convert: use None value for missing files instead of overloading IOError

The internal API used IOError to indicate that a file should be marked as
removed.

There is some correlation between IOError (especially with ENOENT) and files
that should be removed, but using IOErrors to represent file removal internally
required some hacks.

Instead, use the value None to indicate that the file not is present.

Before, spurious IO errors could cause commits that silently removed files.
They will now be reported like all other IO errors so the root cause can be
fixed.

hgext/convert/bzr.py

@@ -1,285 +1,284 b''
 # bzr.py - bzr support for the convert extension
 #
 #  Copyright 2008, 2009 Marek Kubica <[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.
 
 # This module is for handling 'bzr', that was formerly known as Bazaar-NG;
 # it cannot access 'bar' repositories, but they were never used very much
 
 import os
 from mercurial import demandimport
 # these do not work with demandimport, blacklist
 demandimport.ignore.extend([
         'bzrlib.transactions',
         'bzrlib.urlutils',
         'ElementPath',
     ])
 
 from mercurial.i18n import _
 from mercurial import util
 from common import NoRepo, commit, converter_source
 
 try:
     # bazaar imports
     from bzrlib import bzrdir, revision, errors
     from bzrlib.revisionspec import RevisionSpec
 except ImportError:
     pass
 
 supportedkinds = ('file', 'symlink')
 
 class bzr_source(converter_source):
     """Reads Bazaar repositories by using the Bazaar Python libraries"""
 
     def __init__(self, ui, path, rev=None):
         super(bzr_source, self).__init__(ui, path, rev=rev)
 
         if not os.path.exists(os.path.join(path, '.bzr')):
             raise NoRepo(_('%s does not look like a Bazaar repository')
                          % path)
 
         try:
             # access bzrlib stuff
             bzrdir
         except NameError:
             raise NoRepo(_('Bazaar modules could not be loaded'))
 
         path = os.path.abspath(path)
         self._checkrepotype(path)
         try:
             self.sourcerepo = bzrdir.BzrDir.open(path).open_repository()
         except errors.NoRepositoryPresent:
             raise NoRepo(_('%s does not look like a Bazaar repository')
                          % path)
         self._parentids = {}
 
     def _checkrepotype(self, path):
         # Lightweight checkouts detection is informational but probably
         # fragile at API level. It should not terminate the conversion.
         try:
             from bzrlib import bzrdir
             dir = bzrdir.BzrDir.open_containing(path)[0]
             try:
                 tree = dir.open_workingtree(recommend_upgrade=False)
                 branch = tree.branch
             except (errors.NoWorkingTree, errors.NotLocalUrl):
                 tree = None
                 branch = dir.open_branch()
             if (tree is not None and tree.bzrdir.root_transport.base !=
                 branch.bzrdir.root_transport.base):
                 self.ui.warn(_('warning: lightweight checkouts may cause '
                                'conversion failures, try with a regular '
                                'branch instead.\n'))
         except Exception:
             self.ui.note(_('bzr source type could not be determined\n'))
 
     def before(self):
         """Before the conversion begins, acquire a read lock
         for all the operations that might need it. Fortunately
         read locks don't block other reads or writes to the
         repository, so this shouldn't have any impact on the usage of
         the source repository.
 
         The alternative would be locking on every operation that
         needs locks (there are currently two: getting the file and
         getting the parent map) and releasing immediately after,
         but this approach can take even 40% longer."""
         self.sourcerepo.lock_read()
 
     def after(self):
         self.sourcerepo.unlock()
 
     def _bzrbranches(self):
         return self.sourcerepo.find_branches(using=True)
 
     def getheads(self):
         if not self.rev:
             # Set using=True to avoid nested repositories (see issue3254)
             heads = sorted([b.last_revision() for b in self._bzrbranches()])
         else:
             revid = None
             for branch in self._bzrbranches():
                 try:
                     r = RevisionSpec.from_string(self.rev)
                     info = r.in_history(branch)
                 except errors.BzrError:
                     pass
                 revid = info.rev_id
             if revid is None:
                 raise util.Abort(_('%s is not a valid revision') % self.rev)
             heads = [revid]
         # Empty repositories return 'null:', which cannot be retrieved
         heads = [h for h in heads if h != 'null:']
         return heads
 
     def getfile(self, name, rev):
         revtree = self.sourcerepo.revision_tree(rev)
         fileid = revtree.path2id(name.decode(self.encoding or 'utf-8'))
         kind = None
         if fileid is not None:
             kind = revtree.kind(fileid)
         if kind not in supportedkinds:
             # the file is not available anymore - was deleted
-            raise IOError(_('%s is not available in %s anymore') %
-                    (name, rev))
+            return None, None
         mode = self._modecache[(name, rev)]
         if kind == 'symlink':
             target = revtree.get_symlink_target(fileid)
             if target is None:
                 raise util.Abort(_('%s.%s symlink has no target')
                                  % (name, rev))
             return target, mode
         else:
             sio = revtree.get_file(fileid)
             return sio.read(), mode
 
     def getchanges(self, version):
         # set up caches: modecache and revtree
         self._modecache = {}
         self._revtree = self.sourcerepo.revision_tree(version)
         # get the parentids from the cache
         parentids = self._parentids.pop(version)
         # only diff against first parent id
         prevtree = self.sourcerepo.revision_tree(parentids[0])
         return self._gettreechanges(self._revtree, prevtree)
 
     def getcommit(self, version):
         rev = self.sourcerepo.get_revision(version)
         # populate parent id cache
         if not rev.parent_ids:
             parents = []
             self._parentids[version] = (revision.NULL_REVISION,)
         else:
             parents = self._filterghosts(rev.parent_ids)
             self._parentids[version] = parents
 
         branch = self.recode(rev.properties.get('branch-nick', u'default'))
         if branch == 'trunk':
             branch = 'default'
         return commit(parents=parents,
                 date='%d %d' % (rev.timestamp, -rev.timezone),
                 author=self.recode(rev.committer),
                 desc=self.recode(rev.message),
                 branch=branch,
                 rev=version)
 
     def gettags(self):
         bytetags = {}
         for branch in self._bzrbranches():
             if not branch.supports_tags():
                 return {}
             tagdict = branch.tags.get_tag_dict()
             for name, rev in tagdict.iteritems():
                 bytetags[self.recode(name)] = rev
         return bytetags
 
     def getchangedfiles(self, rev, i):
         self._modecache = {}
         curtree = self.sourcerepo.revision_tree(rev)
         if i is not None:
             parentid = self._parentids[rev][i]
         else:
             # no parent id, get the empty revision
             parentid = revision.NULL_REVISION
 
         prevtree = self.sourcerepo.revision_tree(parentid)
         changes = [e[0] for e in self._gettreechanges(curtree, prevtree)[0]]
         return changes
 
     def _gettreechanges(self, current, origin):
         revid = current._revision_id
         changes = []
         renames = {}
         seen = set()
         # Process the entries by reverse lexicographic name order to
         # handle nested renames correctly, most specific first.
         curchanges = sorted(current.iter_changes(origin),
                             key=lambda c: c[1][0] or c[1][1],
                             reverse=True)
         for (fileid, paths, changed_content, versioned, parent, name,
             kind, executable) in curchanges:
 
             if paths[0] == u'' or paths[1] == u'':
                 # ignore changes to tree root
                 continue
 
             # bazaar tracks directories, mercurial does not, so
             # we have to rename the directory contents
             if kind[1] == 'directory':
                 if kind[0] not in (None, 'directory'):
                     # Replacing 'something' with a directory, record it
                     # so it can be removed.
                     changes.append((self.recode(paths[0]), revid))
 
                 if kind[0] == 'directory' and None not in paths:
                     renaming = paths[0] != paths[1]
                     # neither an add nor an delete - a move
                     # rename all directory contents manually
                     subdir = origin.inventory.path2id(paths[0])
                     # get all child-entries of the directory
                     for name, entry in origin.inventory.iter_entries(subdir):
                         # hg does not track directory renames
                         if entry.kind == 'directory':
                             continue
                         frompath = self.recode(paths[0] + '/' + name)
                         if frompath in seen:
                             # Already handled by a more specific change entry
                             # This is important when you have:
                             # a => b
                             # a/c => a/c
                             # Here a/c must not be renamed into b/c
                             continue
                         seen.add(frompath)
                         if not renaming:
                             continue
                         topath = self.recode(paths[1] + '/' + name)
                         # register the files as changed
                         changes.append((frompath, revid))
                         changes.append((topath, revid))
                         # add to mode cache
                         mode = ((entry.executable and 'x')
                                 or (entry.kind == 'symlink' and 's')
                                 or '')
                         self._modecache[(topath, revid)] = mode
                         # register the change as move
                         renames[topath] = frompath
 
                 # no further changes, go to the next change
                 continue
 
             # we got unicode paths, need to convert them
             path, topath = paths
             if path is not None:
                 path = self.recode(path)
             if topath is not None:
                 topath = self.recode(topath)
             seen.add(path or topath)
 
             if topath is None:
                 # file deleted
                 changes.append((path, revid))
                 continue
 
             # renamed
             if path and path != topath:
                 renames[topath] = path
                 changes.append((path, revid))
 
             # populate the mode cache
             kind, executable = [e[1] for e in (kind, executable)]
             mode = ((executable and 'x') or (kind == 'symlink' and 'l')
                     or '')
             self._modecache[(topath, revid)] = mode
             changes.append((topath, revid))
 
         return changes, renames
 
     def _filterghosts(self, ids):
         """Filters out ghost revisions which hg does not support, see
         <http://bazaar-vcs.org/GhostRevision>
         """
         parentmap = self.sourcerepo.get_parent_map(ids)
         parents = tuple([parent for parent in ids if parent in parentmap])
         return parents

hgext/convert/common.py

@@ -1,450 +1,450 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 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(). Raise
-        IOError to indicate that name was deleted in rev.
+        identifier returned by a previous call to getchanges().
+        Data is None if file is missing/deleted in rev.
         """
         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 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):
         """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'.
 
