convert: rewrite gitpipe to use common.commandline (SEC)

CVE-2016-3069 (4/5)

hgext/convert/common.py

@@ -1,478 +1,481 b''
 # common.py - common code for the convert extension
 #
 #  Copyright 2005-2009 Matt 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, errno, subprocess, os, datetime, re
 import cPickle as pickle
 from mercurial import phases, util, error
 from mercurial.i18n import _
 
 propertycache = util.propertycache
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64.encodestring(s)
         lines = [l.splitlines()[0] for l in lines]
         return ''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 def decodeargs(s):
     s = base64.decodestring(s)
     return pickle.loads(s)
 
 class MissingTool(Exception):
     pass
 
 def checktool(exe, name=None, abort=True):
     name = name or exe
     if not util.findexe(exe):
         if abort:
             exc = error.Abort
         else:
             exc = MissingTool
         raise exc(_('cannot find required "%s" tool') % name)
 
 class NoRepo(Exception):
     pass
 
 SKIPREV = 'SKIP'
 
 class commit(object):
     def __init__(self, author, date, desc, parents, branch=None, rev=None,
                  extra={}, sortkey=None, saverev=True, phase=phases.draft):
         self.author = author or 'unknown'
         self.date = date or '0 0'
         self.desc = desc
         self.parents = parents
         self.branch = branch
         self.rev = rev
         self.extra = extra
         self.sortkey = sortkey
         self.saverev = saverev
         self.phase = phase
 
 class converter_source(object):
     """Conversion source interface"""
 
     def __init__(self, ui, 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.encoding = 'utf-8'
 
     def checkhexformat(self, revstr, mapname='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(r'[0-9a-fA-F]{40,40}$', revstr):
             raise error.Abort(_('%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"""
         pass
 
     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 'utf-8'
 
         if isinstance(s, unicode):
             return s.encode("utf-8")
         try:
             return s.decode(encoding).encode("utf-8")
         except UnicodeError:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except UnicodeError:
                 return s.decode(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.'''
         pass
 
     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='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, 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 = []
 
     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"""
         pass
 
     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.
         """
         pass
 
     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.
         """
         pass
 
     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):
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.iteritems():
             if len(k) == 1:
                 cmdline.append('-' + k)
             else:
                 cmdline.append('--' + k.replace('_', '-'))
             try:
                 if len(k) == 1:
                     cmdline.append('' + v)
                 else:
                     cmdline[-1] += '=' + v
             except TypeError:
                 pass
         cmdline = [util.shellquote(arg) for arg in cmdline]
         if not self.ui.debugflag:
             cmdline += ['2>', os.devnull]
         cmdline = ' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         def popen(cmdline):
             p = subprocess.Popen(cmdline, shell=True, bufsize=-1,
                     close_fds=util.closefds,
                     stdout=subprocess.PIPE)
             return p
         return self._dorun(popen, cmd, *args, **kwargs)
 
     def _run2(self, cmd, *args, **kwargs):
         return self._dorun(util.popen2, cmd, *args, **kwargs)
 
+    def _run3(self, cmd, *args, **kwargs):
+        return self._dorun(util.popen3, cmd, *args, **kwargs)
+
     def _dorun(self, openfunc, cmd,  *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug('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(''.join(output))
         return output, p.returncode
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = util.explainexit(status)[0]
             raise error.Abort('%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, ''.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
         bytes = 0
         fl = []
         for fn in arglist:
             b = len(fn) + 3
             if bytes + b < limit or len(fl) == 0:
                 fl.append(fn)
                 bytes += b
             else:
                 yield fl
                 fl = [fn]
                 bytes = 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, 'r')
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for i, line in enumerate(fp):
             line = line.splitlines()[0].rstrip()
             if not line:
                 # Ignore blank lines
                 continue
             try:
                 key, value = line.rsplit(' ', 1)
             except ValueError:
                 raise error.Abort(
                     _('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, 'a')
             except IOError as err:
                 raise error.Abort(_('could not open map file %r: %s') %
                                  (self.path, err.strerror))
         self.fp.write('%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 util.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/git.py

