convert: transcode CVS log messages by specified encoding (issue5597)

Converting from CVS to Mercurial assumes that CVS log messages in "cvs
rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself
is usually unaware of encoding of log messages, in practice.

Therefore, if there are commits, of which log message is encoded in
other than UTF-8, log message of corresponded revisions in the
converted repository will be broken.

To avoid such broken log messages, this patch transcodes CVS log
messages by encoding specified via "convert.cvsps.logencoding"
configuration.

This patch accepts multiple encoding for convenience, because
"multiple encoding mixed in a repository" easily occurs. For example,
UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are
well known encoding for Japanese.

hgext/convert/__init__.py

@@ -1,503 +1,509 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'''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     registrar,
 )
 
 from . import (
     convcmd,
     cvsps,
     subversion,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 @command('convert',
     [('', 'authors', '',
       _('username mapping filename (DEPRECATED) (use --authormap instead)'),
       _('FILE')),
     ('s', 'source-type', '', _('source repository type'), _('TYPE')),
     ('d', 'dest-type', '', _('destination repository type'), _('TYPE')),
     ('r', 'rev', [], _('import up to source revision REV'), _('REV')),
     ('A', 'authormap', '', _('remap usernames using this file'), _('FILE')),
     ('', 'filemap', '', _('remap file names using contents of file'),
      _('FILE')),
     ('', 'full', None,
      _('apply filemap changes by converting all files again')),
     ('', 'splicemap', '', _('splice synthesized history into place'),
      _('FILE')),
     ('', 'branchmap', '', _('change branch names while converting'),
      _('FILE')),
     ('', 'branchsort', None, _('try to sort changesets by branches')),
     ('', 'datesort', None, _('try to sort changesets by date')),
     ('', 'sourcesort', None, _('preserve source changesets order')),
     ('', 'closesort', None, _('try to reorder closed revisions'))],
    _('hg convert [OPTION]... SOURCE [DEST [REVMAP]]'),
    norepo=True)
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
 
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
     - Perforce [p4]
 
     Accepted destination formats [identifiers]:
 
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted.
     Otherwise, convert will only import up to the named revision
     (given in a format understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with ``-hg`` appended. If the destination
     repository doesn't exist, it will be created.
 
     By default, all sources except Mercurial will use --branchsort.
     Mercurial uses --sourcesort to preserve original revision numbers
     order. Sort modes have the following effects:
 
     --branchsort  convert from parent to child revision when possible,
                   which means branches are usually converted one after
                   the other. It generates more compact repositories.
 
     --datesort    sort revisions by date. Converted repositories have
                   good-looking changelogs but are often an order of
                   magnitude larger than the same ones generated by
                   --branchsort.
 
     --sourcesort  try to preserve source revisions order, only
                   supported by Mercurial sources.
 
     --closesort   try to move closed revisions as close as possible
                   to parent branches, only supported by Mercurial
                   sources.
 
     If ``REVMAP`` isn't given, it will be put in a default location
     (``<dest>/.hg/shamap`` by default). The ``REVMAP`` is a simple
     text file that maps each source commit ID to the destination ID
     for that revision, like so::
 
       <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created. It's
     updated on each commit copied, so :hg:`convert` can be interrupted
     and can be run repeatedly to copy new commits.
 
     The authormap is a simple text file that maps each source commit
     author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (e.g.: CVS). One line per
     author mapping and the line format is::
 
       source author = destination author
 
     Empty lines and lines starting with a ``#`` are ignored.
 
     The filemap is a file that allows filtering and remapping of files
     and directories. Each line can contain one of the following
     directives::
 
       include path/to/file-or-dir
 
       exclude path/to/file-or-dir
 
       rename path/to/source path/to/destination
 
     Comment lines start with ``#``. A specified path matches if it
     equals the full relative name of a file or one of its parent
     directories. The ``include`` or ``exclude`` directive with the
     longest matching path applies, so line order does not matter.
 
     The ``include`` directive causes a file, or all files under a
     directory, to be included in the destination repository. The default
     if there are no ``include`` statements is to include everything.
     If there are any ``include`` statements, nothing else is included.
     The ``exclude`` directive causes files or directories to
     be omitted. The ``rename`` directive renames a file or directory if
     it is converted. To rename from a subdirectory into the root of
     the repository, use ``.`` as the path to rename to.
 
     ``--full`` will make sure the converted changesets contain exactly
     the right files with the right content. It will make a full
     conversion of all files, not just the ones that have
     changed. Files that already are correct will not be changed. This
     can be used to apply filemap changes when converting
     incrementally. This is currently only supported for Mercurial and
     Subversion.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision. This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together. Each entry
     contains a key, followed by a space, followed by one or two
     comma-separated values::
 
       key parent1, parent2
 
     The key is the revision ID in the source
     revision control system whose parents should be modified (same
     format as a key in .hg/shamap). The values are the revision IDs
     (in either the source or destination revision control system) that
     should be used as the new parents for that node. For example, if
     you have merged "release-1.0" into "trunk", then you should
     specify the revision on "trunk" as the first parent and the one on
     the "release-1.0" branch as the second.
 
     The branchmap is a file that allows you to rename a branch when it is
     being brought in from whatever external repository. When used in
     conjunction with a splicemap, it allows for a powerful combination
     to help fix even the most badly mismanaged repositories and turn them
     into nicely structured Mercurial repositories. The branchmap contains
     lines of the form::
 
       original_branch_name new_branch_name
 
     where "original_branch_name" is the name of the branch in the
     source repository, and "new_branch_name" is the name of the branch
     is the destination repository. No whitespace is allowed in the new
     branch name. This can be used to (for instance) move code in one
     repository from "default" to a named branch.
 
     Mercurial Source
     ################
 
     The Mercurial source recognizes the following configuration
     options, which you can set on the command line with ``--config``:
 
     :convert.hg.ignoreerrors: ignore integrity errors when reading.
         Use it to fix Mercurial repositories with missing revlogs, by
         converting from and to Mercurial. Default is False.
 
     :convert.hg.saverev: store original revision ID in changeset
         (forces target IDs to change). It takes a boolean argument and
         defaults to False.
 
     :convert.hg.startrev: specify the initial Mercurial revision.
         The default is 0.
 
     :convert.hg.revs: revset specifying the source revisions to convert.
 
     CVS Source
     ##########
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course the
     repository is ``:local:``. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganization in the CVS
     sandbox is ignored.
 
     The following options can be used with ``--config``:
 
     :convert.cvsps.cache: Set to False to disable remote log caching,
         for testing and debugging purposes. Default is True.
 
     :convert.cvsps.fuzz: Specify the maximum time (in seconds) that is
         allowed between commits with identical user and log message in
         a single changeset. When very large files were checked in as
         part of a changeset then the default may not be long enough.
         The default is 60.
 
+    :convert.cvsps.logencoding: Specify encoding name to be used for
+        transcoding CVS log messages. Multiple encoding names can be
+        specified as a list (see :hg:`help config.Syntax`), but only
+        the first acceptable encoding in the list is used per CVS log
+        entries. This transcoding is executed before cvslog hook below.
+
     :convert.cvsps.mergeto: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will insert a dummy revision merging the
         branch on which this log message occurs to the branch
         indicated in the regex. Default is ``{{mergetobranch
         ([-\\w]+)}}``
 
     :convert.cvsps.mergefrom: Specify a regular expression to which
         commit log messages are matched. If a match occurs, then the
         conversion process will add the most recent revision on the
         branch indicated in the regex as the second parent of the
         changeset. Default is ``{{mergefrombranch ([-\\w]+)}}``
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     :hooks.cvslog: Specify a Python function to be called at the end of
         gathering the CVS log. The function is passed a list with the
         log entries, and can modify the entries in-place, or add or
         delete them.
 
     :hooks.cvschangesets: Specify a Python function to be called after
         the changesets are calculated from the CVS log. The
         function is passed a list with the changeset entries, and can
         modify the changesets in-place, or add or delete them.
 
     An additional "debugcvsps" Mercurial command allows the builtin
     changeset merging code to be run without doing a conversion. Its
     parameters and output are similar to that of cvsps 2.1. Please see
     the command help for more details.
 
     Subversion Source
     #################
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied ``svn://repo/path/`` source URL is
     converted as a single branch. If ``svn://repo/path/trunk`` exists
     it replaces the default branch. If ``svn://repo/path/branches``
     exists, its subdirectories are listed as possible branches. If
     ``svn://repo/path/tags`` exists, it is looked for tags referencing
     converted branches. Default ``trunk``, ``branches`` and ``tags``
     values can be overridden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable auto
     detection.
 
     The following options can be set with ``--config``:
 
     :convert.svn.branches: specify the directory containing branches.
         The default is ``branches``.
 
     :convert.svn.tags: specify the directory containing tags. The
         default is ``tags``.
 
     :convert.svn.trunk: specify the name of the trunk branch. The
         default is ``trunk``.
 