         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/cvs.py

@@ -1,275 +1,275 b''
 # cvs.py: CVS conversion code inspired by hg-cvs-import and git-cvsimport
 #
 #  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 os, re, socket, errno
 from cStringIO import StringIO
 from mercurial import encoding, util
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
 from common import makedatetimestamp
 import cvsps
 
 class convert_cvs(converter_source):
     def __init__(self, ui, path, rev=None):
         super(convert_cvs, self).__init__(ui, path, rev=rev)
 
         cvs = os.path.join(path, "CVS")
         if not os.path.exists(cvs):
             raise NoRepo(_("%s does not look like a CVS checkout") % path)
 
         checktool('cvs')
 
         self.changeset = None
         self.files = {}
         self.tags = {}
         self.lastbranch = {}
         self.socket = None
         self.cvsroot = open(os.path.join(cvs, "Root")).read()[:-1]
         self.cvsrepo = open(os.path.join(cvs, "Repository")).read()[:-1]
         self.encoding = encoding.encoding
 
         self._connect()
 
     def _parse(self):
         if self.changeset is not None:
             return
         self.changeset = {}
 
         maxrev = 0
         if self.rev:
             # TODO: handle tags
             try:
                 # patchset number?
                 maxrev = int(self.rev)
             except ValueError:
                 raise util.Abort(_('revision %s is not a patchset number')
                                  % self.rev)
 
         d = os.getcwd()
         try:
             os.chdir(self.path)
             id = None
 
             cache = 'update'
             if not self.ui.configbool('convert', 'cvsps.cache', True):
                 cache = None
             db = cvsps.createlog(self.ui, cache=cache)
             db = cvsps.createchangeset(self.ui, db,
                 fuzz=int(self.ui.config('convert', 'cvsps.fuzz', 60)),
                 mergeto=self.ui.config('convert', 'cvsps.mergeto', None),
                 mergefrom=self.ui.config('convert', 'cvsps.mergefrom', None))
 
             for cs in db:
                 if maxrev and cs.id > maxrev:
                     break
                 id = str(cs.id)
                 cs.author = self.recode(cs.author)
                 self.lastbranch[cs.branch] = id
                 cs.comment = self.recode(cs.comment)
                 if self.ui.configbool('convert', 'localtimezone'):
                     cs.date = makedatetimestamp(cs.date[0])
                 date = util.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2')
                 self.tags.update(dict.fromkeys(cs.tags, id))
 
                 files = {}
                 for f in cs.entries:
                     files[f.file] = "%s%s" % ('.'.join([str(x)
                                                         for x in f.revision]),
                                               ['', '(DEAD)'][f.dead])
 
                 # add current commit to set
                 c = commit(author=cs.author, date=date,
                            parents=[str(p.id) for p in cs.parents],
                            desc=cs.comment, branch=cs.branch or '')
                 self.changeset[id] = c
                 self.files[id] = files
 
             self.heads = self.lastbranch.values()
         finally:
             os.chdir(d)
 
     def _connect(self):
         root = self.cvsroot
         conntype = None
         user, host = None, None
         cmd = ['cvs', 'server']
 
         self.ui.status(_("connecting to %s\n") % root)
 
         if root.startswith(":pserver:"):
             root = root[9:]
             m = re.match(r'(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?(.*)',
                          root)
             if m:
                 conntype = "pserver"
                 user, passw, serv, port, root = m.groups()
                 if not user:
                     user = "anonymous"
                 if not port:
                     port = 2401
                 else:
                     port = int(port)
                 format0 = ":pserver:%s@%s:%s" % (user, serv, root)
                 format1 = ":pserver:%s@%s:%d%s" % (user, serv, port, root)
 
                 if not passw:
                     passw = "A"
                     cvspass = os.path.expanduser("~/.cvspass")
                     try:
                         pf = open(cvspass)
                         for line in pf.read().splitlines():
                             part1, part2 = line.split(' ', 1)
                             # /1 :pserver:[e-mail]:2401/cvsroot/foo
                             # Ah<Z
                             if part1 == '/1':
                                 part1, part2 = part2.split(' ', 1)
                                 format = format1
                             # :pserver:[e-mail]:/cvsroot/foo Ah<Z
                             else:
                                 format = format0
                             if part1 == format:
                                 passw = part2
                                 break
                         pf.close()
                     except IOError, inst:
                         if inst.errno != errno.ENOENT:
                             if not getattr(inst, 'filename', None):
                                 inst.filename = cvspass
                             raise
 
                 sck = socket.socket()
                 sck.connect((serv, port))
                 sck.send("\n".join(["BEGIN AUTH REQUEST", root, user, passw,
                                     "END AUTH REQUEST", ""]))
                 if sck.recv(128) != "I LOVE YOU\n":
                     raise util.Abort(_("CVS pserver authentication failed"))
 
                 self.writep = self.readp = sck.makefile('r+')
 
         if not conntype and root.startswith(":local:"):
             conntype = "local"
             root = root[7:]
 
         if not conntype:
             # :ext:user@host/home/user/path/to/cvsroot
             if root.startswith(":ext:"):
                 root = root[5:]
             m = re.match(r'(?:([^@:/]+)@)?([^:/]+):?(.*)', root)
             # Do not take Windows path "c:\foo\bar" for a connection strings
             if os.path.isdir(root) or not m:
                 conntype = "local"
             else:
                 conntype = "rsh"
                 user, host, root = m.group(1), m.group(2), m.group(3)
 
         if conntype != "pserver":
             if conntype == "rsh":
                 rsh = os.environ.get("CVS_RSH") or "ssh"
                 if user:
                     cmd = [rsh, '-l', user, host] + cmd
                 else:
                     cmd = [rsh, host] + cmd
 
             # popen2 does not support argument lists under Windows
             cmd = [util.shellquote(arg) for arg in cmd]
             cmd = util.quotecommand(' '.join(cmd))
             self.writep, self.readp = util.popen2(cmd)
 
         self.realroot = root
 
         self.writep.write("Root %s\n" % root)
         self.writep.write("Valid-responses ok error Valid-requests Mode"
                           " M Mbinary E Checked-in Created Updated"
                           " Merged Removed\n")
         self.writep.write("valid-requests\n")
         self.writep.flush()
         r = self.readp.readline()
         if not r.startswith("Valid-requests"):
             raise util.Abort(_('unexpected response from CVS server '
                                '(expected "Valid-requests", but got %r)')
                              % r)
         if "UseUnchanged" in r:
             self.writep.write("UseUnchanged\n")
             self.writep.flush()
             r = self.readp.readline()
 
     def getheads(self):
         self._parse()
         return self.heads
 
     def getfile(self, name, rev):
 
         def chunkedread(fp, count):
             # file-objects returned by socket.makefile() do not handle
             # large read() requests very well.
             chunksize = 65536
             output = StringIO()
             while count > 0:
                 data = fp.read(min(count, chunksize))
                 if not data:
                     raise util.Abort(_("%d bytes missing from remote file")
                                      % count)
                 count -= len(data)
                 output.write(data)
             return output.getvalue()
 
         self._parse()
         if rev.endswith("(DEAD)"):
-            raise IOError
+            return None, None
 
         args = ("-N -P -kk -r %s --" % rev).split()
         args.append(self.cvsrepo + '/' + name)
         for x in args:
             self.writep.write("Argument %s\n" % x)
         self.writep.write("Directory .\n%s\nco\n" % self.realroot)
         self.writep.flush()
 
         data = ""
         mode = None
         while True:
             line = self.readp.readline()
             if line.startswith("Created ") or line.startswith("Updated "):
                 self.readp.readline() # path
                 self.readp.readline() # entries
                 mode = self.readp.readline()[:-1]
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             elif line.startswith(" "):
                 data += line[1:]
             elif line.startswith("M "):
                 pass
             elif line.startswith("Mbinary "):
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             else:
                 if line == "ok\n":
                     if mode is None:
                         raise util.Abort(_('malformed response from CVS'))
                     return (data, "x" in mode and "x" or "")
                 elif line.startswith("E "):
                     self.ui.warn(_("cvs server: %s\n") % line[2:])
                 elif line.startswith("Remove"):
                     self.readp.readline()
                 else:
                     raise util.Abort(_("unknown CVS response: %s") % line)
 
     def getchanges(self, rev):
         self._parse()
         return sorted(self.files[rev].iteritems()), {}
 
     def getcommit(self, rev):
         self._parse()
         return self.changeset[rev]
 
     def gettags(self):
         self._parse()
         return self.tags
 
     def getchangedfiles(self, rev, i):
         self._parse()
         return sorted(self.files[rev])

hgext/convert/darcs.py

@@ -1,201 +1,206 b''
 # darcs.py - darcs support for the convert extension
 #
 #  Copyright 2007-2009 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.
 
 from common import NoRepo, checktool, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
-import os, shutil, tempfile, re
+import os, shutil, tempfile, re, errno
 
 # The naming drift of ElementTree is fun!
 
 try:
     from xml.etree.cElementTree import ElementTree, XMLParser
 except ImportError:
     try:
         from xml.etree.ElementTree import ElementTree, XMLParser
     except ImportError:
         try:
             from elementtree.cElementTree import ElementTree, XMLParser
         except ImportError:
             try:
                 from elementtree.ElementTree import ElementTree, XMLParser
             except ImportError:
                 pass
 
 class darcs_source(converter_source, commandline):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev=rev)
         commandline.__init__(self, ui, 'darcs')
 
         # check for _darcs, ElementTree so that we can easily skip
         # test-convert-darcs if ElementTree is not around
         if not os.path.exists(os.path.join(path, '_darcs')):
             raise NoRepo(_("%s does not look like a darcs repository") % path)
 
         checktool('darcs')
         version = self.run0('--version').splitlines()[0].strip()
         if version < '2.1':
             raise util.Abort(_('darcs version 2.1 or newer needed (found %r)') %
                              version)
 
         if "ElementTree" not in globals():
             raise util.Abort(_("Python ElementTree module is not available"))
 
         self.path = os.path.realpath(path)
 
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
 
         # Check darcs repository format
         format = self.format()
         if format:
             if format in ('darcs-1.0', 'hashed'):
                 raise NoRepo(_("%s repository format is unsupported, "
                                "please upgrade") % format)
         else:
             self.ui.warn(_('failed to detect repository format!'))
 
     def before(self):
         self.tmppath = tempfile.mkdtemp(
             prefix='convert-' + os.path.basename(self.path) + '-')
         output, status = self.run('init', repodir=self.tmppath)
         self.checkexit(status)
 
         tree = self.xml('changes', xml_output=True, summary=True,
                         repodir=self.path)
         tagname = None
         child = None
         for elt in tree.findall('patch'):
             node = elt.get('hash')
             name = elt.findtext('name', '')
             if name.startswith('TAG '):
                 tagname = name[4:].strip()
             elif tagname is not None:
                 self.tags[tagname] = node
                 tagname = None
             self.changes[node] = elt
             self.parents[child] = [node]
             child = node
         self.parents[child] = []
 
     def after(self):
         self.ui.debug('cleaning up %s\n' % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def recode(self, s, encoding=None):
         if isinstance(s, unicode):
             # XMLParser returns unicode objects for anything it can't
             # encode into ASCII. We convert them back to str to get
             # recode's normal conversion behavior.
             s = s.encode('latin-1')
         return super(darcs_source, self).recode(s, encoding)
 
     def xml(self, cmd, **kwargs):
         # NOTE: darcs is currently encoding agnostic and will print
         # patch metadata byte-for-byte, even in the XML changelog.
         etree = ElementTree()
         # While we are decoding the XML as latin-1 to be as liberal as
         # possible, etree will still raise an exception if any
         # non-printable characters are in the XML changelog.
         parser = XMLParser(encoding='latin-1')
         p = self._run(cmd, **kwargs)
         etree.parse(p.stdout, parser=parser)
         p.wait()
         self.checkexit(p.returncode)
         return etree.getroot()
 
     def format(self):
         output, status = self.run('show', 'repo', no_files=True,
                                   repodir=self.path)
         self.checkexit(status)
         m = re.search(r'^\s*Format:\s*(.*)$', output, re.MULTILINE)
         if not m:
             return None
         return ','.join(sorted(f.strip() for f in m.group(1).split(',')))
 
     def manifest(self):
         man = []
         output, status = self.run('show', 'files', no_directories=True,
                                   repodir=self.tmppath)
         self.checkexit(status)
         for line in output.split('\n'):
             path = line[2:]
             if path:
                 man.append(path)
         return man
 
     def getheads(self):
         return self.parents[None]
 
