convert: add convert.git.skipsubmodules option

This adds an option to not pull in gitsubmodules during a convert. This is
useful when converting large git repositories where gitsubmodules were allowed
historically, but are no longer wanted.

hgext/convert/__init__.py

@@ -1,447 +1,450 b''
 # 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'''
 
 import convcmd
 import cvsps
 import subversion
 from mercurial import cmdutil, templatekw
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'internal' 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 = 'internal'
 
 # 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
     branch names. 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.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.remoteprefix: remote refs are converted as bookmarks with
         ``convert.git.remoteprefix`` as a prefix followed by a /. The default
         is 'remote'.
 
+    :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
 
 def kwsvnrev(repo, ctx, **args):
     """:svnrev: String. Converted subversion revision number."""
     return kwconverted(ctx, 'svnrev')
 
 def kwsvnpath(repo, ctx, **args):
     """:svnpath: String. Converted subversion revision project path."""
     return kwconverted(ctx, 'svnpath')
 
 def kwsvnuuid(repo, ctx, **args):
     """:svnuuid: String. Converted subversion revision repository identifier."""
     return kwconverted(ctx, 'svnuuid')
 
 def extsetup(ui):
     templatekw.keywords['svnrev'] = kwsvnrev
     templatekw.keywords['svnpath'] = kwsvnpath
     templatekw.keywords['svnuuid'] = kwsvnuuid
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [kwsvnrev, kwsvnpath, kwsvnuuid]

hgext/convert/git.py

@@ -1,410 +1,416 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
 
 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):
     # 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 gitopen(self, s, err=None):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 if err == subprocess.PIPE:
                     (stdin, stdout, stderr) = util.popen3(s)
                     return stdout
                 elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
                 else:
                     return util.popen(s, 'rb')
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
 
         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 gitopen(self, s, err=None):
             if err == subprocess.PIPE:
                 (sin, so, se) = util.popen3('GIT_DIR=%s %s' % (self.path, s))
                 return so
             elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
             else:
                 return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')
 
         def gitpipe(self, s):
             return util.popen3('GIT_DIR=%s %s' % (self.path, s))
 
     def popen_with_stderr(self, s):
         p = subprocess.Popen(s, shell=True, bufsize=-1,
                              close_fds=util.closefds,
                              stdin=subprocess.PIPE,
                              stdout=subprocess.PIPE,
                              stderr=subprocess.STDOUT,
                              universal_newlines=False,
                              env=None)
         return p.stdout
 
     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)
 
         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 util.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 += ' --find-copies-harder'
         else:
             self.simopt = ''
 
         checktool('git', 'git')
 
         self.path = path
         self.submodules = []
 
         self.catfilepipe = self.gitpipe('git cat-file --batch')
 
     def after(self):
         for f in self.catfilepipe:
             f.close()
 
     def getheads(self):
         if not self.revs:
             heads, ret = self.gitread('git rev-parse --branches --remotes')
             heads = heads.splitlines()
             if ret:
                 raise util.Abort(_('cannot retrieve git heads'))
         else:
             heads = []
             for rev in self.revs:
                 rawhead, ret = self.gitread("git rev-parse --verify %s" % rev)
                 heads.append(rawhead[:-1])
                 if ret:
                     raise util.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 util.Abort(_('cannot read %r object at %s') % (type, rev))
         size = int(info[2])
         data = self.catfilepipe[1].read(size)
         if len(data) < size:
             raise util.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.gitread("git 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.gitread("git rev-parse %s:%s" % (version, m.path))
             if ret:
                 continue
             m.node = node.strip()
 
     def getchanges(self, version, full):
         if full:
             raise util.Abort(_("convert from git do not support --full"))
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s %s" % (
             self.simopt, version))
         changes = []
         copies = {}
         seen = set()
         entry = None
         subexists = [False]
         subdeleted = [False]
         difftree = fh.read().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':
-                subexists[0] = True
+                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 fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         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):
         return len([None for _ in self.gitopen('git rev-list --all')])
 
     def gettags(self):
         tags = {}
         alltags = {}
         fh = self.gitopen('git ls-remote --tags "%s"' % self.path,
                           err=subprocess.STDOUT)
         prefix = 'refs/tags/'
 
         # Build complete list of tags, both annotated and bare ones
         for line in fh:
             line = line.strip()
             if line.startswith("error:") or line.startswith("fatal:"):
                 raise util.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
         if fh.close():
             raise util.Abort(_('cannot read tags from %s') % self.path)
 