     :convert.localtimezone: use local time (as determined by the TZ
         environment variable) for changeset date/times. The default
         is False (use UTC).
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     :convert.svn.startrev: specify start Subversion revision number.
         The default is 0.
 
     Git Source
     ##########
 
     The Git importer converts commits from all reachable branches (refs
     in refs/heads) and remotes (refs in refs/remotes) to Mercurial.
     Branches are converted to bookmarks with the same name, with the
     leading 'refs/heads' stripped. Git submodules are converted to Git
     subrepos in Mercurial.
 
     The following options can be set with ``--config``:
 
     :convert.git.similarity: specify how similar files modified in a
         commit must be to be imported as renames or copies, as a
         percentage between ``0`` (disabled) and ``100`` (files must be
         identical). For example, ``90`` means that a delete/add pair will
         be imported as a rename if more than 90% of the file hasn't
         changed. The default is ``50``.
 
     :convert.git.findcopiesharder: while detecting copies, look at all
         files in the working copy instead of just changed ones. This
         is very expensive for large projects, and is only effective when
         ``convert.git.similarity`` is greater than 0. The default is False.
 
     :convert.git.renamelimit: perform rename and copy detection up to this
         many changed files in a commit. Increasing this will make rename
         and copy detection more accurate but will significantly slow down
         computation on large projects. The option is only relevant if
         ``convert.git.similarity`` is greater than 0. The default is
         ``400``.
 
     :convert.git.committeractions: list of actions to take when processing
         author and committer values.
 
         Git commits have separate author (who wrote the commit) and committer
         (who applied the commit) fields. Not all destinations support separate
         author and committer fields (including Mercurial). This config option
         controls what to do with these author and committer fields during
         conversion.
 
         A value of ``messagedifferent`` will append a ``committer: ...``
         line to the commit message if the Git committer is different from the
         author. The prefix of that line can be specified using the syntax
         ``messagedifferent=<prefix>``. e.g. ``messagedifferent=git-committer:``.
         When a prefix is specified, a space will always be inserted between the
         prefix and the value.
 
         ``messagealways`` behaves like ``messagedifferent`` except it will
         always result in a ``committer: ...`` line being appended to the commit
         message. This value is mutually exclusive with ``messagedifferent``.
 
         ``dropcommitter`` will remove references to the committer. Only
         references to the author will remain. Actions that add references
         to the committer will have no effect when this is set.
 
         ``replaceauthor`` will replace the value of the author field with
         the committer. Other actions that add references to the committer
         will still take effect when this is set.
 
         The default is ``messagedifferent``.
 
     :convert.git.extrakeys: list of extra keys from commit metadata to copy to
         the destination. Some Git repositories store extra metadata in commits.
         By default, this non-default metadata will be lost during conversion.
         Setting this config option can retain that metadata. Some built-in
         keys such as ``parent`` and ``branch`` are not allowed to be copied.
 
     :convert.git.remoteprefix: remote refs are converted as bookmarks with
         ``convert.git.remoteprefix`` as a prefix followed by a /. The default
         is 'remote'.
 
     :convert.git.saverev: whether to store the original Git commit ID in the
         metadata of the destination commit. The default is True.
 
     :convert.git.skipsubmodules: does not convert root level .gitmodules files
         or files with 160000 mode indicating a submodule. Default is False.
 
     Perforce Source
     ###############
 
     The Perforce (P4) importer can be given a p4 depot path or a
     client specification as source. It will convert all files in the
     source to a flat Mercurial repository, ignoring labels, branches
     and integrations. Note that when a depot path is given you then
     usually should specify a target directory, because otherwise the
     target may be named ``...-hg``.
 
     The following options can be set with ``--config``:
 
     :convert.p4.encoding: specify the encoding to use when decoding standard
         output of the Perforce command line tool. The default is default system
         encoding.
 
     :convert.p4.startrev: specify initial Perforce revision (a
         Perforce changelist number).
 
     Mercurial Destination
     #####################
 
     The Mercurial destination will recognize Mercurial subrepositories in the
     destination directory, and update the .hgsubstate file automatically if the
     destination subrepositories contain the <dest>/<sub>/.hg/shamap file.
     Converting a repository with subrepositories requires converting a single
     repository at a time, from the bottom up.
 
     .. container:: verbose
 
        An example showing how to convert a repository with subrepositories::
 
          # so convert knows the type when it sees a non empty destination
          $ hg init converted
 
          $ hg convert orig/sub1 converted/sub1
          $ hg convert orig/sub2 converted/sub2
          $ hg convert orig converted
 
     The following options are supported:
 
     :convert.hg.clonebranches: dispatch source branches in separate
         clones. The default is False.
 
     :convert.hg.tagsbranch: branch name for tag revisions, defaults to
         ``default``.
 
     :convert.hg.usebranchnames: preserve branch names. The default is
         True.
 
     :convert.hg.sourcename: records the given string as a 'convert_source' extra
         value on each commit made in the target repository. The default is None.
 
     All Destinations
     ################
 
     All destination types accept the following options:
 
     :convert.skiptags: does not convert tags from the source repo to the target
         repo. The default is False.
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 @command('debugsvnlog', [], 'hg debugsvnlog', norepo=True)
 def debugsvnlog(ui, **opts):
     return subversion.debugsvnlog(ui, **opts)
 
 @command('debugcvsps',
     [
     # Main options shared with cvsps-2.1
     ('b', 'branches', [], _('only return changes on specified branches')),
     ('p', 'prefix', '', _('prefix to remove from file names')),
     ('r', 'revisions', [],
      _('only return changes after or between specified tags')),
     ('u', 'update-cache', None, _("update cvs log cache")),
     ('x', 'new-cache', None, _("create new cvs log cache")),
     ('z', 'fuzz', 60, _('set commit time fuzz in seconds')),
     ('', 'root', '', _('specify cvsroot')),
     # Options specific to builtin cvsps
     ('', 'parents', '', _('show parent changesets')),
     ('', 'ancestors', '', _('show current changeset in ancestor branches')),
     # Options that are ignored for compatibility with cvsps-2.1
     ('A', 'cvs-direct', None, _('ignored for compatibility')),
     ],
     _('hg debugcvsps [OPTION]... [PATH]...'),
     norepo=True)
 def debugcvsps(ui, *args, **opts):
     '''create changeset information from CVS
 
     This command is intended as a debugging tool for the CVS to
     Mercurial converter, and can be used as a direct replacement for
     cvsps.
 
     Hg debugcvsps reads the CVS rlog for current directory (or any
     named directory) in the CVS repository, and converts the log to a
     series of changesets based on matching commit log entries and
     dates.'''
     return cvsps.debugcvsps(ui, *args, **opts)
 
 def kwconverted(ctx, name):
     rev = ctx.extra().get('convert_revision', '')
     if rev.startswith('svn:'):
         if name == 'svnrev':
             return str(subversion.revsplit(rev)[2])
         elif name == 'svnpath':
             return subversion.revsplit(rev)[1]
         elif name == 'svnuuid':
             return subversion.revsplit(rev)[0]
     return rev
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('svnrev')
 def kwsvnrev(repo, ctx, **args):
     """String. Converted subversion revision number."""
     return kwconverted(ctx, 'svnrev')
 
 @templatekeyword('svnpath')
 def kwsvnpath(repo, ctx, **args):
     """String. Converted subversion revision project path."""
     return kwconverted(ctx, 'svnpath')
 
 @templatekeyword('svnuuid')
 def kwsvnuuid(repo, ctx, **args):
     """String. Converted subversion revision repository identifier."""
     return kwconverted(ctx, 'svnuuid')
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [kwsvnrev, kwsvnpath, kwsvnuuid]

hgext/convert/cvsps.py

@@ -1,921 +1,951 b''
 # Mercurial built-in replacement for cvsps.
 #
 # Copyright 2008, Frank Kingswood <[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 __future__ import absolute_import
 
 import os
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
+    error,
     hook,
     pycompat,
     util,
 )
 
 pickle = util.pickle
 
 class logentry(object):
     '''Class logentry has the following attributes:
         .author    - author name as CVS knows it
         .branch    - name of branch this revision is on
         .branches  - revision tuple of branches starting at this revision
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time, tz) tuple
         .dead      - true if file revision is dead
         .file      - Name of file
         .lines     - a tuple (+lines, -lines) or None
         .parent    - Previous revision of this entry
         .rcs       - name of file as returned from CVS
         .revision  - revision number as tuple
         .tags      - list of tags on the file
         .synthetic - is this a synthetic "file ... added on ..." revision?
         .mergepoint - the branch that has been merged from (if present in
                       rlog output) or None
         .branchpoints - the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 class logerror(Exception):
     pass
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath('/foo/bar')
     '/foo/bar'
     >>> getrepopath('c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:10/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:10c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath('user@server/path/to/repository')
     '/path/to/repository'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # CVSpath is splitted into parts and then position of the first occurrence
     # of the '/' char after the '@' is located. The solution is the rest of the
     # string after that '/' sign including it
 
     parts = cvspath.split(':')
     atposition = parts[-1].find('@')
     start = 0
 
     if atposition != -1:
         start = atposition
 
     repopath = parts[-1][parts[-1].find('/', start):]
     return repopath
 
 def createlog(ui, directory=None, root="", rlog=True, cache=None):
     '''Collect the CVS rlog'''
 
