configitems: register the 'convert.git.findcopiesharder' config

hgext/convert/__init__.py

@@ -1,531 +1,534
 # convert.py Foreign SCM converter
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''import revisions from foreign VCS repositories into Mercurial'''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     registrar,
 )
 
 from . import (
     convcmd,
     cvsps,
     subversion,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('convert', 'cvsps.cache',
     default=True,
 )
 configitem('convert', 'cvsps.fuzz',
     default=60,
 )
 configitem('convert', 'cvsps.mergefrom',
     default=None,
 )
 configitem('convert', 'cvsps.mergeto',
     default=None,
 )
 configitem('convert', 'git.committeractions',
     default=lambda: ['messagedifferent'],
 )
 configitem('convert', 'git.extrakeys',
     default=list,
 )
+configitem('convert', 'git.findcopiesharder',
+    default=False,
+)
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 @command('convert',
     [('', 'authors', '',
       _('username mapping filename (DEPRECATED) (use --authormap instead)'),
       _('FILE')),
     ('s', 'source-type', '', _('source repository type'), _('TYPE')),
     ('d', 'dest-type', '', _('destination repository type'), _('TYPE')),
     ('r', 'rev', [], _('import up to source revision REV'), _('REV')),
     ('A', 'authormap', '', _('remap usernames using this file'), _('FILE')),
     ('', 'filemap', '', _('remap file names using contents of file'),
      _('FILE')),
     ('', 'full', None,
      _('apply filemap changes by converting all files again')),
     ('', 'splicemap', '', _('splice synthesized history into place'),
      _('FILE')),
     ('', 'branchmap', '', _('change branch names while converting'),
      _('FILE')),
     ('', 'branchsort', None, _('try to sort changesets by branches')),
     ('', 'datesort', None, _('try to sort changesets by date')),
     ('', 'sourcesort', None, _('preserve source changesets order')),
     ('', 'closesort', None, _('try to reorder closed revisions'))],
    _('hg convert [OPTION]... SOURCE [DEST [REVMAP]]'),
    norepo=True)
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
 
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
     - Perforce [p4]
 
     Accepted destination formats [identifiers]:
 
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted.
     Otherwise, convert will only import up to the named revision
     (given in a format understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with ``-hg`` appended. If the destination
     repository doesn't exist, it will be created.
 
     By default, all sources except Mercurial will use --branchsort.
     Mercurial uses --sourcesort to preserve original revision numbers
     order. Sort modes have the following effects:
 
     --branchsort  convert from parent to child revision when possible,
                   which means branches are usually converted one after
                   the other. It generates more compact repositories.
 
     --datesort    sort revisions by date. Converted repositories have
                   good-looking changelogs but are often an order of
                   magnitude larger than the same ones generated by
                   --branchsort.
 
     --sourcesort  try to preserve source revisions order, only
                   supported by Mercurial sources.
 
     --closesort   try to move closed revisions as close as possible
                   to parent branches, only supported by Mercurial
                   sources.
 
     If ``REVMAP`` isn't given, it will be put in a default location
     (``<dest>/.hg/shamap`` by default). The ``REVMAP`` is a simple
     text file that maps each source commit ID to the destination ID
     for that revision, like so::
 
       <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created. It's
     updated on each commit copied, so :hg:`convert` can be interrupted
     and can be run repeatedly to copy new commits.
 
     The authormap is a simple text file that maps each source commit
     author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (e.g.: CVS). One line per
     author mapping and the line format is::
 
       source author = destination author
 
     Empty lines and lines starting with a ``#`` are ignored.
 
     The filemap is a file that allows filtering and remapping of files
     and directories. Each line can contain one of the following
     directives::
 
       include path/to/file-or-dir
 
       exclude path/to/file-or-dir
 
       rename path/to/source path/to/destination
 
     Comment lines start with ``#``. A specified path matches if it
     equals the full relative name of a file or one of its parent
     directories. The ``include`` or ``exclude`` directive with the
     longest matching path applies, so line order does not matter.
 
