &Skip remaining changes to this file'
                 b'$$ Keep remaining changes to this &file'
                 b'$$ &Done, skip remaining changes and files'
                 b'$$ Keep &all changes to all remaining files'
                 b'$$ &Quit, keeping all changes'
                 b'$$ &? (display help)'
             ),
             b'record': _(
                 b'[Ynesfdaq?]'
                 b'$$ &Yes, record this change'
                 b'$$ &No, skip this change'
                 b'$$ &Edit this change manually'
                 b'$$ &Skip remaining changes to this file'
                 b'$$ Record remaining changes to this &file'
                 b'$$ &Done, skip remaining changes and files'
                 b'$$ Record &all changes to all remaining files'
                 b'$$ &Quit, recording no changes'
                 b'$$ &? (display help)'
             ),
         },
     }
 
 
 def filterpatch(ui, headers, match, operation=None):
     """Interactively filter patch chunks into applied-only chunks"""
     messages = getmessages()
 
     if operation is None:
         operation = b'record'
 
     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[b'help'][operation]
             # IMPORTANT: keep the last line of this prompt short (<40 english
             # chars is a good target) because of issue6158.
             r = ui.promptchoice(b"%s\n(enter ? for help) %s" % (query, resps))
             ui.write(b"\n")
             if r == 8:  # ?
                 for c, t in ui.extractchoices(resps)[1]:
                     ui.write(b'%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(_(b'cannot edit patch for whole file'))
                     ui.write(b"\n")
                     continue
                 if chunk.header.binary():
                     ui.write(_(b'cannot edit patch for binary file'))
                     ui.write(b"\n")
                     continue
                 # Patch comment based on the Git one (based on comment at end of
                 # https://mercurial-scm.org/wiki/RecordExtension)
                 phelp = b'---' + _(
                     b"""
 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) = pycompat.mkstemp(
                     prefix=b"hg-editor-", suffix=b".diff"
                 )
                 ncpatchfp = None
                 try:
                     # Write the initial patch
                     f = util.nativeeolwriter(os.fdopen(patchfd, 'wb'))
                     chunk.header.write(f)
                     chunk.write(f)
                     f.write(
                         b''.join(
                             [b'# ' + i + b'\n' for i in phelp.splitlines()]
                         )
                     )
                     f.close()
                     # Start the editor and wait for it to complete
                     editor = ui.geteditor()
                     ret = ui.system(
                         b"%s \"%s\"" % (editor, patchfn),
                         environ={b'HGUSER': ui.username()},
                         blockedtag=b'filterpatch',
                     )
                     if ret != 0:
                         ui.warn(_(b"editor exited with exit code %d\n") % ret)
                         continue
                     # Remove comment lines
                     patchfp = open(patchfn, 'rb')
                     ncpatchfp = stringio()
-                    for line in util.iterfile(patchfp):
+                    for line in patchfp:
                         line = util.fromnativeeol(line)
                         if not line.startswith(b'#'):
                             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.CanceledError(_(b'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 = b''.join(h.header)
         if hdr in seen:
             continue
         seen.add(hdr)
         if skipall is None:
             h.pretty(ui)
         files = h.files()
         msg = _(b'examine changes to %s?') % _(b' and ').join(
             b"'%s'" % f for f in files
         )
         if all(match.exact(f) for f in files):
             r, skipall, np = True, None, None
         else:
             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[b'single'][operation] % chunk.filename()
             else:
                 idx = pos - len(h.hunks) + i
                 msg = messages[b'multiple'][operation] % (
                     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.values() 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(b'\r\n'):
                     line = line[:-2] + b'\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 PatchParseError(_(b"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)
         try:
             diffhelper.addlines(
                 lr, self.hunk, self.lena, self.lenb, self.a, self.b
             )
         except error.ParseError as e:
             raise PatchParseError(_(b"bad hunk #%d: %s") % (self.number, e))
         # 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 PatchParseError(_(b"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 pycompat.xrange(self.lena):
             l = lr.readline()
             if l.startswith(b'---'):
                 # lines addition, old block is empty
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith(b'- ') or l.startswith(b'! '):
                 u = b'-' + s
             elif l.startswith(b'  '):
                 u = b' ' + s
             else:
                 raise PatchParseError(
                     _(b"bad hunk #%d old text line %d") % (self.number, x)
                 )
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith(br'\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchParseError(_(b"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 pycompat.xrange(self.lenb):
             l = lr.readline()
             if l.startswith(br'\ '):
                 # 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(b'+ ') or l.startswith(b'! '):
                 u = b'+' + s
             elif l.startswith(b'  '):
                 u = b' ' + s
             elif len(self.b) == 0:
                 # line deletions, new block is empty
                 lr.push(l)
                 break
             else:
                 raise PatchParseError(
                     _(b"bad hunk #%d old text line %d") % (self.number, x)
                 )
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = b""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith(b'-'):
                     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(b'-') or x.startswith(b' '):
                     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(b'+') or x.startswith(b' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = b"@@ -%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(br'\ '):
             diffhelper.fixnewline(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 pycompat.xrange(hlen - 1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x + 1].startswith(b' '):
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in pycompat.xrange(hlen - 1):
                     if self.hunk[hlen - bot - 1].startswith(b' '):
                         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 = [b'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, b''.join(lines))]
         return [self.text]
 
     def _read(self, lr):
         def getline(lr, hunk):
             l = lr.readline()
             hunk.append(l)
             return l.rstrip(b'\r\n')
 
         while True:
             line = getline(lr, self.hunk)
             if not line:
                 raise PatchParseError(
                     _(b'could not extract "%s" binary data') % self._fname
                 )
             if line.startswith(b'literal '):
                 size = int(line[8:].rstrip())
                 break
             if line.startswith(b'delta '):
                 size = int(line[6:].rstrip())
                 self.delta = True
                 break
         dec = []
         line = getline(lr, self.hunk)
         while len(line) > 1:
             l = line[0:1]
             if l <= b'Z' and l >= b'A':
                 l = ord(l) - ord(b'A') + 1
             else:
                 l = ord(l) - ord(b'a') + 27
             try:
                 dec.append(util.b85decode(line[1:])[:l])
             except ValueError as e:
                 raise PatchParseError(
                     _(b'could not decode "%s" binary patch: %s')
                     % (self._fname, stringutil.forcebytestr(e))
                 )
             line = getline(lr, self.hunk)
         text = zlib.decompress(b''.join(dec))
         if len(text) != size:
             raise PatchParseError(
                 _(b'"%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(b'\r\n')
     i = s.find(b'\t')
     if i < 0:
         i = s.find(b' ')
         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 = b"""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) or None
     >>> reversedpatch = fp.read()
     >>> print(pycompat.sysstr(reversedpatch))
     diff --git a/folder1/g b/folder1/g
     --- a/folder1/g
     +++ b/folder1/g
     @@ -1,4 +1,3 @@
     -firstline
      c
      1
      2
     @@ -2,6 +1,6 @@
      c
      1
      2
     - 3
     +4
      5
      d
     @@ -6,3 +5,2 @@
      5
      d
     -lastline
 
     '''
 
     newhunks = []
     for c in hunks:
         if util.safehasattr(c, b'reversehunk'):
             c = c.reversehunk()
         newhunks.append(c)
     return newhunks
 
 
 def parsepatch(originalchunks, maxcontext=None):
     """patch -> [] of headers -> [] of hunks
 
     If maxcontext is not None, trim context lines if necessary.
 
