convert: add config to not convert tags

In some cases we do not want to convert tags from the source repo to be tags in
the target repo (for instance, in a large repository, hgtags cause scaling
issues so we want to avoid them). This adds a config option to disable
converting tags.

hgext/convert/__init__.py

@@ -1,426 +1,434 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.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.
 
     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``.
 
     It is possible to limit the amount of source history to be
     converted by specifying an initial Perforce revision:
 
     :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.
+
+    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/convcmd.py

@@ -1,547 +1,548 b''
 # convcmd - convert extension commands definition
 #
 # 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.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil, shlex
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
         except (NoRepo, MissingTool) as inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo as inst:
             ui.note(_("convert: %s\n") % inst)
         except MissingTool as inst:
             raise util.Abort('%s\n' % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.filecount = filecount
         self.retrieved = 0
 
     def getfile(self, file, rev):
         self.retrieved += 1
         self.ui.progress(_('getting files'), self.retrieved,
                          item=file, total=self.filecount)
         return self.source.getfile(file, rev)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.ui.progress(_('getting files'), None)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authormap'):
             self.readauthormap(opts.get('authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = self.parsesplicemap(opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def parsesplicemap(self, path):
         """ check and validate the splicemap format and
             return a child/parents dictionary.
             Format checking has two parts.
             1. generic format which is same across all source types
             2. specific format checking which may be different for
                different source type.  This logic is implemented in
                checkrevformat function in source files like
                hg.py, subversion.py etc.
         """
 
         if not path:
             return {}
         m = {}
         try:
             fp = open(path, 'r')
             for i, line in enumerate(fp):
                 line = line.splitlines()[0].rstrip()
                 if not line:
                     # Ignore blank lines
                     continue
                 # split line
                 lex = shlex.shlex(line, posix=True)
                 lex.whitespace_split = True
                 lex.whitespace += ','
                 line = list(lex)
                 # check number of parents
                 if not (2 <= len(line) <= 3):
                     raise util.Abort(_('syntax error in %s(%d): child parent1'
                                        '[,parent2] expected') % (path, i + 1))
                 for part in line:
                     self.source.checkrevformat(part)
                 child, p1, p2 = line[0], line[1:2], line[2:]
                 if p1 == p2:
                     m[child] = p1
                 else:
                     m[child] = p1 + p2
          # if file does not exist or error reading, exit
         except IOError:
             raise util.Abort(_('splicemap file not found or error reading %s:')
                                % path)
         return m
 
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         numcommits = self.source.numcommits()
         while visit:
             n = visit.pop(0)
             if n in known:
                 continue
             if n in self.map:
                 m = self.map[n]
                 if m == SKIPREV or self.dest.hascommitfrommap(m):
                     continue
             known.add(n)
             self.ui.progress(_('scanning'), len(known), unit=_('revisions'),
                              total=numcommits)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         self.ui.progress(_('scanning'), None)
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in sorted(splicemap):
             if c not in parents:
                 if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(_('splice map revision %s is not being '
                                    'converted, ignoring\n') % c)
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise util.Abort(_('unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = sorted(parents)
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makeclosesorter():
             """Close order sort."""
             keyfn = lambda n: ('close' not in self.commitcache[n].extra,
                                self.commitcache[n].sortkey)
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         elif sortmode == 'closesort':
             picknext = makeclosesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         # If commit.branch is None, this commit is coming from the source
         # repository's default branch and destined for the default branch in the
         # destination repository. For such commits, passing a literal "None"
         # string to branchmap.get() below allows the user to map "None" to an
         # alternate default branch in the destination repository.
         commit.branch = self.branchmap.get(str(commit.branch), commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         full = self.opts.get('full')
         changes = self.source.getchanges(rev, full)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies, cleanp2 = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         if len(pbranches) != 2:
             cleanp2 = set()
         if len(parents) < 3:
             source = progresssource(self.ui, self.source, len(files))
         else:
             # For an octopus merge, we end up traversing the list of
             # changed files N-1 times. This tweak to the number of
             # files makes it so the progress bar doesn't overflow
             # itself.
             source = progresssource(self.ui, self.source,
                                     len(files) * (len(parents) - 1))
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       source, self.map, full, cleanp2)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.ui.progress(_('converting'), i, unit=_('revisions'),
                                  total=len(t))
                 self.copy(c)
             self.ui.progress(_('converting'), None)
 