     def getcommit(self, rev):
         elt = self.changes[rev]
         date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y')
         desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
         # etree can return unicode objects for name, comment, and author,
         # so recode() is used to ensure str objects are emitted.
         return commit(author=self.recode(elt.get('author')),
                       date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=self.recode(desc).strip(),
                       parents=self.parents[rev])
 
     def pull(self, rev):
         output, status = self.run('pull', self.path, all=True,
                                   match='hash %s' % rev,
                                   no_test=True, no_posthook=True,
                                   external_merge='/bin/false',
                                   repodir=self.tmppath)
         if status:
             if output.find('We have conflicts in') == -1:
                 self.checkexit(status, output)
             output, status = self.run('revert', all=True, repodir=self.tmppath)
             self.checkexit(status, output)
 
     def getchanges(self, rev):
         copies = {}
         changes = []
         man = None
         for elt in self.changes[rev].find('summary').getchildren():
             if elt.tag in ('add_directory', 'remove_directory'):
                 continue
             if elt.tag == 'move':
                 if man is None:
                     man = self.manifest()
                 source, dest = elt.get('from'), elt.get('to')
                 if source in man:
                     # File move
                     changes.append((source, rev))
                     changes.append((dest, rev))
                     copies[dest] = source
                 else:
                     # Directory move, deduce file moves from manifest
                     source = source + '/'
                     for f in man:
                         if not f.startswith(source):
                             continue
                         fdest = dest + '/' + f[len(source):]
                         changes.append((f, rev))
                         changes.append((fdest, rev))
                         copies[fdest] = f
             else:
                 changes.append((elt.text.strip(), rev))
         self.pull(rev)
         self.lastrev = rev
         return sorted(changes), copies
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
         path = os.path.join(self.tmppath, name)
-        data = util.readfile(path)
-        mode = os.lstat(path).st_mode
+        try:
+            data = util.readfile(path)
+            mode = os.lstat(path).st_mode
+        except IOError, inst:
+            if inst.errno == errno.ENOENT:
+                return None, None
+            raise
         mode = (mode & 0111) and 'x' or ''
         return data, mode
 
     def gettags(self):
         return self.tags

hgext/convert/git.py

@@ -1,343 +1,343 b''
 # git.py - git support 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 os
 import subprocess
 from mercurial import util, config
 from mercurial.node import hex, nullid
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
 
 class submodule(object):
     def __init__(self, path, node, url):
         self.path = path
         self.node = node
         self.url = url
 
     def hgsub(self):
         return "%s = [git]%s" % (self.path, self.url)
 
     def hgsubstate(self):
         return "%s %s" % (self.node, self.path)
 
 class convert_git(converter_source):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
     if util.safehasattr(os, 'unsetenv'):
         def gitopen(self, s, err=None):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 if err == subprocess.PIPE:
                     (stdin, stdout, stderr) = util.popen3(s)
                     return stdout
                 elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
                 else:
                     return util.popen(s, 'rb')
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
 
         def gitpipe(self, s):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 return util.popen3(s)
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
 
     else:
         def gitopen(self, s, err=None):
             if err == subprocess.PIPE:
                 (sin, so, se) = util.popen3('GIT_DIR=%s %s' % (self.path, s))
                 return so
             elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
             else:
                 return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')
 
         def gitpipe(self, s):
             return util.popen3('GIT_DIR=%s %s' % (self.path, s))
 
     def popen_with_stderr(self, s):
         p = subprocess.Popen(s, shell=True, bufsize=-1,
                              close_fds=util.closefds,
                              stdin=subprocess.PIPE,
                              stdout=subprocess.PIPE,
                              stderr=subprocess.STDOUT,
                              universal_newlines=False,
                              env=None)
         return p.stdout
 
     def gitread(self, s):
         fh = self.gitopen(s)
         data = fh.read()
         return data, fh.close()
 
     def __init__(self, ui, path, rev=None):
         super(convert_git, self).__init__(ui, path, rev=rev)
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
             raise NoRepo(_("%s does not look like a Git repository") % path)
 
         checktool('git', 'git')
 
         self.path = path
         self.submodules = []
 
         self.catfilepipe = self.gitpipe('git cat-file --batch')
 
     def after(self):
         for f in self.catfilepipe:
             f.close()
 
     def getheads(self):
         if not self.rev:
             heads, ret = self.gitread('git rev-parse --branches --remotes')
             heads = heads.splitlines()
         else:
             heads, ret = self.gitread("git rev-parse --verify %s" % self.rev)
             heads = [heads[:-1]]
         if ret:
             raise util.Abort(_('cannot retrieve git heads'))
         return heads
 
     def catfile(self, rev, type):
         if rev == hex(nullid):
             raise IOError
         self.catfilepipe[0].write(rev+'\n')
         self.catfilepipe[0].flush()
         info = self.catfilepipe[1].readline().split()
         if info[1] != type:
             raise util.Abort(_('cannot read %r object at %s') % (type, rev))
         size = int(info[2])
         data = self.catfilepipe[1].read(size)
         if len(data) < size:
             raise util.Abort(_('cannot read %r object at %s: unexpected size')
                              % (type, rev))
         # read the trailing newline
         self.catfilepipe[1].read(1)
         return data
 
     def getfile(self, name, rev):
         if rev == hex(nullid):
-            raise IOError
+            return None, None
         if name == '.hgsub':
             data = '\n'.join([m.hgsub() for m in self.submoditer()])
             mode = ''
         elif name == '.hgsubstate':
             data = '\n'.join([m.hgsubstate() for m in self.submoditer()])
             mode = ''
         else:
             data = self.catfile(rev, "blob")
             mode = self.modecache[(name, rev)]
         return data, mode
 
     def submoditer(self):
         null = hex(nullid)
         for m in sorted(self.submodules, key=lambda p: p.path):
             if m.node != null:
                 yield m
 
     def parsegitmodules(self, content):
         """Parse the formatted .gitmodules file, example file format:
         [submodule "sub"]\n
         \tpath = sub\n
         \turl = git://giturl\n
         """
         self.submodules = []
         c = config.config()
         # Each item in .gitmodules starts with \t that cant be parsed
         c.parse('.gitmodules', content.replace('\t',''))
         for sec in c.sections():
             s = c[sec]
             if 'url' in s and 'path' in s:
                 self.submodules.append(submodule(s['path'], '', s['url']))
 
     def retrievegitmodules(self, version):
         modules, ret = self.gitread("git show %s:%s" % (version, '.gitmodules'))
         if ret:
             raise util.Abort(_('cannot read submodules config file in %s') %
                              version)
         self.parsegitmodules(modules)
         for m in self.submodules:
             node, ret = self.gitread("git rev-parse %s:%s" % (version, m.path))
             if ret:
                 continue
             m.node = node.strip()
 
     def getchanges(self, version):
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s" % version)
         changes = []
         seen = set()
         entry = None
         subexists = False
         subdeleted = False
         for l in fh.read().split('\x00'):
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l
                 continue
             f = l
             if f not in seen:
                 seen.add(f)
                 entry = entry.split()
                 h = entry[3]
                 p = (entry[1] == "100755")
                 s = (entry[1] == "120000")
 
                 if f == '.gitmodules':
                     subexists = True
                     if entry[4] == 'D':
                         subdeleted = True
                         changes.append(('.hgsub', hex(nullid)))
                     else:
                         changes.append(('.hgsub', ''))
                 elif entry[1] == '160000' or entry[0] == ':160000':
                     subexists = True
                 else:
                     self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                     changes.append((f, h))
             entry = None
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         if subexists:
             if subdeleted:
                 changes.append(('.hgsubstate', hex(nullid)))
             else:
                 self.retrievegitmodules(version)
                 changes.append(('.hgsubstate', ''))
         return (changes, {})
 
     def getcommit(self, version):
         c = self.catfile(version, "commit") # read the commit hash
         end = c.find("\n\n")
         message = c[end + 2:]
         message = self.recode(message)
         l = c[:end].splitlines()
         parents = []
         author = committer = None
         for e in l[1:]:
             n, v = e.split(" ", 1)
             if n == "author":
                 p = v.split()
                 tm, tz = p[-2:]
                 author = " ".join(p[:-2])
                 if author[0] == "<": author = author[1:-1]
                 author = self.recode(author)
             if n == "committer":
                 p = v.split()
                 tm, tz = p[-2:]
                 committer = " ".join(p[:-2])
                 if committer[0] == "<": committer = committer[1:-1]
                 committer = self.recode(committer)
             if n == "parent":
                 parents.append(v)
 
         if committer and committer != author:
             message += "\ncommitter: %s\n" % committer
         tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
         tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
         date = tm + " " + str(tz)
 
         c = commit(parents=parents, date=date, author=author, desc=message,
                    rev=version)
         return c
 
     def gettags(self):
         tags = {}
         alltags = {}
         fh = self.gitopen('git ls-remote --tags "%s"' % self.path,
                           err=subprocess.STDOUT)
         prefix = 'refs/tags/'
 
         # Build complete list of tags, both annotated and bare ones
         for line in fh:
             line = line.strip()
             if line.startswith("error:") or line.startswith("fatal:"):
                 raise util.Abort(_('cannot read tags from %s') % self.path)
             node, tag = line.split(None, 1)
             if not tag.startswith(prefix):
                 continue
             alltags[tag[len(prefix):]] = node
         if fh.close():
             raise util.Abort(_('cannot read tags from %s') % self.path)
 
         # Filter out tag objects for annotated tag refs
         for tag in alltags:
             if tag.endswith('^{}'):
                 tags[tag[:-3]] = alltags[tag]
             else:
                 if tag + '^{}' in alltags:
                     continue
                 else:
                     tags[tag] = alltags[tag]
 
         return tags
 
     def getchangedfiles(self, version, i):
         changes = []
         if i is None:
             fh = self.gitopen("git diff-tree --root -m -r %s" % version)
             for l in fh:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
         else:
             fh = self.gitopen('git diff-tree --name-only --root -r %s '
                               '"%s^%s" --' % (version, version, i + 1))
             changes = [f.rstrip('\n') for f in fh]
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         return changes
 
     def getbookmarks(self):
         bookmarks = {}
 
         # Interesting references in git are prefixed
         prefix = 'refs/heads/'
         prefixlen = len(prefix)
 
         # factor two commands
         gitcmd = { 'remote/': 'git ls-remote --heads origin',
                           '': 'git show-ref'}
 
         # Origin heads
         for reftype in gitcmd:
             try:
                 fh = self.gitopen(gitcmd[reftype], err=subprocess.PIPE)
                 for line in fh:
                     line = line.strip()
                     rev, name = line.split(None, 1)
                     if not name.startswith(prefix):
                         continue
                     name = '%s%s' % (reftype, name[prefixlen:])
                     bookmarks[name] = rev
             except Exception:
                 pass
 
         return bookmarks
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ git revision string is a 40 byte hex """
         self.checkhexformat(revstr, mapname)
 

hgext/convert/gnuarch.py

@@ -1,338 +1,337 b''
 # gnuarch.py - GNU Arch support for the convert extension
 #
 #  Copyright 2008, 2009 Aleix Conchillo Flaque <[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.
 
 from common import NoRepo, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import encoding, util
 import os, shutil, tempfile, stat
 from email.Parser import Parser
 
 class gnuarch_source(converter_source, commandline):
 
     class gnuarch_rev(object):
         def __init__(self, rev):
             self.rev = rev
             self.summary = ''
             self.date = None
             self.author = ''
             self.continuationof = None
             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(_("%s does not look like a GNU Arch repository")
                          % path)
 