@@ -1,402 +1,390 b''
 # git.py - git support for the convert extension
 #
 #  Copyright 2005-2009 Matt 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 os
 import subprocess
 from mercurial import util, config, error
 from mercurial.node import hex, nullid
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool, commandline
 
 class submodule(object):
     def __init__(self, path, node, url):
         self.path = path
         self.node = node
         self.url = url
 
     def hgsub(self):
         return "%s = [git]%s" % (self.path, self.url)
 
     def hgsubstate(self):
         return "%s %s" % (self.node, self.path)
 
 class convert_git(converter_source, commandline):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
-    if util.safehasattr(os, 'unsetenv'):
-        def gitpipe(self, s):
-            prevgitdir = os.environ.get('GIT_DIR')
-            os.environ['GIT_DIR'] = self.path
-            try:
-                return util.popen3(s)
-            finally:
-                if prevgitdir is None:
-                    del os.environ['GIT_DIR']
-                else:
-                    os.environ['GIT_DIR'] = prevgitdir
-
-    else:
-        def gitpipe(self, s):
-            return util.popen3('GIT_DIR=%s %s' % (self.path, s))
 
     def _gitcmd(self, cmd, *args, **kwargs):
         return cmd('--git-dir=%s' % self.path, *args, **kwargs)
 
     def gitrun0(self, *args, **kwargs):
         return self._gitcmd(self.run0, *args, **kwargs)
 
     def gitrun(self, *args, **kwargs):
         return self._gitcmd(self.run, *args, **kwargs)
 
     def gitrunlines0(self, *args, **kwargs):
         return self._gitcmd(self.runlines0, *args, **kwargs)
 
     def gitrunlines(self, *args, **kwargs):
         return self._gitcmd(self.runlines, *args, **kwargs)
 
+    def gitpipe(self, *args, **kwargs):
+        return self._gitcmd(self._run3, *args, **kwargs)
+
     def gitread(self, s):
         fh = self.gitopen(s)
         data = fh.read()
         return data, fh.close()
 
     def __init__(self, ui, path, revs=None):
         super(convert_git, self).__init__(ui, path, revs=revs)
         commandline.__init__(self, ui, 'git')
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
             raise NoRepo(_("%s does not look like a Git repository") % path)
 
         # The default value (50) is based on the default for 'git diff'.
         similarity = ui.configint('convert', 'git.similarity', default=50)
         if similarity < 0 or similarity > 100:
             raise error.Abort(_('similarity must be between 0 and 100'))
         if similarity > 0:
             self.simopt = ['-C%d%%' % similarity]
             findcopiesharder = ui.configbool('convert', 'git.findcopiesharder',
                                              False)
             if findcopiesharder:
                 self.simopt.append('--find-copies-harder')
         else:
             self.simopt = []
 
         checktool('git', 'git')
 
         self.path = path
         self.submodules = []
 
-        self.catfilepipe = self.gitpipe('git cat-file --batch')
+        self.catfilepipe = self.gitpipe('cat-file', '--batch')
 
     def after(self):
         for f in self.catfilepipe:
             f.close()
 
     def getheads(self):
         if not self.revs:
             output, status = self.gitrun('rev-parse', '--branches', '--remotes')
             heads = output.splitlines()
             if status:
                 raise error.Abort(_('cannot retrieve git heads'))
         else:
             heads = []
             for rev in self.revs:
                 rawhead, ret = self.gitrun('rev-parse', '--verify', rev)
                 heads.append(rawhead[:-1])
                 if ret:
                     raise error.Abort(_('cannot retrieve git head "%s"') % rev)
         return heads
 
     def catfile(self, rev, type):
         if rev == hex(nullid):
             raise IOError
         self.catfilepipe[0].write(rev+'\n')
         self.catfilepipe[0].flush()
         info = self.catfilepipe[1].readline().split()
         if info[1] != type:
             raise error.Abort(_('cannot read %r object at %s') % (type, rev))
         size = int(info[2])
         data = self.catfilepipe[1].read(size)
         if len(data) < size:
             raise error.Abort(_('cannot read %r object at %s: unexpected size')
                              % (type, rev))
         # read the trailing newline
         self.catfilepipe[1].read(1)
         return data
 
