convert: fix history topology when using hg.tagsbranch

When using hg.tagsbranch, all conversions fail at
transcribing the source repo topology with conversion
scenarios interleaving:
 - initial repo conversion,
 - then upstream tag
 - then later incremental conversion

The problem is caused by the usage of the last source
revid as source revid for the tagnode in the revision
map.

On a later incremental conversion, when resolving some
child commit of the true last source revid, convert
will parent the nodes to the tag node. If using
tagsbranch you get a bad topology where all incremental
commit nodes end up in the tag branch.

Analysis and test by Edouard Gomez <[e-mail]>

tests/test-convert-tagsbranch-topology

@@ -0,0 +1,64 b''
+#!/bin/sh
+
+"$TESTDIR/hghave" git || exit 80
+
+echo "[extensions]" >> $HGRCPATH
+echo "convert=" >> $HGRCPATH
+echo 'hgext.graphlog =' >> $HGRCPATH
+echo '[convert]' >> $HGRCPATH
+echo 'hg.usebranchnames = True' >> $HGRCPATH
+echo 'hg.tagsbranch = tags-update' >> $HGRCPATH
+
+GIT_AUTHOR_NAME='test'; export GIT_AUTHOR_NAME
+GIT_AUTHOR_EMAIL='[e-mail]'; export GIT_AUTHOR_EMAIL
+GIT_AUTHOR_DATE="2007-01-01 00:00:00 +0000"; export GIT_AUTHOR_DATE
+GIT_COMMITTER_NAME="$GIT_AUTHOR_NAME"; export GIT_COMMITTER_NAME
+GIT_COMMITTER_EMAIL="$GIT_AUTHOR_EMAIL"; export GIT_COMMITTER_EMAIL
+GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"; export GIT_COMMITTER_DATE
+
+count=10
+action()
+{
+    GIT_AUTHOR_DATE="2007-01-01 00:00:$count +0000"
+    GIT_COMMITTER_DATE="$GIT_AUTHOR_DATE"
+    git "$@" >/dev/null 2>/dev/null || echo "git command error"
+    count=`expr $count + 1`
+}
+
+glog()
+{
+    hg glog --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
+}
+
+convertrepo()
+{
+    hg convert --datesort git-repo hg-repo
+}
+
+# Build a GIT repo with at least 1 tag
+mkdir git-repo
+cd git-repo
+git init >/dev/null 2>&1
+echo a > a
+git add a
+action commit -m "rev1"
+action tag -m "tag1" tag1
+cd ..
+
+# Do a first conversion
+convertrepo
+
+# Simulate upstream  updates after first conversion
+cd git-repo
+echo b > a
+git add a
+action commit -m "rev2"
+action tag -m "tag2" tag2
+cd ..
+
+# Perform an incremental conversion
+convertrepo
+
+# Print the log
+cd hg-repo
+glog

tests/test-convert-tagsbranch-topology.out

@@ -0,0 +1,19 b''
+initializing destination hg-repo repository
+scanning source...
+sorting...
+converting...
+0 rev1
+updating tags
+scanning source...
+sorting...
+converting...
+0 rev2
+updating tags
+o  3 "update tags" files: .hgtags
+|
+| o  2 "rev2" files: a
+| |
+o |  1 "update tags" files: .hgtags
+ /
+o  0 "rev1" files: a
+

hgext/convert/common.py

@@ -1,389 +1,391 b''
 # common.py - common code for the convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 import base64, errno
 import os
 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)
 
 class MissingTool(Exception): pass
 
 def checktool(exe, name=None, abort=True):
     name = name or exe
     if not util.find_exe(exe):
         exc = abort and util.Abort or MissingTool
         raise exc(_('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={}, sortkey=None):
         self.author = author or 'unknown'
         self.date = date or '0 0'
         self.desc = desc
         self.parents = parents
         self.branch = branch
         self.rev = rev
         self.extra = extra
         self.sortkey = sortkey
 
 class converter_source(object):
     """Conversion source interface"""
 
     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. rev is the identifier returned
         by a previous call to getchanges(). Raise IOError to indicate that
         name was deleted in rev.
         """
         raise NotImplementedError()
 
     def getmode(self, name, rev):
         """Return file mode, eg. '', 'x', or 'l'. rev is the identifier
         returned by a previous call to getchanges().
         """
         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 between version and its first parent returned by
         getcommit(). 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
 
         Tag names must be UTF-8 strings.
         """
         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
 
     def hasnativeorder(self):
         """Return true if this source has a meaningful, native revision
         order. For instance, Mercurial revisions are store sequentially
         while there is no such global ordering with Darcs.
         """
         return False
 
     def lookuprev(self, rev):
         """If rev is a meaningful revision reference in source, return
         the referenced identifier in the same format used by getcommit().
         return None otherwise.
         """
         return None
 
 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 putcommit(self, files, copies, parents, commit, source, revmap):
         """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.  'files' is a list of (path, version) tuples,
         'copies' is a dictionary mapping destinations to sources,
         'source' is the source repository, and 'revmap' is a mapfile
         of source revisions to converted revisions. Only getfile(),
         getmode(), and lookuprev() should be called on 'source'.
 