     The ``include`` directive causes a file, or all files under a
     directory, to be included in the destination repository. The default
     if there are no ``include`` statements is to include everything.
     If there are any ``include`` statements, nothing else is included.
     The ``exclude`` directive causes files or directories to
     be omitted. The ``rename`` directive renames a file or directory if
     it is converted. To rename from a subdirectory into the root of
     the repository, use ``.`` as the path to rename to.
 
     ``--full`` will make sure the converted changesets contain exactly
     the right files with the right content. It will make a full
     conversion of all files, not just the ones that have
     changed. Files that already are correct will not be changed. This
     can be used to apply filemap changes when converting
     incrementally. This is currently only supported for Mercurial and
     Subversion.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision. This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together. Each entry
     contains a key, followed by a space, followed by one or two
     comma-separated values::
 
       key parent1, parent2
 
     The key is the revision ID in the source
     revision control system whose parents should be modified (same
     format as a key in .hg/shamap). The values are the revision IDs
     (in either the source or destination revision control system) that
     should be used as the new parents for that node. For example, if
     you have merged "release-1.0" into "trunk", then you should
     specify the revision on "trunk" as the first parent and the one on
     the "release-1.0" branch as the second.
 
     The branchmap is a file that allows you to rename a branch when it is
     being brought in from whatever external repository. When used in
     conjunction with a splicemap, it allows for a powerful combination
     to help fix even the most badly mismanaged repositories and turn them
     into nicely structured Mercurial repositories. The branchmap contains
     lines of the form::
 
       original_branch_name new_branch_name
 
     where "original_branch_name" is the name of the branch in the
     source repository, and "new_branch_name" is the name of the branch
     is the destination repository. No whitespace is allowed in the new
     branch name. This can be used to (for instance) move code in one
     repository from "default" to a named branch.
 
     Mercurial Source
     ################
 
     The Mercurial source recognizes the following configuration
     options, which you can set on the command line with ``--config``:
 
     :convert.hg.ignoreerrors: ignore integrity errors when reading.
         Use it to fix Mercurial repositories with missing revlogs, by
         converting from and to Mercurial. Default is False.
 
     :convert.hg.saverev: store original revision ID in changeset
         (forces target IDs to change). It takes a boolean argument and
         defaults to False.
 
     :convert.hg.startrev: specify the initial Mercurial revision.
         The default is 0.
 
     :convert.hg.revs: revset specifying the source revisions to convert.
 
     CVS Source
     ##########
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course the
     repository is ``:local:``. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganization in the CVS
     sandbox is ignored.
 
     The following options can be used with ``--config``:
 
     :convert.cvsps.cache: Set to False to disable remote log caching,
         for testing and debugging purposes. Default is True.
 
     :convert.cvsps.fuzz: Specify the maximum time (in seconds) that is
         allowed between commits with identical user and log message in
         a single changeset. When very large files were checked in as
         part of a changeset then the default may not be long enough.
         The default is 60.
 
     :convert.cvsps.logencoding: Specify encoding name to be used for
         transcoding CVS log messages. Multiple encoding names can be
         specified as a list (see :hg:`help config.Syntax`), but only
         the first acceptable encoding in the list is used per CVS log
         entries. This transcoding is executed before cvslog hook below.
 
     :convert.cvsps.mergeto: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will insert a dummy revision merging the
         branch on which this log message occurs to the branch
         indicated in the regex. Default is ``{{mergetobranch
         ([-\\w]+)}}``
 
     :convert.cvsps.mergefrom: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will add the most recent revision on the
         branch indicated in the regex as the second parent of the
         changeset. Default is ``{{mergefrombranch ([-\\w]+)}}``
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     :hooks.cvslog: Specify a Python function to be called at the end of
         gathering the CVS log. The function is passed a list with the
         log entries, and can modify the entries in-place, or add or
         delete them.
 
     :hooks.cvschangesets: Specify a Python function to be called after
         the changesets are calculated from the CVS log. The
         function is passed a list with the changeset entries, and can
         modify the changesets in-place, or add or delete them.
 
     An additional "debugcvsps" Mercurial command allows the builtin
     changeset merging code to be run without doing a conversion. Its
     parameters and output are similar to that of cvsps 2.1. Please see
     the command help for more details.
 