     def getfile(self, name, rev):
         if rev == hex(nullid):
             return None, None
         if name == '.hgsub':
             data = '\n'.join([m.hgsub() for m in self.submoditer()])
             mode = ''
         elif name == '.hgsubstate':
             data = '\n'.join([m.hgsubstate() for m in self.submoditer()])
             mode = ''
         else:
             data = self.catfile(rev, "blob")
             mode = self.modecache[(name, rev)]
         return data, mode
 
     def submoditer(self):
         null = hex(nullid)
         for m in sorted(self.submodules, key=lambda p: p.path):
             if m.node != null:
                 yield m
 
     def parsegitmodules(self, content):
         """Parse the formatted .gitmodules file, example file format:
         [submodule "sub"]\n
         \tpath = sub\n
         \turl = git://giturl\n
         """
         self.submodules = []
         c = config.config()
         # Each item in .gitmodules starts with whitespace that cant be parsed
         c.parse('.gitmodules', '\n'.join(line.strip() for line in
                                content.split('\n')))
         for sec in c.sections():
             s = c[sec]
             if 'url' in s and 'path' in s:
                 self.submodules.append(submodule(s['path'], '', s['url']))
 
     def retrievegitmodules(self, version):
         modules, ret = self.gitrun('show', '%s:%s' % (version, '.gitmodules'))
         if ret:
             # This can happen if a file is in the repo that has permissions
             # 160000, but there is no .gitmodules file.
             self.ui.warn(_("warning: cannot read submodules config file in "
                            "%s\n") % version)
             return
 
         try:
             self.parsegitmodules(modules)
         except error.ParseError:
             self.ui.warn(_("warning: unable to parse .gitmodules in %s\n")
                          % version)
             return
 
         for m in self.submodules:
             node, ret = self.gitrun('rev-parse', '%s:%s' % (version, m.path))
             if ret:
                 continue
             m.node = node.strip()
 
     def getchanges(self, version, full):
         if full:
             raise error.Abort(_("convert from git does not support --full"))
         self.modecache = {}
         cmd = ['diff-tree','-z', '--root', '-m', '-r'] + self.simopt + [version]
         output, status = self.gitrun(*cmd)
         if status:
             raise error.Abort(_('cannot read changes in %s') % version)
         changes = []
         copies = {}
         seen = set()
         entry = None
         subexists = [False]
         subdeleted = [False]
         difftree = output.split('\x00')
         lcount = len(difftree)
         i = 0
 
         skipsubmodules = self.ui.configbool('convert', 'git.skipsubmodules',
                                             False)
         def add(entry, f, isdest):
             seen.add(f)
             h = entry[3]
             p = (entry[1] == "100755")
             s = (entry[1] == "120000")
             renamesource = (not isdest and entry[4][0] == 'R')
 
             if f == '.gitmodules':
                 if skipsubmodules:
                     return
 
                 subexists[0] = True
                 if entry[4] == 'D' or renamesource:
                     subdeleted[0] = True
                     changes.append(('.hgsub', hex(nullid)))
                 else:
                     changes.append(('.hgsub', ''))
             elif entry[1] == '160000' or entry[0] == ':160000':
                 if not skipsubmodules:
                     subexists[0] = True
             else:
                 if renamesource:
                     h = hex(nullid)
                 self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                 changes.append((f, h))
 
         while i < lcount:
             l = difftree[i]
             i += 1
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l.split()
                 continue
             f = l
             if entry[4][0] == 'C':
                 copysrc = f
                 copydest = difftree[i]
                 i += 1
                 f = copydest
                 copies[copydest] = copysrc
             if f not in seen:
                 add(entry, f, False)
             # A file can be copied multiple times, or modified and copied
             # simultaneously. So f can be repeated even if fdest isn't.
             if entry[4][0] == 'R':
                 # rename: next line is the destination
                 fdest = difftree[i]
                 i += 1
                 if fdest not in seen:
                     add(entry, fdest, True)
                     # .gitmodules isn't imported at all, so it being copied to
                     # and fro doesn't really make sense
                     if f != '.gitmodules' and fdest != '.gitmodules':
                         copies[fdest] = f
             entry = None
 