         # 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:
             fh = self.gitopen("git diff-tree --root -m -r %s" % version)
             for l in fh:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
         else:
             fh = self.gitopen('git diff-tree --name-only --root -r %s '
                               '"%s^%s" --' % (version, version, i + 1))
             changes = [f.rstrip('\n') for f in fh]
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         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:
             fh = self.gitopen('git show-ref', err=subprocess.PIPE)
             for line in fh:
                 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)

tests/test-convert-git.t

@@ -1,728 +1,734 b''
 #require git
 
   $ echo "[core]" >> $HOME/.gitconfig
   $ echo "autocrlf = false" >> $HOME/.gitconfig
   $ echo "[core]" >> $HOME/.gitconfig
   $ echo "autocrlf = false" >> $HOME/.gitconfig
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "convert=" >> $HGRCPATH
   $ GIT_AUTHOR_NAME='test'; export GIT_AUTHOR_NAME
   $ GIT_AUTHOR_EMAIL='[e-mail]'; export GIT_AUTHOR_EMAIL
   $ GIT_AUTHOR_DATE="2007-01-01 00:00:00 +0000"; export GIT_AUTHOR_DATE
   $ GIT_COMMITTER_NAME="$GIT_AUTHOR_NAME"; export GIT_COMMITTER_NAME
   $ GIT_COMMITTER_EMAIL="$GIT_AUTHOR_EMAIL"; export GIT_COMMITTER_EMAIL
   $ GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"; export GIT_COMMITTER_DATE
   $ INVALIDID1=afd12345af
   $ INVALIDID2=28173x36ddd1e67bf7098d541130558ef5534a86
   $ VALIDID1=39b3d83f9a69a9ba4ebb111461071a0af0027357
   $ VALIDID2=8dd6476bd09d9c7776355dc454dafe38efaec5da
   $ count=10
   $ commit()
   > {
   >     GIT_AUTHOR_DATE="2007-01-01 00:00:$count +0000"
   >     GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"
   >     git commit "$@" >/dev/null 2>/dev/null || echo "git commit error"
   >     count=`expr $count + 1`
   > }
   $ mkdir git-repo
   $ cd git-repo
   $ git init-db >/dev/null 2>/dev/null
   $ echo a > a
   $ mkdir d
   $ echo b > d/b
   $ git add a d
   $ commit -a -m t1
 
 Remove the directory, then try to replace it with a file (issue754)
 
   $ git rm -f d/b
   rm 'd/b'
   $ commit -m t2
   $ echo d > d
   $ git add d
   $ commit -m t3
   $ echo b >> a
   $ commit -a -m t4.1
   $ git checkout -b other HEAD~ >/dev/null 2>/dev/null
   $ echo c > a
   $ echo a >> a
   $ commit -a -m t4.2
   $ git checkout master >/dev/null 2>/dev/null
   $ git pull --no-commit . other > /dev/null 2>/dev/null
   $ commit -m 'Merge branch other'
   $ cd ..
   $ hg convert --config extensions.progress= --config progress.assume-tty=1 \
   >   --config progress.delay=0 --config progress.changedelay=0 \
   >   --config progress.refresh=0 --config progress.width=60 \
   > --datesort git-repo
   \r (no-eol) (esc)
   scanning [======>                                     ] 1/6\r (no-eol) (esc)
   scanning [=============>                              ] 2/6\r (no-eol) (esc)
   scanning [=====================>                      ] 3/6\r (no-eol) (esc)
   scanning [============================>               ] 4/6\r (no-eol) (esc)
   scanning [===================================>        ] 5/6\r (no-eol) (esc)
   scanning [===========================================>] 6/6\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [                                          ] 0/6\r (no-eol) (esc)
   getting files [==================>                    ] 1/2\r (no-eol) (esc)
   getting files [======================================>] 2/2\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [======>                                   ] 1/6\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [=============>                            ] 2/6\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [====================>                     ] 3/6\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [===========================>              ] 4/6\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [==================================>       ] 5/6\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   assuming destination git-repo-hg
   initializing destination git-repo-hg repository
   scanning source...
   sorting...
   converting...
   5 t1
   4 t2
   3 t3
   2 t4.1
   1 t4.2
   0 Merge branch other
   updating bookmarks
   $ hg up -q -R git-repo-hg
   $ hg -R git-repo-hg tip -v
   changeset:   5:c78094926be2
   bookmark:    master
   tag:         tip
   parent:      3:f5f5cb45432b
   parent:      4:4e174f80c67c
   user:        test <[e-mail]>
   date:        Mon Jan 01 00:00:15 2007 +0000
   files:       a
   description:
   Merge branch other
   
