convert: some tidyups, doc improvements, and test fixes

The various back end options are now documented.
The hg source can now be configured not to hand out a revision ID.

hgext/convert/__init__.py

@@ -1,383 +1,401 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, incorporated herein by reference.
 
 from common import NoRepo, SKIPREV, converter_source, converter_sink, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import debugsvnlog, svn_source, svn_sink
 import filemap
 
 import os, shutil
 from mercurial import hg, ui, util, commands
 from mercurial.i18n import _
 
 commands.norepo += " convert debugsvnlog"
 
 source_converters = [
     ('cvs', convert_cvs),
     ('git', convert_git),
     ('svn', svn_source),
     ('hg', mercurial_source),
     ('darcs', darcs_source),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     for name, source in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev)
         except NoRepo, inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write(_("%s\n") % inst)
     raise util.Abort('%s: unknown repository type' % path)
 
 def convertsink(ui, path, type):
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
     raise util.Abort('%s: unknown repository type' % path)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authors'):
             self.readauthormap(opts.get('authors'))
             self.authorfile = self.dest.authorfile()
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = {}
         parents = {}
         while visit:
             n = visit.pop(0)
             if n in known or n in self.map: continue
             known[n] = 1
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
 
         return parents
 
     def toposort(self, parents):
         '''Return an ordering such that every uncommitted changeset is
         preceeded by all its uncommitted ancestors.'''
         visit = parents.keys()
         seen = {}
         children = {}
 
         while visit:
             n = visit.pop(0)
             if n in seen: continue
             seen[n] = 1
             # Ensure that nodes without parents are present in the 'children'
             # mapping.
             children.setdefault(n, [])
             for p in parents[n]:
                 if not p in self.map:
                     visit.append(p)
                 children.setdefault(p, []).append(n)
 
         s = []
         removed = {}
         visit = children.keys()
         while visit:
             n = visit.pop(0)
             if n in removed: continue
             dep = 0
             if n in parents:
                 for p in parents[n]:
                     if p in self.map: continue
                     if p not in removed:
                         # we're still dependent
                         visit.append(n)
                         dep = 1
                         break
 
             if not dep:
                 # all n's parents are in the list
                 removed[n] = 1
                 if n not in self.map:
                     s.append(n)
                 if n in children:
                     for c in children[n]:
                         visit.insert(0, c)
 
         if self.opts.get('datesort'):
             depth = {}
             for n in s:
                 depth[n] = 0
                 pl = [p for p in self.commitcache[n].parents
                       if p not in self.map]
                 if pl:
                     depth[n] = max([depth[p] for p in pl]) + 1
 
             s = [(depth[n], self.commitcache[n].date, n) for n in s]
             s.sort()
             s = [e[2] for e in s]
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
            self.ui.status('Writing author map file %s\n' % authorfile)
            ofile = open(authorfile, 'w+')
            for author in self.authors:
                ofile.write("%s=%s\n" % (author, self.authors[author]))
            ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
             try:
                 srcauthor = line.split('=')[0].strip()
                 dstauthor = line.split('=')[1].strip()
                 if srcauthor in self.authors and dstauthor != self.authors[srcauthor]:
                     self.ui.status(
                         'Overriding mapping for author %s, was %s, will be %s\n'
                         % (srcauthor, self.authors[srcauthor], dstauthor))
                 else:
                     self.ui.debug('Mapping author %s to %s\n'
                                   % (srcauthor, dstauthor))
                     self.authors[srcauthor] = dstauthor
             except IndexError:
                 self.ui.warn(
                     'Ignoring bad line in author file map %s: %s\n'
                     % (authorfile, line))
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         do_copies = hasattr(self.dest, 'copyfile')
         filenames = []
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies = changes
         parents = [self.map[r] for r in commit.parents]
         if commit.parents:
             prev = commit.parents[0]
             if prev not in self.commitcache:
                 self.cachecommit(prev)
             pbranch = self.commitcache[prev].branch
         else:
             pbranch = None
         self.dest.setbranch(commit.branch, pbranch, parents)
         for f, v in files:
             filenames.append(f)
             try:
                 data = self.source.getfile(f, v)
             except IOError, inst:
                 self.dest.delfile(f)
             else:
                 e = self.source.getmode(f, v)
                 self.dest.putfile(f, e, data)
                 if do_copies:
                     if f in copies:
                         copyf = copies[f]
                         # Merely marks that a copy happened.
                         self.dest.copyfile(copyf, f)
 
         newnode = self.dest.putcommit(filenames, parents, commit)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status("scanning source...\n")
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.ui.status("sorting...\n")
             t = self.toposort(parents)
             num = len(t)
             c = None
 
             self.ui.status("converting...\n")
             for c in t:
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 self.ui.status("%d %s\n" % (num, desc))
                 self.copy(c)
 
             tags = self.source.gettags()
             ctags = {}
             for k in tags:
                 v = tags[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     ctags[k] = self.map[v]
 
             if c and ctags:
                 nrev = self.dest.puttags(ctags)
                 # write another hash correspondence to override the previous
                 # one so we don't end up with extra tag heads
                 if nrev:
                     self.map[c] = nrev
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats:
     - Mercurial
     - CVS
     - Darcs
     - git
     - Subversion
 
     Accepted destination formats:
     - Mercurial
     - Subversion (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.
 