         # Could use checktool, but we want to check for baz or tla.
         self.execmd = None
         if util.findexe('baz'):
             self.execmd = 'baz'
         else:
             if util.findexe('tla'):
                 self.execmd = 'tla'
             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.catlogparser = Parser()
         self.encoding = encoding.encoding
         self.archives = []
 
     def before(self):
         # Get registered archives
         self.archives = [i.rstrip('\n')
                          for i in self.runlines0('archives', '-n')]
 
         if self.execmd == 'tla':
             output = self.run0('tree-version', self.path)
         else:
             output = self.run0('tree-version', '-d', self.path)
         self.treeversion = output.strip()
 
         # Get name of temporary directory
         version = self.treeversion.split('/')
         self.tmppath = os.path.join(tempfile.gettempdir(),
                                     'hg-%s' % version[1])
 
         # Generate parents dictionary
         self.parents[None] = []
         treeversion = self.treeversion
         child = None
         while treeversion:
             self.ui.status(_('analyzing tree version %s...\n') % treeversion)
 
             archive = treeversion.split('/')[0]
             if archive not in self.archives:
                 self.ui.status(_('tree analysis stopped because it points to '
                                  'an unregistered archive %s...\n') % archive)
                 break
 
             # Get the complete list of revisions for that tree version
             output, status = self.runlines('revisions', '-r', '-f', treeversion)
             self.checkexit(status, 'failed retrieving revisions for %s'
                            % treeversion)
 
             # No new iteration unless a revision has a continuation-of header
             treeversion = None
 
             for l in output:
                 rev = l.strip()
                 self.changes[rev] = self.gnuarch_rev(rev)
                 self.parents[rev] = []
 
                 # Read author, date and summary
                 catlog, status = self.run('cat-log', '-d', self.path, rev)
                 if status:
                     catlog  = self.run0('cat-archive-log', rev)
                 self._parsecatlog(catlog, rev)
 
                 # Populate the parents map
                 self.parents[child].append(rev)
 
                 # Keep track of the current revision as the child of the next
                 # revision scanned
                 child = rev
 
                 # Check if we have to follow the usual incremental history
                 # or if we have to 'jump' to a different treeversion given
                 # by the continuation-of header.
                 if self.changes[rev].continuationof:
                     treeversion = '--'.join(
                         self.changes[rev].continuationof.split('--')[:-1])
                     break
 
                 # If we reached a base-0 revision w/o any continuation-of
                 # header, it means the tree history ends here.
                 if rev[-6:] == 'base-0':
                     break
 
     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.lexists(os.path.join(self.tmppath, name)):
-            raise IOError
+            return None, None
 
         return self._getfile(name, rev)
 
     def getchanges(self, rev):
         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[to] = src
 
         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]
             copies.update(cps)
 
         self.lastrev = rev
         return sorted(set(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], rev=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 += ['>', os.devnull, '2>', os.devnull]
         cmdline = util.quotecommand(' '.join(cmdline))
         self.ui.debug(cmdline, '\n')
         return os.system(cmdline)
 
     def _update(self, rev):
         self.ui.debug('applying revision %s...\n' % rev)
         changeset, status = self.runlines('replay', '-d', self.tmppath,
                                               rev)
         if status:
             # Something went wrong while merging (baz or tla
             # issue?), get latest revision and try from there
             shutil.rmtree(self.tmppath, ignore_errors=True)
             self._obtainrevision(rev)
         else:
             old_rev = self.parents[rev][0]
             self.ui.debug('computing changeset between %s and %s...\n'
                           % (old_rev, rev))
             self._parsechangeset(changeset, 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)
             # os.walk could be used, but here we avoid internal GNU
             # Arch files and directories, thus saving a lot time.
             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[d] = s
         return changes, copies
 
     def _obtainrevision(self, rev):
         self.ui.debug('obtaining revision %s...\n' % rev)
         output = self._execute('get', rev, self.tmppath)
         self.checkexit(output)
         self.ui.debug('analyzing revision %s...\n' % rev)
         files = self._readcontents(self.tmppath)
         self.changes[rev].add_files += files
 
     def _stripbasepath(self, path):
         if path.startswith('./'):
             return path[2:]
         return path
 
     def _parsecatlog(self, data, rev):
         try:
             catlog = self.catlogparser.parsestr(data)
 
             # Commit date
             self.changes[rev].date = util.datestr(
                 util.strdate(catlog['Standard-date'],
                              '%Y-%m-%d %H:%M:%S'))
 
             # Commit author
             self.changes[rev].author = self.recode(catlog['Creator'])
 
             # Commit description
             self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
                                                     catlog.get_payload()))
             self.changes[rev].summary = self.recode(self.changes[rev].summary)
 
             # Commit revision origin when dealing with a branch or tag
             if 'Continuation-of' in catlog:
                 self.changes[rev].continuationof = self.recode(
                     catlog['Continuation-of'])
         except Exception:
             raise util.Abort(_('could not parse cat-log of %s') % rev)
 
     def _parsechangeset(self, data, rev):
         for l in data:
             l = l.strip()
             # Added file (ignore added directory)
             if l.startswith('A') and not l.startswith('A/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].add_files.append(file)
             # Deleted file (ignore deleted directory)
             elif l.startswith('D') and not l.startswith('D/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].del_files.append(file)
             # Modified binary file
             elif l.startswith('Mb'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified link
             elif l.startswith('M->'):
                 file = self._stripbasepath(l[3:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified file
             elif l.startswith('M'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed file (or link)
             elif l.startswith('=>'):
                 files = l[2:].strip().split(' ')
                 if len(files) == 1:
                     files = l[2:].strip().split('\t')
                 src = self._stripbasepath(files[0])
                 dst = self._stripbasepath(files[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_files[src] = dst
             # Conversion from file to link or from link to file (modified)
             elif l.startswith('ch'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed directory
             elif l.startswith('/>'):
                 dirs = l[2:].strip().split(' ')
                 if len(dirs) == 1:
                     dirs = l[2:].strip().split('\t')
                 src = self._stripbasepath(dirs[0])
                 dst = self._stripbasepath(dirs[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_dirs[src] = dst

hgext/convert/hg.py

@@ -1,470 +1,472 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 or any later version.
 
 # 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, bookmarks, error, scmutil
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 import re
 sha1re = re.compile(r'\b[0-9a-f]{6,40}\b')
 
 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 repository')
                                  % 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 repository')
                                  % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
                 raise NoRepo(_("could not create hg repository %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')
         if self.lock:
             self.lock.release()
         if self.wlock:
             self.wlock.release()
 
     def revmapfile(self):
         return self.repo.join("shamap")
 
     def authorfile(self):
         return self.repo.join("authormap")
 
     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 Exception:
                 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 Exception:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in sorted(missings.iteritems()):
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.peer(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, mode = source.getfile(f, v)
+            if data is None:
+                return None
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             return context.memfilectx(self.repo, f, data, 'l' in mode,
                                       'x' in mode, 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
 
         sha1s = re.findall(sha1re, text)
         for sha1 in sha1s:
             oldrev = source.lookuprev(sha1)
             newrev = revmap.get(oldrev)
             if newrev is not None:
                 text = text.replace(sha1, newrev[:len(sha1)])
 
         extra = commit.extra.copy()
 
         for label in ('source', 'transplant_source', 'rebase_source'):
             node = extra.get(label)
 
             if node is None:
                 continue
 
             # Only transplant stores its reference in binary
             if label == 'transplant_source':
                 node = hex(node)
 
             newrev = revmap.get(node)
             if newrev is not None:
                 if label == 'transplant_source':
                     newrev = bin(newrev)
 
                 extra[label] = newrev
 
         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]
             closed = 'close' in commit.extra
             if not closed and not man.cmp(m1node, man.revision(mnode)):
                 self.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback(force=True)
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         oldlines = set()
         for branch, heads in self.repo.branchmap().iteritems():
             for h in heads:
                 if '.hgtags' in self.repo[h]:
                     oldlines.update(
                         set(self.repo[h]['.hgtags'].data().splitlines(True)))
         oldlines = sorted(list(oldlines))
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
             return None, None
 
         # if the old and new tags match, then there is nothing to update
         oldtags = set()
         newtags = set()
         for line in oldlines:
             s = line.strip().split(' ', 1)
             if len(s) != 2:
                 continue
             oldtags.add(s[1])
         for line in newlines:
             s = line.strip().split(' ', 1)
             if len(s) != 2:
                 continue
             if s[1] not in oldtags:
                 newtags.add(s[1].strip())
 
         if not newtags:
             return None, None
 
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(repo, 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()), hex(tagparent)
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
     def putbookmarks(self, updatedbookmark):
         if not len(updatedbookmark):
             return
 
         self.ui.status(_("updating bookmarks\n"))
         destmarks = self.repo._bookmarks
         for bookmark in updatedbookmark:
             destmarks[bookmark] = bin(updatedbookmark[bookmark])
         destmarks.write()
 
     def hascommitfrommap(self, rev):
         # the exact semantics of clonebranches is unclear so we can't say no
         return rev in self.repo or self.clonebranches
 
     def hascommitforsplicemap(self, rev):
         if rev not in self.repo and self.clonebranches:
             raise util.Abort(_('revision %s not found in destination '
                                'repository (lookups with clonebranches=true '
                                'are not implemented)') % rev)
         return rev in self.repo
 
 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 repository") % 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')
         hgrevs = ui.config('convert', 'hg.revs')
         if hgrevs is None:
             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 r in self.repo.changelog.descendants([startrev]):
                     children[self.repo.changelog.node(r)] = 1
                 self.keep = children.__contains__
             else:
                 self.keep = util.always
             if rev:
                 self._heads = [self.repo[rev].node()]
             else:
                 self._heads = self.repo.heads()
         else:
             if rev or startnode is not None:
                 raise util.Abort(_('hg.revs cannot be combined with '
                                    'hg.startrev or --rev'))
             nodes = set()
             parents = set()
             for r in scmutil.revrange(self.repo, [hgrevs]):
                 ctx = self.repo[r]
                 nodes.add(ctx.node())
                 parents.update(p.node() for p in ctx.parents())
             self.keep = nodes.__contains__
             self._heads = nodes - parents
 