     >>> rawpatch = b'''diff --git a/folder1/g b/folder1/g
     ... --- a/folder1/g
     ... +++ b/folder1/g
     ... @@ -1,8 +1,10 @@
     ...  1
     ...  2
     ... -3
     ...  4
     ...  5
     ...  6
     ... +6.1
     ... +6.2
     ...  7
     ...  8
     ... +9'''
     >>> out = util.stringio()
     >>> headers = parsepatch([rawpatch], maxcontext=1)
     >>> for header in headers:
     ...     header.write(out)
     ...     for hunk in header.hunks:
     ...         hunk.write(out)
     >>> print(pycompat.sysstr(out.getvalue()))
     diff --git a/folder1/g b/folder1/g
     --- a/folder1/g
     +++ b/folder1/g
     @@ -2,3 +2,2 @@
      2
     -3
      4
     @@ -6,2 +5,4 @@
      6
     +6.1
     +6.2
      7
     @@ -8,1 +9,2 @@
      8
     +9
     """
 
     class parser(object):
         """patch parsing state machine"""
 
         def __init__(self):
             self.fromline = 0
             self.toline = 0
             self.proc = b''
             self.header = None
             self.context = []
             self.before = []
             self.hunk = []
             self.headers = []
 
         def addrange(self, limits):
             self.addcontext([])
             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,
                     maxcontext,
                 )
                 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 = []
             if self.hunk:
                 self.addcontext([])
             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 = {
             b'file': {
                 b'context': addcontext,
                 b'file': newfile,
                 b'hunk': addhunk,
                 b'range': addrange,
             },
             b'context': {
                 b'file': newfile,
                 b'hunk': addhunk,
                 b'range': addrange,
                 b'other': addother,
             },
             b'hunk': {
                 b'context': addcontext,
                 b'file': newfile,
                 b'range': addrange,
             },
             b'range': {b'context': addcontext, b'hunk': addhunk},
             b'other': {b'other': addother},
         }
 
     p = parser()
     fp = stringio()
     fp.write(b''.join(originalchunks))
     fp.seek(0)
 
     state = b'context'
     for newstate, data in scanpatch(fp):
         try:
             p.transitions[state][newstate](p, data)
         except KeyError:
             raise PatchParseError(
                 b'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(b'a/b/c', 0, b'')
     ('', 'a/b/c')
     >>> pathtransform(b'   a/b/c   ', 0, b'')
     ('', '   a/b/c')
     >>> pathtransform(b'   a/b/c   ', 2, b'')
     ('a/b/', 'c')
     >>> pathtransform(b'a/b/c', 0, b'd/e/')
     ('', 'd/e/a/b/c')
     >>> pathtransform(b'   a//b/c   ', 2, b'd/e/')
     ('a//b/', 'd/e/c')
     >>> pathtransform(b'a/b/c', 3, b'')
     Traceback (most recent call last):
     PatchApplicationError: unable to strip away 1 of 3 dirs from a/b/c
     """
     pathlen = len(path)
     i = 0
     if strip == 0:
         return b'', prefix + path.rstrip()
     count = strip
     while count > 0:
         i = path.find(b'/', i)
         if i == -1:
             raise PatchApplicationError(
                 _(b"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] == b'/':
             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 == b"/dev/null"
     nullb = bfile_orig == b"/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(b'/') + 1]
     bbasedir = bfile[: bfile.rfind(b'/') + 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 PatchParseError(_(b"undefined source and destination files"))
 
     gp = patchmeta(fname)
     if create:
         gp.op = b'ADD'
     elif remove:
         gp.op = b'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(br'@@ -(\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, b''):
             if p(line):
                 lines.append(line)
             else:
                 lr.push(line)
                 break
         return lines
 
     for line in iter(lr.readline, b''):
         if line.startswith(b'diff --git a/') or line.startswith(b'diff -r '):
 
             def notheader(line):
                 s = line.split(None, 1)
                 return not s or s[0] not in (b'---', b'diff')
 
             header = scanwhile(line, notheader)
             fromfile = lr.readline()
             if fromfile.startswith(b'---'):
                 tofile = lr.readline()
                 header += [fromfile, tofile]
             else:
                 lr.push(fromfile)
             yield b'file', header
         elif line.startswith(b' '):
             cs = (b' ', b'\\')
             yield b'context', scanwhile(line, lambda l: l.startswith(cs))
         elif line.startswith((b'-', b'+')):
             cs = (b'-', b'+', b'\\')
             yield b'hunk', scanwhile(line, lambda l: l.startswith(cs))
         else:
             m = lines_re.match(line)
             if m:
                 yield b'range', m.groups()
             else:
                 yield b'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 = b""
     bfile = b""
     state = None
     hunknum = 0
     emitfile = newfile = False
     gitpatches = None
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
 
     for x in iter(lr.readline, b''):
         if state == BFILE and (
             (not context and x.startswith(b'@'))
             or (context is not False and x.startswith(b'***************'))
             or x.startswith(b'GIT binary patch')
         ):
             gp = None
             if gitpatches and gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
             if x.startswith(b'GIT binary patch'):
                 h = binhunk(lr, gp.path)
             else:
                 if context is None and x.startswith(b'***************'):
                     context = True
                 h = hunk(x, hunknum + 1, lr, context)
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield b'file', (afile, bfile, h, gp and gp.copy() or None)
             yield b'hunk', h
         elif x.startswith(b'diff --git a/'):
             m = gitre.match(x.rstrip(b'\r\n'))
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = scangitpatch(lr, x)
                 yield b'git', [
                     g.copy() for g in gitpatches if g.op in (b'COPY', b'RENAME')
                 ]
                 gitpatches.reverse()
             afile = b'a/' + m.group(1)
             bfile = b'b/' + m.group(2)
             while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
                 yield b'file', (
                     b'a/' + gp.path,
                     b'b/' + gp.path,
                     None,
                     gp.copy(),
                 )
             if not gitpatches:
                 raise PatchParseError(
                     _(b'failed to synchronize metadata for "%s"') % afile[2:]
                 )
             newfile = True
         elif x.startswith(b'---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith(b'+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith(b'***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith(b'---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith(b"***************"):
                 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 b'file', (b'a/' + gp.path, b'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 pycompat.bytestr(binchunk):
             i += 1
             if not (ord(c) & 0x80):
                 return i
         return i
 
     out = b""
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     i = 0
     while i < len(binchunk):
         cmd = ord(binchunk[i : i + 1])
         i += 1
         if cmd & 0x80:
             offset = 0
             size = 0
             if cmd & 0x01:
                 offset = ord(binchunk[i : i + 1])
                 i += 1
             if cmd & 0x02:
                 offset |= ord(binchunk[i : i + 1]) << 8
                 i += 1
             if cmd & 0x04:
                 offset |= ord(binchunk[i : i + 1]) << 16
                 i += 1
             if cmd & 0x08:
                 offset |= ord(binchunk[i : i + 1]) << 24
                 i += 1
             if cmd & 0x10:
                 size = ord(binchunk[i : i + 1])
                 i += 1
             if cmd & 0x20:
                 size |= ord(binchunk[i : i + 1]) << 8
                 i += 1
             if cmd & 0x40:
                 size |= ord(binchunk[i : i + 1]) << 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 PatchApplicationError(_(b'unexpected delta opcode 0'))
     return out
 