     If <MAPFILE> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <MAPFILE> 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 convert-repo can be interrupted and can
     be run repeatedly to copy new commits.
 
     The [username mapping] file 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 (eg: CVS). One line per author
     mapping and the line format is:
     srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files
     and directories.  Comment lines start with '#'.  Each line can
     contain one of the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
     
     The 'include' directive causes a file, or all files under a
     directory, to be included in the destination repository, and the
     exclusion of all other files and dirs not explicitely included.
     The 'exclude' directive causes files or directories to be omitted.
     The 'rename' directive renames a file or directory.  To rename from a
     subdirectory into the root of the repository, use '.' as the path to
     rename to.
+
+    Back end options:
+
+    --config convert.hg.clonebranches=False   (boolean)
+        hg target: XXX not documented
+    --config convert.hg.saverev=True          (boolean)
+        hg source: allow target to preserve source revision ID
+    --config convert.hg.tagsbranch=default    (branch name)
+        hg target: XXX not documented
+    --config convert.hg.usebranchnames=True   (boolean)
+        hg target: preserve branch names
+
+    --config convert.svn.branches=branches    (directory name)
+        svn source: specify the directory containing branches
+    --config convert.svn.tags=tags            (directory name)
+        svn source: specify the directory containing tags
+    --config convert.svn.trunk=trunk          (directory name)
+        svn source: specify the name of the trunk branch
     """
 
     util._encoding = 'UTF-8'
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status("assuming destination %s\n" % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc = convertsource(ui, src, opts.get('source_type'),
                              opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         try:
             revmapfile = destc.revmapfile()
         except:
             revmapfile = os.path.join(destc, "map")
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert()
 
 
 cmdtable = {
     "convert":
         (convert,
          [('A', 'authors', '', 'username mapping filename'),
           ('d', 'dest-type', '', 'destination repository type'),
           ('', 'filemap', '', 'remap file names using contents of file'),
           ('r', 'rev', '', 'import up to target revision REV'),
           ('s', 'source-type', '', 'source repository type'),
           ('', 'datesort', None, 'try to sort changesets by date')],
          'hg convert [OPTION]... SOURCE [DEST [MAPFILE]]'),
     "debugsvnlog":
         (debugsvnlog,
          [],
          'hg debugsvnlog'),
 }
 

hgext/convert/common.py

@@ -1,297 +1,297 b''
 # common code for the convert extension
 import base64, errno
 import cPickle as pickle
 from mercurial import util
 from mercurial.i18n import _
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64.encodestring(s)
         lines = [l.splitlines()[0] for l in lines]
         return ''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 def decodeargs(s):
     s = base64.decodestring(s)
     return pickle.loads(s)
 
 def checktool(exe, name=None):
     name = name or exe
     if not util.find_exe(exe):
         raise util.Abort('cannot find required "%s" tool' % name)
 
 class NoRepo(Exception): pass
 
 SKIPREV = 'SKIP'
 
 class commit(object):
     def __init__(self, author, date, desc, parents, branch=None, rev=None,
                  extra={}):
         self.author = author
         self.date = date
         self.desc = desc
         self.parents = parents
         self.branch = branch
         self.rev = rev
         self.extra = extra
 
 class converter_source(object):
     """Conversion source interface"""
 
-    def __init__(self, ui, path, rev=None):
+    def __init__(self, ui, path=None, rev=None):
         """Initialize conversion source (or raise NoRepo("message")
         exception if path is not a valid repository)"""
         self.ui = ui
         self.path = path
         self.rev = rev
 
         self.encoding = 'utf-8'
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def setrevmap(self, revmap):
         """set the map of already-converted revisions"""
         pass
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError()
 
     def getfile(self, name, rev):
         """Return file contents as a string"""
         raise NotImplementedError()
 
     def getmode(self, name, rev):
         """Return file mode, eg. '', 'x', or 'l'"""
         raise NotImplementedError()
 
     def getchanges(self, version):
         """Returns a tuple of (files, copies)
         Files is a sorted list of (filename, id) tuples for all files changed
         in version, where id is the source revision id of the file.
 
         copies is a dictionary of dest: source
         """
         raise NotImplementedError()
 
     def getcommit(self, version):
         """Return the commit object for version"""
         raise NotImplementedError()
 
     def gettags(self):
         """Return the tags as a dictionary of name: revision"""
         raise NotImplementedError()
 
     def recode(self, s, encoding=None):
         if not encoding:
             encoding = self.encoding or 'utf-8'
 
         if isinstance(s, unicode):
             return s.encode("utf-8")
         try:
             return s.decode(encoding).encode("utf-8")
         except:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except:
                 return s.decode(encoding, "replace").encode("utf-8")
 
     def getchangedfiles(self, rev, i):
         """Return the files changed by rev compared to parent[i].
     
         i is an index selecting one of the parents of rev.  The return
         value should be the list of files that are different in rev and
         this parent.
 
         If rev has no parents, i is None.
     