     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 for p in ctx.parents() if p and self.keep(p.node())]
 
     def getheads(self):
         return [hex(h) for h in self._heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             fctx = self.changectx(rev)[name]
             return fctx.data(), fctx.flags()
-        except error.LookupError, err:
-            raise IOError(err)
+        except error.LookupError:
+            return None, None
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents:
             files = sorted(ctx.manifest())
             # getcopies() is not needed for roots, but it is a simple way to
             # detect missing revlogs and abort on errors or populate
             # self.ignored
             self.getcopies(ctx, parents, 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].node(), ctx.node())[:3]
         # getcopies() detects missing revlogs early, run it before
         # filtering the changes.
         copies = self.getcopies(ctx, parents, 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, parents, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
                 copysource, _copynode = ctx.filectx(name).renamed()
                 if copysource in self.ignored:
                     continue
                 # Ignore copy sources not in parent revisions
                 found = False
                 for p in parents:
                     if copysource in p:
                         found = True
                         break
                 if not found:
                     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 = [p.hex() for p in self.parents(ctx)]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(),
                       date=util.datestr(ctx.date(), '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev())
 
     def gettags(self):
         # This will get written to .hgtags, filter non global tags out.
         tags = [t for t in self.repo.tagslist()
                 if self.repo.tagtype(t[0]) == 'global']
         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].node(), 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(self.repo.join('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 hasnativeclose(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except error.RepoError:
             return None
 
     def getbookmarks(self):
         return bookmarks.listbookmarks(self.repo)
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ Mercurial, revision string is a 40 byte hex """
         self.checkhexformat(revstr, mapname)

hgext/convert/monotone.py

@@ -1,359 +1,359 b''
 # monotone.py - monotone support for the convert extension
 #
 #  Copyright 2008, 2009 Mikkel Fahnoe Jorgensen <[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 os, re
 from mercurial import util
 from common import NoRepo, commit, converter_source, checktool
 from common import commandline
 from mercurial.i18n import _
 
 class monotone_source(converter_source, commandline):
     def __init__(self, ui, path=None, rev=None):
         converter_source.__init__(self, ui, path, rev)
         commandline.__init__(self, ui, 'mtn')
 
         self.ui = ui
         self.path = path
         self.automatestdio = False
         self.rev = rev
 
         norepo = NoRepo(_("%s does not look like a monotone repository")
                         % path)
         if not os.path.exists(os.path.join(path, '_MTN')):
             # Could be a monotone repository (SQLite db file)
             try:
                 f = file(path, 'rb')
                 header = f.read(16)
                 f.close()
             except IOError:
                 header = ''
             if header != 'SQLite format 3\x00':
                 raise norepo
 
         # regular expressions for parsing monotone output
         space    = r'\s*'
         name     = r'\s+"((?:\\"|[^"])*)"\s*'
         value    = name
         revision = r'\s+\[(\w+)\]\s*'
         lines    = r'(?:.|\n)+'
 
         self.dir_re      = re.compile(space + "dir" + name)
         self.file_re     = re.compile(space + "file" + name +
                                       "content" + revision)
         self.add_file_re = re.compile(space + "add_file" + name +
                                       "content" + revision)
         self.patch_re    = re.compile(space + "patch" + name +
                                       "from" + revision + "to" + revision)
         self.rename_re   = re.compile(space + "rename" + name + "to" + name)
         self.delete_re   = re.compile(space + "delete" + name)
         self.tag_re      = re.compile(space + "tag" + name + "revision" +
                                       revision)
         self.cert_re     = re.compile(lines + space + "name" + name +
                                       "value" + value)
 
         attr = space + "file" + lines + space + "attr" + space
         self.attr_execute_re = re.compile(attr  + '"mtn:execute"' +
                                           space + '"true"')
 
         # cached data
         self.manifest_rev = None
         self.manifest = None
         self.files = None
         self.dirs  = None
 
         checktool('mtn', abort=False)
 
     def mtnrun(self, *args, **kwargs):
         if self.automatestdio:
             return self.mtnrunstdio(*args, **kwargs)
         else:
             return self.mtnrunsingle(*args, **kwargs)
 
     def mtnrunsingle(self, *args, **kwargs):
         kwargs['d'] = self.path
         return self.run0('automate', *args, **kwargs)
 
     def mtnrunstdio(self, *args, **kwargs):
         # Prepare the command in automate stdio format
         command = []
         for k, v in kwargs.iteritems():
             command.append("%s:%s" % (len(k), k))
             if v:
                 command.append("%s:%s" % (len(v), v))
         if command:
             command.insert(0, 'o')
             command.append('e')
 
         command.append('l')
         for arg in args:
             command += "%s:%s" % (len(arg), arg)
         command.append('e')
         command = ''.join(command)
 
         self.ui.debug("mtn: sending '%s'\n" % command)
         self.mtnwritefp.write(command)
         self.mtnwritefp.flush()
 
         return self.mtnstdioreadcommandoutput(command)
 
     def mtnstdioreadpacket(self):
         read = None
         commandnbr = ''
         while read != ':':
             read = self.mtnreadfp.read(1)
             if not read:
                 raise util.Abort(_('bad mtn packet - no end of commandnbr'))
             commandnbr += read
         commandnbr = commandnbr[:-1]
 
         stream = self.mtnreadfp.read(1)
         if stream not in 'mewptl':
             raise util.Abort(_('bad mtn packet - bad stream type %s') % stream)
 
         read = self.mtnreadfp.read(1)
         if read != ':':
             raise util.Abort(_('bad mtn packet - no divider before size'))
 
         read = None
         lengthstr = ''
         while read != ':':
             read = self.mtnreadfp.read(1)
             if not read:
                 raise util.Abort(_('bad mtn packet - no end of packet size'))
             lengthstr += read
         try:
             length = long(lengthstr[:-1])
         except TypeError:
             raise util.Abort(_('bad mtn packet - bad packet size %s')
                 % lengthstr)
 
         read = self.mtnreadfp.read(length)
         if len(read) != length:
             raise util.Abort(_("bad mtn packet - unable to read full packet "
                 "read %s of %s") % (len(read), length))
 
         return (commandnbr, stream, length, read)
 
     def mtnstdioreadcommandoutput(self, command):
         retval = []
         while True:
             commandnbr, stream, length, output = self.mtnstdioreadpacket()
             self.ui.debug('mtn: read packet %s:%s:%s\n' %
                 (commandnbr, stream, length))
 
             if stream == 'l':
                 # End of command
                 if output != '0':
                     raise util.Abort(_("mtn command '%s' returned %s") %
                         (command, output))
                 break
             elif stream in 'ew':
                 # Error, warning output
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             elif stream == 'p':
                 # Progress messages
                 self.ui.debug('mtn: ' + output)
             elif stream == 'm':
                 # Main stream - command output
                 retval.append(output)
 
         return ''.join(retval)
 
     def mtnloadmanifest(self, rev):
         if self.manifest_rev == rev:
             return
         self.manifest = self.mtnrun("get_manifest_of", rev).split("\n\n")
         self.manifest_rev = rev
         self.files = {}
         self.dirs = {}
 
         for e in self.manifest:
             m = self.file_re.match(e)
             if m:
                 attr = ""
                 name = m.group(1)
                 node = m.group(2)
                 if self.attr_execute_re.match(e):
                     attr += "x"
                 self.files[name] = (node, attr)
             m = self.dir_re.match(e)
             if m:
                 self.dirs[m.group(1)] = True
 
     def mtnisfile(self, name, rev):
         # a non-file could be a directory or a deleted or renamed file
         self.mtnloadmanifest(rev)
         return name in self.files
 
     def mtnisdir(self, name, rev):
         self.mtnloadmanifest(rev)
         return name in self.dirs
 
     def mtngetcerts(self, rev):
         certs = {"author":"<missing>", "date":"<missing>",
             "changelog":"<missing>", "branch":"<missing>"}
         certlist = self.mtnrun("certs", rev)
         # mtn < 0.45:
         #   key "[e-mail]"
         # mtn >= 0.45:
         #   key [ff58a7ffb771907c4ff68995eada1c4da068d328]
         certlist = re.split('\n\n      key ["\[]', certlist)
         for e in certlist:
             m = self.cert_re.match(e)
             if m:
                 name, value = m.groups()
                 value = value.replace(r'\"', '"')
                 value = value.replace(r'\\', '\\')
                 certs[name] = value
         # Monotone may have subsecond dates: 2005-02-05T09:39:12.364306
         # and all times are stored in UTC
         certs["date"] = certs["date"].split('.')[0] + " UTC"
         return certs
 
     # implement the converter_source interface:
 
     def getheads(self):
         if not self.rev:
             return self.mtnrun("leaves").splitlines()
         else:
             return [self.rev]
 
     def getchanges(self, rev):
         revision = self.mtnrun("get_revision", rev).split("\n\n")
         files = {}
         ignoremove = {}
         renameddirs = []
         copies = {}
         for e in revision:
             m = self.add_file_re.match(e)
             if m:
                 files[m.group(1)] = rev
                 ignoremove[m.group(1)] = rev
             m = self.patch_re.match(e)
             if m:
                 files[m.group(1)] = rev
             # Delete/rename is handled later when the convert engine
             # discovers an IOError exception from getfile,
             # but only if we add the "from" file to the list of changes.
             m = self.delete_re.match(e)
             if m:
                 files[m.group(1)] = rev
             m = self.rename_re.match(e)
             if m:
                 toname = m.group(2)
                 fromname = m.group(1)
                 if self.mtnisfile(toname, rev):
                     ignoremove[toname] = 1
                     copies[toname] = fromname
                     files[toname] = rev
                     files[fromname] = rev
                 elif self.mtnisdir(toname, rev):
                     renameddirs.append((fromname, toname))
 
         # Directory renames can be handled only once we have recorded
         # all new files
         for fromdir, todir in renameddirs:
             renamed = {}
             for tofile in self.files:
                 if tofile in ignoremove:
                     continue
                 if tofile.startswith(todir + '/'):
                     renamed[tofile] = fromdir + tofile[len(todir):]
                     # Avoid chained moves like:
                     # d1(/a) => d3/d1(/a)
                     # d2 => d3
                     ignoremove[tofile] = 1
             for tofile, fromfile in renamed.items():
                 self.ui.debug (_("copying file in renamed directory "
                                  "from '%s' to '%s'")
                                % (fromfile, tofile), '\n')
                 files[tofile] = rev
                 copies[tofile] = fromfile
             for fromfile in renamed.values():
                 files[fromfile] = rev
 
         return (files.items(), copies)
 
     def getfile(self, name, rev):
         if not self.mtnisfile(name, rev):
-            raise IOError # file was deleted or renamed
+            return None, None
         try:
             data = self.mtnrun("get_file_of", name, r=rev)
         except Exception:
-            raise IOError # file was deleted or renamed
+            return None, None
         self.mtnloadmanifest(rev)
         node, attr = self.files.get(name, (None, ""))
         return data, attr
 
     def getcommit(self, rev):
         extra = {}
         certs = self.mtngetcerts(rev)
         if certs.get('suspend') == certs["branch"]:
             extra['close'] = '1'
         return commit(
             author=certs["author"],
             date=util.datestr(util.strdate(certs["date"], "%Y-%m-%dT%H:%M:%S")),
             desc=certs["changelog"],
             rev=rev,
             parents=self.mtnrun("parents", rev).splitlines(),
             branch=certs["branch"],
             extra=extra)
 
     def gettags(self):
         tags = {}
         for e in self.mtnrun("tags").split("\n\n"):
             m = self.tag_re.match(e)
             if m:
                 tags[m.group(1)] = m.group(2)
         return tags
 
     def getchangedfiles(self, rev, i):
         # This function is only needed to support --filemap
         # ... and we don't support that
         raise NotImplementedError
 
     def before(self):
         # Check if we have a new enough version to use automate stdio
         version = 0.0
         try:
             versionstr = self.mtnrunsingle("interface_version")
             version = float(versionstr)
         except Exception:
             raise util.Abort(_("unable to determine mtn automate interface "
                 "version"))
 
         if version >= 12.0:
             self.automatestdio = True
             self.ui.debug("mtn automate version %s - using automate stdio\n" %
                 version)
 
