convert: added GNU Arch source converter

hgext/convert/gnuarch.py

@@ -0,0 +1,263
+# GNU Arch support for the convert extension
+
+from common import NoRepo, checktool, commandline, commit, converter_source
+from mercurial.i18n import _
+from mercurial import util
+import os, shutil, tempfile, stat
+
+class gnuarch_source(converter_source, commandline):
+
+    class gnuarch_rev:
+        def __init__(self, rev):
+            self.rev = rev
+            self.summary = ''
+            self.date = None
+            self.author = ''
+            self.add_files = []
+            self.mod_files = []
+            self.del_files = []
+            self.ren_files = {}
+            self.ren_dirs = {}
+
+    def __init__(self, ui, path, rev=None):
+        super(gnuarch_source, self).__init__(ui, path, rev=rev)
+
+        if not os.path.exists(os.path.join(path, '{arch}')):
+            raise NoRepo(_("couldn't open GNU Arch repo %s" % path))
+
+        # Could use checktool, but we want to check for baz or tla.
+        self.execmd = None
+        if util.find_exe('tla'):
+            self.execmd = 'tla'
+        else:
+            if util.find_exe('baz'):
+                self.execmd = 'baz'
+            else:
+                raise util.Abort(_('cannot find a GNU Arch tool'))
+
+        commandline.__init__(self, ui, self.execmd)
+
+        self.path = os.path.realpath(path)
+        self.tmppath = None
+
+        self.treeversion = None
+        self.lastrev = None
+        self.changes = {}
+        self.parents = {}
+        self.tags = {}
+        self.modecache = {}
+
+    def before(self):
+        if self.execmd == 'tla':
+            output = self.run0('tree-version', self.path)
+        else:
+            output = self.run0('tree-version', '-d', self.path)
+        self.treeversion = output.strip()
+
+        self.ui.status(_('analyzing tree version %s...\n' % self.treeversion))
+
+        # Get name of temporary directory
+        version = self.treeversion.split('/')
+        self.tmppath = os.path.join(tempfile.gettempdir(),
+                                    'hg-%s' % version[1])
+
+        # Generate parents dictionary
+        child = []
+        output, status = self.runlines('revisions', self.treeversion)
+        self.checkexit(status, 'archive registered?')
+        for l in output:
+            rev = l.strip()
+            self.changes[rev] = self.gnuarch_rev(rev)
+
+            # Read author, date and summary
+            catlog = self.runlines0('cat-log', '-d', self.path, rev)
+            self._parsecatlog(catlog, rev)
+
+            self.parents[rev] = child
+            child = [rev]
+            if rev == self.rev:
+                break
+        self.parents[None] = child
+
+    def after(self):
+        self.ui.debug(_('cleaning up %s\n' % self.tmppath))
+        shutil.rmtree(self.tmppath, ignore_errors=True)
+
+    def getheads(self):
+        return self.parents[None]
+
+    def getfile(self, name, rev):
+        if rev != self.lastrev:
+            raise util.Abort(_('internal calling inconsistency'))
+
+        # Raise IOError if necessary (i.e. deleted files).
+        if not os.path.exists(os.path.join(self.tmppath, name)):
+            raise IOError
+
+        data, mode = self._getfile(name, rev)
+        self.modecache[(name, rev)] = mode
+
+        return data
+
+    def getmode(self, name, rev):
+        return self.modecache[(name, rev)]
+
+    def getchanges(self, rev):
+        self.modecache = {}
+        self._update(rev)
+        changes = []
+        copies = {}
+
+        for f in self.changes[rev].add_files:
+            changes.append((f, rev))
+
+        for f in self.changes[rev].mod_files:
+            changes.append((f, rev))
+
+        for f in self.changes[rev].del_files:
+            changes.append((f, rev))
+
+        for src in self.changes[rev].ren_files:
+            to = self.changes[rev].ren_files[src]
+            changes.append((src, rev))
+            changes.append((to, rev))
+            copies[src] = to
+
+        for src in self.changes[rev].ren_dirs:
+            to = self.changes[rev].ren_dirs[src]
+            chgs, cps = self._rendirchanges(src, to);
+            changes += [(f, rev) for f in chgs]
+            for c in cps:
+                copies[c] = cps[c]
+
+        changes.sort()
+        self.lastrev = rev
+
+        return changes, copies
+
+    def getcommit(self, rev):
+        changes = self.changes[rev]
+        return commit(author = changes.author, date = changes.date,
+                      desc = changes.summary, parents = self.parents[rev])
+
+    def gettags(self):
+        return self.tags
+
+    def _execute(self, cmd, *args, **kwargs):
+        cmdline = [self.execmd, cmd]
+        cmdline += args
+        cmdline = [util.shellquote(arg) for arg in cmdline]
+        cmdline += ['>', util.nulldev, '2>', util.nulldev]
+        cmdline = util.quotecommand(' '.join(cmdline))
+        self.ui.debug(cmdline, '\n')
+        return os.system(cmdline)
+
+    def _update(self, rev):
+        if rev == 'base-0':
+            # Initialise 'base-0' revision
+            self.ui.debug(_('obtaining revision %s...\n' % rev))
+            revision = '%s--%s' % (self.treeversion, rev)
+            output = self._execute('get', revision, self.tmppath)
+            self.ui.debug(_('analysing revision %s...\n' % rev))
+            files = self._readcontents(self.tmppath)
+            self.changes[rev].add_files += files
+        else:
+            self.ui.debug(_('applying revision %s...\n' % rev))
+            revision = '%s--%s' % (self.treeversion, rev)
+            output = self._execute('replay', '-d', self.tmppath, revision)
+
+            old_rev = self.parents[rev][0]
+            self.ui.debug(_('computing changeset between %s and %s...\n' \
+                               % (old_rev, rev)))
+            rev_a = '%s--%s' % (self.treeversion, old_rev)
+            rev_b = '%s--%s' % (self.treeversion, rev)
+            delta = self.runlines0('delta', '-n', rev_a, rev_b)
+            self._parsedelta(delta, rev)
+
+    def _getfile(self, name, rev):
+        mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
+        if stat.S_ISLNK(mode):
+            data = os.readlink(os.path.join(self.tmppath, name))
+            mode = mode and 'l' or ''
+        else:
+            data = open(os.path.join(self.tmppath, name), 'rb').read()
+            mode = (mode & 0111) and 'x' or ''
+        return data, mode
+
+    def _exclude(self, name):
+        exclude = [ '{arch}', '.arch-ids', '.arch-inventory' ]
+        for exc in exclude:
+            if name.find(exc) != -1:
+                return True
+        return False
+
+    def _readcontents(self, path):
+        files = []
+        contents = os.listdir(path)
+        while len(contents) > 0:
+            c = contents.pop()
+            p = os.path.join(path, c)
+            if not self._exclude(p):
+                if os.path.isdir(p):
+                    contents += [os.path.join(c, f) for f in os.listdir(p)]
+                else:
+                    files.append(c)
+        return files
+
+    def _rendirchanges(self, src, dest):
+        changes = []
+        copies = {}
+        files = self._readcontents(os.path.join(self.tmppath, dest))
+        for f in files:
+            s = os.path.join(src, f)
+            d = os.path.join(dest, f)
+            changes.append(s)
+            changes.append(d)
+            copies[s] = d
+        return changes, copies
+
+    def _parsecatlog(self, data, rev):
+        for l in data:
+            l = l.strip()
+            if l.startswith('Summary:'):
+                self.changes[rev].summary = l[len('Summary: '):]
+
+            if l.startswith('Standard-date:'):
+                date = l[len('Standard-date: '):]
+                strdate = util.strdate(date, '%Y-%m-%d %H:%M:%S')
+                self.changes[rev].date = util.datestr(strdate)
+
+            if l.startswith('Creator:'):
+                self.changes[rev].author = l[len('Creator: '):]
+
+    def _parsedelta(self, data, rev):
+        for l in data:
+            l = l.strip()
+            if l.startswith('A') and not l.startswith('A/'):
+                file = l[1:].strip()
+                if not self._exclude(file):
+                    self.changes[rev].add_files.append(file)
+            elif l.startswith('/>'):
+                dirs = l[2:].strip().split(' ')
+                if len(dirs) == 1:
+                    dirs = l[2:].strip().split('\t')
+                if not self._exclude(dirs[0]) and not self._exclude(dirs[1]):
+                    self.changes[rev].ren_dirs[dirs[0]] = dirs[1]
+            elif l.startswith('M'):
+                file = l[1:].strip()
+                if not self._exclude(file):
+                    self.changes[rev].mod_files.append(file)
+            elif l.startswith('->'):
+                file = l[2:].strip()
+                if not self._exclude(file):
+                    self.changes[rev].mod_files.append(file)
+            elif l.startswith('D') and not l.startswith('D/'):
+                file = l[1:].strip()
+                if not self._exclude(file):
+                    self.changes[rev].del_files.append(file)
+            elif l.startswith('=>'):
+                files = l[2:].strip().split(' ')
+                if len(files) == 1:
+                    files = l[2:].strip().split('\t')
+                if not self._exclude(files[0]) and not self._exclude(files[1]):
+                    self.changes[rev].ren_files[files[0]] = files[1]