         This function is only needed to support --filemap
         """
         raise NotImplementedError()
 
     def converted(self, rev, sinkrev):
         '''Notify the source that a revision has been converted.'''
         pass
 
 
 class converter_sink(object):
     """Conversion sink (target) interface"""
 
     def __init__(self, ui, path):
         """Initialize conversion sink (or raise NoRepo("message")
         exception if path is not a valid repository)
 
         created is a list of paths to remove if a fatal error occurs
         later"""
         self.ui = ui
         self.path = path
         self.created = []
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError()
 
     def revmapfile(self):
         """Path to a file that will contain lines
         source_rev_id sink_rev_id
         mapping equivalent revision identifiers for each system."""
         raise NotImplementedError()
 
     def authorfile(self):
         """Path to a file that will contain lines
         srcauthor=dstauthor
         mapping equivalent authors identifiers for each system."""
         return None
 
     def putfile(self, f, e, data):
         """Put file for next putcommit().
         f: path to file
         e: '', 'x', or 'l' (regular file, executable, or symlink)
         data: file contents"""
         raise NotImplementedError()
 
     def delfile(self, f):
         """Delete file for next putcommit().
         f: path to file"""
         raise NotImplementedError()
 
     def putcommit(self, files, parents, commit):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object containing
         at a minimum the author, date, and message for this changeset.
         Called after putfile() and delfile() calls. Note that the sink
         repository is not told to update itself to a particular revision
         (or even what that revision would be) before it receives the
         file data."""
         raise NotImplementedError()
 
     def puttags(self, tags):
         """Put tags into sink.
         tags: {tagname: sink_rev_id, ...}"""
         raise NotImplementedError()
 
     def setbranch(self, branch, pbranch, parents):
         """Set the current branch name. Called before the first putfile
         on the branch.
         branch: branch name for subsequent commits
         pbranch: branch name of parent commit
         parents: destination revisions of parent"""
         pass
 
     def setfilemapmode(self, active):
         """Tell the destination that we're using a filemap
 
         Some converter_sources (svn in particular) can claim that a file
         was changed in a revision, even if there was no change.  This method
         tells the destination that we're using a filemap and that it should
         filter empty revisions.
         """
         pass
 
     def before(self):
         pass
 
     def after(self):
         pass
 
 
 class commandline(object):
     def __init__(self, ui, command):
         self.ui = ui
         self.command = command
 
     def prerun(self):
         pass
 
     def postrun(self):
         pass
 
     def _run(self, cmd, *args, **kwargs):
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.iteritems():
             if len(k) == 1:
                 cmdline.append('-' + k)
             else:
                 cmdline.append('--' + k.replace('_', '-'))
             try:
                 if len(k) == 1:
                     cmdline.append('' + v)
                 else:
                     cmdline[-1] += '=' + v
             except TypeError:
                 pass
         cmdline = [util.shellquote(arg) for arg in cmdline]
         cmdline += ['<', util.nulldev]
         cmdline = ' '.join(cmdline)
         self.ui.debug(cmdline, '\n')
 
         self.prerun()
         try:
             return util.popen(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         fp = self._run(cmd, *args, **kwargs)
         output = fp.read()
         self.ui.debug(output)
         return output, fp.close()
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = util.explain_exit(status)[0]
             raise util.Abort(_('%s %s') % (self.command, msg))
 
     def run0(self, cmd, *args, **kwargs):
         output, status = self.run(cmd, *args, **kwargs)
         self.checkexit(status, output)
         return output
 
 
 class mapfile(dict):
     def __init__(self, ui, path):
         super(mapfile, self).__init__()
         self.ui = ui
         self.path = path
         self.fp = None
         self.order = []
         self._read()
 
     def _read(self):
         try:
             fp = open(self.path, 'r')
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for line in fp:
             key, value = line[:-1].split(' ', 1)
             if key not in self:
                 self.order.append(key)
             super(mapfile, self).__setitem__(key, value)
         fp.close()
             
     def __setitem__(self, key, value):
         if self.fp is None:
             try:
                 self.fp = open(self.path, 'a')
             except IOError, err:
                 raise util.Abort(_('could not open map file %r: %s') %
                                  (self.path, err.strerror))
         self.fp.write('%s %s\n' % (key, value))
         self.fp.flush()
         super(mapfile, self).__setitem__(key, value)
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None

hgext/convert/filemap.py

@@ -1,352 +1,346 b''
 # Copyright 2007 Bryan O'Sullivan <[e-mail]>
 # Copyright 2007 Alexis S. L. Carvalho <[e-mail]>
 #
 # This software may be used and distributed according to the terms of
 # the GNU General Public License, incorporated herein by reference.
 
 import shlex
 from mercurial.i18n import _
 from mercurial import util
-from common import SKIPREV
+from common import SKIPREV, converter_source
 
 def rpairs(name):
     e = len(name)
     while e != -1:
         yield name[:e], name[e+1:]
         e = name.rfind('/', 0, e)
 
 class filemapper(object):
     '''Map and filter filenames when importing.
     A name can be mapped to itself, a new name, or None (omit from new
     repository).'''
 