 
 def applydiff(ui, fp, backend, store, strip=1, prefix=b'', eolmode=b'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 _canonprefix(repo, prefix):
     if prefix:
         prefix = pathutil.canonpath(repo.root, repo.getcwd(), prefix)
         if prefix != b'':
             prefix += b'/'
     return prefix
 
 
 def _applydiff(
     ui, fp, patcher, backend, store, strip=1, prefix=b'', eolmode=b'strict'
 ):
     prefix = _canonprefix(backend.repo, 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 == b'hunk':
             if not current_file:
                 continue
             ret = current_file.apply(values)
             if ret > 0:
                 err = 1
         elif state == b'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 == b'RENAME':
                 backend.unlink(gp.oldpath)
             if not first_hunk:
                 if gp.op == b'DELETE':
                     backend.unlink(gp.path)
                     continue
                 data, mode = None, None
                 if gp.op in (b'RENAME', b'COPY'):
                     data, mode = store.getfile(gp.oldpath)[:2]
                     if data is None:
                         # This means that the old path does not exist
                         raise PatchApplicationError(
                             _(b"source file '%s' does not exist") % gp.oldpath
                         )
                 if gp.mode:
                     mode = gp.mode
                     if gp.op == b'ADD':
                         # Added files without content have no hunk and
                         # must be created
                         data = b''
                 if data or mode:
                     if gp.op in (b'ADD', b'RENAME', b'COPY') and backend.exists(
                         gp.path
                     ):
                         raise PatchApplicationError(
                             _(
                                 b"cannot create %s: destination "
                                 b"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(stringutil.forcebytestr(inst) + b'\n')
                 current_file = None
                 rejects += 1
                 continue
         elif state == b'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(_(b'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(b'-d %s' % procutil.shellquote(cwd))
     cmd = b'%s %s -p%d < %s' % (
         patcher,
         b' '.join(args),
         strip,
         procutil.shellquote(patchname),
     )
     ui.debug(b'Using external patch tool: %s\n' % cmd)
     fp = procutil.popen(cmd, b'rb')
     try:
-        for line in util.iterfile(fp):
+        for line in fp:
             line = line.rstrip()
             ui.note(line + b'\n')
             if line.startswith(b'patching file '):
                 pf = util.parsepatchoutput(line)
                 printed_file = False
                 files.add(pf)
             elif line.find(b'with fuzz') >= 0:
                 fuzz = True
                 if not printed_file:
                     ui.warn(pf + b'\n')
                     printed_file = True
                 ui.warn(line + b'\n')
             elif line.find(b'saving rejects to file') >= 0:
                 ui.warn(line + b'\n')
             elif line.find(b'FAILED') >= 0:
                 if not printed_file:
                     ui.warn(pf + b'\n')
                     printed_file = True
                 ui.warn(line + b'\n')
     finally:
         if files:
             scmutil.marktouched(repo, files, similarity)
     code = fp.close()
     if code:
         raise PatchApplicationError(
             _(b"patch command failed: %s") % procutil.explainexit(code)
         )
     return fuzz
 
 
 def patchbackend(
     ui, backend, patchobj, strip, prefix, files=None, eolmode=b'strict'
 ):
     if files is None:
         files = set()
     if eolmode is None:
         eolmode = ui.config(b'patch', b'eol')
     if eolmode.lower() not in eolmodes:
         raise error.Abort(_(b'unsupported line endings type: %s') % eolmode)
     eolmode = eolmode.lower()
 
     store = filestore()
     try:
         fp = open(patchobj, b'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 PatchApplicationError(_(b'patch failed to apply'))
     return ret > 0
 
 
 def internalpatch(
     ui,
     repo,
     patchobj,
     strip,
     prefix=b'',
     files=None,
     eolmode=b'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=b'strict'
 ):
     backend = repobackend(ui, repo, ctx, store)
     return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)
 
 
 def patch(
     ui,
     repo,
     patchname,
     strip=1,
     prefix=b'',
     files=None,
     eolmode=b'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(b'ui', b'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, prefix=b''):
     backend = fsbackend(ui, repo.root)
     prefix = _canonprefix(repo, prefix)
     with open(patchpath, b'rb') as fp:
         changed = set()
         for state, values in iterhunks(fp):
             if state == b'file':
                 afile, bfile, first_hunk, gp = values
                 if gp:
                     gp.path = pathtransform(gp.path, strip - 1, prefix)[1]
                     if gp.oldpath:
                         gp.oldpath = pathtransform(
                             gp.oldpath, strip - 1, prefix
                         )[1]
                 else:
                     gp = makepatchmeta(
                         backend, afile, bfile, first_hunk, strip, prefix
                     )
                 changed.add(gp.path)
                 if gp.op == b'RENAME':
                     changed.add(gp.oldpath)
             elif state not in (b'hunk', b'git'):
                 raise error.Abort(_(b'unsupported parser state: %s') % state)
         return changed
 
 
 class GitDiffRequired(Exception):
     pass
 
 
 diffopts = diffutil.diffallopts
 diffallopts = diffutil.diffallopts
 difffeatureopts = diffutil.difffeatureopts
 
 
 def diff(
     repo,
     node1=None,
     node2=None,
     match=None,
     changes=None,
     opts=None,
     losedatafn=None,
     pathfn=None,
     copy=None,
     copysourcematch=None,
     hunksfilterfn=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.
 
     if copysourcematch is not None, then copy sources will be filtered by this
     matcher
 
     hunksfilterfn, if not None, should be a function taking a filectx and
     hunks generator that may yield filtered hunks.
     """
     if not node1 and not node2:
         node1 = repo.dirstate.p1()
 
     ctx1 = repo[node1]
     ctx2 = repo[node2]
 
     for fctx1, fctx2, hdr, hunks in diffhunks(
         repo,
         ctx1=ctx1,
         ctx2=ctx2,
         match=match,
         changes=changes,
         opts=opts,
         losedatafn=losedatafn,
         pathfn=pathfn,
         copy=copy,
         copysourcematch=copysourcematch,
     ):
         if hunksfilterfn is not None:
             # If the file has been removed, fctx2 is None; but this should
             # not occur here since we catch removed files early in
             # logcmdutil.getlinerangerevs() for 'hg log -L'.
             assert (
                 fctx2 is not None
             ), b'fctx2 unexpectly None in diff hunks filtering'
             hunks = hunksfilterfn(fctx2, hunks)
         text = b''.join(b''.join(hlines) for hrange, hlines in hunks)
         if hdr and (text or len(hdr) > 1):
             yield b'\n'.join(hdr) + b'\n'
         if text:
             yield text
 
 
 def diffhunks(
     repo,
     ctx1,
     ctx2,
     match=None,
     changes=None,
     opts=None,
     losedatafn=None,
     pathfn=None,
     copy=None,
     copysourcematch=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
 
     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()
 
     if not changes:
         changes = ctx1.status(ctx2, match=match)
     if isinstance(changes, list):
         modified, added, removed = changes[:3]
     else:
         modified, added, removed = (
             changes.modified,
             changes.added,
             changes.removed,
         )
 
     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 copysourcematch:
         # filter out copies where source side isn't inside the matcher
         # (copies.pathcopies() already filtered out the destination)
         copy = {dst: src for dst, src in copy.items() if copysourcematch(src)}
 