         if subexists[0]:
             if subdeleted[0]:
                 changes.append(('.hgsubstate', hex(nullid)))
             else:
                 self.retrievegitmodules(version)
                 changes.append(('.hgsubstate', ''))
         return (changes, copies, set())
 
     def getcommit(self, version):
         c = self.catfile(version, "commit") # read the commit hash
         end = c.find("\n\n")
         message = c[end + 2:]
         message = self.recode(message)
         l = c[:end].splitlines()
         parents = []
         author = committer = None
         for e in l[1:]:
             n, v = e.split(" ", 1)
             if n == "author":
                 p = v.split()
                 tm, tz = p[-2:]
                 author = " ".join(p[:-2])
                 if author[0] == "<": author = author[1:-1]
                 author = self.recode(author)
             if n == "committer":
                 p = v.split()
                 tm, tz = p[-2:]
                 committer = " ".join(p[:-2])
                 if committer[0] == "<": committer = committer[1:-1]
                 committer = self.recode(committer)
             if n == "parent":
                 parents.append(v)
 
         if committer and committer != author:
             message += "\ncommitter: %s\n" % committer
         tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
         tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
         date = tm + " " + str(tz)
 
         c = commit(parents=parents, date=date, author=author, desc=message,
                    rev=version)
         return c
 
     def numcommits(self):
         output, ret = self.gitrunlines('rev-list', '--all')
         if ret:
             raise error.Abort(_('cannot retrieve number of commits in %s') \
                               % self.path)
         return len(output)
 
     def gettags(self):
         tags = {}
         alltags = {}
         output, status = self.gitrunlines('ls-remote', '--tags', self.path)
 
         if status:
             raise error.Abort(_('cannot read tags from %s') % self.path)
         prefix = 'refs/tags/'
 
         # Build complete list of tags, both annotated and bare ones
         for line in output:
             line = line.strip()
             if line.startswith("error:") or line.startswith("fatal:"):
                 raise error.Abort(_('cannot read tags from %s') % self.path)
             node, tag = line.split(None, 1)
             if not tag.startswith(prefix):
                 continue
             alltags[tag[len(prefix):]] = node
 
         # Filter out tag objects for annotated tag refs
         for tag in alltags:
             if tag.endswith('^{}'):
                 tags[tag[:-3]] = alltags[tag]
             else:
                 if tag + '^{}' in alltags:
                     continue
                 else:
                     tags[tag] = alltags[tag]
 
         return tags
 
     def getchangedfiles(self, version, i):
         changes = []
         if i is None:
             output, status = self.gitrunlines('diff-tree', '--root', '-m',
                                               '-r', version)
             if status:
                 raise error.Abort(_('cannot read changes in %s') % version)
             for l in output:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
         else:
             output, status = self.gitrunlines('diff-tree', '--name-only',
                                               '--root', '-r', version,
                                               '%s^%s' % (version, i + 1), '--')
             changes = [f.rstrip('\n') for f in output]
 
         return changes
 
     def getbookmarks(self):
         bookmarks = {}
 
         # Handle local and remote branches
         remoteprefix = self.ui.config('convert', 'git.remoteprefix', 'remote')
         reftypes = [
             # (git prefix, hg prefix)
             ('refs/remotes/origin/', remoteprefix + '/'),
             ('refs/heads/', '')
         ]
 
         exclude = set([
             'refs/remotes/origin/HEAD',
         ])
 
         try:
             output, status = self.gitrunlines('show-ref')
             for line in output:
                 line = line.strip()
                 rev, name = line.split(None, 1)
                 # Process each type of branch
                 for gitprefix, hgprefix in reftypes:
                     if not name.startswith(gitprefix) or name in exclude:
                         continue
                     name = '%s%s' % (hgprefix, name[len(gitprefix):])
                     bookmarks[name] = rev
         except Exception:
             pass
 
         return bookmarks
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ git revision string is a 40 byte hex """
         self.checkhexformat(revstr, mapname)