     def __init__(self, ui, path=None):
         self.ui = ui
         self.include = {}
         self.exclude = {}
         self.rename = {}
         if path:
             if self.parse(path):
                 raise util.Abort(_('errors in filemap'))
 
     def parse(self, path):
         errs = 0
         def check(name, mapping, listname):
             if name in mapping:
                 self.ui.warn(_('%s:%d: %r already in %s list\n') %
                              (lex.infile, lex.lineno, name, listname))
                 return 1
             return 0
         lex = shlex.shlex(open(path), path, True)
         lex.wordchars += '!@#$%^&*()-=+[]{}|;:,./<>?'
         cmd = lex.get_token()
         while cmd:
             if cmd == 'include':
                 name = lex.get_token()
                 errs += check(name, self.exclude, 'exclude')
                 self.include[name] = name
             elif cmd == 'exclude':
                 name = lex.get_token()
                 errs += check(name, self.include, 'include')
                 errs += check(name, self.rename, 'rename')
                 self.exclude[name] = name
             elif cmd == 'rename':
                 src = lex.get_token()
                 dest = lex.get_token()
                 errs += check(src, self.exclude, 'exclude')
                 self.rename[src] = dest
             elif cmd == 'source':
                 errs += self.parse(lex.get_token())
             else:
                 self.ui.warn(_('%s:%d: unknown directive %r\n') %
                              (lex.infile, lex.lineno, cmd))
                 errs += 1
             cmd = lex.get_token()
         return errs
 
     def lookup(self, name, mapping):
         for pre, suf in rpairs(name):
             try:
                 return mapping[pre], pre, suf
             except KeyError, err:
                 pass
         return '', name, ''
 
     def __call__(self, name):
         if self.include:
             inc = self.lookup(name, self.include)[0]
         else:
             inc = name
         if self.exclude:
             exc = self.lookup(name, self.exclude)[0]
         else:
             exc = ''
         if not inc or exc:
             return None
         newpre, pre, suf = self.lookup(name, self.rename)
         if newpre:
             if newpre == '.':
                 return suf
             if suf:
                 return newpre + '/' + suf
             return newpre
         return name
 
     def active(self):
         return bool(self.include or self.exclude or self.rename)
 
 # This class does two additional things compared to a regular source:
 #
 # - Filter and rename files.  This is mostly wrapped by the filemapper
 #   class above. We hide the original filename in the revision that is
 #   returned by getchanges to be able to find things later in getfile
 #   and getmode.
 #
 # - Return only revisions that matter for the files we're interested in.
 #   This involves rewriting the parents of the original revision to
 #   create a graph that is restricted to those revisions.
 #
 #   This set of revisions includes not only revisions that directly
 #   touch files we're interested in, but also merges that merge two
 #   or more interesting revisions.
 
-class filemap_source(object):
+class filemap_source(converter_source):
     def __init__(self, ui, baseconverter, filemap):
-        self.ui = ui
+        super(filemap_source, self).__init__(ui)
         self.base = baseconverter
         self.filemapper = filemapper(ui, filemap)
         self.commits = {}
         # if a revision rev has parent p in the original revision graph, then
         # rev will have parent self.parentmap[p] in the restricted graph.
         self.parentmap = {}
         # self.wantedancestors[rev] is the set of all ancestors of rev that
         # are in the restricted graph.
         self.wantedancestors = {}
         self.convertedorder = None
         self._rebuilt = False
         self.origparents = {}
         self.children = {}
         self.seenchildren = {}
 
     def setrevmap(self, revmap):
         # rebuild our state to make things restartable
         #
         # To avoid calling getcommit for every revision that has already
         # been converted, we rebuild only the parentmap, delaying the
         # rebuild of wantedancestors until we need it (i.e. until a
         # merge).
         #
         # We assume the order argument lists the revisions in
         # topological order, so that we can infer which revisions were
         # wanted by previous runs.
         self._rebuilt = not revmap
         seen = {SKIPREV: SKIPREV}
         dummyset = util.set()
         converted = []
         for rev in revmap.order:
             mapped = revmap[rev]
             wanted = mapped not in seen
             if wanted:
                 seen[mapped] = rev
                 self.parentmap[rev] = rev
             else:
                 self.parentmap[rev] = seen[mapped]
             self.wantedancestors[rev] = dummyset
             arg = seen[mapped]
             if arg == SKIPREV:
                 arg = None
             converted.append((rev, wanted, arg))
         self.convertedorder = converted
         return self.base.setrevmap(revmap)
 
     def rebuild(self):
         if self._rebuilt:
             return True
         self._rebuilt = True
         self.parentmap.clear()
         self.wantedancestors.clear()
         self.seenchildren.clear()
         for rev, wanted, arg in self.convertedorder:
             if rev not in self.origparents:
                 self.origparents[rev] = self.getcommit(rev).parents
             if arg is not None:
                 self.children[arg] = self.children.get(arg, 0) + 1
 
         for rev, wanted, arg in self.convertedorder:
             parents = self.origparents[rev]
             if wanted:
                 self.mark_wanted(rev, parents)
             else:
                 self.mark_not_wanted(rev, arg)
             self._discard(arg, *parents)
 
         return True
 
     def getheads(self):
         return self.base.getheads()
 
     def getcommit(self, rev):
         # We want to save a reference to the commit objects to be able
         # to rewrite their parents later on.
         c = self.commits[rev] = self.base.getcommit(rev)
         for p in c.parents:
             self.children[p] = self.children.get(p, 0) + 1
         return c
 
     def _discard(self, *revs):
         for r in revs:
             if r is None:
                 continue
             self.seenchildren[r] = self.seenchildren.get(r, 0) + 1
             if self.seenchildren[r] == self.children[r]:
                 del self.wantedancestors[r]
                 del self.parentmap[r]
                 del self.seenchildren[r]
                 if self._rebuilt:
                     del self.children[r]
 
     def wanted(self, rev, i):
         # Return True if we're directly interested in rev.
         #
         # i is an index selecting one of the parents of rev (if rev
         # has no parents, i is None).  getchangedfiles will give us
         # the list of files that are different in rev and in the parent
         # indicated by i.  If we're interested in any of these files,
         # we're interested in rev.
         try:
             files = self.base.getchangedfiles(rev, i)
         except NotImplementedError:
             raise util.Abort(_("source repository doesn't support --filemap"))
         for f in files:
             if self.filemapper(f):
                 return True
         return False
 
     def mark_not_wanted(self, rev, p):
         # Mark rev as not interesting and update data structures.
 