     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 list(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]
 
     prefetchmatch = scmutil.matchfiles(
         repo, list(modifiedset | addedset | removedset)
     )
     revmatches = [
         (ctx1.rev(), prefetchmatch),
         (ctx2.rev(), prefetchmatch),
     ]
     scmutil.prefetchfiles(repo, revmatches)
 
     def difffn(opts, losedata):
         return trydiff(
             repo,
             revs,
             ctx1,
             ctx2,
             modified,
             added,
             removed,
             copy,
             getfilectx,
             opts,
             losedata,
             pathfn,
         )
 
     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 diffsinglehunk(hunklines):
     """yield tokens for a list of lines in a single hunk"""
     for line in hunklines:
         # chomp
         chompline = line.rstrip(b'\r\n')
         # highlight tabs and trailing whitespace
         stripline = chompline.rstrip()
         if line.startswith(b'-'):
             label = b'diff.deleted'
         elif line.startswith(b'+'):
             label = b'diff.inserted'
         else:
             raise error.ProgrammingError(b'unexpected hunk line: %s' % line)
         for token in tabsplitter.findall(stripline):
             if token.startswith(b'\t'):
                 yield (token, b'diff.tab')
             else:
                 yield (token, label)
 
         if chompline != stripline:
             yield (chompline[len(stripline) :], b'diff.trailingwhitespace')
         if chompline != line:
             yield (line[len(chompline) :], b'')
 
 
 def diffsinglehunkinline(hunklines):
     """yield tokens for a list of lines in a single hunk, with inline colors"""
     # prepare deleted, and inserted content
     a = bytearray()
     b = bytearray()
     for line in hunklines:
         if line[0:1] == b'-':
             a += line[1:]
         elif line[0:1] == b'+':
             b += line[1:]
         else:
             raise error.ProgrammingError(b'unexpected hunk line: %s' % line)
     # fast path: if either side is empty, use diffsinglehunk
     if not a or not b:
         for t in diffsinglehunk(hunklines):
             yield t
         return
     # re-split the content into words
     al = wordsplitter.findall(bytes(a))
     bl = wordsplitter.findall(bytes(b))
     # re-arrange the words to lines since the diff algorithm is line-based
     aln = [s if s == b'\n' else s + b'\n' for s in al]
     bln = [s if s == b'\n' else s + b'\n' for s in bl]
     an = b''.join(aln)
     bn = b''.join(bln)
     # run the diff algorithm, prepare atokens and btokens
     atokens = []
     btokens = []
     blocks = mdiff.allblocks(an, bn, lines1=aln, lines2=bln)
     for (a1, a2, b1, b2), btype in blocks:
         changed = btype == b'!'
         for token in mdiff.splitnewlines(b''.join(al[a1:a2])):
             atokens.append((changed, token))
         for token in mdiff.splitnewlines(b''.join(bl[b1:b2])):
             btokens.append((changed, token))
 
     # yield deleted tokens, then inserted ones
     for prefix, label, tokens in [
         (b'-', b'diff.deleted', atokens),
         (b'+', b'diff.inserted', btokens),
     ]:
         nextisnewline = True
         for changed, token in tokens:
             if nextisnewline:
                 yield (prefix, label)
                 nextisnewline = False
             # special handling line end
             isendofline = token.endswith(b'\n')
             if isendofline:
                 chomp = token[:-1]  # chomp
                 if chomp.endswith(b'\r'):
                     chomp = chomp[:-1]
                 endofline = token[len(chomp) :]
                 token = chomp.rstrip()  # detect spaces at the end
                 endspaces = chomp[len(token) :]
             # scan tabs
             for maybetab in tabsplitter.findall(token):
                 if b'\t' == maybetab[0:1]:
                     currentlabel = b'diff.tab'
                 else:
                     if changed:
                         currentlabel = label + b'.changed'
                     else:
                         currentlabel = label + b'.unchanged'
                 yield (maybetab, currentlabel)
             if isendofline:
                 if endspaces:
                     yield (endspaces, b'diff.trailingwhitespace')
                 yield (endofline, b'')
                 nextisnewline = True
 
 
 def difflabel(func, *args, **kw):
     '''yields 2-tuples of (output, label) based on the output of func()'''
     if kw.get('opts') and kw['opts'].worddiff:
         dodiffhunk = diffsinglehunkinline
     else:
         dodiffhunk = diffsinglehunk
     headprefixes = [
         (b'diff', b'diff.diffline'),
         (b'copy', b'diff.extended'),
         (b'rename', b'diff.extended'),
         (b'old', b'diff.extended'),
         (b'new', b'diff.extended'),
         (b'deleted', b'diff.extended'),
         (b'index', b'diff.extended'),
         (b'similarity', b'diff.extended'),
         (b'---', b'diff.file_a'),
         (b'+++', b'diff.file_b'),
     ]
     textprefixes = [
         (b'@', b'diff.hunk'),
         # - and + are handled by diffsinglehunk
     ]
     head = False
 
     # buffers a hunk, i.e. adjacent "-", "+" lines without other changes.
     hunkbuffer = []
 
     def consumehunkbuffer():
         if hunkbuffer:
             for token in dodiffhunk(hunkbuffer):
                 yield token
             hunkbuffer[:] = []
 
     for chunk in func(*args, **kw):
         lines = chunk.split(b'\n')
         linecount = len(lines)
         for i, line in enumerate(lines):
             if head:
                 if line.startswith(b'@'):
                     head = False
             else:
                 if line and not line.startswith(
                     (b' ', b'+', b'-', b'@', b'\\')
                 ):
                     head = True
             diffline = False
             if not head and line and line.startswith((b'+', b'-')):
                 diffline = True
 
             prefixes = textprefixes
             if head:
                 prefixes = headprefixes
             if diffline:
                 # buffered
                 bufferedline = line
                 if i + 1 < linecount:
                     bufferedline += b"\n"
                 hunkbuffer.append(bufferedline)
             else:
                 # unbuffered
                 for token in consumehunkbuffer():
                     yield token
                 stripline = line.rstrip()
                 for prefix, label in prefixes:
                     if stripline.startswith(prefix):
                         yield (stripline, label)
                         if line != stripline:
                             yield (
                                 line[len(stripline) :],
                                 b'diff.trailingwhitespace',
                             )
                         break
                 else:
                     yield (line, b'')
                 if i + 1 < linecount:
                     yield (b'\n', b'')
         for token in consumehunkbuffer():
             yield token
 
 
 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 = {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 = b'rename'
                         gone.add(f1)
                     else:
                         copyop = b'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 _gitindex(text):
     if not text:
         text = b""
     l = len(text)
     s = hashutil.sha1(b'blob %d\0' % l)
     s.update(text)
     return hex(s.digest())
 
 
 _gitmode = {b'l': b'120000', b'x': b'100755', b'': b'100644'}
 
 
 def trydiff(
     repo,
     revs,
     ctx1,
     ctx2,
     modified,
     added,
     removed,
     copy,
     getfilectx,
     opts,
     losedatafn,
     pathfn,
 ):
     """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.
 
