convert: add support for deterministic progress bar on scanning phase

This makes it possible to estimate how long the "scanning source"
phase will take, if the specified source repo type supports a quick
"how many changes" check.

hgext/convert/common.py

@@ -1,452 +1,459
 # 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 or any later version.
 
 import base64, errno, subprocess, os, datetime, re
 import cPickle as pickle
 from mercurial import util
 from mercurial.i18n import _
 
 propertycache = util.propertycache
 
 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.findexe(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 checkhexformat(self, revstr, mapname='splicemap'):
         """ fails if revstr is not a 40 byte hex. mercurial and git both uses
             such format for their revision numbering
         """
         if not re.match(r'[0-9a-fA-F]{40,40}$', revstr):
             raise util.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     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 a pair (data, mode) where data is the file content
         as a string and mode one of '', 'x' or 'l'. rev is the
         identifier returned by a previous call to getchanges().
         Data is None if file is missing/deleted in rev.
         """
         raise NotImplementedError
 
     def getchanges(self, version, full):
         """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(). If full, all files in that revision is returned.
         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 numcommits(self):
+        """Return the number of commits in this source.
+
+        If unknown, return None.
+        """
+        return None
+
     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 UnicodeError:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except UnicodeError:
                 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 hasnativeclose(self):
         """Return true if this source has ability to close branch.
         """
         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
 
     def getbookmarks(self):
         """Return the bookmarks as a dictionary of name: revision
 
         Bookmark names are to be UTF-8 strings.
         """
         return {}
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """revstr is a string that describes a revision in the given
            source control system.  Return true if revstr has correct
            format.
         """
         return True
 
 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 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, full):
         """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() and
         lookuprev() should be called on 'source'. 'full' means that 'files'
         is complete and all other files should be removed.
 
         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
 
     def putbookmarks(self, bookmarks):
         """Put bookmarks into sink.
 
         bookmarks: {bookmarkname: sink_rev_id, ...}
         where bookmarkname is an UTF-8 string.
         """
         pass
 
     def hascommitfrommap(self, rev):
         """Return False if a rev mentioned in a filemap is known to not be
         present."""
         raise NotImplementedError
 
     def hascommitforsplicemap(self, rev):
         """This method is for the special needs for splicemap handling and not
         for general use. Returns True if the sink contains rev, aborts on some
         special cases."""
         raise NotImplementedError
 
 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>', os.devnull]
         cmdline = ' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         def popen(cmdline):
             p = subprocess.Popen(cmdline, shell=True, bufsize=-1,
                     close_fds=util.closefds,
                     stdout=subprocess.PIPE)
             return p
         return self._dorun(popen, cmd, *args, **kwargs)
 
     def _run2(self, cmd, *args, **kwargs):
         return self._dorun(util.popen2, cmd, *args, **kwargs)
 
     def _dorun(self, openfunc, cmd,  *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug('running: %s\n' % (cmdline,))
         self.prerun()
         try:
             return openfunc(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.communicate()[0]
         self.ui.debug(output)
         return output, p.returncode
 
     def runlines(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.stdout.readlines()
         p.wait()
         self.ui.debug(''.join(output))
         return output, p.returncode
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = util.explainexit(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
 
     @propertycache
     def argmax(self):
         # POSIX requires at least 4096 bytes for ARG_MAX
         argmax = 4096
         try:
             argmax = os.sysconf("SC_ARG_MAX")
         except (AttributeError, ValueError):
             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).
         return argmax // 2 - 1
 
     def _limit_arglist(self, arglist, cmd, *args, **kwargs):
         cmdlen = len(self._cmdline(cmd, *args, **kwargs))
         limit = self.argmax - cmdlen
         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):
             line = line.splitlines()[0].rstrip()
             if not line:
                 # Ignore blank lines
                 continue
             try:
                 key, value = line.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
 
 def makedatetimestamp(t):
     """Like util.makedate() but for time t instead of current time"""
     delta = (datetime.datetime.utcfromtimestamp(t) -
              datetime.datetime.fromtimestamp(t))
     tz = delta.days * 86400 + delta.seconds
     return t, tz