         if p is None:
             # A root revision. Use SKIPREV to indicate that it doesn't
             # map to any revision in the restricted graph.  Put SKIPREV
             # in the set of wanted ancestors to simplify code elsewhere
             self.parentmap[rev] = SKIPREV
             self.wantedancestors[rev] = util.set((SKIPREV,))
             return
 
         # Reuse the data from our parent.
         self.parentmap[rev] = self.parentmap[p]
         self.wantedancestors[rev] = self.wantedancestors[p]
 
     def mark_wanted(self, rev, parents):
         # Mark rev ss wanted and update data structures.
 
         # rev will be in the restricted graph, so children of rev in
         # the original graph should still have rev as a parent in the
         # restricted graph.
         self.parentmap[rev] = rev
 
         # The set of wanted ancestors of rev is the union of the sets
         # of wanted ancestors of its parents. Plus rev itself.
         wrev = util.set()
         for p in parents:
             wrev.update(self.wantedancestors[p])
         wrev.add(rev)
         self.wantedancestors[rev] = wrev
 
     def getchanges(self, rev):
         parents = self.commits[rev].parents
         if len(parents) > 1:
             self.rebuild()
 
         # To decide whether we're interested in rev we:
         #
         # - calculate what parents rev will have if it turns out we're
         #   interested in it.  If it's going to have more than 1 parent,
         #   we're interested in it.
         #
         # - otherwise, we'll compare it with the single parent we found.
         #   If any of the files we're interested in is different in the
         #   the two revisions, we're interested in rev.
 
         # A parent p is interesting if its mapped version (self.parentmap[p]):
         # - is not SKIPREV
         # - is still not in the list of parents (we don't want duplicates)
         # - is not an ancestor of the mapped versions of the other parents
         mparents = []
         wp = None
         for i, p1 in enumerate(parents):
             mp1 = self.parentmap[p1]
             if mp1 == SKIPREV or mp1 in mparents:
                 continue
             for p2 in parents:
                 if p1 == p2 or mp1 == self.parentmap[p2]:
                     continue
                 if mp1 in self.wantedancestors[p2]:
                     break
             else:
                 mparents.append(mp1)
                 wp = i
 
         if wp is None and parents:
             wp = 0
 
         self.origparents[rev] = parents
 
         if len(mparents) < 2 and not self.wanted(rev, wp):
             # We don't want this revision.
             # Update our state and tell the convert process to map this
             # revision to the same revision its parent as mapped to.
             p = None
             if parents:
                 p = parents[wp]
             self.mark_not_wanted(rev, p)
             self.convertedorder.append((rev, False, p))
             self._discard(*parents)
             return self.parentmap[rev]
 
         # We want this revision.
         # Rewrite the parents of the commit object
         self.commits[rev].parents = mparents
         self.mark_wanted(rev, parents)
         self.convertedorder.append((rev, True, None))
         self._discard(*parents)
 
         # Get the real changes and do the filtering/mapping.
         # To be able to get the files later on in getfile and getmode,
         # we hide the original filename in the rev part of the return
         # value.
         changes, copies = self.base.getchanges(rev)
         newnames = {}
         files = []
         for f, r in changes:
             newf = self.filemapper(f)
             if newf:
                 files.append((newf, (f, r)))
                 newnames[f] = newf
 
         ncopies = {}
         for c in copies:
             newc = self.filemapper(c)
             if newc:
                 newsource = self.filemapper(copies[c])
                 if newsource:
                     ncopies[newc] = newsource
 
         return files, ncopies
 
     def getfile(self, name, rev):
         realname, realrev = rev
         return self.base.getfile(realname, realrev)
 
     def getmode(self, name, rev):
         realname, realrev = rev
         return self.base.getmode(realname, realrev)
 
     def gettags(self):
         return self.base.gettags()
-
-    def before(self):
-        pass
-
-    def after(self):
-        pass

hgext/convert/hg.py

@@ -1,265 +1,276 b''
 # hg backend for convert extension
 
-# Note for hg->hg conversion: Old versions of Mercurial didn't trim
-# the whitespace from the ends of commit messages, but new versions
-# do.  Changesets created by those older versions, then converted, may
-# thus have different hashes for changesets that are otherwise
-# identical.
+# Notes for hg->hg conversion:
+#
+# * Old versions of Mercurial didn't trim the whitespace from the ends
+#   of commit messages, but new versions do.  Changesets created by
+#   those older versions, then converted, may thus have different
+#   hashes for changesets that are otherwise identical.
+#
+# * By default, the source revision is stored in the converted
+#   revision.  This will cause the converted revision to have a
+#   different identity than the source.  To avoid this, use the
+#   following option: "--config convert.hg.saverev=false"
 