   
   $ count=10
   $ mkdir git-repo2
   $ cd git-repo2
   $ git init-db >/dev/null 2>/dev/null
   $ echo foo > foo
   $ git add foo
   $ commit -a -m 'add foo'
   $ echo >> foo
   $ commit -a -m 'change foo'
   $ git checkout -b Bar HEAD~ >/dev/null 2>/dev/null
   $ echo quux >> quux
   $ git add quux
   $ commit -a -m 'add quux'
   $ echo bar > bar
   $ git add bar
   $ commit -a -m 'add bar'
   $ git checkout -b Baz HEAD~ >/dev/null 2>/dev/null
   $ echo baz > baz
   $ git add baz
   $ commit -a -m 'add baz'
   $ git checkout master >/dev/null 2>/dev/null
   $ git pull --no-commit . Bar Baz > /dev/null 2>/dev/null
   $ commit -m 'Octopus merge'
   $ echo bar >> bar
   $ commit -a -m 'change bar'
   $ git checkout -b Foo HEAD~ >/dev/null 2>/dev/null
   $ echo >> foo
   $ commit -a -m 'change foo'
   $ git checkout master >/dev/null 2>/dev/null
   $ git pull --no-commit -s ours . Foo > /dev/null 2>/dev/null
   $ commit -m 'Discard change to foo'
   $ cd ..
   $ glog()
   > {
   >     hg log -G --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
   > }
   $ splitrepo()
   > {
   >     msg="$1"
   >     files="$2"
   >     opts=$3
   >     echo "% $files: $msg"
   >     prefix=`echo "$files" | sed -e 's/ /-/g'`
   >     fmap="$prefix.fmap"
   >     repo="$prefix.repo"
   >     for i in $files; do
   >         echo "include $i" >> "$fmap"
   >     done
   >     hg -q convert $opts --filemap "$fmap" --datesort git-repo2 "$repo"
   >     hg up -q -R "$repo"
   >     glog -R "$repo"
   >     hg -R "$repo" manifest --debug
   > }
 
 full conversion
 
   $ hg convert --datesort git-repo2 fullrepo \
   > --config extensions.progress= --config progress.assume-tty=1 \
   > --config progress.delay=0 --config progress.changedelay=0 \
   > --config progress.refresh=0 --config progress.width=60
   \r (no-eol) (esc)
   scanning [===>                                        ] 1/9\r (no-eol) (esc)
   scanning [========>                                   ] 2/9\r (no-eol) (esc)
   scanning [=============>                              ] 3/9\r (no-eol) (esc)
   scanning [==================>                         ] 4/9\r (no-eol) (esc)
   scanning [=======================>                    ] 5/9\r (no-eol) (esc)
   scanning [============================>               ] 6/9\r (no-eol) (esc)
   scanning [=================================>          ] 7/9\r (no-eol) (esc)
   scanning [======================================>     ] 8/9\r (no-eol) (esc)
   scanning [===========================================>] 9/9\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [                                          ] 0/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [===>                                      ] 1/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [========>                                 ] 2/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [=============>                            ] 3/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [=================>                        ] 4/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [======================>                   ] 5/9\r (no-eol) (esc)
   getting files [===>                                   ] 1/8\r (no-eol) (esc)
   getting files [========>                              ] 2/8\r (no-eol) (esc)
   getting files [=============>                         ] 3/8\r (no-eol) (esc)
   getting files [==================>                    ] 4/8\r (no-eol) (esc)
   getting files [=======================>               ] 5/8\r (no-eol) (esc)
   getting files [============================>          ] 6/8\r (no-eol) (esc)
   getting files [=================================>     ] 7/8\r (no-eol) (esc)
   getting files [======================================>] 8/8\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [===========================>              ] 6/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [===============================>          ] 7/9\r (no-eol) (esc)
   getting files [======================================>] 1/1\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   \r (no-eol) (esc)
   converting [====================================>     ] 8/9\r (no-eol) (esc)
   getting files [==================>                    ] 1/2\r (no-eol) (esc)
   getting files [======================================>] 2/2\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
   initializing destination fullrepo repository
   scanning source...
   sorting...
   converting...
   8 add foo
   7 change foo
   6 add quux
   5 add bar
   4 add baz
   3 Octopus merge
   2 change bar
   1 change foo
   0 Discard change to foo
   updating bookmarks
   $ hg up -q -R fullrepo
   $ glog -R fullrepo
   @    9 "Discard change to foo" files: foo
   |\
   | o  8 "change foo" files: foo
   | |
   o |  7 "change bar" files: bar
   |/
   o    6 "(octopus merge fixup)" files:
   |\
   | o    5 "Octopus merge" files: baz
   | |\
   o | |  4 "add baz" files: baz
   | | |
   +---o  3 "add bar" files: bar
   | |
   o |  2 "add quux" files: quux
   | |
   | o  1 "change foo" files: foo
   |/
   o  0 "add foo" files: foo
   