             # launch the long-running automate stdio process
             self.mtnwritefp, self.mtnreadfp = self._run2('automate', 'stdio',
                 '-d', self.path)
             # read the headers
             read = self.mtnreadfp.readline()
             if read != 'format-version: 2\n':
                 raise util.Abort(_('mtn automate stdio header unexpected: %s')
                     % read)
             while read != '\n':
                 read = self.mtnreadfp.readline()
                 if not read:
                     raise util.Abort(_("failed to reach end of mtn automate "
                         "stdio headers"))
         else:
             self.ui.debug("mtn automate version %s - not using automate stdio "
                 "(automate >= 12.0 - mtn >= 0.46 is needed)\n" % version)
 
     def after(self):
         if self.automatestdio:
             self.mtnwritefp.close()
             self.mtnwritefp = None
             self.mtnreadfp.close()
             self.mtnreadfp = None
 

hgext/convert/p4.py

@@ -1,205 +1,205 b''
 # Perforce source for convert extension.
 #
 # Copyright 2009, Frank Kingswood <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from mercurial import util
 from mercurial.i18n import _
 
 from common import commit, converter_source, checktool, NoRepo
 import marshal
 import re
 
 def loaditer(f):
     "Yield the dictionary objects generated by p4"
     try:
         while True:
             d = marshal.load(f)
             if not d:
                 break
             yield d
     except EOFError:
         pass
 
 class p4_source(converter_source):
     def __init__(self, ui, path, rev=None):
         super(p4_source, self).__init__(ui, path, rev=rev)
 
         if "/" in path and not path.startswith('//'):
             raise NoRepo(_('%s does not look like a P4 repository') % path)
 
         checktool('p4', abort=False)
 
         self.p4changes = {}
         self.heads = {}
         self.changeset = {}
         self.files = {}
         self.tags = {}
         self.lastbranch = {}
         self.parent = {}
         self.encoding = "latin_1"
         self.depotname = {}           # mapping from local name to depot name
         self.re_type = re.compile(
             "([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
             "(\+\w+)?$")
         self.re_keywords = re.compile(
             r"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
             r":[^$\n]*\$")
         self.re_keywords_old = re.compile("\$(Id|Header):[^$\n]*\$")
 
         self._parse(ui, path)
 
     def _parse_view(self, path):
         "Read changes affecting the path"
         cmd = 'p4 -G changes -s submitted %s' % util.shellquote(path)
         stdout = util.popen(cmd, mode='rb')
         for d in loaditer(stdout):
             c = d.get("change", None)
             if c:
                 self.p4changes[c] = True
 
     def _parse(self, ui, path):
         "Prepare list of P4 filenames and revisions to import"
         ui.status(_('reading p4 views\n'))
 
         # read client spec or view
         if "/" in path:
             self._parse_view(path)
             if path.startswith("//") and path.endswith("/..."):
                 views = {path[:-3]:""}
             else:
                 views = {"//": ""}
         else:
             cmd = 'p4 -G client -o %s' % util.shellquote(path)
             clientspec = marshal.load(util.popen(cmd, mode='rb'))
 
             views = {}
             for client in clientspec:
                 if client.startswith("View"):
                     sview, cview = clientspec[client].split()
                     self._parse_view(sview)
                     if sview.endswith("...") and cview.endswith("..."):
                         sview = sview[:-3]
                         cview = cview[:-3]
                     cview = cview[2:]
                     cview = cview[cview.find("/") + 1:]
                     views[sview] = cview
 
         # list of changes that affect our source files
         self.p4changes = self.p4changes.keys()
         self.p4changes.sort(key=int)
 
         # list with depot pathnames, longest first
         vieworder = views.keys()
         vieworder.sort(key=len, reverse=True)
 
         # handle revision limiting
         startrev = self.ui.config('convert', 'p4.startrev', default=0)
         self.p4changes = [x for x in self.p4changes
                           if ((not startrev or int(x) >= int(startrev)) and
                               (not self.rev or int(x) <= int(self.rev)))]
 
         # now read the full changelists to get the list of file revisions
         ui.status(_('collecting p4 changelists\n'))
         lastid = None
         for change in self.p4changes:
             cmd = "p4 -G describe -s %s" % change
             stdout = util.popen(cmd, mode='rb')
             d = marshal.load(stdout)
             desc = self.recode(d.get("desc", ""))
             shortdesc = desc.split("\n", 1)[0]
             t = '%s %s' % (d["change"], repr(shortdesc)[1:-1])
             ui.status(util.ellipsis(t, 80) + '\n')
 
             if lastid:
                 parents = [lastid]
             else:
                 parents = []
 
             date = (int(d["time"]), 0)     # timezone not set
             c = commit(author=self.recode(d["user"]),
                        date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                        parents=parents, desc=desc, branch='',
                        extra={"p4": change})
 
             files = []
             i = 0
             while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
                 oldname = d["depotFile%d" % i]
                 filename = None
                 for v in vieworder:
                     if oldname.startswith(v):
                         filename = views[v] + oldname[len(v):]
                         break
                 if filename:
                     files.append((filename, d["rev%d" % i]))
                     self.depotname[filename] = oldname
                 i += 1
             self.changeset[change] = c
             self.files[change] = files
             lastid = change
 
         if lastid:
             self.heads = [lastid]
 
     def getheads(self):
         return self.heads
 
     def getfile(self, name, rev):
         cmd = 'p4 -G print %s' \
             % util.shellquote("%s#%s" % (self.depotname[name], rev))
         stdout = util.popen(cmd, mode='rb')
 
         mode = None
         contents = ""
         keywords = None
 
         for d in loaditer(stdout):
             code = d["code"]
             data = d.get("data")
 
             if code == "error":
                 raise IOError(d["generic"], data)
 
             elif code == "stat":
                 if d.get("action") == "purge":
                     return None, None
                 p4type = self.re_type.match(d["type"])
                 if p4type:
                     mode = ""
                     flags = (p4type.group(1) or "") + (p4type.group(3) or "")
                     if "x" in flags:
                         mode = "x"
                     if p4type.group(2) == "symlink":
                         mode = "l"
                     if "ko" in flags:
                         keywords = self.re_keywords_old
                     elif "k" in flags:
                         keywords = self.re_keywords
 
             elif code == "text" or code == "binary":
                 contents += data
 
         if mode is None:
-            raise IOError(0, "bad stat")
+            return None, None
 
         if keywords:
             contents = keywords.sub("$\\1$", contents)
         if mode == "l" and contents.endswith("\n"):
             contents = contents[:-1]
 
         return contents, mode
 
     def getchanges(self, rev):
         return self.files[rev], {}
 
     def getcommit(self, rev):
         return self.changeset[rev]
 
     def gettags(self):
         return self.tags
 
     def getchangedfiles(self, rev, i):
         return sorted([x[0] for x in self.files[rev]])

hgext/convert/subversion.py

@@ -1,1315 +1,1314 b''
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 
 import os, re, sys, tempfile, urllib, urllib2
 import xml.dom.minidom
 import cPickle as pickle
 
 from mercurial import strutil, scmutil, util, encoding
 from mercurial.i18n import _
 
 propertycache = util.propertycache
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 from cStringIO import StringIO
 
 from common import NoRepo, MissingTool, commit, encodeargs, decodeargs
 from common import commandline, converter_source, converter_sink, mapfile
 from common import makedatetimestamp
 
 try:
     from svn.core import SubversionException, Pool
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     import transport
     import warnings
     warnings.filterwarnings('ignore',
             module='svn.core',
             category=DeprecationWarning)
 
 except ImportError:
     svn = None
 
 class SvnPathNotFound(Exception):
     pass
 
 def revsplit(rev):
     """Parse a revision string and return (uuid, path, revnum).
     >>> revsplit('svn:a2147622-4a9f-4db4-a8d3-13562ff547b2'
     ...          '/proj%20B/mytrunk/mytrunk@1')
     ('a2147622-4a9f-4db4-a8d3-13562ff547b2', '/proj%20B/mytrunk/mytrunk', 1)
     >>> revsplit('svn:8af66a51-67f5-4354-b62c-98d67cc7be1d@1')
     ('', '', 1)
     >>> revsplit('@7')
     ('', '', 7)
     >>> revsplit('7')
     ('', '', 0)
     >>> revsplit('bad')
     ('', '', 0)
     """
     parts = rev.rsplit('@', 1)
     revnum = 0
     if len(parts) > 1:
         revnum = int(parts[1])
     parts = parts[0].split('/', 1)
     uuid = ''
     mod = ''
     if len(parts) > 1 and parts[0].startswith('svn:'):
         uuid = parts[0][4:]
         mod = '/' + parts[1]
     return uuid, mod, revnum
 
 def quote(s):
     # As of svn 1.7, many svn calls expect "canonical" paths. In
     # theory, we should call svn.core.*canonicalize() on all paths
     # before passing them to the API.  Instead, we assume the base url
     # is canonical and copy the behaviour of svn URL encoding function
     # so we can extend it safely with new components. The "safe"
     # characters were taken from the "svn_uri__char_validity" table in
     # libsvn_subr/path.c.
     return urllib.quote(s, "!$&'()*+,-./:=@_~")
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except SubversionException:
         # svn.client.url_from_path() fails with local repositories
         pass
     if os.path.isdir(path):
         path = os.path.normpath(os.path.abspath(path))
         if os.name == 'nt':
             path = '/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
         path = encoding.tolocal(path)
         path = 'file://%s' % quote(path)
     return svn.core.svn_path_canonicalize(path)
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         paths = {}
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 paths[k] = changedpath(v)
         pickle.dump((paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except IOError:
         # Caller may interrupt the iteration
         pickle.dump(None, fp, protocol)
     except Exception, inst:
         pickle.dump(str(inst), fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.close()
     # With large history, cleanup process goes crazy and suddenly
     # consumes *huge* amount of memory. The output file being closed,
     # there is no need for clean termination.
     os._exit(0)
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     if svn is None:
         raise util.Abort(_('debugsvnlog could not load Subversion python '
                            'bindings'))
 
     util.setbinary(sys.stdin)
     util.setbinary(sys.stdout)
     args = decodeargs(sys.stdin.read())
     get_log_child(sys.stdout, *args)
 
 class logstream(object):
     """Interruptible revision log iterator."""
     def __init__(self, stdout):
         self._stdout = stdout
 
     def __iter__(self):
         while True:
             try:
                 entry = pickle.load(self._stdout)
             except EOFError:
                 raise util.Abort(_('Mercurial failed to run itself, check'
                                    ' hg executable is in PATH'))
             try:
                 orig_paths, revnum, author, date, message = entry
             except (TypeError, ValueError):
                 if entry is None:
                     break
                 raise util.Abort(_("log stream exception '%s'") % entry)
             yield entry
 
     def close(self):
         if self._stdout:
             self._stdout.close()
             self._stdout = None
 
 class directlogstream(list):
     """Direct revision log iterator.
     This can be used for debugging and development but it will probably leak
     memory and is not suitable for real conversions."""
     def __init__(self, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
 
         def receiver(orig_paths, revnum, author, date, message, pool):
             paths = {}
             if orig_paths is not None:
                 for k, v in orig_paths.iteritems():
                     paths[k] = changedpath(v)
             self.append((paths, revnum, author, date, message))
 