     pathfn is applied to every path in the diff output.
     """
 
     if opts.noprefix:
         aprefix = bprefix = b''
     else:
         aprefix = b'a/'
         bprefix = b'b/'
 
     def diffline(f, revs):
         revinfo = b' '.join([b"-r %s" % rev for rev in revs])
         return b'diff %s %s' % (revinfo, f)
 
     def isempty(fctx):
         return fctx is None or fctx.size() == 0
 
     date1 = dateutil.datestr(ctx1.date())
     date2 = dateutil.datestr(ctx2.date())
 
     if not pathfn:
         pathfn = lambda f: f
 
     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"
         if opts.text:
             binary = False
         else:
             binary = 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 = pathfn(f1 or f2)
         path2 = pathfn(f2 or f1)
         header = []
         if opts.git:
             header.append(
                 b'diff --git %s%s %s%s' % (aprefix, path1, bprefix, path2)
             )
             if not f1:  # added
                 header.append(b'new file mode %s' % _gitmode[flag2])
             elif not f2:  # removed
                 header.append(b'deleted file mode %s' % _gitmode[flag1])
             else:  # modified/copied/renamed
                 mode1, mode2 = _gitmode[flag1], _gitmode[flag2]
                 if mode1 != mode2:
                     header.append(b'old mode %s' % mode1)
                     header.append(b'new mode %s' % mode2)
                 if copyop is not None:
                     if opts.showsimilarity:
                         sim = similar.score(ctx1[path1], ctx2[path2]) * 100
                         header.append(b'similarity index %d%%' % sim)
                     header.append(b'%s from %s' % (copyop, path1))
                     header.append(b'%s to %s' % (copyop, path2))
         elif revs:
             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()
 
         data1 = (ctx1, fctx1, path1, flag1, content1, date1)
         data2 = (ctx2, fctx2, path2, flag2, content2, date2)
         yield diffcontent(data1, data2, header, binary, opts)
 
 
 def diffcontent(data1, data2, header, binary, opts):
     """diffs two versions of a file.
 
     data1 and data2 are tuples containg:
 
         * ctx: changeset for the file
         * fctx: file context for that file
         * path1: name of the file
         * flag: flags of the file
         * content: full content of the file (can be null in case of binary)
         * date: date of the changeset
 
     header: the patch header
     binary: whether the any of the version of file is binary or not
     opts:   user passed options
 
     It exists as a separate function so that extensions like extdiff can wrap
     it and use the file content directly.
     """
 
     ctx1, fctx1, path1, flag1, content1, date1 = data1
     ctx2, fctx2, path2, flag2, content2, date2 = data2
     index1 = _gitindex(content1) if path1 in ctx1 else sha1nodeconstants.nullhex
     index2 = _gitindex(content2) if path2 in ctx2 else sha1nodeconstants.nullhex
     if binary and opts.git and not opts.nobinary:
         text = mdiff.b85diff(content1, content2)
         if text:
             header.append(b'index %s..%s' % (index1, index2))
         hunks = ((None, [text]),)
     else:
         if opts.git and opts.index > 0:
             flag = flag1
             if flag is None:
                 flag = flag2
             header.append(
                 b'index %s..%s %s'
                 % (
                     index1[0 : opts.index],
                     index2[0 : opts.index],
                     _gitmode[flag],
                 )
             )
 
         uheaders, hunks = mdiff.unidiff(
             content1,
             date1,
             content2,
             date2,
             path1,
             path2,
             binary=binary,
             opts=opts,
         )
         header.extend(uheaders)
     return fctx1, fctx2, 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(br'^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(b'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(b'diff --git a/'):
                 filename = gitre.search(line).group(2)
             elif line.startswith(b'diff -r'):
                 # format: "diff -r ... -r ... filename"
                 filename = diffre.search(line).group(1)
         elif line.startswith(b'@@'):
             inheader = False
         elif line.startswith(b'+') and not inheader:
             adds += 1
         elif line.startswith(b'-') and not inheader:
             removes += 1
         elif line.startswith(b'GIT binary patch') or line.startswith(
             b'Binary file'
         ):
             isbinary = True
         elif line.startswith(b'rename from'):
             filename = line[12:]
         elif line.startswith(b'rename to'):
             filename += b' => %s' % line[10:]
     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 = b'Bin'
         else:
             count = b'%d' % (adds + removes)
         pluses = b'+' * scale(adds)
         minuses = b'-' * scale(removes)
         output.append(
             b' %s%s |  %*s %s%s\n'
             % (
                 filename,
                 b' ' * (maxname - encoding.colwidth(filename)),
                 countwidth,
                 count,
                 pluses,
                 minuses,
             )
         )
 
     if stats:
         output.append(
             _(b' %d files changed, %d insertions(+), %d deletions(-)\n')
             % (len(stats), totaladds, totalremoves)
         )
 
     return b''.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 b'+-':
             name, graph = line.rsplit(b' ', 1)
             yield (name + b' ', b'')
             m = re.search(br'\++', graph)
             if m:
                 yield (m.group(0), b'diffstat.inserted')
             m = re.search(br'-+', graph)
             if m:
                 yield (m.group(0), b'diffstat.deleted')
         else:
             yield (line, b'')
         yield (b'\n', b'')

mercurial/store.py

@@ -1,849 +1,849 b''
 # store.py - repository store handling for Mercurial
 #
 # Copyright 2008 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import errno
 import functools
 import os
 import re
 import stat
 
 from .i18n import _
 from .pycompat import getattr
 from .node import hex
 from . import (
     changelog,
     error,
     manifest,
     policy,
     pycompat,
     util,
     vfs as vfsmod,
 )
 from .utils import hashutil
 
 parsers = policy.importmod('parsers')
 # how much bytes should be read from fncache in one read
 # It is done to prevent loading large fncache files into memory
 fncache_chunksize = 10 ** 6
 
 
 def _matchtrackedpath(path, matcher):
     """parses a fncache entry and returns whether the entry is tracking a path
     matched by matcher or not.
 
     If matcher is None, returns True"""
 
     if matcher is None:
         return True
     path = decodedir(path)
     if path.startswith(b'data/'):
         return matcher(path[len(b'data/') : -len(b'.i')])
     elif path.startswith(b'meta/'):
         return matcher.visitdir(path[len(b'meta/') : -len(b'/00manifest.i')])
 
     raise error.ProgrammingError(b"cannot decode path %s" % path)
 
 
 # This avoids a collision between a file named foo and a dir named
 # foo.i or foo.d
 def _encodedir(path):
     """
     >>> _encodedir(b'data/foo.i')
     'data/foo.i'
     >>> _encodedir(b'data/foo.i/bla.i')
     'data/foo.i.hg/bla.i'
     >>> _encodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i.hg.hg/bla.i'
     >>> _encodedir(b'data/foo.i\\ndata/foo.i/bla.i\\ndata/foo.i.hg/bla.i\\n')
     'data/foo.i\\ndata/foo.i.hg/bla.i\\ndata/foo.i.hg.hg/bla.i\\n'
     """
     return (
         path.replace(b".hg/", b".hg.hg/")
         .replace(b".i/", b".i.hg/")
         .replace(b".d/", b".d.hg/")
     )
 
 
 encodedir = getattr(parsers, 'encodedir', _encodedir)
 
 
 def decodedir(path):
     """
     >>> decodedir(b'data/foo.i')
     'data/foo.i'
     >>> decodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i/bla.i'
     >>> decodedir(b'data/foo.i.hg.hg/bla.i')
     'data/foo.i.hg/bla.i'
     """
     if b".hg/" not in path:
         return path
     return (
         path.replace(b".d.hg/", b".d/")
         .replace(b".i.hg/", b".i/")
         .replace(b".hg.hg/", b".hg/")
     )
 
 
 def _reserved():
     """characters that are problematic for filesystems
 
     * ascii escapes (0..31)
     * ascii hi (126..255)
     * windows specials
 
     these characters will be escaped by encodefunctions
     """
     winreserved = [ord(x) for x in u'\\:*?"<>|']
     for x in range(32):
         yield x
     for x in range(126, 256):
         yield x
     for x in winreserved:
         yield x
 
 
 def _buildencodefun():
     """
     >>> enc, dec = _buildencodefun()
 
     >>> enc(b'nothing/special.txt')
     'nothing/special.txt'
     >>> dec(b'nothing/special.txt')
     'nothing/special.txt'
 
     >>> enc(b'HELLO')
     '_h_e_l_l_o'
     >>> dec(b'_h_e_l_l_o')
     'HELLO'
 
     >>> enc(b'hello:world?')
     'hello~3aworld~3f'
     >>> dec(b'hello~3aworld~3f')
     'hello:world?'
 