   $ hg -R fullrepo manifest --debug
   245a3b8bc653999c2b22cdabd517ccb47aecafdf 644   bar
   354ae8da6e890359ef49ade27b68bbc361f3ca88 644   baz
   9277c9cc8dd4576fc01a17939b4351e5ada93466 644   foo
   88dfeab657e8cf2cef3dec67b914f49791ae76b1 644   quux
   $ splitrepo 'octopus merge' 'foo bar baz'
   % foo bar baz: octopus merge
   @    8 "Discard change to foo" files: foo
   |\
   | o  7 "change foo" files: foo
   | |
   o |  6 "change bar" files: bar
   |/
   o    5 "(octopus merge fixup)" files:
   |\
   | o    4 "Octopus merge" files: baz
   | |\
   o | |  3 "add baz" files: baz
   | | |
   +---o  2 "add bar" files: bar
   | |
   | o  1 "change foo" files: foo
   |/
   o  0 "add foo" files: foo
   
   245a3b8bc653999c2b22cdabd517ccb47aecafdf 644   bar
   354ae8da6e890359ef49ade27b68bbc361f3ca88 644   baz
   9277c9cc8dd4576fc01a17939b4351e5ada93466 644   foo
   $ splitrepo 'only some parents of an octopus merge; "discard" a head' 'foo baz quux'
   % foo baz quux: only some parents of an octopus merge; "discard" a head
   @  6 "Discard change to foo" files: foo
   |
   o  5 "change foo" files: foo
   |
   o    4 "Octopus merge" files:
   |\
   | o  3 "add baz" files: baz
   | |
   | o  2 "add quux" files: quux
   | |
   o |  1 "change foo" files: foo
   |/
   o  0 "add foo" files: foo
   
   354ae8da6e890359ef49ade27b68bbc361f3ca88 644   baz
   9277c9cc8dd4576fc01a17939b4351e5ada93466 644   foo
   88dfeab657e8cf2cef3dec67b914f49791ae76b1 644   quux
 
 test importing git renames and copies
 
   $ cd git-repo2
   $ git mv foo foo-renamed
 since bar is not touched in this commit, this copy will not be detected
   $ cp bar bar-copied
   $ cp baz baz-copied
   $ cp baz baz-copied2
   $ cp baz ba-copy
   $ echo baz2 >> baz
   $ git add bar-copied baz-copied baz-copied2 ba-copy
   $ commit -a -m 'rename and copy'
   $ cd ..
 
 input validation
   $ hg convert --config convert.git.similarity=foo --datesort git-repo2 fullrepo
   abort: convert.git.similarity is not an integer ('foo')
   [255]
   $ hg convert --config convert.git.similarity=-1 --datesort git-repo2 fullrepo
   abort: similarity must be between 0 and 100
   [255]
   $ hg convert --config convert.git.similarity=101 --datesort git-repo2 fullrepo
   abort: similarity must be between 0 and 100
   [255]
 
   $ hg -q convert --config convert.git.similarity=100 --datesort git-repo2 fullrepo
   $ hg -R fullrepo status -C --change master
   M baz
   A ba-copy
     baz
   A bar-copied
   A baz-copied
     baz
   A baz-copied2
     baz
   A foo-renamed
     foo
   R foo
 
 Ensure that the modification to the copy source was preserved
 (there was a bug where if the copy dest was alphabetically prior to the copy
 source, the copy source took the contents of the copy dest)
   $ hg cat -r tip fullrepo/baz
   baz
   baz2
 
   $ cd git-repo2
   $ echo bar2 >> bar
   $ commit -a -m 'change bar'
   $ cp bar bar-copied2
   $ git add bar-copied2
   $ commit -a -m 'copy with no changes'
   $ cd ..
 