     # Because we store many duplicate commit log messages, reusing strings
     # saves a lot of memory and pickle storage space.
     _scache = {}
     def scache(s):
         "return a shared version of a string"
         return _scache.setdefault(s, s)
 
     ui.status(_('collecting CVS rlog\n'))
 
     log = []      # list of logentry objects containing the CVS state
 
     # patterns to match in CVS (r)log output, by state of use
     re_00 = re.compile('RCS file: (.+)$')
     re_01 = re.compile('cvs \\[r?log aborted\\]: (.+)$')
     re_02 = re.compile('cvs (r?log|server): (.+)\n$')
     re_03 = re.compile("(Cannot access.+CVSROOT)|"
                        "(can't create temporary directory.+)$")
     re_10 = re.compile('Working file: (.+)$')
     re_20 = re.compile('symbolic names:')
     re_30 = re.compile('\t(.+): ([\\d.]+)$')
     re_31 = re.compile('----------------------------$')
     re_32 = re.compile('======================================='
                        '======================================$')
     re_50 = re.compile('revision ([\\d.]+)(\s+locked by:\s+.+;)?$')
     re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
                        r'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
                        r'(\s+commitid:\s+([^;]+);)?'
                        r'(.*mergepoint:\s+([^;]+);)?')
     re_70 = re.compile('branches: (.+);$')
 
     file_added_re = re.compile(r'file [^/]+ was (initially )?added on branch')
 
     prefix = ''   # leading path to strip of what we get from CVS
 
     if directory is None:
         # Current working directory
 
         # Get the real directory in the repository
         try:
             prefix = open(os.path.join('CVS','Repository')).read().strip()
             directory = prefix
             if prefix == ".":
                 prefix = ""
         except IOError:
             raise logerror(_('not a CVS sandbox'))
 
         if prefix and not prefix.endswith(pycompat.ossep):
             prefix += pycompat.ossep
 
         # Use the Root file in the sandbox, if it exists
         try:
             root = open(os.path.join('CVS','Root')).read().strip()
         except IOError:
             pass
 
     if not root:
         root = encoding.environ.get('CVSROOT', '')
 
     # read log cache if one exists
     oldlog = []
     date = None
 
     if cache:
         cachedir = os.path.expanduser('~/.hg.cvsps')
         if not os.path.exists(cachedir):
             os.mkdir(cachedir)
 
         # The cvsps cache pickle needs a uniquified name, based on the
         # repository location. The address may have all sort of nasties
         # in it, slashes, colons and such. So here we take just the
         # alphanumeric characters, concatenated in a way that does not
         # mix up the various components, so that
         #    :pserver:user@server:/path
         # and
         #    /pserver/user/server/path
         # are mapped to different cache file names.
         cachefile = root.split(":") + [directory, "cache"]
         cachefile = ['-'.join(re.findall(r'\w+', s)) for s in cachefile if s]
         cachefile = os.path.join(cachedir,
                                  '.'.join([s for s in cachefile if s]))
 
     if cache == 'update':
         try:
             ui.note(_('reading cvs log cache %s\n') % cachefile)
             oldlog = pickle.load(open(cachefile))
             for e in oldlog:
                 if not (util.safehasattr(e, 'branchpoints') and
                         util.safehasattr(e, 'commitid') and
                         util.safehasattr(e, 'mergepoint')):
                     ui.status(_('ignoring old cache\n'))
                     oldlog = []
                     break
 
             ui.note(_('cache has %d log entries\n') % len(oldlog))
         except Exception as e:
             ui.note(_('error reading cache: %r\n') % e)
 
         if oldlog:
             date = oldlog[-1].date    # last commit date as a (time,tz) tuple
             date = util.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')
 
     # build the CVS commandline
     cmd = ['cvs', '-q']
     if root:
         cmd.append('-d%s' % root)
         p = util.normpath(getrepopath(root))
         if not p.endswith('/'):
             p += '/'
         if prefix:
             # looks like normpath replaces "" by "."
             prefix = p + util.normpath(prefix)
         else:
             prefix = p
     cmd.append(['log', 'rlog'][rlog])
     if date:
         # no space between option and date string
         cmd.append('-d>%s' % date)
     cmd.append(directory)
 
     # state machine begins here
     tags = {}     # dictionary of revisions on current file with their tags
     branchmap = {} # mapping between branch names and revision numbers
     rcsmap = {}
     state = 0
     store = False # set when a new record can be appended
 
     cmd = [util.shellquote(arg) for arg in cmd]
     ui.note(_("running %s\n") % (' '.join(cmd)))
     ui.debug("prefix=%r directory=%r root=%r\n" % (prefix, directory, root))
 
     pfp = util.popen(' '.join(cmd))
     peek = pfp.readline()
     while True:
         line = peek
         if line == '':
             break
         peek = pfp.readline()
         if line.endswith('\n'):
             line = line[:-1]
         #ui.debug('state=%d line=%r\n' % (state, line))
 
         if state == 0:
             # initial state, consume input until we see 'RCS file'
             match = re_00.match(line)
             if match:
                 rcs = match.group(1)
                 tags = {}
                 if rlog:
                     filename = util.normpath(rcs[:-2])
                     if filename.startswith(prefix):
                         filename = filename[len(prefix):]
                     if filename.startswith('/'):
                         filename = filename[1:]
                     if filename.startswith('Attic/'):
                         filename = filename[6:]
                     else:
                         filename = filename.replace('/Attic/', '/')
                     state = 2
                     continue
                 state = 1
                 continue
             match = re_01.match(line)
             if match:
                 raise logerror(match.group(1))
             match = re_02.match(line)
             if match:
                 raise logerror(match.group(2))
             if re_03.match(line):
                 raise logerror(line)
 
         elif state == 1:
             # expect 'Working file' (only when using log instead of rlog)
             match = re_10.match(line)
             assert match, _('RCS file must be followed by working file')
             filename = util.normpath(match.group(1))
             state = 2
 
         elif state == 2:
             # expect 'symbolic names'
             if re_20.match(line):
                 branchmap = {}
                 state = 3
 
         elif state == 3:
             # read the symbolic names and store as tags
             match = re_30.match(line)
             if match:
                 rev = [int(x) for x in match.group(2).split('.')]
 
                 # Convert magic branch number to an odd-numbered one
                 revn = len(rev)
                 if revn > 3 and (revn % 2) == 0 and rev[-2] == 0:
                     rev = rev[:-2] + rev[-1:]
                 rev = tuple(rev)
 
                 if rev not in tags:
                     tags[rev] = []
                 tags[rev].append(match.group(1))
                 branchmap[match.group(1)] = match.group(2)
 
             elif re_31.match(line):
                 state = 5
             elif re_32.match(line):
                 state = 0
 
         elif state == 4:
             # expecting '------' separator before first revision
             if re_31.match(line):
                 state = 5
             else:
                 assert not re_32.match(line), _('must have at least '
                                                 'some revisions')
 
         elif state == 5:
             # expecting revision number and possibly (ignored) lock indication
             # we create the logentry here from values stored in states 0 to 4,
             # as this state is re-entered for subsequent revisions of a file.
             match = re_50.match(line)
             assert match, _('expected revision number')
             e = logentry(rcs=scache(rcs),
                          file=scache(filename),
                          revision=tuple([int(x) for x in
                                          match.group(1).split('.')]),
                          branches=[],
                          parent=None,
                          commitid=None,
                          mergepoint=None,
                          branchpoints=set())
 
             state = 6
 
         elif state == 6:
             # expecting date, author, state, lines changed
             match = re_60.match(line)
             assert match, _('revision must be followed by date line')
             d = match.group(1)
             if d[2] == '/':
                 # Y2K
                 d = '19' + d
 
             if len(d.split()) != 3:
                 # cvs log dates always in GMT
                 d = d + ' UTC'
             e.date = util.parsedate(d, ['%y/%m/%d %H:%M:%S',
                                         '%Y/%m/%d %H:%M:%S',
                                         '%Y-%m-%d %H:%M:%S'])
             e.author = scache(match.group(2))
             e.dead = match.group(3).lower() == 'dead'
 
             if match.group(5):
                 if match.group(6):
                     e.lines = (int(match.group(5)), int(match.group(6)))
                 else:
                     e.lines = (int(match.group(5)), 0)
             elif match.group(6):
                 e.lines = (0, int(match.group(6)))
             else:
                 e.lines = None
 