     Subversion Source
     #################
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied ``svn://repo/path/`` source URL is
     converted as a single branch. If ``svn://repo/path/trunk`` exists
     it replaces the default branch. If ``svn://repo/path/branches``
     exists, its subdirectories are listed as possible branches. If
     ``svn://repo/path/tags`` exists, it is looked for tags referencing
     converted branches. Default ``trunk``, ``branches`` and ``tags``
     values can be overridden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable auto
     detection.
 
     The following options can be set with ``--config``:
 
     :convert.svn.branches: specify the directory containing branches.
         The default is ``branches``.
 
     :convert.svn.tags: specify the directory containing tags. The
         default is ``tags``.
 
     :convert.svn.trunk: specify the name of the trunk branch. The
         default is ``trunk``.
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     :convert.svn.startrev: specify start Subversion revision number.
         The default is 0.
 
     Git Source
     ##########
 
     The Git importer converts commits from all reachable branches (refs
     in refs/heads) and remotes (refs in refs/remotes) to Mercurial.
     Branches are converted to bookmarks with the same name, with the
     leading 'refs/heads' stripped. Git submodules are converted to Git
     subrepos in Mercurial.
 
     The following options can be set with ``--config``:
 
     :convert.git.similarity: specify how similar files modified in a
         commit must be to be imported as renames or copies, as a
         percentage between ``0`` (disabled) and ``100`` (files must be
         identical). For example, ``90`` means that a delete/add pair will
         be imported as a rename if more than 90% of the file hasn't
         changed. The default is ``50``.
 
     :convert.git.findcopiesharder: while detecting copies, look at all
         files in the working copy instead of just changed ones. This
         is very expensive for large projects, and is only effective when
         ``convert.git.similarity`` is greater than 0. The default is False.
 
     :convert.git.renamelimit: perform rename and copy detection up to this
         many changed files in a commit. Increasing this will make rename
         and copy detection more accurate but will significantly slow down
         computation on large projects. The option is only relevant if
         ``convert.git.similarity`` is greater than 0. The default is
         ``400``.
 
     :convert.git.committeractions: list of actions to take when processing
         author and committer values.
 
         Git commits have separate author (who wrote the commit) and committer
         (who applied the commit) fields. Not all destinations support separate
         author and committer fields (including Mercurial). This config option
         controls what to do with these author and committer fields during
         conversion.
 
         A value of ``messagedifferent`` will append a ``committer: ...``
         line to the commit message if the Git committer is different from the
         author. The prefix of that line can be specified using the syntax
         ``messagedifferent=<prefix>``. e.g. ``messagedifferent=git-committer:``.
         When a prefix is specified, a space will always be inserted between the
         prefix and the value.
 
         ``messagealways`` behaves like ``messagedifferent`` except it will
         always result in a ``committer: ...`` line being appended to the commit
         message. This value is mutually exclusive with ``messagedifferent``.
 
         ``dropcommitter`` will remove references to the committer. Only
         references to the author will remain. Actions that add references
         to the committer will have no effect when this is set.
 
         ``replaceauthor`` will replace the value of the author field with
         the committer. Other actions that add references to the committer
         will still take effect when this is set.
 
         The default is ``messagedifferent``.
 
     :convert.git.extrakeys: list of extra keys from commit metadata to copy to
         the destination. Some Git repositories store extra metadata in commits.
         By default, this non-default metadata will be lost during conversion.
         Setting this config option can retain that metadata. Some built-in
         keys such as ``parent`` and ``branch`` are not allowed to be copied.
 
     :convert.git.remoteprefix: remote refs are converted as bookmarks with
         ``convert.git.remoteprefix`` as a prefix followed by a /. The default
         is 'remote'.
 
     :convert.git.saverev: whether to store the original Git commit ID in the
         metadata of the destination commit. The default is True.
 
     :convert.git.skipsubmodules: does not convert root level .gitmodules files
         or files with 160000 mode indicating a submodule. Default is False.
 
     Perforce Source
     ###############
 
     The Perforce (P4) importer can be given a p4 depot path or a
     client specification as source. It will convert all files in the
     source to a flat Mercurial repository, ignoring labels, branches
     and integrations. Note that when a depot path is given you then
     usually should specify a target directory, because otherwise the
     target may be named ``...-hg``.
 