   $ hg -q convert --config convert.git.similarity=100 \
   > --config convert.git.findcopiesharder=1 --datesort git-repo2 fullrepo
   $ hg -R fullrepo status -C --change master
   A bar-copied2
     bar
 
 test binary conversion (issue1359)
 
   $ count=19
   $ mkdir git-repo3
   $ cd git-repo3
   $ git init-db >/dev/null 2>/dev/null
   $ $PYTHON -c 'file("b", "wb").write("".join([chr(i) for i in range(256)])*16)'
   $ git add b
   $ commit -a -m addbinary
   $ cd ..
 
 convert binary file
 
   $ hg convert git-repo3 git-repo3-hg
   initializing destination git-repo3-hg repository
   scanning source...
   sorting...
   converting...
   0 addbinary
   updating bookmarks
   $ cd git-repo3-hg
   $ hg up -C
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ $PYTHON -c 'print len(file("b", "rb").read())'
   4096
   $ cd ..
 
 test author vs committer
 
   $ mkdir git-repo4
   $ cd git-repo4
   $ git init-db >/dev/null 2>/dev/null
   $ echo >> foo
   $ git add foo
   $ commit -a -m addfoo
   $ echo >> foo
   $ GIT_AUTHOR_NAME="nottest"
   $ commit -a -m addfoo2
   $ cd ..
 
 convert author committer
 
   $ hg convert git-repo4 git-repo4-hg
   initializing destination git-repo4-hg repository
   scanning source...
   sorting...
   converting...
   1 addfoo
   0 addfoo2
   updating bookmarks
   $ hg -R git-repo4-hg log -v
   changeset:   1:d63e967f93da
   bookmark:    master
   tag:         tip
   user:        nottest <[e-mail]>
   date:        Mon Jan 01 00:00:21 2007 +0000
   files:       foo
   description:
   addfoo2
   
   committer: test <[e-mail]>
   
   
   changeset:   0:0735477b0224
   user:        test <[e-mail]>
   date:        Mon Jan 01 00:00:20 2007 +0000
   files:       foo
   description:
   addfoo
   
   
 
 --sourceorder should fail
 
   $ hg convert --sourcesort git-repo4 git-repo4-sourcesort-hg
   initializing destination git-repo4-sourcesort-hg repository
   abort: --sourcesort is not supported by this data source
   [255]
 
 test converting certain branches
 
   $ mkdir git-testrevs
   $ cd git-testrevs
   $ git init
   Initialized empty Git repository in $TESTTMP/git-testrevs/.git/
   $ echo a >> a ; git add a > /dev/null; git commit -m 'first' > /dev/null
   $ echo a >> a ; git add a > /dev/null; git commit -m 'master commit' > /dev/null
   $ git checkout -b goodbranch 'HEAD^'
   Switched to a new branch 'goodbranch'
   $ echo a >> b ; git add b > /dev/null; git commit -m 'good branch commit' > /dev/null
   $ git checkout -b badbranch 'HEAD^'
   Switched to a new branch 'badbranch'
   $ echo a >> c ; git add c > /dev/null; git commit -m 'bad branch commit' > /dev/null
   $ cd ..
   $ hg convert git-testrevs hg-testrevs --rev master --rev goodbranch
   initializing destination hg-testrevs repository
   scanning source...
   sorting...
   converting...
   2 first
   1 good branch commit
   0 master commit
   updating bookmarks
   $ cd hg-testrevs
   $ hg log -G -T '{rev} {bookmarks}'
   o  2 master
   |
   | o  1 goodbranch
   |/
   o  0
   
   $ cd ..
 
 test sub modules
 
   $ mkdir git-repo5
   $ cd git-repo5
   $ git init-db >/dev/null 2>/dev/null
   $ echo 'sub' >> foo
   $ git add foo
   $ commit -a -m 'addfoo'
   $ BASE=`pwd`
   $ cd ..
   $ mkdir git-repo6
   $ cd git-repo6
   $ git init-db >/dev/null 2>/dev/null
   $ git submodule add ${BASE} >/dev/null 2>/dev/null
   $ commit -a -m 'addsubmodule' >/dev/null 2>/dev/null
 
 test non-tab whitespace .gitmodules
 
   $ cat >> .gitmodules <<EOF
   > [submodule "git-repo5"]
   >   path = git-repo5
   >   url = git-repo5
   > EOF
   $ git commit -q -a -m "weird white space submodule"
   $ cd ..
   $ hg convert git-repo6 hg-repo6
   initializing destination hg-repo6 repository
   scanning source...
   sorting...
   converting...
   1 addsubmodule
   0 weird white space submodule
   updating bookmarks
 
   $ rm -rf hg-repo6
   $ cd git-repo6
   $ git reset --hard 'HEAD^' > /dev/null
 
 test missing .gitmodules
 
   $ git submodule add ../git-repo4 >/dev/null 2>/dev/null
   $ git checkout HEAD .gitmodules
   $ git rm .gitmodules
   rm '.gitmodules'
   $ git commit -q -m "remove .gitmodules" .gitmodules
   $ git commit -q -m "missing .gitmodules"
   $ cd ..
   $ hg convert git-repo6 hg-repo6 --traceback
   fatal: Path '.gitmodules' does not exist in '*' (glob)
   initializing destination hg-repo6 repository
   scanning source...
   sorting...
   converting...
   2 addsubmodule
   1 remove .gitmodules
   0 missing .gitmodules
   warning: cannot read submodules config file in * (glob)
   updating bookmarks
   $ rm -rf hg-repo6
   $ cd git-repo6
   $ rm -rf git-repo4
   $ git reset --hard 'HEAD^^' > /dev/null
   $ cd ..
 