 
 import os, time
 from mercurial.i18n import _
 from mercurial.node import *
 from mercurial import hg, lock, revlog, util
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
             except hg.RepoError, err:
                 ui.print_exc()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 self.created.append(path)
             except hg.RepoError, err:
                 ui.print_exc()
                 raise NoRepo("could not create hg repo %s as sink" % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
         self.repo.dirstate.clear()
 
     def after(self):
         self.repo.dirstate.invalidate()
         self.lock = None
         self.wlock = None
 
     def revmapfile(self):
         return os.path.join(self.path, ".hg", "shamap")
 
     def authorfile(self):
         return os.path.join(self.path, ".hg", "authormap")
 
     def getheads(self):
         h = self.repo.changelog.heads()
         return [ hex(x) for x in h ]
 
     def putfile(self, f, e, data):
         self.repo.wwrite(f, data, e)
         if f not in self.repo.dirstate:
             self.repo.dirstate.normallookup(f)
 
     def copyfile(self, source, dest):
         self.repo.copy(source, dest)
 
     def delfile(self, f):
         try:
             util.unlink(self.repo.wjoin(f))
             #self.repo.remove([f])
         except OSError:
             pass
 
     def setbranch(self, branch, pbranch, parents):
         if (not self.clonebranches) or (branch == self.lastbranch):
             return
 
         self.lastbranch = branch
         self.after()
         if not branch:
             branch = 'default'
         if not pbranch:
             pbranch = 'default'
 
         branchpath = os.path.join(self.path, branch)
         try:
             self.repo = hg.repository(self.ui, branchpath)
         except:
             if not parents:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             else:
                 self.ui.note(_('cloning branch %s to %s\n') % (pbranch, branch))
                 hg.clone(self.ui, os.path.join(self.path, pbranch),
                          branchpath, rev=parents, update=False,
                          stream=True)
                 self.repo = hg.repository(self.ui, branchpath)
         self.before()
 
     def putcommit(self, files, parents, commit):
         seen = {}
         pl = []
         for p in parents:
             if p not in seen:
                 pl.append(p)
                 seen[p] = 1
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2: parents.append("0" * 40)
         if len(parents) < 2: parents.append("0" * 40)
         p2 = parents.pop(0)
 
         text = commit.desc
         extra = commit.extra.copy()
         if self.branchnames and commit.branch:
             extra['branch'] = commit.branch
         if commit.rev:
             extra['convert_revision'] = commit.rev
 
         while parents:
             p1 = p2
             p2 = parents.pop(0)
             a = self.repo.rawcommit(files, text, commit.author, commit.date,
                                     bin(p1), bin(p2), extra=extra)
             self.repo.dirstate.clear()
             text = "(octopus merge fixup)\n"
             p2 = hg.hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             if not man.cmp(m1node, man.revision(mnode)):
                 self.repo.rollback()
                 self.repo.dirstate.clear()
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             old = self.repo.wfile(".hgtags").read()
             oldlines = old.splitlines(1)
             oldlines.sort()
         except:
             oldlines = []
 
         k = tags.keys()
         k.sort()
         newlines = []
         for tag in k:
             newlines.append("%s %s\n" % (tags[tag], tag))
 
         newlines.sort()
 
         if newlines != oldlines:
             self.ui.status("updating tags\n")
             f = self.repo.wfile(".hgtags", "w")
             f.write("".join(newlines))
             f.close()
             if not oldlines: self.repo.add([".hgtags"])
             date = "%s 0" % int(time.mktime(time.gmtime()))
             extra = {}
             if self.tagsbranch != 'default':
                 extra['branch'] = self.tagsbranch
             try:
                 tagparent = self.repo.changectx(self.tagsbranch).node()
             except hg.RepoError, inst:
                 tagparent = nullid
             self.repo.rawcommit([".hgtags"], "update tags", "convert-repo",
                                 date, tagparent, nullid)
             return hex(self.repo.changelog.tip())
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
+        self.saverev = ui.configbool('convert', 'hg.saverev', True)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise hg.RepoError()
         except hg.RepoError:
             ui.print_exc()
             raise NoRepo("%s is not a local Mercurial repo" % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo.changectx(rev)
             self.lastrev = rev
         return self.lastctx
 
     def getheads(self):
         if self.rev:
             return [hex(self.repo.changectx(self.rev).node())]
         else:
             return [hex(node) for node in self.repo.heads()]
 
     def getfile(self, name, rev):
         try:
             return self.changectx(rev).filectx(name).data()
         except revlog.LookupError, err:
             raise IOError(err)
 
     def getmode(self, name, rev):
         m = self.changectx(rev).manifest()
         return (m.execf(name) and 'x' or '') + (m.linkf(name) and 'l' or '')
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(ctx.parents()[0].node(), ctx.node())[:3]
         changes = [(name, rev) for name in m + a + r]
         changes.sort()
         return (changes, self.getcopies(ctx, m + a))
 
     def getcopies(self, ctx, files):
         copies = {}
         for name in files:
             try:
                 copies[name] = ctx.filectx(name).renamed()[0]
             except TypeError:
                 pass
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [hex(p.node()) for p in ctx.parents() if p.node() != nullid]
+        if self.saverev:
+            crev = rev
+        else:
+            crev = None
         return commit(author=ctx.user(), date=util.datestr(ctx.date()),
-                      desc=ctx.description(), rev=rev, parents=parents,
+                      desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra())
 