             if match.group(7): # cvs 1.12 commitid
                 e.commitid = match.group(8)
 
             if match.group(9): # cvsnt mergepoint
                 myrev = match.group(10).split('.')
                 if len(myrev) == 2: # head
                     e.mergepoint = 'HEAD'
                 else:
                     myrev = '.'.join(myrev[:-2] + ['0', myrev[-2]])
                     branches = [b for b in branchmap if branchmap[b] == myrev]
                     assert len(branches) == 1, ('unknown branch: %s'
                                                 % e.mergepoint)
                     e.mergepoint = branches[0]
 
             e.comment = []
             state = 7
 
         elif state == 7:
             # read the revision numbers of branches that start at this revision
             # or store the commit log message otherwise
             m = re_70.match(line)
             if m:
                 e.branches = [tuple([int(y) for y in x.strip().split('.')])
                                 for x in m.group(1).split(';')]
                 state = 8
             elif re_31.match(line) and re_50.match(peek):
                 state = 5
                 store = True
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         elif state == 8:
             # store commit log message
             if re_31.match(line):
                 cpeek = peek
                 if cpeek.endswith('\n'):
                     cpeek = cpeek[:-1]
                 if re_50.match(cpeek):
                     state = 5
                     store = True
                 else:
                     e.comment.append(line)
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         # When a file is added on a branch B1, CVS creates a synthetic
         # dead trunk revision 1.1 so that the branch has a root.
         # Likewise, if you merge such a file to a later branch B2 (one
         # that already existed when the file was added on B1), CVS
         # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
         # these revisions now, but mark them synthetic so
         # createchangeset() can take care of them.
         if (store and
               e.dead and
               e.revision[-1] == 1 and      # 1.1 or 1.1.x.1
               len(e.comment) == 1 and
               file_added_re.match(e.comment[0])):
             ui.debug('found synthetic revision in %s: %r\n'
                      % (e.rcs, e.comment[0]))
             e.synthetic = True
 
         if store:
             # clean up the results and save in the log.
             store = False
             e.tags = sorted([scache(x) for x in tags.get(e.revision, [])])
             e.comment = scache('\n'.join(e.comment))
 
             revn = len(e.revision)
             if revn > 3 and (revn % 2) == 0:
                 e.branch = tags.get(e.revision[:-1], [None])[0]
             else:
                 e.branch = None
 
             # find the branches starting from this revision
             branchpoints = set()
             for branch, revision in branchmap.iteritems():
                 revparts = tuple([int(i) for i in revision.split('.')])
                 if len(revparts) < 2: # bad tags
                     continue
                 if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                     # normal branch
                     if revparts[:-2] == e.revision:
                         branchpoints.add(branch)
                 elif revparts == (1, 1, 1): # vendor branch
                     if revparts in e.branches:
                         branchpoints.add(branch)
             e.branchpoints = branchpoints
 
             log.append(e)
 
             rcsmap[e.rcs.replace('/Attic/', '/')] = e.rcs
 
             if len(log) % 100 == 0:
                 ui.status(util.ellipsis('%d %s' % (len(log), e.file), 80)+'\n')
 
     log.sort(key=lambda x: (x.rcs, x.revision))
 
     # find parent revisions of individual files
     versions = {}
     for e in sorted(oldlog, key=lambda x: (x.rcs, x.revision)):
         rcs = e.rcs.replace('/Attic/', '/')
         if rcs in rcsmap:
             e.rcs = rcsmap[rcs]
         branch = e.revision[:-1]
         versions[(e.rcs, branch)] = e.revision
 
     for e in log:
         branch = e.revision[:-1]
         p = versions.get((e.rcs, branch), None)
         if p is None:
             p = e.revision[:-2]
         e.parent = p
         versions[(e.rcs, branch)] = e.revision
 
     # update the log cache
     if cache:
         if log:
             # join up the old and new logs
             log.sort(key=lambda x: x.date)
 
             if oldlog and oldlog[-1].date >= log[0].date:
                 raise logerror(_('log cache overlaps with new log entries,'
                                  ' re-run without cache.'))
 
             log = oldlog + log
 
             # write the new cachefile
             ui.note(_('writing cvs log cache %s\n') % cachefile)
             pickle.dump(log, open(cachefile, 'w'))
         else:
             log = oldlog
 
     ui.status(_('%d log entries\n') % len(log))
 
+    encodings = ui.configlist('convert', 'cvsps.logencoding')
+    if encodings:
+        def revstr(r):
+            # this is needed, because logentry.revision is a tuple of "int"
+            # (e.g. (1, 2) for "1.2")
+            return '.'.join(pycompat.maplist(pycompat.bytestr, r))
+
+        for entry in log:
+            comment = entry.comment
+            for e in encodings:
+                try:
+                    entry.comment = comment.decode(e).encode('utf-8')
+                    if ui.debugflag:
+                        ui.debug("transcoding by %s: %s of %s\n" %
+                                 (e, revstr(entry.revision), entry.file))
+                    break
+                except UnicodeDecodeError:
+                    pass # try next encoding
+                except LookupError as inst: # unknown encoding, maybe
+                    raise error.Abort(inst,
+                                      hint=_('check convert.cvsps.logencoding'
+                                             ' configuration'))
+            else:
+                raise error.Abort(_("no encoding can transcode"
+                                    " CVS log message for %s of %s")
+                                  % (revstr(entry.revision), entry.file),
+                                  hint=_('check convert.cvsps.logencoding'
+                                         ' configuration'))
+
     hook.hook(ui, None, "cvslog", True, log=log)
 
     return log
 
 
 class changeset(object):
     '''Class changeset has the following attributes:
         .id        - integer identifying this changeset (list index)
         .author    - author name as CVS knows it
         .branch    - name of branch this changeset is on, or None
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time,tz) tuple
         .entries   - list of logentry objects in this changeset
         .parents   - list of one or two parent changesets
         .tags      - list of tags on this changeset
         .synthetic - from synthetic revision "file ... added on branch ..."
         .mergepoint- the branch that has been merged from or None
         .branchpoints- the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.id = None
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_('creating changesets\n'))
 
     # try to order commitids by date
     mindate = {}
     for e in log:
         if e.commitid:
             mindate[e.commitid] = min(e.date, mindate.get(e.commitid))
 
     # Merge changesets
     log.sort(key=lambda x: (mindate.get(x.commitid), x.commitid, x.comment,
                             x.author, x.branch, x.date, x.branchpoints))
 
     changesets = []
     files = set()
     c = None
     for i, e in enumerate(log):
 
         # Check if log entry belongs to the current changeset or not.
 
         # Since CVS is file-centric, two different file revisions with
         # different branchpoints should be treated as belonging to two
         # different changesets (and the ordering is important and not
         # honoured by cvsps at this point).
         #
         # Consider the following case:
         # foo 1.1 branchpoints: [MYBRANCH]
         # bar 1.1 branchpoints: [MYBRANCH, MYBRANCH2]
         #
         # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
         # later version of foo may be in MYBRANCH2, so foo should be the
         # first changeset and bar the next and MYBRANCH and MYBRANCH2
         # should both start off of the bar changeset. No provisions are
         # made to ensure that this is, in fact, what happens.
         if not (c and e.branchpoints == c.branchpoints and
                 (# cvs commitids
                  (e.commitid is not None and e.commitid == c.commitid) or
                  (# no commitids, use fuzzy commit detection
                   (e.commitid is None or c.commitid is None) and
                    e.comment == c.comment and
                    e.author == c.author and
                    e.branch == c.branch and
                    ((c.date[0] + c.date[1]) <=
                     (e.date[0] + e.date[1]) <=
                     (c.date[0] + c.date[1]) + fuzz) and
                    e.file not in files))):
             c = changeset(comment=e.comment, author=e.author,
                           branch=e.branch, date=e.date,
                           entries=[], mergepoint=e.mergepoint,
                           branchpoints=e.branchpoints, commitid=e.commitid)
             changesets.append(c)
 
             files = set()
             if len(changesets) % 100 == 0:
                 t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
                 ui.status(util.ellipsis(t, 80) + '\n')
 
         c.entries.append(e)
         files.add(e.file)
         c.date = e.date       # changeset date is date of latest commit in it
 
     # Mark synthetic changesets
 
     for c in changesets:
         # Synthetic revisions always get their own changeset, because
         # the log message includes the filename.  E.g. if you add file3
         # and file4 on a branch, you get four log entries and three
         # changesets:
         #   "File file3 was added on branch ..." (synthetic, 1 entry)
         #   "File file4 was added on branch ..." (synthetic, 1 entry)
         #   "Add file3 and file4 to fix ..."     (real, 2 entries)
         # Hence the check for 1 entry here.
         c.synthetic = len(c.entries) == 1 and c.entries[0].synthetic
 