         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, ...} where tagname is an UTF-8 string.
+        Return a pair (tag_revision, tag_parent_revision), or (None, None)
+        if nothing was changed.
         """
         raise NotImplementedError()
 
     def setbranch(self, branch, pbranches):
         """Set the current branch name. Called before the first putcommit
         on the branch.
         branch: branch name for subsequent commits
         pbranches: (converted parent revision, parent branch) tuples"""
         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 _cmdline(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]
         if not self.ui.debugflag:
             cmdline += ['2>', util.nulldev]
         cmdline += ['<', util.nulldev]
         cmdline = ' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug(_('running: %s\n') % (cmdline,))
         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 runlines(self, cmd, *args, **kwargs):
         fp = self._run(cmd, *args, **kwargs)
         output = fp.readlines()
         self.ui.debug(''.join(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
 
     def runlines0(self, cmd, *args, **kwargs):
         output, status = self.runlines(cmd, *args, **kwargs)
         self.checkexit(status, ''.join(output))
         return output
 
     def getargmax(self):
         if '_argmax' in self.__dict__:
             return self._argmax
 
         # POSIX requires at least 4096 bytes for ARG_MAX
         self._argmax = 4096
         try:
             self._argmax = os.sysconf("SC_ARG_MAX")
         except:
             pass
 
         # Windows shells impose their own limits on command line length,
         # down to 2047 bytes for cmd.exe under Windows NT/2k and 2500 bytes
         # for older 4nt.exe. See http://support.microsoft.com/kb/830473 for
         # details about cmd.exe limitations.
 
         # Since ARG_MAX is for command line _and_ environment, lower our limit
         # (and make happy Windows shells while doing this).
 
         self._argmax = self._argmax/2 - 1
         return self._argmax
 
     def limit_arglist(self, arglist, cmd, *args, **kwargs):
         limit = self.getargmax() - len(self._cmdline(cmd, *args, **kwargs))
         bytes = 0
         fl = []
         for fn in arglist:
             b = len(fn) + 3
             if bytes + b < limit or len(fl) == 0:
                 fl.append(fn)
                 bytes += b
             else:
                 yield fl
                 fl = [fn]
                 bytes = b
         if fl:
             yield fl
 
     def xargs(self, arglist, cmd, *args, **kwargs):
         for l in self.limit_arglist(arglist, cmd, *args, **kwargs):
             self.run0(cmd, *(list(args) + l), **kwargs)
 
 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):
         if not self.path:
             return
         try:
             fp = open(self.path, 'r')
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for i, line in enumerate(fp):
             try:
                 key, value = line[:-1].rsplit(' ', 1)
             except ValueError:
                 raise util.Abort(_('syntax error in %s(%d): key/value pair expected')
                                  % (self.path, i+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/convcmd.py

@@ -1,396 +1,399 b''
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
         except (NoRepo, MissingTool), inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     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
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authors'):
             self.readauthormap(opts.get('authors'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = mapfile(ui, opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         while visit:
             n = visit.pop(0)
             if n in known or n in self.map: continue
             known.add(n)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
 
         return parents
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceeded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = parents.keys()
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if not p in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('Writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('Ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         commit.branch = self.branchmap.get(commit.branch, commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
 
         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
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev].replace(',', ' ').split()
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       self.source, self.map)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             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]
                 # convert log message to local encoding without using
                 # tolocal() because encoding.encoding conver() use it as
                 # 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 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
+                nrev, tagsparent = self.dest.puttags(ctags)
+                if nrev and tagsparent:
+                    # write another hash correspondence to override the previous
+                    # one so we don't end up with extra tag heads
+                    tagsparents = [e for e in self.map.iteritems()
+                                   if e[1] == tagsparent]
+                    if tagsparents:
+                        self.map[tagsparents[0][0]] = nrev
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     sortmode = sortmode and sortmode[0] or defaultsort
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         try:
             revmapfile = destc.revmapfile()
         except:
             revmapfile = os.path.join(destc, "map")
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)
 

hgext/convert/hg.py

@@ -1,363 +1,363 b''
 # hg.py - hg backend for convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 # 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.
 #
 # * Using "--config convert.hg.saverev=true" will make the source
 #   identifier to be stored in the converted revision. This will cause
 #   the converted revision to have a different identity than the
 #   source.
 
 
 import os, time, cStringIO
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import hg, util, context, error
 
 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)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repo') % path)
             except error.RepoError, err:
                 ui.traceback()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repo') % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
                 raise NoRepo("could not create hg repo %s as sink" % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.ui.debug(_('run hg sink pre-conversion action\n'))
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
 
     def after(self):
         self.ui.debug(_('run hg sink post-conversion action\n'))
         self.lock.release()
         self.wlock.release()
 