     def gettags(self):
         tags = [t for t in self.repo.tagslist() if t[0] != 'tip']
         return dict([(name, hex(node)) for name, node in tags])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         i = i or 0
         changes = self.repo.status(ctx.parents()[i].node(), ctx.node())[:3]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.path, '.hg', 'shamap'),
                                   'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()

tests/test-convert

@@ -1,37 +1,41 b''
 #!/bin/sh
 
-echo "[extensions]" >> $HGRCPATH
-echo "convert=" >> $HGRCPATH
+cat >> $HGRCPATH <<EOF
+[extensions]
+convert=
+[convert]
+hg.saverev=False
+EOF
 
 hg help convert
 
 hg init a
 cd a
 echo a > a
 hg ci -d'0 0' -Ama
 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'
 hg --cwd a-hg pull ../a
 
 touch bogusfile
 echo % should fail
 hg convert a bogusfile
 
 mkdir bogusdir
 chmod 000 bogusdir
 
 echo % should fail
 hg convert a bogusdir
 
 echo % should succeed
 chmod 700 bogusdir
 hg convert a bogusdir

tests/test-convert-cvs.out

@@ -1,71 +1,69 b''
 % create cvs repository
 % create source directory
 % import source directory
 N src/a
 N src/b/c
 
 No conflicts created by this import
 
 % checkout source directory
 U src/a
 U src/b/c
 % commit a new revision changing b/c
 checking in src/b/c,v
 % convert fresh repo
 initializing destination src-hg repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 0 ci0
 updating tags
 a
 c
 c
 % convert fresh repo with --filemap
 initializing destination src-filemap repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 rolling back last transaction
 0 ci0
 updating tags
 c
 c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 % commit new file revisions
 checking in src/a,v
 checking in src/b/c,v
 % convert again
-destination src-hg is a Mercurial repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 a
 a
 c
 c
 c
 % convert again with --filemap
-destination src-filemap is a Mercurial repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 c
 c
 c
 3 ci1 files: b/c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c

tests/test-convert-hg-sink

@@ -1,53 +1,57 b''
 #!/bin/sh
 
-echo "[extensions]" >> $HGRCPATH
-echo "hgext.convert=" >> $HGRCPATH
+cat >> $HGRCPATH <<EOF
+[extensions]
+convert=
+[convert]
+hg.saverev=False
+EOF
 
 hg init orig
 cd orig
 echo foo > foo
 echo bar > bar
 hg ci -qAm 'add foo and bar' -d '0 0'
 
 hg rm foo
 hg ci -m 'remove foo' -d '0 0'
 
 mkdir foo
 echo file > foo/file
 hg ci -qAm 'add foo/file' -d '0 0'
 
 hg tag -d '0 0' some-tag
 
 hg log
 cd ..
 
 hg convert orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'
 cd new
 hg out ../orig
 
 echo '% dirstate should be empty:'
 hg debugstate
 hg parents -q
 
 hg up -C
 hg copy bar baz
 echo '% put something in the dirstate:'
 hg debugstate > debugstate
 grep baz debugstate
 
 echo '% add a new revision in the original repo'
 cd ../orig
 echo baz > baz
 hg ci -qAm 'add baz'
 
 cd ..
 hg convert orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'
 cd new
 hg out ../orig
 echo '% dirstate should be the same (no output below):'
 hg debugstate > new-debugstate
 diff debugstate new-debugstate
 
 echo '% no copies'
 hg up -C
 hg debugrename baz

tests/test-convert-hg-sink.out

@@ -1,51 +1,50 b''
 changeset:   3:593cbf6fb2b4
 tag:         tip
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     Added tag some-tag for changeset ad681a868e44
 
 changeset:   2:ad681a868e44
 tag:         some-tag
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     add foo/file
 
 changeset:   1:cbba8ecc03b7
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     remove foo
 
 changeset:   0:327daa9251fa
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     add foo and bar
 
 initializing destination new repository
 scanning source...
 sorting...
 converting...
 3 add foo and bar
 2 remove foo
 1 add foo/file
 0 Added tag some-tag for changeset ad681a868e44
 comparing with ../orig
 searching for changes
 no changes found
 % dirstate should be empty:
 3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 % put something in the dirstate:
 a   0         -1 unset             baz
 copy: bar -> baz
 % add a new revision in the original repo
-destination new is a Mercurial repository
 scanning source...
 sorting...
 converting...
 0 add baz
 comparing with ../orig
 searching for changes
 no changes found
 % dirstate should be the same (no output below):
 % no copies
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 baz not renamed

tests/test-convert-hg-source

@@ -1,33 +1,37 b''
 #!/bin/sh
 
-echo "[extensions]" >> $HGRCPATH
-echo "hgext.convert=" >> $HGRCPATH
+cat >> $HGRCPATH <<EOF
+[extensions]
+convert=
+[convert]
+hg.saverev=False
+EOF
 
 hg init orig
 cd orig
 
 echo foo > foo
 echo bar > bar
 hg ci -qAm 'add foo bar' -d '0 0'
 
 echo >> foo
 hg ci -m 'change foo' -d '1 0'
 