     # Sort files in each changeset
 
     def entitycompare(l, r):
         'Mimic cvsps sorting order'
         l = l.file.split('/')
         r = r.file.split('/')
         nl = len(l)
         nr = len(r)
         n = min(nl, nr)
         for i in range(n):
             if i + 1 == nl and nl < nr:
                 return -1
             elif i + 1 == nr and nl > nr:
                 return +1
             elif l[i] < r[i]:
                 return -1
             elif l[i] > r[i]:
                 return +1
         return 0
 
     for c in changesets:
         c.entries.sort(entitycompare)
 
     # Sort changesets by date
 
     odd = set()
     def cscmp(l, r):
         d = sum(l.date) - sum(r.date)
         if d:
             return d
 
         # detect vendor branches and initial commits on a branch
         le = {}
         for e in l.entries:
             le[e.rcs] = e.revision
         re = {}
         for e in r.entries:
             re[e.rcs] = e.revision
 
         d = 0
         for e in l.entries:
             if re.get(e.rcs, None) == e.parent:
                 assert not d
                 d = 1
                 break
 
         for e in r.entries:
             if le.get(e.rcs, None) == e.parent:
                 if d:
                     odd.add((l, r))
                 d = -1
                 break
         # By this point, the changesets are sufficiently compared that
         # we don't really care about ordering. However, this leaves
         # some race conditions in the tests, so we compare on the
         # number of files modified, the files contained in each
         # changeset, and the branchpoints in the change to ensure test
         # output remains stable.
 
         # recommended replacement for cmp from
         # https://docs.python.org/3.0/whatsnew/3.0.html
         c = lambda x, y: (x > y) - (x < y)
         # Sort bigger changes first.
         if not d:
             d = c(len(l.entries), len(r.entries))
         # Try sorting by filename in the change.
         if not d:
             d = c([e.file for e in l.entries], [e.file for e in r.entries])
         # Try and put changes without a branch point before ones with
         # a branch point.
         if not d:
             d = c(len(l.branchpoints), len(r.branchpoints))
         return d
 
     changesets.sort(cscmp)
 
     # Collect tags
 
     globaltags = {}
     for c in changesets:
         for e in c.entries:
             for tag in e.tags:
                 # remember which is the latest changeset to have this tag
                 globaltags[tag] = c
 
     for c in changesets:
         tags = set()
         for e in c.entries:
             tags.update(e.tags)
         # remember tags only if this is the latest changeset to have it
         c.tags = sorted(tag for tag in tags if globaltags[tag] is c)
 
     # Find parent changesets, handle {{mergetobranch BRANCHNAME}}
     # by inserting dummy changesets with two parents, and handle
     # {{mergefrombranch BRANCHNAME}} by setting two parents.
 
     if mergeto is None:
         mergeto = r'{{mergetobranch ([-\w]+)}}'
     if mergeto:
         mergeto = re.compile(mergeto)
 
     if mergefrom is None:
         mergefrom = r'{{mergefrombranch ([-\w]+)}}'
     if mergefrom:
         mergefrom = re.compile(mergefrom)
 
     versions = {}    # changeset index where we saw any particular file version
     branches = {}    # changeset index where we saw a branch
     n = len(changesets)
     i = 0
     while i < n:
         c = changesets[i]
 
         for f in c.entries:
             versions[(f.rcs, f.revision)] = i
 
         p = None
         if c.branch in branches:
             p = branches[c.branch]
         else:
             # first changeset on a new branch
             # the parent is a changeset with the branch in its
             # branchpoints such that it is the latest possible
             # commit without any intervening, unrelated commits.
 
             for candidate in xrange(i):
                 if c.branch not in changesets[candidate].branchpoints:
                     if p is not None:
                         break
                     continue
                 p = candidate
 
         c.parents = []
         if p is not None:
             p = changesets[p]
 
             # Ensure no changeset has a synthetic changeset as a parent.
             while p.synthetic:
                 assert len(p.parents) <= 1, \
                        _('synthetic changeset cannot have multiple parents')
                 if p.parents:
                     p = p.parents[0]
                 else:
                     p = None
                     break
 
             if p is not None:
                 c.parents.append(p)
 
         if c.mergepoint:
             if c.mergepoint == 'HEAD':
                 c.mergepoint = None
             c.parents.append(changesets[branches[c.mergepoint]])
 
         if mergefrom:
             m = mergefrom.search(c.comment)
             if m:
                 m = m.group(1)
                 if m == 'HEAD':
                     m = None
                 try:
                     candidate = changesets[branches[m]]
                 except KeyError:
                     ui.warn(_("warning: CVS commit message references "
                               "non-existent branch %r:\n%s\n")
                             % (m, c.comment))
                 if m in branches and c.branch != m and not candidate.synthetic:
                     c.parents.append(candidate)
 
         if mergeto:
             m = mergeto.search(c.comment)
             if m:
                 if m.groups():
                     m = m.group(1)
                     if m == 'HEAD':
                         m = None
                 else:
                     m = None   # if no group found then merge to HEAD
                 if m in branches and c.branch != m:
                     # insert empty changeset for merge
                     cc = changeset(
                         author=c.author, branch=m, date=c.date,
                         comment='convert-repo: CVS merge from branch %s'
                         % c.branch,
                         entries=[], tags=[],
                         parents=[changesets[branches[m]], c])
                     changesets.insert(i + 1, cc)
                     branches[m] = i + 1
 
                     # adjust our loop counters now we have inserted a new entry
                     n += 1
                     i += 2
                     continue
 
         branches[c.branch] = i
         i += 1
 
     # Drop synthetic changesets (safe now that we have ensured no other
     # changesets can have them as parents).
     i = 0
     while i < len(changesets):
         if changesets[i].synthetic:
             del changesets[i]
         else:
             i += 1
 
     # Number changesets
 
     for i, c in enumerate(changesets):
         c.id = i + 1
 
     if odd:
         for l, r in odd:
             if l.id is not None and r.id is not None:
                 ui.warn(_('changeset %d is both before and after %d\n')
                         % (l.id, r.id))
 
     ui.status(_('%d changeset entries\n') % len(changesets))
 
     hook.hook(ui, None, "cvschangesets", True, changesets=changesets)
 
     return changesets
 
 
 def debugcvsps(ui, *args, **opts):
     '''Read CVS rlog for current directory or named path in
     repository, and convert the log to changesets based on matching
     commit log entries and dates.
     '''
     if opts["new_cache"]:
         cache = "write"
     elif opts["update_cache"]:
         cache = "update"
     else:
         cache = None
 
     revisions = opts["revisions"]
 
     try:
         if args:
             log = []
             for d in args:
                 log += createlog(ui, d, root=opts["root"], cache=cache)
         else:
             log = createlog(ui, root=opts["root"], cache=cache)
     except logerror as e:
         ui.write("%r\n"%e)
         return
 
     changesets = createchangeset(ui, log, opts["fuzz"])
     del log
 
     # Print changesets (optionally filtered)
 
     off = len(revisions)
     branches = {}    # latest version number in each branch
     ancestors = {}   # parent branch
     for cs in changesets:
 
         if opts["ancestors"]:
             if cs.branch not in branches and cs.parents and cs.parents[0].id:
                 ancestors[cs.branch] = (changesets[cs.parents[0].id - 1].branch,
                                         cs.parents[0].id)
             branches[cs.branch] = cs.id
 
         # limit by branches
         if opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]:
             continue
 
         if not off:
             # Note: trailing spaces on several lines here are needed to have
             #       bug-for-bug compatibility with cvsps.
             ui.write('---------------------\n')
             ui.write(('PatchSet %d \n' % cs.id))
             ui.write(('Date: %s\n' % util.datestr(cs.date,
                                                  '%Y/%m/%d %H:%M:%S %1%2')))
             ui.write(('Author: %s\n' % cs.author))
             ui.write(('Branch: %s\n' % (cs.branch or 'HEAD')))
             ui.write(('Tag%s: %s \n' % (['', 's'][len(cs.tags) > 1],
                                   ','.join(cs.tags) or '(none)')))
             if cs.branchpoints:
                 ui.write(('Branchpoints: %s \n') %
                          ', '.join(sorted(cs.branchpoints)))
             if opts["parents"] and cs.parents:
                 if len(cs.parents) > 1:
                     ui.write(('Parents: %s\n' %
                              (','.join([str(p.id) for p in cs.parents]))))
                 else:
                     ui.write(('Parent: %d\n' % cs.parents[0].id))
 
             if opts["ancestors"]:
                 b = cs.branch
                 r = []
                 while b:
                     b, c = ancestors[b]
                     r.append('%s:%d:%d' % (b or "HEAD", c, branches[b]))
                 if r:
                     ui.write(('Ancestors: %s\n' % (','.join(r))))
 
             ui.write(('Log:\n'))
             ui.write('%s\n\n' % cs.comment)
             ui.write(('Members: \n'))
             for f in cs.entries:
                 fn = f.file
                 if fn.startswith(opts["prefix"]):
                     fn = fn[len(opts["prefix"]):]
                 ui.write('\t%s:%s->%s%s \n' % (
                         fn, '.'.join([str(x) for x in f.parent]) or 'INITIAL',
                         '.'.join([str(x) for x in f.revision]),
                         ['', '(DEAD)'][f.dead]))
             ui.write('\n')
 