 test invalid splicemap1
 
   $ cat > splicemap <<EOF
   > $VALIDID1
   > EOF
   $ hg convert --splicemap splicemap git-repo2 git-repo2-splicemap1-hg
   initializing destination git-repo2-splicemap1-hg repository
   abort: syntax error in splicemap(1): child parent1[,parent2] expected
   [255]
 
 test invalid splicemap2
 
   $ cat > splicemap <<EOF
   > $VALIDID1 $VALIDID2, $VALIDID2, $VALIDID2
   > EOF
   $ hg convert --splicemap splicemap git-repo2 git-repo2-splicemap2-hg
   initializing destination git-repo2-splicemap2-hg repository
   abort: syntax error in splicemap(1): child parent1[,parent2] expected
   [255]
 
 test invalid splicemap3
 
   $ cat > splicemap <<EOF
   > $INVALIDID1 $INVALIDID2
   > EOF
   $ hg convert --splicemap splicemap git-repo2 git-repo2-splicemap3-hg
   initializing destination git-repo2-splicemap3-hg repository
   abort: splicemap entry afd12345af is not a valid revision identifier
   [255]
 
 convert sub modules
   $ hg convert git-repo6 git-repo6-hg
   initializing destination git-repo6-hg repository
   scanning source...
   sorting...
   converting...
   0 addsubmodule
   updating bookmarks
   $ hg -R git-repo6-hg log -v
   changeset:   0:* (glob)
   bookmark:    master
   tag:         tip
   user:        nottest <[e-mail]>
   date:        Mon Jan 01 00:00:23 2007 +0000
   files:       .hgsub .hgsubstate
   description:
   addsubmodule
   
   committer: test <[e-mail]>
   
   
 
   $ cd git-repo6-hg
   $ hg up >/dev/null 2>/dev/null
   $ cat .hgsubstate
   * git-repo5 (glob)
   $ cd git-repo5
   $ cat foo
   sub
 
   $ cd ../..
 
 make sure rename detection doesn't break removing and adding gitmodules
 
   $ cd git-repo6
   $ git mv .gitmodules .gitmodules-renamed
   $ commit -a -m 'rename .gitmodules'
   $ git mv .gitmodules-renamed .gitmodules
   $ commit -a -m 'rename .gitmodules back'
   $ cd ..
 
   $ hg --config convert.git.similarity=100 convert -q git-repo6 git-repo6-hg
   $ hg -R git-repo6-hg log -r 'tip^' -T "{desc|firstline}\n"
   rename .gitmodules
   $ hg -R git-repo6-hg status -C --change 'tip^'
   A .gitmodules-renamed
   R .hgsub
   R .hgsubstate
   $ hg -R git-repo6-hg log -r tip -T "{desc|firstline}\n"
   rename .gitmodules back
   $ hg -R git-repo6-hg status -C --change tip
   A .hgsub
   A .hgsubstate
   R .gitmodules-renamed
 
 convert the revision removing '.gitmodules' itself (and related
 submodules)
 
   $ cd git-repo6
   $ git rm .gitmodules
   rm '.gitmodules'
   $ git rm --cached git-repo5
   rm 'git-repo5'
   $ commit -a -m 'remove .gitmodules and submodule git-repo5'
   $ cd ..
 
   $ hg convert -q git-repo6 git-repo6-hg
   $ hg -R git-repo6-hg tip -T "{desc|firstline}\n"
   remove .gitmodules and submodule git-repo5
   $ hg -R git-repo6-hg tip -T "{file_dels}\n"
   .hgsub .hgsubstate
 