     >>> enc(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     >>> dec(b'the~07quick~adshot')
     'the\\x07quick\\xadshot'
     """
     e = b'_'
     xchr = pycompat.bytechr
     asciistr = list(map(xchr, range(127)))
     capitals = list(range(ord(b"A"), ord(b"Z") + 1))
 
     cmap = {x: x for x in asciistr}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in capitals + [ord(e)]:
         cmap[xchr(x)] = e + xchr(x).lower()
 
     dmap = {}
     for k, v in cmap.items():
         dmap[v] = k
 
     def decode(s):
         i = 0
         while i < len(s):
             for l in pycompat.xrange(1, 4):
                 try:
                     yield dmap[s[i : i + l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
 
     return (
         lambda s: b''.join(
             [cmap[s[c : c + 1]] for c in pycompat.xrange(len(s))]
         ),
         lambda s: b''.join(list(decode(s))),
     )
 
 
 _encodefname, _decodefname = _buildencodefun()
 
 
 def encodefilename(s):
     """
     >>> encodefilename(b'foo.i/bar.d/bla.hg/hi:world?/HELLO')
     'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o'
     """
     return _encodefname(encodedir(s))
 
 
 def decodefilename(s):
     """
     >>> decodefilename(b'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o')
     'foo.i/bar.d/bla.hg/hi:world?/HELLO'
     """
     return decodedir(_decodefname(s))
 
 
 def _buildlowerencodefun():
     """
     >>> f = _buildlowerencodefun()
     >>> f(b'nothing/special.txt')
     'nothing/special.txt'
     >>> f(b'HELLO')
     'hello'
     >>> f(b'hello:world?')
     'hello~3aworld~3f'
     >>> f(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     """
     xchr = pycompat.bytechr
     cmap = {xchr(x): xchr(x) for x in pycompat.xrange(127)}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in range(ord(b"A"), ord(b"Z") + 1):
         cmap[xchr(x)] = xchr(x).lower()
 
     def lowerencode(s):
         return b"".join([cmap[c] for c in pycompat.iterbytestr(s)])
 
     return lowerencode
 
 
 lowerencode = getattr(parsers, 'lowerencode', None) or _buildlowerencodefun()
 
 # Windows reserved names: con, prn, aux, nul, com1..com9, lpt1..lpt9
 _winres3 = (b'aux', b'con', b'prn', b'nul')  # length 3
 _winres4 = (b'com', b'lpt')  # length 4 (with trailing 1..9)
 
 
 def _auxencode(path, dotencode):
     """
     Encodes filenames containing names reserved by Windows or which end in
     period or space. Does not touch other single reserved characters c.
     Specifically, c in '\\:*?"<>|' or ord(c) <= 31 are *not* encoded here.
     Additionally encodes space or period at the beginning, if dotencode is
     True. Parameter path is assumed to be all lowercase.
     A segment only needs encoding if a reserved name appears as a
     basename (e.g. "aux", "aux.foo"). A directory or file named "foo.aux"
     doesn't need encoding.
 
     >>> s = b'.foo/aux.txt/txt.aux/con/prn/nul/foo.'
     >>> _auxencode(s.split(b'/'), True)
     ['~2efoo', 'au~78.txt', 'txt.aux', 'co~6e', 'pr~6e', 'nu~6c', 'foo~2e']
     >>> s = b'.com1com2/lpt9.lpt4.lpt1/conprn/com0/lpt0/foo.'
     >>> _auxencode(s.split(b'/'), False)
     ['.com1com2', 'lp~749.lpt4.lpt1', 'conprn', 'com0', 'lpt0', 'foo~2e']
     >>> _auxencode([b'foo. '], True)
     ['foo.~20']
     >>> _auxencode([b' .foo'], True)
     ['~20.foo']
     """
     for i, n in enumerate(path):
         if not n:
             continue
         if dotencode and n[0] in b'. ':
             n = b"~%02x" % ord(n[0:1]) + n[1:]
             path[i] = n
         else:
             l = n.find(b'.')
             if l == -1:
                 l = len(n)
             if (l == 3 and n[:3] in _winres3) or (
                 l == 4
                 and n[3:4] <= b'9'
                 and n[3:4] >= b'1'
                 and n[:3] in _winres4
             ):
                 # encode third letter ('aux' -> 'au~78')
                 ec = b"~%02x" % ord(n[2:3])
                 n = n[0:2] + ec + n[3:]
                 path[i] = n
         if n[-1] in b'. ':
             # encode last period or space ('foo...' -> 'foo..~2e')
             path[i] = n[:-1] + b"~%02x" % ord(n[-1:])
     return path
 
 
 _maxstorepathlen = 120
 _dirprefixlen = 8
 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4
 
 
 def _hashencode(path, dotencode):
     digest = hex(hashutil.sha1(path).digest())
     le = lowerencode(path[5:]).split(b'/')  # skips prefix 'data/' or 'meta/'
     parts = _auxencode(le, dotencode)
     basename = parts[-1]
     _root, ext = os.path.splitext(basename)
     sdirs = []
     sdirslen = 0
     for p in parts[:-1]:
         d = p[:_dirprefixlen]
         if d[-1] in b'. ':
             # Windows can't access dirs ending in period or space
             d = d[:-1] + b'_'
         if sdirslen == 0:
             t = len(d)
         else:
             t = sdirslen + 1 + len(d)
             if t > _maxshortdirslen:
                 break
         sdirs.append(d)
         sdirslen = t
     dirs = b'/'.join(sdirs)
     if len(dirs) > 0:
         dirs += b'/'
     res = b'dh/' + dirs + digest + ext
     spaceleft = _maxstorepathlen - len(res)
     if spaceleft > 0:
         filler = basename[:spaceleft]
         res = b'dh/' + dirs + filler + digest + ext
     return res
 
 
 def _hybridencode(path, dotencode):
     """encodes path with a length limit
 
     Encodes all paths that begin with 'data/', according to the following.
 
     Default encoding (reversible):
 
     Encodes all uppercase letters 'X' as '_x'. All reserved or illegal
     characters are encoded as '~xx', where xx is the two digit hex code
     of the character (see encodefilename).
     Relevant path components consisting of Windows reserved filenames are
     masked by encoding the third character ('aux' -> 'au~78', see _auxencode).
 