         # have we seen the start tag?
         if revisions and off:
             if revisions[0] == str(cs.id) or \
                 revisions[0] in cs.tags:
                 off = False
 
         # see if we reached the end tag
         if len(revisions) > 1 and not off:
             if revisions[1] == str(cs.id) or \
                 revisions[1] in cs.tags:
                 break

tests/test-convert-cvs.t

@@ -1,500 +1,654 b''
 #require cvs
 
   $ cvscall()
   > {
   >     cvs -f "$@"
   > }
   $ hgcat()
   > {
   >     hg --cwd src-hg cat -r tip "$1"
   > }
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "convert = " >> $HGRCPATH
   $ cat > cvshooks.py <<EOF
   > def cvslog(ui,repo,hooktype,log):
   >     print "%s hook: %d entries"%(hooktype,len(log))
   > 
   > def cvschangesets(ui,repo,hooktype,changesets):
   >     print "%s hook: %d changesets"%(hooktype,len(changesets))
   > EOF
   $ hookpath=`pwd`
   $ cat <<EOF >> $HGRCPATH
   > [hooks]
   > cvslog = python:$hookpath/cvshooks.py:cvslog
   > cvschangesets = python:$hookpath/cvshooks.py:cvschangesets
   > EOF
 
 create cvs repository
 
   $ mkdir cvsrepo
   $ cd cvsrepo
   $ CVSROOT=`pwd`
   $ export CVSROOT
   $ CVS_OPTIONS=-f
   $ export CVS_OPTIONS
   $ cd ..
   $ rmdir cvsrepo
   $ cvscall -q -d "$CVSROOT" init
 
 create source directory
 
   $ mkdir src-temp
   $ cd src-temp
   $ echo a > a
   $ mkdir b
   $ cd b
   $ echo c > c
   $ cd ..
 
 import source directory
 
   $ cvscall -q import -m import src INITIAL start
   N src/a
   N src/b/c
   
   No conflicts created by this import
   
   $ cd ..
 
 checkout source directory
 
   $ cvscall -q checkout src
   U src/a
   U src/b/c
 
 commit a new revision changing b/c
 
   $ cd src
   $ sleep 1
   $ echo c >> b/c
   $ cvscall -q commit -mci0 . | grep '<--'
   $TESTTMP/cvsrepo/src/b/c,v  <--  *c (glob)
   $ cd ..
 
 convert fresh repo and also check localtimezone option
 
 NOTE: This doesn't check all time zones -- it merely determines that
 the configuration option is taking effect.
 
 An arbitrary (U.S.) time zone is used here.  TZ=US/Hawaii is selected
 since it does not use DST (unlike other U.S. time zones) and is always
 a fixed difference from UTC.
 
   $ TZ=US/Hawaii hg convert --config convert.localtimezone=True src src-hg
   initializing destination src-hg repository
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   5 log entries
   cvslog hook: 5 entries
   creating changesets
   3 changeset entries
   cvschangesets hook: 3 changesets
   sorting...
   converting...
   2 Initial revision
   1 ci0
   0 import
   updating tags
   $ hgcat a
   a
   $ hgcat b/c
   c
   c
 
 convert fresh repo with --filemap
 
   $ echo include b/c > filemap
   $ hg convert --filemap filemap src src-filemap
   initializing destination src-filemap repository
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   5 log entries
   cvslog hook: 5 entries
   creating changesets
   3 changeset entries
   cvschangesets hook: 3 changesets
   sorting...
   converting...
   2 Initial revision
   1 ci0
   0 import
   filtering out empty revision
   repository tip rolled back to revision 1 (undo convert)
   updating tags
   $ hgcat b/c
   c
   c
   $ hg -R src-filemap log --template '{rev} {desc} files: {files}\n'
   2 update tags files: .hgtags
   1 ci0 files: b/c
   0 Initial revision files: b/c
 
 convert full repository (issue1649)
 
   $ cvscall -q -d "$CVSROOT" checkout -d srcfull "." | grep -v CVSROOT
   U srcfull/src/a
   U srcfull/src/b/c
   $ ls srcfull
   CVS
   CVSROOT
   src
   $ hg convert srcfull srcfull-hg \
   >     | grep -v 'log entries' | grep -v 'hook:' \
   >     | grep -v '^[0-3] .*' # filter instable changeset order
   initializing destination srcfull-hg repository
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   creating changesets
   4 changeset entries
   sorting...
   converting...
   updating tags
   $ hg cat -r tip --cwd srcfull-hg src/a
   a
   $ hg cat -r tip --cwd srcfull-hg src/b/c
   c
   c
 
 commit new file revisions
 
   $ cd src
   $ echo a >> a
   $ echo c >> b/c
   $ cvscall -q commit -mci1 . | grep '<--'
   $TESTTMP/cvsrepo/src/a,v  <--  a
   $TESTTMP/cvsrepo/src/b/c,v  <--  *c (glob)
   $ cd ..
 
 convert again
 
   $ TZ=US/Hawaii hg convert --config convert.localtimezone=True src src-hg
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   7 log entries
   cvslog hook: 7 entries
   creating changesets
   4 changeset entries
   cvschangesets hook: 4 changesets
   sorting...
   converting...
   0 ci1
   $ hgcat a
   a
   a
   $ hgcat b/c
   c
   c
   c
 
 convert again with --filemap
 
   $ hg convert --filemap filemap src src-filemap
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   7 log entries
   cvslog hook: 7 entries
   creating changesets
   4 changeset entries
   cvschangesets hook: 4 changesets
   sorting...
   converting...
   0 ci1
   $ hgcat b/c
   c
   c
   c
   $ hg -R src-filemap log --template '{rev} {desc} files: {files}\n'
   3 ci1 files: b/c
   2 update tags files: .hgtags
   1 ci0 files: b/c
   0 Initial revision files: b/c
 
 commit branch
 
   $ cd src
   $ cvs -q update -r1.1 b/c
   U b/c
   $ cvs -q tag -b branch
   T a
   T b/c
   $ cvs -q update -r branch > /dev/null
   $ sleep 1
   $ echo d >> b/c
   $ cvs -q commit -mci2 . | grep '<--'
   $TESTTMP/cvsrepo/src/b/c,v  <--  *c (glob)
   $ cd ..
 
 convert again
 
   $ TZ=US/Hawaii hg convert --config convert.localtimezone=True src src-hg
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   8 log entries
   cvslog hook: 8 entries
   creating changesets
   5 changeset entries
   cvschangesets hook: 5 changesets
   sorting...
   converting...
   0 ci2
   $ hgcat b/c
   c
   d
 
 convert again with --filemap
 
   $ TZ=US/Hawaii hg convert --config convert.localtimezone=True --filemap filemap src src-filemap
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   8 log entries
   cvslog hook: 8 entries
   creating changesets
   5 changeset entries
   cvschangesets hook: 5 changesets
   sorting...
   converting...
   0 ci2
   $ hgcat b/c
   c
   d
   $ hg -R src-filemap log --template '{rev} {desc} files: {files}\n'
   4 ci2 files: b/c
   3 ci1 files: b/c
   2 update tags files: .hgtags
   1 ci0 files: b/c
   0 Initial revision files: b/c
 
 commit a new revision with funny log message
 
   $ cd src
   $ sleep 1
   $ echo e >> a
   $ cvscall -q commit -m'funny
   > ----------------------------
   > log message' . | grep '<--' |\
   >  sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
   checking in src/a,v
 
 commit new file revisions with some fuzz
 
   $ sleep 1
   $ echo f >> a
   $ cvscall -q commit -mfuzzy . | grep '<--'
   $TESTTMP/cvsrepo/src/a,v  <--  a
   $ sleep 4 # the two changes will be split if fuzz < 4
   $ echo g >> b/c
   $ cvscall -q commit -mfuzzy . | grep '<--'
   $TESTTMP/cvsrepo/src/b/c,v  <--  *c (glob)
   $ cd ..
 