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
 
     def close(self):
         pass
 
 # Check to see if the given path is a local Subversion repo. Verify this by
 # looking for several svn-specific files and directories in the given
 # directory.
 def filecheck(ui, path, proto):
     for x in ('locks', 'hooks', 'format', 'db'):
         if not os.path.exists(os.path.join(path, x)):
             return False
     return True
 
 # Check to see if a given path is the root of an svn repo over http. We verify
 # this by requesting a version-controlled URL we know can't exist and looking
 # for the svn-specific "not found" XML.
 def httpcheck(ui, path, proto):
     try:
         opener = urllib2.build_opener()
         rsp = opener.open('%s://%s/!svn/ver/0/.svn' % (proto, path))
         data = rsp.read()
     except urllib2.HTTPError, inst:
         if inst.code != 404:
             # Except for 404 we cannot know for sure this is not an svn repo
             ui.warn(_('svn: cannot probe remote repository, assume it could '
                       'be a subversion repository. Use --source-type if you '
                       'know better.\n'))
             return True
         data = inst.fp.read()
     except Exception:
         # Could be urllib2.URLError if the URL is invalid or anything else.
         return False
     return '<m:human-readable errcode="160013">' in data
 
 protomap = {'http': httpcheck,
             'https': httpcheck,
             'file': filecheck,
             }
 def issvnurl(ui, url):
     try:
         proto, path = url.split('://', 1)
         if proto == 'file':
             if (os.name == 'nt' and path[:1] == '/' and path[1:2].isalpha()
                 and path[2:6].lower() == '%3a/'):
                 path = path[:2] + ':/' + path[6:]
             path = urllib.url2pathname(path)
     except ValueError:
         proto = 'file'
         path = os.path.abspath(url)
     if proto == 'file':
         path = util.pconvert(path)
     check = protomap.get(proto, lambda *args: False)
     while '/' in path:
         if check(ui, path, proto):
             return True
         path = path.rsplit('/', 1)[0]
     return False
 
 # SVN conversion code stolen from bzr-svn and tailor
 #
 # Subversion looks like a versioned filesystem, branches structures
 # are defined by conventions and not enforced by the tool. First,
 # we define the potential branches (modules) as "trunk" and "branches"
 # children directories. Revisions are then identified by their
 # module and revision number (and a repository identifier).
 #
 # The revision graph is really a tree (or a forest). By default, a
 # revision parent is the previous revision in the same module. If the
 # module directory is copied/moved from another module then the
 # revision is the module root and its parent the source revision in
 # the parent module. A revision has at most one parent.
 #
 class svn_source(converter_source):
     def __init__(self, ui, url, rev=None):
         super(svn_source, self).__init__(ui, url, rev=rev)
 
         if not (url.startswith('svn://') or url.startswith('svn+ssh://') or
                 (os.path.exists(url) and
                  os.path.exists(os.path.join(url, '.svn'))) or
                 issvnurl(ui, url)):
             raise NoRepo(_("%s does not look like a Subversion repository")
                          % url)
         if svn is None:
             raise MissingTool(_('could not load Subversion python bindings'))
 
         try:
             version = svn.core.SVN_VER_MAJOR, svn.core.SVN_VER_MINOR
             if version < (1, 4):
                 raise MissingTool(_('Subversion python bindings %d.%d found, '
                                     '1.4 or later required') % version)
         except AttributeError:
             raise MissingTool(_('Subversion python bindings are too old, 1.4 '
                                 'or later required'))
 
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at + 1:])
                 url = url[:at]
         except ValueError:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.baseurl = svn.ra.get_repos_root(self.ra)
             # Module is either empty or a repository path starting with
             # a slash and not ending with a slash.
             self.module = urllib.unquote(self.url[len(self.baseurl):])
             self.prevmodule = None
             self.rootmodule = self.module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra)
         except SubversionException:
             ui.traceback()
             raise NoRepo(_("%s does not look like a Subversion repository")
                          % self.url)
 
         if rev:
             try:
                 latest = int(rev)
             except ValueError:
                 raise util.Abort(_('svn: revision %s is not an integer') % rev)
 
         self.trunkname = self.ui.config('convert', 'svn.trunk',
                                         'trunk').strip('/')
         self.startrev = self.ui.config('convert', 'svn.startrev', default=0)
         try:
             self.startrev = int(self.startrev)
             if self.startrev < 0:
                 self.startrev = 0
         except ValueError:
             raise util.Abort(_('svn: start revision %s is not an integer')
                              % self.startrev)
 
         try:
             self.head = self.latest(self.module, latest)
         except SvnPathNotFound:
             self.head = None
         if not self.head:
             raise util.Abort(_('no revision found in module %s')
                              % self.module)
         self.last_changed = self.revnum(self.head)
 
         self._changescache = None
 
         if os.path.exists(os.path.join(url, '.svn/entries')):
             self.wc = url
         else:
             self.wc = None
         self.convertfp = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.iterkeys():
             uuid, module, revnum = revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + quote(path),
                                  optrev, False, self.ctx)
             return True
         except SubversionException:
             return False
 
     def getheads(self):
 
         def isdir(path, revnum):
             kind = self._checkpath(path, revnum)
             return kind == svn.core.svn_node_dir
 
         def getcfgpath(name, rev):
             cfgpath = self.ui.config('convert', 'svn.' + name)
             if cfgpath is not None and cfgpath.strip() == '':
                 return None
             path = (cfgpath or name).strip('/')
             if not self.exists(path, rev):
                 if self.module.endswith(path) and name == 'trunk':
                     # we are converting from inside this directory
                     return None
                 if cfgpath:
                     raise util.Abort(_('expected %s to be at %r, but not found')
                                  % (name, path))
                 return None
             self.ui.note(_('found %s at %r\n') % (name, path))
             return path
 
         rev = optrev(self.last_changed)
         oldmodule = ''
         trunk = getcfgpath('trunk', rev)
         self.tags = getcfgpath('tags', rev)
         branches = getcfgpath('branches', rev)
 
         # If the project has a trunk or branches, we will extract heads
         # from them. We keep the project root otherwise.
         if trunk:
             oldmodule = self.module or ''
             self.module += '/' + trunk
             self.head = self.latest(self.module, self.last_changed)
             if not self.head:
                 raise util.Abort(_('no revision found in module %s')
                                  % self.module)
 
         # First head in the list is the module's head
         self.heads = [self.head]
         if self.tags is not None:
             self.tags = '%s/%s' % (oldmodule , (self.tags or 'tags'))
 
         # Check if branches bring a few more heads to the list
         if branches:
             rpath = self.url.strip('/')
             branchnames = svn.client.ls(rpath + '/' + quote(branches),
                                         rev, False, self.ctx)
             for branch in sorted(branchnames):
                 module = '%s/%s/%s' % (oldmodule, branches, branch)
                 if not isdir(module, self.last_changed):
                     continue
                 brevid = self.latest(module, self.last_changed)
                 if not brevid:
                     self.ui.note(_('ignoring empty branch %s\n') % branch)
                     continue
                 self.ui.note(_('found branch %s at %d\n') %
                              (branch, self.revnum(brevid)))
                 self.heads.append(brevid)
 
         if self.startrev and self.heads:
             if len(self.heads) > 1:
                 raise util.Abort(_('svn: start revision is not supported '
                                    'with more than one branch'))
             revnum = self.revnum(self.heads[0])
             if revnum < self.startrev:
                 raise util.Abort(
                     _('svn: no revision found after start revision %d')
                                  % self.startrev)
 
         return self.heads
 
     def getchanges(self, rev):
         if self._changescache and self._changescache[0] == rev:
             return self._changescache[1]
         self._changescache = None
         (paths, parents) = self.paths[rev]
         if parents:
             files, self.removed, copies = self.expandpaths(rev, paths, parents)
         else:
             # Perform a full checkout on roots
             uuid, module, revnum = revsplit(rev)
             entries = svn.client.ls(self.baseurl + quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
             copies = {}
             self.removed = set()
 
         files.sort()
         files = zip(files, [rev] * len(files))
 
         # caller caches the result, so free it here to release memory
         del self.paths[rev]
         return (files, copies)
 
     def getchangedfiles(self, rev, i):
         changes = self.getchanges(rev)
         self._changescache = (rev, changes)
         return [f[0] for f in changes[0]]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = revsplit(rev)
             self.module = module
             self.reparent(module)
             # We assume that:
             # - requests for revisions after "stop" come from the
             # revision graph backward traversal. Cache all of them
             # down to stop, they will be used eventually.
             # - requests for revisions before "stop" come to get
             # isolated branches parents. Just fetch what is needed.
             stop = self.lastrevs.get(module, 0)
             if revnum < stop:
                 stop = revnum + 1
             self._fetch_revisions(revnum, stop)
             if rev not in self.commits:
                 raise util.Abort(_('svn: revision %s not found') % revnum)
         revcommit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return revcommit
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ fails if revision format does not match the correct format"""
         if not re.match(r'svn:[0-9a-f]{8,8}-[0-9a-f]{4,4}-'
                               '[0-9a-f]{4,4}-[0-9a-f]{4,4}-[0-9a-f]'
                               '{12,12}(.*)\@[0-9]+$',revstr):
             raise util.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def gettags(self):
         tags = {}
         if self.tags is None:
             return tags
 
         # svn tags are just a convention, project branches left in a
         # 'tags' directory. There is no other relationship than
         # ancestry, which is expensive to discover and makes them hard
         # to update incrementally.  Worse, past revisions may be
         # referenced by tags far away in the future, requiring a deep
         # history traversal on every calculation.  Current code
         # performs a single backward traversal, tracking moves within
         # the tags directory (tag renaming) and recording a new tag
         # everytime a project is copied from outside the tags
         # directory. It also lists deleted tags, this behaviour may
         # change in the future.
         pendings = []
         tagspath = self.tags
         start = svn.ra.get_latest_revnum(self.ra)
         stream = self._getlog([self.tags], start, self.startrev)
         try:
             for entry in stream:
                 origpaths, revnum, author, date, message = entry
                 if not origpaths:
                     origpaths = []
                 copies = [(e.copyfrom_path, e.copyfrom_rev, p) for p, e
                           in origpaths.iteritems() if e.copyfrom_path]
                 # Apply moves/copies from more specific to general
                 copies.sort(reverse=True)
 
                 srctagspath = tagspath
                 if copies and copies[-1][2] == tagspath:
                     # Track tags directory moves
                     srctagspath = copies.pop()[0]
 
                 for source, sourcerev, dest in copies:
                     if not dest.startswith(tagspath + '/'):
                         continue
                     for tag in pendings:
                         if tag[0].startswith(dest):
                             tagpath = source + tag[0][len(dest):]
                             tag[:2] = [tagpath, sourcerev]
                             break
                     else:
                         pendings.append([source, sourcerev, dest])
 
                 # Filter out tags with children coming from different
                 # parts of the repository like:
                 # /tags/tag.1 (from /trunk:10)
                 # /tags/tag.1/foo (from /branches/foo:12)
                 # Here/tags/tag.1 discarded as well as its children.
                 # It happens with tools like cvs2svn. Such tags cannot
                 # be represented in mercurial.
                 addeds = dict((p, e.copyfrom_path) for p, e
                               in origpaths.iteritems()
                               if e.action == 'A' and e.copyfrom_path)
                 badroots = set()
                 for destroot in addeds:
                     for source, sourcerev, dest in pendings:
                         if (not dest.startswith(destroot + '/')
                             or source.startswith(addeds[destroot] + '/')):
                             continue
                         badroots.add(destroot)
                         break
 
                 for badroot in badroots:
                     pendings = [p for p in pendings if p[2] != badroot
                                 and not p[2].startswith(badroot + '/')]
 