     Hashed encoding (not reversible):
 
     If the default-encoded path is longer than _maxstorepathlen, a
     non-reversible hybrid hashing of the path is done instead.
     This encoding uses up to _dirprefixlen characters of all directory
     levels of the lowerencoded path, but not more levels than can fit into
     _maxshortdirslen.
     Then follows the filler followed by the sha digest of the full path.
     The filler is the beginning of the basename of the lowerencoded path
     (the basename is everything after the last path separator). The filler
     is as long as possible, filling in characters from the basename until
     the encoded path has _maxstorepathlen characters (or all chars of the
     basename have been taken).
     The extension (e.g. '.i' or '.d') is preserved.
 
     The string 'data/' at the beginning is replaced with 'dh/', if the hashed
     encoding was used.
     """
     path = encodedir(path)
     ef = _encodefname(path).split(b'/')
     res = b'/'.join(_auxencode(ef, dotencode))
     if len(res) > _maxstorepathlen:
         res = _hashencode(path, dotencode)
     return res
 
 
 def _pathencode(path):
     de = encodedir(path)
     if len(path) > _maxstorepathlen:
         return _hashencode(de, True)
     ef = _encodefname(de).split(b'/')
     res = b'/'.join(_auxencode(ef, True))
     if len(res) > _maxstorepathlen:
         return _hashencode(de, True)
     return res
 
 
 _pathencode = getattr(parsers, 'pathencode', _pathencode)
 
 
 def _plainhybridencode(f):
     return _hybridencode(f, False)
 
 
 def _calcmode(vfs):
     try:
         # files in .hg/ will be created using this mode
         mode = vfs.stat().st_mode
         # avoid some useless chmods
         if (0o777 & ~util.umask) == (0o777 & mode):
             mode = None
     except OSError:
         mode = None
     return mode
 
 
 _data = [
     b'bookmarks',
     b'narrowspec',
     b'data',
     b'meta',
     b'00manifest.d',
     b'00manifest.i',
     b'00changelog.d',
     b'00changelog.i',
     b'phaseroots',
     b'obsstore',
     b'requires',
 ]
 
 REVLOG_FILES_MAIN_EXT = (b'.i', b'i.tmpcensored')
 REVLOG_FILES_OTHER_EXT = (
     b'.idx',
     b'.d',
     b'.dat',
     b'.n',
     b'.nd',
     b'.sda',
     b'd.tmpcensored',
 )
 # files that are "volatile" and might change between listing and streaming
 #
 # note: the ".nd" file are nodemap data and won't "change" but they might be
 # deleted.
 REVLOG_FILES_VOLATILE_EXT = (b'.n', b'.nd')
 
 # some exception to the above matching
 #
 # XXX This is currently not in use because of issue6542
 EXCLUDED = re.compile(b'.*undo\.[^/]+\.(nd?|i)$')
 
 
 def is_revlog(f, kind, st):
     if kind != stat.S_IFREG:
         return None
     return revlog_type(f)
 
 
 def revlog_type(f):
     # XXX we need to filter `undo.` created by the transaction here, however
     # being naive about it also filter revlog for `undo.*` files, leading to
     # issue6542. So we no longer use EXCLUDED.
     if f.endswith(REVLOG_FILES_MAIN_EXT):
         return FILEFLAGS_REVLOG_MAIN
     elif f.endswith(REVLOG_FILES_OTHER_EXT):
         t = FILETYPE_FILELOG_OTHER
         if f.endswith(REVLOG_FILES_VOLATILE_EXT):
             t |= FILEFLAGS_VOLATILE
         return t
     return None
 
 
 # the file is part of changelog data
 FILEFLAGS_CHANGELOG = 1 << 13
 # the file is part of manifest data
 FILEFLAGS_MANIFESTLOG = 1 << 12
 # the file is part of filelog data
 FILEFLAGS_FILELOG = 1 << 11
 # file that are not directly part of a revlog
 FILEFLAGS_OTHER = 1 << 10
 
 # the main entry point for a revlog
 FILEFLAGS_REVLOG_MAIN = 1 << 1
 # a secondary file for a revlog
 FILEFLAGS_REVLOG_OTHER = 1 << 0
 
 # files that are "volatile" and might change between listing and streaming
 FILEFLAGS_VOLATILE = 1 << 20
 
 FILETYPE_CHANGELOG_MAIN = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_CHANGELOG_OTHER = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_MANIFESTLOG_MAIN = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_MANIFESTLOG_OTHER = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_FILELOG_MAIN = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_FILELOG_OTHER = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_OTHER = FILEFLAGS_OTHER
 
 
 class basicstore(object):
     '''base class for local repository stores'''
 
     def __init__(self, path, vfstype):
         vfs = vfstype(path)
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodedir)
         self.opener = self.vfs
 
     def join(self, f):
         return self.path + b'/' + encodedir(f)
 
     def _walk(self, relpath, recurse):
         '''yields (revlog_type, unencoded, size)'''
         path = self.path
         if relpath:
             path += b'/' + relpath
         striplen = len(self.path) + 1
         l = []
         if self.rawvfs.isdir(path):
             visit = [path]
             readdir = self.rawvfs.readdir
             while visit:
                 p = visit.pop()
                 for f, kind, st in readdir(p, stat=True):
                     fp = p + b'/' + f
                     rl_type = is_revlog(f, kind, st)
                     if rl_type is not None:
                         n = util.pconvert(fp[striplen:])
                         l.append((rl_type, decodedir(n), st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
         l.sort()
         return l
 
     def changelog(self, trypending, concurrencychecker=None):
         return changelog.changelog(
             self.vfs,
             trypending=trypending,
             concurrencychecker=concurrencychecker,
         )
 
     def manifestlog(self, repo, storenarrowmatch):
         rootstore = manifest.manifestrevlog(repo.nodeconstants, self.vfs)
         return manifest.manifestlog(self.vfs, repo, rootstore, storenarrowmatch)
 
     def datafiles(self, matcher=None, undecodable=None):
         """Like walk, but excluding the changelog and root manifest.
 
         When [undecodable] is None, revlogs names that can't be
         decoded cause an exception. When it is provided, it should
         be a list and the filenames that can't be decoded are added
         to it instead. This is very rarely needed."""
         files = self._walk(b'data', True) + self._walk(b'meta', True)
         for (t, u, s) in files:
             yield (FILEFLAGS_FILELOG | t, u, s)
 
     def topfiles(self):
         # yield manifest before changelog
         files = reversed(self._walk(b'', False))
         for (t, u, s) in files:
             if u.startswith(b'00changelog'):
                 yield (FILEFLAGS_CHANGELOG | t, u, s)
             elif u.startswith(b'00manifest'):
                 yield (FILEFLAGS_MANIFESTLOG | t, u, s)
             else:
                 yield (FILETYPE_OTHER | t, u, s)
 
     def walk(self, matcher=None):
         """return file related to data storage (ie: revlogs)
 
         yields (file_type, unencoded, size)
 
         if a matcher is passed, storage files of only those tracked paths
         are passed with matches the matcher
         """
         # yield data files first
         for x in self.datafiles(matcher):
             yield x
         for x in self.topfiles():
             yield x
 
     def copylist(self):
         return _data
 
     def write(self, tr):
         pass
 
     def invalidatecaches(self):
         pass
 
     def markremoved(self, fn):
         pass
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # file?
         if self.vfs.exists(path + b".i"):
             return True
         # dir?
         if not path.endswith(b"/"):
             path = path + b"/"
         return self.vfs.exists(path)
 
 
 class encodedstore(basicstore):
     def __init__(self, path, vfstype):
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodefilename)
         self.opener = self.vfs
 