hgext/convert/__init__.py

@@ -1,108 +1,109
 # 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.
 
 import convcmd
 from mercurial import commands
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 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
+    - GNU Arch
 
     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
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 def debugsvnlog(ui, **opts):
     return convcmd.debugsvnlog(ui, **opts)
 
 commands.norepo += " convert debugsvnlog"
 
 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

@@ -1,343 +1,354
 # common code for the convert extension
 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)
 
 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 or 'unknown'
         self.date = date or '0 0'
         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=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, pbranches):
         """Set the current branch name. Called before the first putfile
         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]
-        cmdline += ['<', util.nulldev]
+        cmdline += ['2>', util.nulldev, '<', util.nulldev]
         cmdline = ' '.join(cmdline)
         self.ui.debug(cmdline, '\n')
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         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(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, 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 self.path is None:
             return
         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/convcmd.py

@@ -1,328 +1,330
 # 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, 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
+from gnuarch import gnuarch_source
 import filemap
 
 import os, shutil
 from mercurial import hg, util
 from mercurial.i18n import _
 
 source_converters = [
     ('cvs', convert_cvs),
     ('git', convert_git),
     ('svn', svn_source),
     ('hg', mercurial_source),
     ('darcs', darcs_source),
+    ('gnuarch', gnuarch_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()
 
         self.splicemap = mapfile(ui, ui.config('convert', 'splicemap'))
 
     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], util.parsedate(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
         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)
         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)
 
         try:
             parents = [self.splicemap[rev]]
             self.ui.debug('spliced in %s as parents of %s\n' %
                           (parents, rev))
         except KeyError:
             parents = [b[0] for b in pbranches]
         newnode = self.dest.putcommit(filenames, parents, commit)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self):
 
         def recode(s):
             return s.decode('utf-8').encode(orig_encoding, 'replace')
 
         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]
                 # convert log message to local encoding without using
                 # tolocal() because util._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
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 orig_encoding = 'ascii'
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = util._encoding
     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()