     The following options can be set with ``--config``:
 
     :convert.p4.encoding: specify the encoding to use when decoding standard
         output of the Perforce command line tool. The default is default system
         encoding.
 
     :convert.p4.startrev: specify initial Perforce revision (a
         Perforce changelist number).
 
     Mercurial Destination
     #####################
 
     The Mercurial destination will recognize Mercurial subrepositories in the
     destination directory, and update the .hgsubstate file automatically if the
     destination subrepositories contain the <dest>/<sub>/.hg/shamap file.
     Converting a repository with subrepositories requires converting a single
     repository at a time, from the bottom up.
 
     .. container:: verbose
 
        An example showing how to convert a repository with subrepositories::
 
          # so convert knows the type when it sees a non empty destination
          $ hg init converted
 
          $ hg convert orig/sub1 converted/sub1
          $ hg convert orig/sub2 converted/sub2
          $ hg convert orig converted
 
     The following options are supported:
 
     :convert.hg.clonebranches: dispatch source branches in separate
         clones. The default is False.
 
     :convert.hg.tagsbranch: branch name for tag revisions, defaults to
         ``default``.
 
     :convert.hg.usebranchnames: preserve branch names. The default is
         True.
 
     :convert.hg.sourcename: records the given string as a 'convert_source' extra
         value on each commit made in the target repository. The default is None.
 
     All Destinations
     ################
 
     All destination types accept the following options:
 
     :convert.skiptags: does not convert tags from the source repo to the target
         repo. The default is False.
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 @command('debugsvnlog', [], 'hg debugsvnlog', norepo=True)
 def debugsvnlog(ui, **opts):
     return subversion.debugsvnlog(ui, **opts)
 
 @command('debugcvsps',
     [
     # Main options shared with cvsps-2.1
     ('b', 'branches', [], _('only return changes on specified branches')),
     ('p', 'prefix', '', _('prefix to remove from file names')),
     ('r', 'revisions', [],
      _('only return changes after or between specified tags')),
     ('u', 'update-cache', None, _("update cvs log cache")),
     ('x', 'new-cache', None, _("create new cvs log cache")),
     ('z', 'fuzz', 60, _('set commit time fuzz in seconds')),
     ('', 'root', '', _('specify cvsroot')),
     # Options specific to builtin cvsps
     ('', 'parents', '', _('show parent changesets')),
     ('', 'ancestors', '', _('show current changeset in ancestor branches')),
     # Options that are ignored for compatibility with cvsps-2.1
     ('A', 'cvs-direct', None, _('ignored for compatibility')),
     ],
     _('hg debugcvsps [OPTION]... [PATH]...'),
     norepo=True)
 def debugcvsps(ui, *args, **opts):
     '''create changeset information from CVS
 
     This command is intended as a debugging tool for the CVS to
     Mercurial converter, and can be used as a direct replacement for
     cvsps.
 
     Hg debugcvsps reads the CVS rlog for current directory (or any
     named directory) in the CVS repository, and converts the log to a
     series of changesets based on matching commit log entries and
     dates.'''
     return cvsps.debugcvsps(ui, *args, **opts)
 
 def kwconverted(ctx, name):
     rev = ctx.extra().get('convert_revision', '')
     if rev.startswith('svn:'):
         if name == 'svnrev':
             return str(subversion.revsplit(rev)[2])
         elif name == 'svnpath':
             return subversion.revsplit(rev)[1]
         elif name == 'svnuuid':
             return subversion.revsplit(rev)[0]
     return rev
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('svnrev')
 def kwsvnrev(repo, ctx, **args):
     """String. Converted subversion revision number."""
     return kwconverted(ctx, 'svnrev')
 
 @templatekeyword('svnpath')
 def kwsvnpath(repo, ctx, **args):
     """String. Converted subversion revision project path."""
     return kwconverted(ctx, 'svnpath')
 
 @templatekeyword('svnuuid')
 def kwsvnuuid(repo, ctx, **args):
     """String. Converted subversion revision repository identifier."""
     return kwconverted(ctx, 'svnuuid')
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [kwsvnrev, kwsvnpath, kwsvnuuid]

hgext/convert/git.py

@@ -1,479 +1,478
 # 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.
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     config,
     error,
     node as nodemod,
 )
 
 from . import (
     common,
 )
 