+skip submodules in the conversion
+
+  $ hg convert -q git-repo6 no-submodules --config convert.git.skipsubmodules=True
+  $ hg -R no-submodules manifest --all
+  .gitmodules-renamed
+
 convert using a different remote prefix
   $ git init git-repo7
   Initialized empty Git repository in $TESTTMP/git-repo7/.git/
   $ cd git-repo7
 TODO: it'd be nice to use (?) lines instead of grep -v to handle the
 git output variance, but that doesn't currently work in the middle of
 a block, so do this for now.
   $ touch a && git add a && git commit -am "commit a" | grep -v changed
   [master (root-commit) 8ae5f69] commit a
    Author: nottest <[e-mail]>
    create mode 100644 a
   $ cd ..
   $ git clone git-repo7 git-repo7-client
   Cloning into 'git-repo7-client'...
   done.
   $ hg convert --config convert.git.remoteprefix=origin git-repo7-client hg-repo7
   initializing destination hg-repo7 repository
   scanning source...
   sorting...
   converting...
   0 commit a
   updating bookmarks
   $ hg -R hg-repo7 bookmarks
      master                    0:03bf38caa4c6
      origin/master             0:03bf38caa4c6
 
 Run convert when the remote branches have changed
 (there was an old bug where the local convert read branches from the server)
 
   $ cd git-repo7
   $ echo a >> a
   $ git commit -am "move master forward"
   [master 0c81947] move master forward
    Author: nottest <[e-mail]>
    1 file changed, 1 insertion(+)
   $ cd ..
   $ rm -rf hg-repo7
   $ hg convert --config convert.git.remoteprefix=origin git-repo7-client hg-repo7
   initializing destination hg-repo7 repository
   scanning source...
   sorting...
   converting...
   0 commit a
   updating bookmarks
   $ hg -R hg-repo7 bookmarks
      master                    0:03bf38caa4c6
      origin/master             0:03bf38caa4c6
 
 damaged git repository tests:
 In case the hard-coded hashes change, the following commands can be used to
 list the hashes and their corresponding types in the repository:
 cd git-repo4/.git/objects
 find . -type f | cut -c 3- | sed 's_/__' | xargs -n 1 -t git cat-file -t
 cd ../../..
 
 damage git repository by renaming a commit object
   $ COMMIT_OBJ=1c/0ce3c5886f83a1d78a7b517cdff5cf9ca17bdd
   $ mv git-repo4/.git/objects/$COMMIT_OBJ git-repo4/.git/objects/$COMMIT_OBJ.tmp
   $ hg convert git-repo4 git-repo4-broken-hg 2>&1 | grep 'abort:'
   abort: cannot read tags from git-repo4/.git
   $ mv git-repo4/.git/objects/$COMMIT_OBJ.tmp git-repo4/.git/objects/$COMMIT_OBJ
 damage git repository by renaming a blob object
 
   $ BLOB_OBJ=8b/137891791fe96927ad78e64b0aad7bded08bdc
   $ mv git-repo4/.git/objects/$BLOB_OBJ git-repo4/.git/objects/$BLOB_OBJ.tmp
   $ hg convert git-repo4 git-repo4-broken-hg 2>&1 | grep 'abort:'
   abort: cannot read 'blob' object at 8b137891791fe96927ad78e64b0aad7bded08bdc
   $ mv git-repo4/.git/objects/$BLOB_OBJ.tmp git-repo4/.git/objects/$BLOB_OBJ
 damage git repository by renaming a tree object
 
   $ TREE_OBJ=72/49f083d2a63a41cc737764a86981eb5f3e4635
   $ mv git-repo4/.git/objects/$TREE_OBJ git-repo4/.git/objects/$TREE_OBJ.tmp
   $ hg convert git-repo4 git-repo4-broken-hg 2>&1 | grep 'abort:'
   abort: cannot read changes in 1c0ce3c5886f83a1d78a7b517cdff5cf9ca17bdd

tests/test-convert.t

@@ -1,532 +1,535 b''
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > convert=
   > [convert]
   > hg.saverev=False
   > EOF
   $ hg help convert
   hg convert [OPTION]... SOURCE [DEST [REVMAP]]
   
   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 branch names. 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.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.remoteprefix
                     remote refs are converted as bookmarks with
                     "convert.git.remoteprefix" as a prefix followed by a /. The
                     default is 'remote'.
+      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.
   
       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.
   
   options ([+] can be repeated):
   
    -s --source-type TYPE source repository type
    -d --dest-type TYPE   destination repository type
    -r --rev REV [+]      import up to source revision REV
    -A --authormap FILE   remap usernames using this file
       --filemap FILE     remap file names using contents of file
       --full             apply filemap changes by converting all files again
       --splicemap FILE   splice synthesized history into place
       --branchmap FILE   change branch names while converting
       --branchsort       try to sort changesets by branches
       --datesort         try to sort changesets by date
       --sourcesort       preserve source changesets order
       --closesort        try to reorder closed revisions
   