 convert again
 
   $ TZ=US/Hawaii hg convert --config convert.cvsps.fuzz=2 --config convert.localtimezone=True src src-hg
   connecting to $TESTTMP/cvsrepo
   scanning source...
   collecting CVS rlog
   11 log entries
   cvslog hook: 11 entries
   creating changesets
   8 changeset entries
   cvschangesets hook: 8 changesets
   sorting...
   converting...
   2 funny
   1 fuzzy
   0 fuzzy
   $ hg -R src-hg log -G --template '{rev} ({branches}) {desc} date: {date|date} files: {files}\n'
   o  8 (branch) fuzzy date: * -1000 files: b/c (glob)
   |
   o  7 (branch) fuzzy date: * -1000 files: a (glob)
   |
   o  6 (branch) funny
   |  ----------------------------
   |  log message date: * -1000 files: a (glob)
   o  5 (branch) ci2 date: * -1000 files: b/c (glob)
   
   o  4 () ci1 date: * -1000 files: a b/c (glob)
   |
   o  3 () update tags date: * +0000 files: .hgtags (glob)
   |
   | o  2 (INITIAL) import date: * -1000 files: (glob)
   | |
   o |  1 () ci0 date: * -1000 files: b/c (glob)
   |/
   o  0 () Initial revision date: * -1000 files: a b/c (glob)
   
 
 testing debugcvsps
 
   $ cd src
   $ hg debugcvsps --fuzz=2 -x >/dev/null
 
 commit a new revision changing a and removing b/c
 
   $ cvscall -q update -A
   U a
   U b/c
   $ sleep 1
   $ echo h >> a
   $ cvscall -Q remove -f b/c
   $ cvscall -q commit -mci | grep '<--'
   $TESTTMP/cvsrepo/src/a,v  <--  a
   $TESTTMP/cvsrepo/src/b/c,v  <--  *c (glob)
 
 update and verify the cvsps cache
 
   $ hg debugcvsps --fuzz=2 -u
   collecting CVS rlog
   13 log entries
   cvslog hook: 13 entries
   creating changesets
   11 changeset entries
   cvschangesets hook: 11 changesets
   ---------------------
   PatchSet 1 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Branchpoints: INITIAL 
   Log:
   Initial revision
   
   Members: 
   	a:INITIAL->1.1 
   
   ---------------------
   PatchSet 2 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Branchpoints: INITIAL, branch 
   Log:
   Initial revision
   
   Members: 
   	b/c:INITIAL->1.1 
   
   ---------------------
   PatchSet 3 
   Date: * (glob)
   Author: * (glob)
   Branch: INITIAL
   Tag: start 
   Log:
   import
   
   Members: 
   	a:1.1->1.1.1.1 
   	b/c:1.1->1.1.1.1 
   
   ---------------------
   PatchSet 4 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Log:
   ci0
   
   Members: 
   	b/c:1.1->1.2 
   
   ---------------------
   PatchSet 5 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Branchpoints: branch 
   Log:
   ci1
   
   Members: 
   	a:1.1->1.2 
   
   ---------------------
   PatchSet 6 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Log:
   ci1
   
   Members: 
   	b/c:1.2->1.3 
   
   ---------------------
   PatchSet 7 
   Date: * (glob)
   Author: * (glob)
   Branch: branch
   Tag: (none) 
   Log:
   ci2
   
   Members: 
   	b/c:1.1->1.1.2.1 
   
   ---------------------
   PatchSet 8 
   Date: * (glob)
   Author: * (glob)
   Branch: branch
   Tag: (none) 
   Log:
   funny
   ----------------------------
   log message
   
   Members: 
   	a:1.2->1.2.2.1 
   
   ---------------------
   PatchSet 9 
   Date: * (glob)
   Author: * (glob)
   Branch: branch
   Tag: (none) 
   Log:
   fuzzy
   
   Members: 
   	a:1.2.2.1->1.2.2.2 
   
   ---------------------
   PatchSet 10 
   Date: * (glob)
   Author: * (glob)
   Branch: branch
   Tag: (none) 
   Log:
   fuzzy
   
   Members: 
   	b/c:1.1.2.1->1.1.2.2 
   
   ---------------------
   PatchSet 11 
   Date: * (glob)
   Author: * (glob)
   Branch: HEAD
   Tag: (none) 
   Log:
   ci
   
   Members: 
   	a:1.2->1.3 
   	b/c:1.3->1.4(DEAD) 
   
 
   $ cd ..
+
+Test transcoding CVS log messages (issue5597)
+=============================================
+
+To emulate commit messages in (non-ascii) multiple encodings portably,
+this test scenario writes CVS history file (*,v file) directly via
+python code.
+
+Commit messages of version 1.2 - 1.4 use u3042 in 3 encodings below.
+
+|encoding  |byte sequence | decodable as:      |
+|          |              | utf-8 euc-jp cp932 |
++----------+--------------+--------------------+
+|utf-8     |\xe3\x81\x82  |  o      x     x    |
+|euc-jp    |\xa4\xa2      |  x      o     o    |
+|cp932     |\x82\xa0      |  x      x     o    |
+
+  $ mkdir -p cvsrepo/transcoding
+  $ python <<EOF
+  > fp = open('cvsrepo/transcoding/file,v', 'w')
+  > fp.write(('''
+  > head	1.4;
+  > access;
+  > symbols
+  > 	start:1.1.1.1 INITIAL:1.1.1;
+  > locks; strict;
+  > comment	@# @;
+  > 
+  > 
+  > 1.4
+  > date	2017.07.10.00.00.04;	author nobody;	state Exp;
+  > branches;
+  > next	1.3;
+  > commitid	10059635D016A510FFA;
+  > 
+  > 1.3
+  > date	2017.07.10.00.00.03;	author nobody;	state Exp;
+  > branches;
+  > next	1.2;
+  > commitid	10059635CFF6A4FF34E;
+  > 
+  > 1.2
+  > date	2017.07.10.00.00.02;	author nobody;	state Exp;
+  > branches;
+  > next	1.1;
+  > commitid	10059635CFD6A4D5095;
+  > 
+  > 1.1
+  > date	2017.07.10.00.00.01;	author nobody;	state Exp;
+  > branches
+  > 	1.1.1.1;
+  > next	;
+  > commitid	10059635CFB6A4A3C33;
+  > 
+  > 1.1.1.1
+  > date	2017.07.10.00.00.01;	author nobody;	state Exp;
+  > branches;
+  > next	;
+  > commitid	10059635CFB6A4A3C33;
+  > 
+  > 
+  > desc
+  > @@
+  > 
+  > 
+  > 1.4
+  > log
+  > @''' + u'\u3042'.encode('cp932') + ''' (cp932)
+  > @
+  > text
+  > @1
+  > 2
+  > 3
+  > 4
+  > @
+  > 
+  > 
+  > 1.3
+  > log
+  > @''' + u'\u3042'.encode('euc-jp') + ''' (euc-jp)
+  > @
+  > text
+  > @d4 1
+  > @
+  > 
+  > 
+  > 1.2
+  > log
+  > @''' + u'\u3042'.encode('utf-8') +  ''' (utf-8)
+  > @
+  > text
+  > @d3 1
+  > @
+  > 
+  > 
+  > 1.1
+  > log
+  > @Initial revision
+  > @
+  > text
+  > @d2 1
+  > @
+  > 
+  > 
+  > 1.1.1.1
+  > log
+  > @import
+  > @
+  > text
+  > @@
+  > ''').lstrip())
+  > EOF
+
+  $ cvscall -q checkout transcoding
+  U transcoding/file
+
+Test converting in normal case
+------------------------------
+
+(filtering by grep in order to check only form of debug messages)
+
+  $ hg convert --config convert.cvsps.logencoding=utf-8,euc-jp,cp932 -q --debug transcoding transcoding-hg | grep 'transcoding by'
+  transcoding by utf-8: 1.1 of file
+  transcoding by utf-8: 1.1.1.1 of file
+  transcoding by utf-8: 1.2 of file
+  transcoding by euc-jp: 1.3 of file
+  transcoding by cp932: 1.4 of file
+  $ hg -R transcoding-hg --encoding utf-8 log -T "{rev}: {desc}\n"
+  5: update tags
+  4: import
+  3: \xe3\x81\x82 (cp932) (esc)
+  2: \xe3\x81\x82 (euc-jp) (esc)
+  1: \xe3\x81\x82 (utf-8) (esc)
+  0: Initial revision
+  $ rm -rf transcoding-hg
+
+Test converting in error cases
+------------------------------
+
+unknown encoding in convert.cvsps.logencoding
+
+  $ hg convert --config convert.cvsps.logencoding=foobar -q transcoding transcoding-hg
+  abort: unknown encoding: foobar
+  (check convert.cvsps.logencoding configuration)
+  [255]
+  $ rm -rf transcoding-hg
+
+no acceptable encoding in convert.cvsps.logencoding
+
+  $ hg convert --config convert.cvsps.logencoding=utf-8,euc-jp -q transcoding transcoding-hg
+  abort: no encoding can transcode CVS log message for 1.4 of file
+  (check convert.cvsps.logencoding configuration)
+  [255]
+  $ rm -rf transcoding-hg

tests/test-convert.t

@@ -1,610 +1,616 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 new branch name.
       This can be used to (for instance) move code in one repository from
       "default" to a named branch.
   