 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)
 
 # Keys in extra fields that should not be copied if the user requests.
 bannedextrakeys = {
     # Git commit object built-ins.
     'tree',
     'parent',
     'author',
     'committer',
     # Mercurial built-ins.
     'branch',
     'close',
 }
 
 class convert_git(common.converter_source, common.commandline):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
 
     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 __init__(self, ui, path, revs=None):
         super(convert_git, self).__init__(ui, path, revs=revs)
         common.commandline.__init__(self, ui, 'git')
 
         # Pass an absolute path to git to prevent from ever being interpreted
         # as a URL
         path = os.path.abspath(path)
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
             raise common.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)
+            findcopiesharder = ui.configbool('convert', 'git.findcopiesharder')
             if findcopiesharder:
                 self.simopt.append('--find-copies-harder')
 
             renamelimit = ui.configint('convert', 'git.renamelimit',
                                        default=400)
             self.simopt.append('-l%d' % renamelimit)
         else:
             self.simopt = []
 
         common.checktool('git', 'git')
 
         self.path = path
         self.submodules = []
 
         self.catfilepipe = self.gitpipe('cat-file', '--batch')
 
         self.copyextrakeys = self.ui.configlist('convert', 'git.extrakeys')
         banned = set(self.copyextrakeys) & bannedextrakeys
         if banned:
             raise error.Abort(_('copying of extra key is forbidden: %s') %
                               _(', ').join(sorted(banned)))
 
         committeractions = self.ui.configlist('convert', 'git.committeractions')
 
         messagedifferent = None
         messagealways = None
         for a in committeractions:
             if a.startswith(('messagedifferent', 'messagealways')):
                 k = a
                 v = None
                 if '=' in a:
                     k, v = a.split('=', 1)
 
                 if k == 'messagedifferent':
                     messagedifferent = v or 'committer:'
                 elif k == 'messagealways':
                     messagealways = v or 'committer:'
 
         if messagedifferent and messagealways:
             raise error.Abort(_('committeractions cannot define both '
                                 'messagedifferent and messagealways'))
 
         dropcommitter = 'dropcommitter' in committeractions
         replaceauthor = 'replaceauthor' in committeractions
 
         if dropcommitter and replaceauthor:
             raise error.Abort(_('committeractions cannot define both '
                                 'dropcommitter and replaceauthor'))
 
         if dropcommitter and messagealways:
             raise error.Abort(_('committeractions cannot define both '
                                 'dropcommitter and messagealways'))
 
         if not messagedifferent and not messagealways:
             messagedifferent = 'committer:'
 
         self.committeractions = {
             'dropcommitter': dropcommitter,
             'replaceauthor': replaceauthor,
             'messagedifferent': messagedifferent,
             'messagealways': messagealways,
         }
 
     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 == nodemod.nullhex:
             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 == nodemod.nullhex:
             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 = nodemod.nullhex
         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', nodemod.nullhex))
                 else:
                     changes.append(('.hgsub', ''))
             elif entry[1] == '160000' or entry[0] == ':160000':
                 if not skipsubmodules:
                     subexists[0] = True
             else:
                 if renamesource:
                     h = nodemod.nullhex
                 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', nodemod.nullhex))
             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
         extra = {}
         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 n in self.copyextrakeys:
                 extra[n] = v
 
         if self.committeractions['dropcommitter']:
             committer = None
         elif self.committeractions['replaceauthor']:
             author = committer
 
         if committer:
             messagealways = self.committeractions['messagealways']
             messagedifferent = self.committeractions['messagedifferent']
             if messagealways:
                 message += '\n%s %s\n' % (messagealways, committer)
             elif messagedifferent and author != committer:
                 message += '\n%s %s\n' % (messagedifferent, 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)
         saverev = self.ui.configbool('convert', 'git.saverev', True)
 
         c = common.commit(parents=parents, date=date, author=author,
                           desc=message,
                           rev=version,
                           extra=extra,
                           saverev=saverev)
         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), '--')
             if status:
                 raise error.Abort(_('cannot read changes in %s') % version)
             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 = {
             '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)