   (some details hidden, use --verbose to show complete help)
   $ hg init a
   $ cd a
   $ echo a > a
   $ hg ci -d'0 0' -Ama
   adding a
   $ hg cp a b
   $ hg ci -d'1 0' -mb
   $ hg rm a
   $ hg ci -d'2 0' -mc
   $ hg mv b a
   $ hg ci -d'3 0' -md
   $ echo a >> a
   $ hg ci -d'4 0' -me
   $ cd ..
   $ hg convert a 2>&1 | grep -v 'subversion python bindings could not be loaded'
   assuming destination a-hg
   initializing destination a-hg repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
   $ hg --cwd a-hg pull ../a
   pulling from ../a
   searching for changes
   no changes found
 
 conversion to existing file should fail
 
   $ touch bogusfile
   $ hg convert a bogusfile
   initializing destination bogusfile repository
   abort: cannot create new bundle repository
   [255]
 
 #if unix-permissions no-root
 
 conversion to dir without permissions should fail
 
   $ mkdir bogusdir
   $ chmod 000 bogusdir
 
   $ hg convert a bogusdir
   abort: Permission denied: 'bogusdir'
   [255]
 
 user permissions should succeed
 
   $ chmod 700 bogusdir
   $ hg convert a bogusdir
   initializing destination bogusdir repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 #endif
 
 test pre and post conversion actions
 
   $ echo 'include b' > filemap
   $ hg convert --debug --filemap filemap a partialb | \
   >     grep 'run hg'
   run hg source pre-conversion action
   run hg sink pre-conversion action
   run hg sink post-conversion action
   run hg source post-conversion action
 
 converting empty dir should fail "nicely
 
   $ mkdir emptydir
 
 override $PATH to ensure p4 not visible; use $PYTHON in case we're
 running from a devel copy, not a temp installation
 
   $ PATH="$BINDIR" $PYTHON "$BINDIR"/hg convert emptydir
   assuming destination emptydir-hg
   initializing destination emptydir-hg repository
   emptydir does not look like a CVS checkout
   emptydir does not look like a Git repository
   emptydir does not look like a Subversion repository
   emptydir is not a local Mercurial repository
   emptydir does not look like a darcs repository
   emptydir does not look like a monotone repository
   emptydir does not look like a GNU Arch repository
   emptydir does not look like a Bazaar repository
   cannot find required "p4" tool
   abort: emptydir: missing or unsupported repository
   [255]
 
 convert with imaginary source type
 
   $ hg convert --source-type foo a a-foo
   initializing destination a-foo repository
   abort: foo: invalid source repository type
   [255]
 
 convert with imaginary sink type
 
   $ hg convert --dest-type foo a a-foo
   abort: foo: invalid destination repository type
   [255]
 
 testing: convert must not produce duplicate entries in fncache
 
   $ hg convert a b
   initializing destination b repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 contents of fncache file:
 
   $ cat b/.hg/store/fncache | sort
   data/a.i
   data/b.i
 
 test bogus URL
 
   $ hg convert -q bzr+ssh://[e-mail]/baz baz
   abort: bzr+ssh://[e-mail]/baz: missing or unsupported repository
   [255]
 
 test revset converted() lookup
 
   $ hg --config convert.hg.saverev=True convert a c
   initializing destination c repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
   $ echo f > c/f
   $ hg -R c ci -d'0 0' -Amf
   adding f
   created new head
   $ hg -R c log -r "converted(09d945a62ce6)"
   changeset:   1:98c3dd46a874
   user:        test
   date:        Thu Jan 01 00:00:01 1970 +0000
   summary:     b
   
   $ hg -R c log -r "converted()"
   changeset:   0:31ed57b2037c
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     a
   
   changeset:   1:98c3dd46a874
   user:        test
   date:        Thu Jan 01 00:00:01 1970 +0000
   summary:     b
   
   changeset:   2:3b9ca06ef716
   user:        test
   date:        Thu Jan 01 00:00:02 1970 +0000
   summary:     c
   
   changeset:   3:4e0debd37cf2
   user:        test
   date:        Thu Jan 01 00:00:03 1970 +0000
   summary:     d
   
   changeset:   4:9de3bc9349c5
   user:        test
   date:        Thu Jan 01 00:00:04 1970 +0000
   summary:     e
   
 
 test specifying a sourcename
   $ echo g > a/g
   $ hg -R a ci -d'0 0' -Amg
   adding g
   $ hg --config convert.hg.sourcename=mysource --config convert.hg.saverev=True convert a c
   scanning source...
   sorting...
   converting...
   0 g
   $ hg -R c log -r tip --template '{extras % "{extra}\n"}'
   branch=default
   convert_revision=a3bc6100aa8ec03e00aaf271f1f50046fb432072
   convert_source=mysource