       Mercurial Source
       ################
   
       The Mercurial source recognizes the following configuration options, which
       you can set on the command line with "--config":
   
       convert.hg.ignoreerrors
                     ignore integrity errors when reading. Use it to fix
                     Mercurial repositories with missing revlogs, by converting
                     from and to Mercurial. Default is False.
       convert.hg.saverev
                     store original revision ID in changeset (forces target IDs
                     to change). It takes a boolean argument and defaults to
                     False.
       convert.hg.startrev
                     specify the initial Mercurial revision. The default is 0.
       convert.hg.revs
                     revset specifying the source revisions to convert.
   
       CVS Source
       ##########
   
       CVS source will use a sandbox (i.e. a checked-out copy) from CVS to
       indicate the starting point of what will be converted. Direct access to
       the repository files is not needed, unless of course the repository is
       ":local:". The conversion uses the top level directory in the sandbox to
       find the CVS repository, and then uses CVS rlog commands to find files to
       convert. This means that unless a filemap is given, all files under the
       starting directory will be converted, and that any directory
       reorganization in the CVS sandbox is ignored.
   
       The following options can be used with "--config":
   
       convert.cvsps.cache
                     Set to False to disable remote log caching, for testing and
                     debugging purposes. Default is True.
       convert.cvsps.fuzz
                     Specify the maximum time (in seconds) that is allowed
                     between commits with identical user and log message in a
                     single changeset. When very large files were checked in as
                     part of a changeset then the default may not be long enough.
                     The default is 60.
+      convert.cvsps.logencoding
+                    Specify encoding name to be used for transcoding CVS log
+                    messages. Multiple encoding names can be specified as a list
+                    (see 'hg help config.Syntax'), but only the first acceptable
+                    encoding in the list is used per CVS log entries. This
+                    transcoding is executed before cvslog hook below.
       convert.cvsps.mergeto
                     Specify a regular expression to which commit log messages
                     are matched. If a match occurs, then the conversion process
                     will insert a dummy revision merging the branch on which
                     this log message occurs to the branch indicated in the
                     regex. Default is "{{mergetobranch ([-\w]+)}}"
       convert.cvsps.mergefrom
                     Specify a regular expression to which commit log messages
                     are matched. If a match occurs, then the conversion process
                     will add the most recent revision on the branch indicated in
                     the regex as the second parent of the changeset. Default is
                     "{{mergefrombranch ([-\w]+)}}"
       convert.localtimezone
                     use local time (as determined by the TZ environment
                     variable) for changeset date/times. The default is False
                     (use UTC).
       hooks.cvslog  Specify a Python function to be called at the end of
                     gathering the CVS log. The function is passed a list with
                     the log entries, and can modify the entries in-place, or add
                     or delete them.
       hooks.cvschangesets
                     Specify a Python function to be called after the changesets
                     are calculated from the CVS log. The function is passed a
                     list with the changeset entries, and can modify the
                     changesets in-place, or add or delete them.
   
       An additional "debugcvsps" Mercurial command allows the builtin changeset
       merging code to be run without doing a conversion. Its parameters and
       output are similar to that of cvsps 2.1. Please see the command help for
       more details.
   
       Subversion Source
       #################
   
       Subversion source detects classical trunk/branches/tags layouts. By
       default, the supplied "svn://repo/path/" source URL is converted as a
       single branch. If "svn://repo/path/trunk" exists it replaces the default
       branch. If "svn://repo/path/branches" exists, its subdirectories are
       listed as possible branches. If "svn://repo/path/tags" exists, it is
       looked for tags referencing converted branches. Default "trunk",
       "branches" and "tags" values can be overridden with following options. Set
       them to paths relative to the source URL, or leave them blank to disable
       auto detection.
   
       The following options can be set with "--config":
   
       convert.svn.branches
                     specify the directory containing branches. The default is
                     "branches".
       convert.svn.tags
                     specify the directory containing tags. The default is
                     "tags".
       convert.svn.trunk
                     specify the name of the trunk branch. The default is
                     "trunk".
       convert.localtimezone
                     use local time (as determined by the TZ environment
                     variable) for changeset date/times. The default is False
                     (use UTC).
   
       Source history can be retrieved starting at a specific revision, instead
       of being integrally converted. Only single branch conversions are
       supported.
   
       convert.svn.startrev
                     specify start Subversion revision number. The default is 0.
   
       Git Source
       ##########
   
       The Git importer converts commits from all reachable branches (refs in
       refs/heads) and remotes (refs in refs/remotes) to Mercurial. Branches are
       converted to bookmarks with the same name, with the leading 'refs/heads'
       stripped. Git submodules are converted to Git subrepos in Mercurial.
   
       The following options can be set with "--config":
   
       convert.git.similarity
                     specify how similar files modified in a commit must be to be
                     imported as renames or copies, as a percentage between "0"
                     (disabled) and "100" (files must be identical). For example,
                     "90" means that a delete/add pair will be imported as a
                     rename if more than 90% of the file hasn't changed. The
                     default is "50".
       convert.git.findcopiesharder
                     while detecting copies, look at all files in the working
                     copy instead of just changed ones. This is very expensive
                     for large projects, and is only effective when
                     "convert.git.similarity" is greater than 0. The default is
                     False.
       convert.git.renamelimit
                     perform rename and copy detection up to this many changed
                     files in a commit. Increasing this will make rename and copy
                     detection more accurate but will significantly slow down
                     computation on large projects. The option is only relevant
                     if "convert.git.similarity" is greater than 0. The default
                     is "400".
       convert.git.committeractions
                     list of actions to take when processing author and committer
                     values.
   
           Git commits have separate author (who wrote the commit) and committer
           (who applied the commit) fields. Not all destinations support separate
           author and committer fields (including Mercurial). This config option
           controls what to do with these author and committer fields during
           conversion.
   
           A value of "messagedifferent" will append a "committer: ..." line to
           the commit message if the Git committer is different from the author.
           The prefix of that line can be specified using the syntax
           "messagedifferent=<prefix>". e.g. "messagedifferent=git-committer:".
           When a prefix is specified, a space will always be inserted between
           the prefix and the value.
   
           "messagealways" behaves like "messagedifferent" except it will always
           result in a "committer: ..." line being appended to the commit
           message. This value is mutually exclusive with "messagedifferent".
   
           "dropcommitter" will remove references to the committer. Only
           references to the author will remain. Actions that add references to
           the committer will have no effect when this is set.
   
           "replaceauthor" will replace the value of the author field with the
           committer. Other actions that add references to the committer will
           still take effect when this is set.
   
           The default is "messagedifferent".
   
       convert.git.extrakeys
                     list of extra keys from commit metadata to copy to the
                     destination. Some Git repositories store extra metadata in
                     commits. By default, this non-default metadata will be lost
                     during conversion. Setting this config option can retain
                     that metadata. Some built-in keys such as "parent" and
                     "branch" are not allowed to be copied.
       convert.git.remoteprefix
                     remote refs are converted as bookmarks with
                     "convert.git.remoteprefix" as a prefix followed by a /. The
                     default is 'remote'.
       convert.git.saverev
                     whether to store the original Git commit ID in the metadata
                     of the destination commit. The default is True.
       convert.git.skipsubmodules
                     does not convert root level .gitmodules files or files with
                     160000 mode indicating a submodule. Default is False.
   
       Perforce Source
       ###############
   
       The Perforce (P4) importer can be given a p4 depot path or a client
       specification as source. It will convert all files in the source to a flat
       Mercurial repository, ignoring labels, branches and integrations. Note
       that when a depot path is given you then usually should specify a target
       directory, because otherwise the target may be named "...-hg".
   
       The following options can be set with "--config":
   
       convert.p4.encoding
                     specify the encoding to use when decoding standard output of
                     the Perforce command line tool. The default is default
                     system encoding.
       convert.p4.startrev
                     specify initial Perforce revision (a Perforce changelist
                     number).
   
       Mercurial Destination
       #####################
   
       The Mercurial destination will recognize Mercurial subrepositories in the
       destination directory, and update the .hgsubstate file automatically if
       the destination subrepositories contain the <dest>/<sub>/.hg/shamap file.
       Converting a repository with subrepositories requires converting a single
       repository at a time, from the bottom up.
   
       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
   $TESTTMP/emptydir does not look like a Git repository (glob)
   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
 
   $ cat > branchmap.txt << EOF
   > old branch new_branch
   > EOF
 
   $ hg -R a branch -q 'old branch'
   $ echo gg > a/g
   $ hg -R a ci -m 'branch name with spaces'
   $ hg convert --branchmap branchmap.txt a d
   initializing destination d repository
   scanning source...
   sorting...
   converting...
   6 a
   5 b
   4 c
   3 d
   2 e
   1 g
   0 branch name with spaces
 
   $ hg -R a branches
   old branch                     6:a24a66ade009
   default                        5:a3bc6100aa8e (inactive)
   $ hg -R d branches
   new_branch                     6:64ed208b732b
   default                        5:a3bc6100aa8e (inactive)