hgext/convert/convcmd.py

@@ -1,532 +1,534
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil, shlex
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
         except (NoRepo, MissingTool), inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
         except MissingTool, inst:
             raise util.Abort('%s\n' % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.filecount = filecount
         self.retrieved = 0
 
     def getfile(self, file, rev):
         self.retrieved += 1
         self.ui.progress(_('getting files'), self.retrieved,
                          item=file, total=self.filecount)
         return self.source.getfile(file, rev)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.ui.progress(_('getting files'), None)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authormap'):
             self.readauthormap(opts.get('authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = self.parsesplicemap(opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def parsesplicemap(self, path):
         """ check and validate the splicemap format and
             return a child/parents dictionary.
             Format checking has two parts.
             1. generic format which is same across all source types
             2. specific format checking which may be different for
                different source type.  This logic is implemented in
                checkrevformat function in source files like
                hg.py, subversion.py etc.
         """
 
         if not path:
             return {}
         m = {}
         try:
             fp = open(path, 'r')
             for i, line in enumerate(fp):
                 line = line.splitlines()[0].rstrip()
                 if not line:
                     # Ignore blank lines
                     continue
                 # split line
                 lex = shlex.shlex(line, posix=True)
                 lex.whitespace_split = True
                 lex.whitespace += ','
                 line = list(lex)
                 # check number of parents
                 if not (2 <= len(line) <= 3):
                     raise util.Abort(_('syntax error in %s(%d): child parent1'
                                        '[,parent2] expected') % (path, i + 1))
                 for part in line:
                     self.source.checkrevformat(part)
                 child, p1, p2 = line[0], line[1:2], line[2:]
                 if p1 == p2:
                     m[child] = p1
                 else:
                     m[child] = p1 + p2
          # if file does not exist or error reading, exit
         except IOError:
             raise util.Abort(_('splicemap file not found or error reading %s:')
                                % path)
         return m
 
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
+        numcommits = self.source.numcommits()
         while visit:
             n = visit.pop(0)
             if n in known:
                 continue
             if n in self.map:
                 m = self.map[n]
                 if m == SKIPREV or self.dest.hascommitfrommap(m):
                     continue
             known.add(n)
-            self.ui.progress(_('scanning'), len(known), unit=_('revisions'))
+            self.ui.progress(_('scanning'), len(known), unit=_('revisions'),
+                             total=numcommits)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         self.ui.progress(_('scanning'), None)
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in sorted(splicemap):
             if c not in parents:
                 if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(_('splice map revision %s is not being '
                                    'converted, ignoring\n') % c)
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise util.Abort(_('unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = sorted(parents)
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makeclosesorter():
             """Close order sort."""
             keyfn = lambda n: ('close' not in self.commitcache[n].extra,
                                self.commitcache[n].sortkey)
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         elif sortmode == 'closesort':
             picknext = makeclosesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         # If commit.branch is None, this commit is coming from the source
         # repository's default branch and destined for the default branch in the
         # destination repository. For such commits, passing a literal "None"
         # string to branchmap.get() below allows the user to map "None" to an
         # alternate default branch in the destination repository.
         commit.branch = self.branchmap.get(str(commit.branch), commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         full = self.opts.get('full')
         changes = self.source.getchanges(rev, full)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         source = progresssource(self.ui, self.source, len(files))
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       source, self.map, full)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.ui.progress(_('converting'), i, unit=_('revisions'),
                                  total=len(t))
                 self.copy(c)
             self.ui.progress(_('converting'), None)
 
             tags = self.source.gettags()
             ctags = {}
             for k in tags:
                 v = tags[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     ctags[k] = self.map[v]
 
             if c and ctags:
                 nrev, tagsparent = self.dest.puttags(ctags)
                 if nrev and tagsparent:
                     # write another hash correspondence to override the previous
                     # one so we don't end up with extra tag heads
                     tagsparents = [e for e in self.map.iteritems()
                                    if e[1] == tagsparent]
                     if tagsparents:
                         self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get('authormap'):
         opts['authormap'] = opts.get('authors')
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort', 'closesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     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'))
     if sortmode == 'closesort' and not srcc.hasnativeclose():
         raise util.Abort(_('--closesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         revmapfile = destc.revmapfile()
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)