 hg up -qC 0
 hg copy --after --force foo bar
 hg copy foo baz
 hg ci -m 'make bar and baz copies of foo' -d '2 0'
 
 hg merge
 hg ci -m 'merge local copy' -d '3 0'
 
 hg up -C 1
 hg merge 2
 hg ci -m 'merge remote copy' -d '4 0'
 
 cd ..
 hg convert --datesort orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'
 cd new
 hg out ../orig
 
 true

tests/test-convert-svn-source.out

@@ -1,114 +1,112 b''
 % initial svn import
 Adding         t/a
 
 Committed revision 1.
 % update svn repository
 A    t2/a
 Checked out revision 1.
 A         b
 Sending        a
 Adding         b
 Transmitting file data ..
 Committed revision 2.
 % convert to hg once
 assuming destination trunk-hg
 initializing destination trunk-hg repository
 scanning source...
 sorting...
 converting...
 1 init
 0 changea
 % update svn repository again
 Sending        a
 Sending        b
 Transmitting file data ..
 Committed revision 3.
 % test incremental conversion
 assuming destination trunk-hg
-destination trunk-hg is a Mercurial repository
 scanning source...
 sorting...
 converting...
 0 changeb
 % test filemap
 initializing destination fmap repository
 scanning source...
 sorting...
 converting...
 2 init
 1 changea
 0 changeb
 o  1 changeb files: b
 |
 o  0 changea files: b
 
 # now tests that it works with trunk/branches/tags layout
 
 % initial svn import
 Adding         projA/trunk
 Adding         projA/branches
 Adding         projA/tags
 
 Committed revision 4.
 % update svn repository
 Checked out revision 4.
 A         letter.txt
 Adding         letter.txt
 Transmitting file data .
 Committed revision 5.
 Sending        letter.txt
 Transmitting file data .
 Committed revision 6.
 
 Committed revision 7.
 Sending        letter.txt
 Transmitting file data .
 Committed revision 8.
 % convert to hg once
 initializing destination A-hg repository
 scanning source...
 sorting...
 converting...
 3 init projA
 2 hello
 1 world
 0 nice day
 updating tags
 % update svn repository again
 A         letter2.txt
 Sending        letter.txt
 Adding         letter2.txt
 Transmitting file data ..
 Committed revision 9.
 
 Committed revision 10.
 Sending        letter2.txt
 Transmitting file data .
 Committed revision 11.
 % test incremental conversion
-destination A-hg is a Mercurial repository
 scanning source...
 sorting...
 converting...
 1 second letter
 0 work in progress
 updating tags
 o  7 update tags files: .hgtags
 |
 o  6 work in progress files: letter2.txt
 |
 o  5 second letter files: letter.txt letter2.txt
 |
 o  4 update tags files: .hgtags
 |
 o  3 nice day files: letter.txt
 |
 o  2 world files: letter.txt
 |
 o  1 hello files: letter.txt
 |
 o  0 init projA files:
 
 tip
 v0.2
 v0.1

tests/test-convert.out

@@ -1,96 +1,114 b''
 hg convert [OPTION]... SOURCE [DEST [MAPFILE]]
 
 Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats:
     - Mercurial
     - CVS
     - Darcs
     - git
     - Subversion
 
     Accepted destination formats:
     - Mercurial
     - Subversion (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.
 
     If <MAPFILE> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <MAPFILE> 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 convert-repo can be interrupted and can
     be run repeatedly to copy new commits.
 
     The [username mapping] file 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 (eg: CVS). One line per author
     mapping and the line format is:
     srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files
     and directories.  Comment lines start with '#'.  Each line can
     contain one of the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
     
     The 'include' directive causes a file, or all files under a
     directory, to be included in the destination repository, and the
     exclusion of all other files and dirs not explicitely included.
     The 'exclude' directive causes files or directories to be omitted.
     The 'rename' directive renames a file or directory.  To rename from a
     subdirectory into the root of the repository, use '.' as the path to
     rename to.
 
+    Back end options:
+
+    --config convert.hg.clonebranches=False   (boolean)
+        hg target: XXX not documented
+    --config convert.hg.saverev=True          (boolean)
+        hg source: allow target to preserve source revision ID
+    --config convert.hg.tagsbranch=default    (branch name)
+        hg target: XXX not documented
+    --config convert.hg.usebranchnames=True   (boolean)
+        hg target: preserve branch names
+
+    --config convert.svn.branches=branches    (directory name)
+        svn source: specify the directory containing branches
+    --config convert.svn.tags=tags            (directory name)
+        svn source: specify the directory containing tags
+    --config convert.svn.trunk=trunk          (directory name)
+        svn source: specify the name of the trunk branch
+
 options:
 
  -A --authors      username mapping filename
  -d --dest-type    destination repository type
     --filemap      remap file names using contents of file
  -r --rev          import up to target revision REV
  -s --source-type  source repository type
     --datesort     try to sort changesets by date
 
 use "hg -v help convert" to show global options
 adding a
 assuming destination a-hg
 initializing destination a-hg repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 pulling from ../a
 searching for changes
 no changes found
 % should fail
 initializing destination bogusfile repository
 abort: cannot create new bundle repository
 % should fail
 abort: Permission denied: bogusdir
 % should succeed
 initializing destination bogusdir repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e