-            tags = self.source.gettags()
-            ctags = {}
-            for k in tags:
-                v = tags[k]
-                if self.map.get(v, SKIPREV) != SKIPREV:
-                    ctags[k] = self.map[v]
+            if not self.ui.configbool('convert', 'skiptags'):
+                tags = self.source.gettags()
+                ctags = {}
+                for k in tags:
+                    v = tags[k]
+                    if self.map.get(v, SKIPREV) != SKIPREV:
+                        ctags[k] = self.map[v]
 
-            if c and ctags:
-                nrev, tagsparent = self.dest.puttags(ctags)
-                if nrev and tagsparent:
-                    # write another hash correspondence to override the previous
-                    # one so we don't end up with extra tag heads
-                    tagsparents = [e for e in self.map.iteritems()
-                                   if e[1] == tagsparent]
-                    if tagsparents:
-                        self.map[tagsparents[0][0]] = nrev
+                if c and ctags:
+                    nrev, tagsparent = self.dest.puttags(ctags)
+                    if nrev and tagsparent:
+                        # write another hash correspondence to override the
+                        # previous one so we don't end up with extra tag heads
+                        tagsparents = [e for e in self.map.iteritems()
+                                       if e[1] == tagsparent]
+                        if tagsparents:
+                            self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get('authormap'):
         opts['authormap'] = opts.get('authors')
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort', 'closesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     if sortmode:
         sortmode = sortmode[0]
     else:
         sortmode = defaultsort
 
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
     if sortmode == 'closesort' and not srcc.hasnativeclose():
         raise util.Abort(_('--closesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         revmapfile = destc.revmapfile()
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)

tests/test-convert-tagsbranch-topology.t

@@ -1,91 +1,104 b''
 #require git
 
   $ echo "[core]" >> $HOME/.gitconfig
   $ echo "autocrlf = false" >> $HOME/.gitconfig
   $ echo "[core]" >> $HOME/.gitconfig
   $ echo "autocrlf = false" >> $HOME/.gitconfig
   $ cat <<EOF >> $HGRCPATH
   > [extensions]
   > convert =
   > [convert]
   > hg.usebranchnames = True
   > hg.tagsbranch = tags-update
   > EOF
   $ 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
   $ count=10
   $ action()
   > {
   >     GIT_AUTHOR_DATE="2007-01-01 00:00:$count +0000"
   >     GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"
   >     git "$@" >/dev/null 2>/dev/null || echo "git command error"
   >     count=`expr $count + 1`
   > }
   $ glog()
   > {
   >     hg log -G --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
   > }
   $ convertrepo()
   > {
   >     hg convert --datesort git-repo hg-repo
   > }
 
 Build a GIT repo with at least 1 tag
 
   $ mkdir git-repo
   $ cd git-repo
   $ git init >/dev/null 2>&1
   $ echo a > a
   $ git add a
   $ action commit -m "rev1"
   $ action tag -m "tag1" tag1
   $ cd ..
 
+Convert without tags
+
+  $ hg convert git-repo hg-repo --config convert.skiptags=True
+  initializing destination hg-repo repository
+  scanning source...
+  sorting...
+  converting...
+  0 rev1
+  updating bookmarks
+  $ hg -R hg-repo tags
+  tip                                0:d98c8ad3a4cf
+  $ rm -rf hg-repo
+
 Do a first conversion
 
   $ convertrepo
   initializing destination hg-repo repository
   scanning source...
   sorting...
   converting...
   0 rev1
   updating tags
   updating bookmarks
 
 Simulate upstream  updates after first conversion
 
   $ cd git-repo
   $ echo b > a
   $ git add a
   $ action commit -m "rev2"
   $ action tag -m "tag2" tag2
   $ cd ..
 
 Perform an incremental conversion
 
   $ convertrepo
   scanning source...
   sorting...
   converting...
   0 rev2
   updating tags
   updating bookmarks
 
 Print the log
 
   $ cd hg-repo
   $ glog
   o  3 "update tags" files: .hgtags
   |
   | o  2 "rev2" files: a
   | |
   o |  1 "update tags" files: .hgtags
    /
   o  0 "rev1" files: a
   
 
   $ cd ..

tests/test-convert.t

@@ -1,496 +1,505 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.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.
   
       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".
   
       It is possible to limit the amount of source history to be converted by
       specifying an initial Perforce revision:
   
       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.
   
+      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:
   
    -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