     # note: topfiles would also need a decode phase. It is just that in
     # practice we do not have any file outside of `data/` that needs encoding.
     # However that might change so we should probably add a test and encoding
     # decoding for it too. see issue6548
 
     def datafiles(self, matcher=None, undecodable=None):
         for t, f1, size in super(encodedstore, self).datafiles():
             try:
                 f2 = decodefilename(f1)
             except KeyError:
                 if undecodable is None:
                     msg = _(b'undecodable revlog name %s') % f1
                     raise error.StorageError(msg)
                 else:
                     undecodable.append(f1)
                     continue
             if not _matchtrackedpath(f2, matcher):
                 continue
             yield t, f2, size
 
     def join(self, f):
         return self.path + b'/' + encodefilename(f)
 
     def copylist(self):
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in _data]
 
 
 class fncache(object):
     # the filename used to be partially encoded
     # hence the encodedir/decodedir dance
     def __init__(self, vfs):
         self.vfs = vfs
         self.entries = None
         self._dirty = False
         # set of new additions to fncache
         self.addls = set()
 
     def ensureloaded(self, warn=None):
         """read the fncache file if not already read.
 
         If the file on disk is corrupted, raise. If warn is provided,
         warn and keep going instead."""
         if self.entries is None:
             self._load(warn)
 
     def _load(self, warn=None):
         '''fill the entries from the fncache file'''
         self._dirty = False
         try:
             fp = self.vfs(b'fncache', mode=b'rb')
         except IOError:
             # skip nonexistent file
             self.entries = set()
             return
 
         self.entries = set()
         chunk = b''
         for c in iter(functools.partial(fp.read, fncache_chunksize), b''):
             chunk += c
             try:
                 p = chunk.rindex(b'\n')
                 self.entries.update(decodedir(chunk[: p + 1]).splitlines())
                 chunk = chunk[p + 1 :]
             except ValueError:
                 # substring '\n' not found, maybe the entry is bigger than the
                 # chunksize, so let's keep iterating
                 pass
 
         if chunk:
             msg = _(b"fncache does not ends with a newline")
             if warn:
                 warn(msg + b'\n')
             else:
                 raise error.Abort(
                     msg,
                     hint=_(
                         b"use 'hg debugrebuildfncache' to "
                         b"rebuild the fncache"
                     ),
                 )
         self._checkentries(fp, warn)
         fp.close()
 
     def _checkentries(self, fp, warn):
         """make sure there is no empty string in entries"""
         if b'' in self.entries:
             fp.seek(0)
-            for n, line in enumerate(util.iterfile(fp)):
+            for n, line in enumerate(fp):
                 if not line.rstrip(b'\n'):
                     t = _(b'invalid entry in fncache, line %d') % (n + 1)
                     if warn:
                         warn(t + b'\n')
                     else:
                         raise error.Abort(t)
 
     def write(self, tr):
         if self._dirty:
             assert self.entries is not None
             self.entries = self.entries | self.addls
             self.addls = set()
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'wb', atomictemp=True)
             if self.entries:
                 fp.write(encodedir(b'\n'.join(self.entries) + b'\n'))
             fp.close()
             self._dirty = False
         if self.addls:
             # if we have just new entries, let's append them to the fncache
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'ab', atomictemp=True)
             if self.addls:
                 fp.write(encodedir(b'\n'.join(self.addls) + b'\n'))
             fp.close()
             self.entries = None
             self.addls = set()
 
     def add(self, fn):
         if self.entries is None:
             self._load()
         if fn not in self.entries:
             self.addls.add(fn)
 
     def remove(self, fn):
         if self.entries is None:
             self._load()
         if fn in self.addls:
             self.addls.remove(fn)
             return
         try:
             self.entries.remove(fn)
             self._dirty = True
         except KeyError:
             pass
 
     def __contains__(self, fn):
         if fn in self.addls:
             return True
         if self.entries is None:
             self._load()
         return fn in self.entries
 
     def __iter__(self):
         if self.entries is None:
             self._load()
         return iter(self.entries | self.addls)
 
 
 class _fncachevfs(vfsmod.proxyvfs):
     def __init__(self, vfs, fnc, encode):
         vfsmod.proxyvfs.__init__(self, vfs)
         self.fncache = fnc
         self.encode = encode
 
     def __call__(self, path, mode=b'r', *args, **kw):
         encoded = self.encode(path)
         if mode not in (b'r', b'rb') and (
             path.startswith(b'data/') or path.startswith(b'meta/')
         ):
             # do not trigger a fncache load when adding a file that already is
             # known to exist.
             notload = self.fncache.entries is None and self.vfs.exists(encoded)
             if notload and b'r+' in mode and not self.vfs.stat(encoded).st_size:
                 # when appending to an existing file, if the file has size zero,
                 # it should be considered as missing. Such zero-size files are
                 # the result of truncation when a transaction is aborted.
                 notload = False
             if not notload:
                 self.fncache.add(path)
         return self.vfs(encoded, mode, *args, **kw)
 
     def join(self, path):
         if path:
             return self.vfs.join(self.encode(path))
         else:
             return self.vfs.join(path)
 
     def register_file(self, path):
         """generic hook point to lets fncache steer its stew"""
         if path.startswith(b'data/') or path.startswith(b'meta/'):
             self.fncache.add(path)
 
 
 class fncachestore(basicstore):
     def __init__(self, path, vfstype, dotencode):
         if dotencode:
             encode = _pathencode
         else:
             encode = _plainhybridencode
         self.encode = encode
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.pathsep = self.path + b'/'
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         fnc = fncache(vfs)
         self.fncache = fnc
         self.vfs = _fncachevfs(vfs, fnc, encode)
         self.opener = self.vfs
 
     def join(self, f):
         return self.pathsep + self.encode(f)
 
     def getsize(self, path):
         return self.rawvfs.stat(path).st_size
 
     def datafiles(self, matcher=None, undecodable=None):
         for f in sorted(self.fncache):
             if not _matchtrackedpath(f, matcher):
                 continue
             ef = self.encode(f)
             try:
                 t = revlog_type(f)
                 assert t is not None, f
                 t |= FILEFLAGS_FILELOG
                 yield t, f, self.getsize(ef)
             except OSError as err:
                 if err.errno != errno.ENOENT:
                     raise
 
     def copylist(self):
         d = (
             b'bookmarks',
             b'narrowspec',
             b'data',
             b'meta',
             b'dh',
             b'fncache',
             b'phaseroots',
             b'obsstore',
             b'00manifest.d',
             b'00manifest.i',
             b'00changelog.d',
             b'00changelog.i',
             b'requires',
         )
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in d]
 
     def write(self, tr):
         self.fncache.write(tr)
 
     def invalidatecaches(self):
         self.fncache.entries = None
         self.fncache.addls = set()
 
     def markremoved(self, fn):
         self.fncache.remove(fn)
 
     def _exists(self, f):
         ef = self.encode(f)
         try:
             self.getsize(ef)
             return True
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             # nonexistent entry
             return False
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # check for files (exact match)
         e = path + b'.i'
         if e in self.fncache and self._exists(e):
             return True
         # now check for directories (prefix match)
         if not path.endswith(b'/'):
             path += b'/'
         for e in self.fncache:
             if e.startswith(path) and self._exists(e):
                 return True
         return False