     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 setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         pbranch = pbranches and pbranches[0][1] or 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in missings.iteritems():
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.repository(self.ui, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
     def _rewritetags(self, source, revmap, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
             revid = revmap.get(source.lookuprev(s[0]))
             if not revid:
                 continue
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
 
         files = dict(files)
         def getfilectx(repo, memctx, f):
             v = files[f]
             data = source.getfile(f, v)
             e = source.getmode(f, v)
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             return context.memfilectx(f, data, 'l' in e, 'x' in e, copies.get(f))
 
         pl = []
         for p in parents:
             if p not in pl:
                 pl.append(p)
         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(nullid)
         if len(parents) < 2: parents.append(nullid)
         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)
             ctx = context.memctx(self.repo, (p1, p2), text, files.keys(), getfilectx,
                                  commit.author, commit.date, extra)
             self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = 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.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback()
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         try:
             oldlines = sorted(parentctx['.hgtags'].data().splitlines(1))
         except:
             oldlines = []
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
-            return None
+            return None, None
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(f, data, False, False, None)
 
         self.ui.status(_("updating tags\n"))
         date = "%s 0" % int(time.mktime(time.gmtime()))
         extra = {'branch': self.tagsbranch}
         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
                              [".hgtags"], getfilectx, "convert-repo", date,
                              extra)
         self.repo.commitctx(ctx)
-        return hex(self.repo.changelog.tip())
+        return hex(self.repo.changelog.tip()), hex(tagparent)
 
     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.ignoreerrors = ui.configbool('convert', 'hg.ignoreerrors', False)
         self.ignored = set()
         self.saverev = ui.configbool('convert', 'hg.saverev', False)
         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 error.RepoError()
         except error.RepoError:
             ui.traceback()
             raise NoRepo("%s is not a local Mercurial repo" % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
         # Restrict converted revisions to startrev descendants
         startnode = ui.config('convert', 'hg.startrev')
         if startnode is not None:
             try:
                 startnode = self.repo.lookup(startnode)
             except error.RepoError:
                 raise util.Abort(_('%s is not a valid start revision')
                                  % startnode)
             startrev = self.repo.changelog.rev(startnode)
             children = {startnode: 1}
             for rev in self.repo.changelog.descendants(startrev):
                 children[self.repo.changelog.node(rev)] = 1
             self.keep = children.__contains__
         else:
             self.keep = util.always
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def parents(self, ctx):
         return [p.node() for p in ctx.parents()
                 if p and self.keep(p.node())]
 
     def getheads(self):
         if self.rev:
             heads = [self.repo[self.rev].node()]
         else:
             heads = self.repo.heads()
         return [hex(h) for h in heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             return self.changectx(rev)[name].data()
         except error.LookupError, err:
             raise IOError(err)
 
     def getmode(self, name, rev):
         return self.changectx(rev).manifest().flags(name)
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents:
             files = sorted(ctx.manifest())
             if self.ignoreerrors:
                 # calling getcopies() is a simple way to detect missing
                 # revlogs and populate self.ignored
                 self.getcopies(ctx, files)
             return [(f, rev) for f in files if f not in self.ignored], {}
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(parents[0], ctx.node())[:3]
         # getcopies() detects missing revlogs early, run it before
         # filtering the changes.
         copies = self.getcopies(ctx, m + a)
         changes = [(name, rev) for name in m + a + r
                    if name not in self.ignored]
         return sorted(changes), copies
 
     def getcopies(self, ctx, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
                 copysource, copynode = ctx.filectx(name).renamed()
                 if copysource in self.ignored or not self.keep(copynode):
                     continue
                 copies[name] = copysource
             except TypeError:
                 pass
             except error.LookupError, e:
                 if not self.ignoreerrors:
                     raise
                 self.ignored.add(name)
                 self.ui.warn(_('ignoring: %s\n') % e)
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [hex(p) for p in self.parents(ctx)]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(), date=util.datestr(ctx.date()),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev())
 
     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
                      if self.keep(node)])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents and i is None:
             i = 0
             changes = [], ctx.manifest().keys(), []
         else:
             i = i or 0
             changes = self.repo.status(parents[i], ctx.node())[:3]
         changes = [[f for f in l if f not in self.ignored] for l in changes]
 
         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()
 
     def before(self):
         self.ui.debug(_('run hg source pre-conversion action\n'))
 
     def after(self):
         self.ui.debug(_('run hg source post-conversion action\n'))
 
     def hasnativeorder(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except error.RepoError:
             return None

tests/test-convert-clonebranches.out

@@ -1,29 +1,29 b''
 marked working directory as branch branch0
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 % convert
 3 adda
 2 changea
 1 addb
 pulling from default into branch0
 1 changesets found
 0 mergeab
 pulling from default into branch0
 1 changesets found
 marked working directory as branch branch1
 marked working directory as branch branch2
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 marked working directory as branch branch3
 % incremental conversion
 2 c1
 pulling from branch0 into branch1
-2 changesets found
+4 changesets found
 1 c2
 pulling from branch0 into branch2
-2 changesets found
+4 changesets found
 0 c3
 pulling from branch2 into branch3
-3 changesets found
+5 changesets found
 pulling from branch1 into branch3
 1 changesets found