                 # Tell tag renamings from tag creations
                 renamings = []
                 for source, sourcerev, dest in pendings:
                     tagname = dest.split('/')[-1]
                     if source.startswith(srctagspath):
                         renamings.append([source, sourcerev, tagname])
                         continue
                     if tagname in tags:
                         # Keep the latest tag value
                         continue
                     # From revision may be fake, get one with changes
                     try:
                         tagid = self.latest(source, sourcerev)
                         if tagid and tagname not in tags:
                             tags[tagname] = tagid
                     except SvnPathNotFound:
                         # It happens when we are following directories
                         # we assumed were copied with their parents
                         # but were really created in the tag
                         # directory.
                         pass
                 pendings = renamings
                 tagspath = srctagspath
         finally:
             stream.close()
         return tags
 
     def converted(self, rev, destrev):
         if not self.wc:
             return
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.wc, '.svn', 'hg-shamap'),
                                   'a')
         self.convertfp.write('%s %d\n' % (destrev, self.revnum(rev)))
         self.convertfp.flush()
 
     def revid(self, revnum, module=None):
         return 'svn:%s%s@%s' % (self.uuid, module or self.module, revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def latest(self, path, stop=None):
         """Find the latest revid affecting path, up to stop revision
         number. If stop is None, default to repository latest
         revision. It may return a revision in a different module,
         since a branch may be moved without a change being
         reported. Return None if computed module does not belong to
         rootmodule subtree.
         """
         def findchanges(path, start, stop=None):
             stream = self._getlog([path], start, stop or 1)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if stop is None and paths:
                         # We do not know the latest changed revision,
                         # keep the first one with changed paths.
                         break
                     if revnum <= stop:
                         break
 
                     for p in paths:
                         if (not path.startswith(p) or
                             not paths[p].copyfrom_path):
                             continue
                         newpath = paths[p].copyfrom_path + path[len(p):]
                         self.ui.debug("branch renamed from %s to %s at %d\n" %
                                       (path, newpath, revnum))
                         path = newpath
                         break
                 if not paths:
                     revnum = None
                 return revnum, path
             finally:
                 stream.close()
 
         if not path.startswith(self.rootmodule):
             # Requests on foreign branches may be forbidden at server level
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
 
         if stop is None:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             prevmodule = self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(prevmodule)
         except SubversionException:
             dirent = None
         if not dirent:
             raise SvnPathNotFound(_('%s not found up to revision %d')
                                   % (path, stop))
 
         # stat() gives us the previous revision on this line of
         # development, but it might be in *another module*. Fetch the
         # log and detect renames down to the latest revision.
         revnum, realpath = findchanges(path, stop, dirent.created_rev)
         if revnum is None:
             # Tools like svnsync can create empty revision, when
             # synchronizing only a subtree for instance. These empty
             # revisions created_rev still have their original values
             # despite all changes having disappeared and can be
             # returned by ra.stat(), at least when stating the root
             # module. In that case, do not trust created_rev and scan
             # the whole history.
             revnum, realpath = findchanges(path, stop)
             if revnum is None:
                 self.ui.debug('ignoring empty branch %r\n' % realpath)
                 return None
 
         if not realpath.startswith(self.rootmodule):
             self.ui.debug('ignoring foreign branch %r\n' % realpath)
             return None
         return self.revid(revnum, realpath)
 
     def reparent(self, module):
         """Reparent the svn transport and return the previous parent."""
         if self.prevmodule == module:
             return module
         svnurl = self.baseurl + quote(module)
         prevmodule = self.prevmodule
         if prevmodule is None:
             prevmodule = ''
         self.ui.debug("reparent to %s\n" % svnurl)
         svn.ra.reparent(self.ra, svnurl)
         self.prevmodule = module
         return prevmodule
 
     def expandpaths(self, rev, paths, parents):
         changed, removed = set(), set()
         copies = {}
 
         new_module, revnum = revsplit(rev)[1:]
         if new_module != self.module:
             self.module = new_module
             self.reparent(self.module)
 
         for i, (path, ent) in enumerate(paths):
             self.ui.progress(_('scanning paths'), i, item=path,
                              total=len(paths))
             entrypath = self.getrelpath(path)
 
             kind = self._checkpath(entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 changed.add(self.recode(entrypath))
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrom_path = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrom_path:
                     continue
                 self.ui.debug("copied to %s from %s@%s\n" %
                               (entrypath, copyfrom_path, ent.copyfrom_rev))
                 copies[self.recode(entrypath)] = self.recode(copyfrom_path)
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 parentpath = pmodule + "/" + entrypath
                 fromkind = self._checkpath(entrypath, prevnum, pmodule)
 
                 if fromkind == svn.core.svn_node_file:
                     removed.add(self.recode(entrypath))
                 elif fromkind == svn.core.svn_node_dir:
                     oroot = parentpath.strip('/')
                     nroot = path.strip('/')
                     children = self._iterfiles(oroot, prevnum)
                     for childpath in children:
                         childpath = childpath.replace(oroot, nroot)
                         childpath = self.getrelpath("/" + childpath, pmodule)
                         if childpath:
                             removed.add(self.recode(childpath))
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 if ent.action == 'M':
                     # If the directory just had a prop change,
                     # then we shouldn't need to look for its children.
                     continue
                 if ent.action == 'R' and parents:
                     # If a directory is replacing a file, mark the previous
                     # file as deleted
                     pmodule, prevnum = revsplit(parents[0])[1:]
                     pkind = self._checkpath(entrypath, prevnum, pmodule)
                     if pkind == svn.core.svn_node_file:
                         removed.add(self.recode(entrypath))
                     elif pkind == svn.core.svn_node_dir:
                         # We do not know what files were kept or removed,
                         # mark them all as changed.
                         for childpath in self._iterfiles(pmodule, prevnum):
                             childpath = self.getrelpath("/" + childpath)
                             if childpath:
                                 changed.add(self.recode(childpath))
 
                 for childpath in self._iterfiles(path, revnum):
                     childpath = self.getrelpath("/" + childpath)
                     if childpath:
                         changed.add(self.recode(childpath))
 
                 # Handle directory copies
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrompath = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrompath:
                     continue
                 self.ui.debug("mark %s came from %s:%d\n"
                               % (path, copyfrompath, ent.copyfrom_rev))
                 children = self._iterfiles(ent.copyfrom_path, ent.copyfrom_rev)
                 for childpath in children:
                     childpath = self.getrelpath("/" + childpath, pmodule)
                     if not childpath:
                         continue
                     copytopath = path + childpath[len(copyfrompath):]
                     copytopath = self.getrelpath(copytopath)
                     copies[self.recode(copytopath)] = self.recode(childpath)
 
         self.ui.progress(_('scanning paths'), None)
         changed.update(removed)
         return (list(changed), removed, copies)
 
     def _fetch_revisions(self, from_revnum, to_revnum):
         if from_revnum < to_revnum:
             from_revnum, to_revnum = to_revnum, from_revnum
 
         self.child_cset = None
 
         def parselogentry(orig_paths, revnum, author, date, message):
             """Return the parsed commit object or None, and True if
             the revision is a branch root.
             """
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             branched = False
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
 
             if rev in self.commits or revnum < to_revnum:
                 return None, branched
 
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
             orig_paths = sorted(orig_paths.iteritems())
             root_paths = [(p, e) for p, e in orig_paths
                           if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
                 if ent.copyfrom_path:
                     branched = True
                     newpath = ent.copyfrom_path + self.module[len(path):]
                     # ent.copyfrom_rev may not be the actual last revision
                     previd = self.latest(newpath, ent.copyfrom_rev)
                     if previd is not None:
                         prevmodule, prevnum = revsplit(previd)[1:]
                         if prevnum >= self.startrev:
                             parents = [previd]
                             self.ui.note(
                                 _('found parent of branch %s at %d: %s\n') %
                                 (self.module, prevnum, prevmodule))
                 else:
                     self.ui.debug("no copyfrom path, don't know what to do.\n")
 
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if self.getrelpath(path) is None:
                     continue
                 paths.append((path, ent))
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = util.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
             if self.ui.configbool('convert', 'localtimezone'):
                 date = makedatetimestamp(date[0])
 
             log = message and self.recode(message) or ''
             author = author and self.recode(author) or ''
             try:
                 branch = self.module.split("/")[-1]
                 if branch == self.trunkname:
                     branch = None
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev)
 
             self.commits[rev] = cset
             # The parents list is *shared* among self.paths and the
             # commit object. Both will be updated below.
             self.paths[rev] = (paths, cset.parents)
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents[:] = [rev]
             self.child_cset = cset
             return cset, branched
 
         self.ui.note(_('fetching revision log for "%s" from %d to %d\n') %
                      (self.module, from_revnum, to_revnum))
 
         try:
             firstcset = None
             lastonbranch = False
             stream = self._getlog([self.module], from_revnum, to_revnum)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if revnum < self.startrev:
                         lastonbranch = True
                         break
                     if not paths:
                         self.ui.debug('revision %d has no entries\n' % revnum)
                         # If we ever leave the loop on an empty
                         # revision, do not try to get a parent branch
                         lastonbranch = lastonbranch or revnum == 0
                         continue
                     cset, lastonbranch = parselogentry(paths, revnum, author,
                                                        date, message)
                     if cset:
                         firstcset = cset
                     if lastonbranch:
                         break
             finally:
                 stream.close()
 
             if not lastonbranch and firstcset and not firstcset.parents:
                 # The first revision of the sequence (the last fetched one)
                 # has invalid parents if not a branch root. Find the parent
                 # revision now, if any.
                 try:
                     firstrevnum = self.revnum(firstcset.rev)
                     if firstrevnum > 1:
                         latest = self.latest(self.module, firstrevnum - 1)
                         if latest:
                             firstcset.parents.append(latest)
                 except SvnPathNotFound:
                     pass
         except SubversionException, (inst, num):
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise util.Abort(_('svn: branch has no revision %s')
                                  % to_revnum)
             raise
 
     def getfile(self, file, rev):
         # TODO: ra.get_file transmits the whole file instead of diffs.
         if file in self.removed:
-            raise IOError
+            return None, None
         mode = ''
         try:
             new_module, revnum = revsplit(rev)[1:]
             if self.module != new_module:
                 self.module = new_module
                 self.reparent(self.module)
             io = StringIO()
             info = svn.ra.get_file(self.ra, file, revnum, io)
             data = io.getvalue()
             # ra.get_file() seems to keep a reference on the input buffer
             # preventing collection. Release it explicitly.
             io.close()
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
         except SubversionException, e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
-                raise IOError
+                return None, None
             raise
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _iterfiles(self, path, revnum):
         """Enumerate all files in path at revnum, recursively."""
         path = path.strip('/')
         pool = Pool()
         rpath = '/'.join([self.baseurl, quote(path)]).strip('/')
         entries = svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool)
         if path:
             path += '/'
         return ((path + p) for p, e in entries.iteritems()
                 if e.kind == svn.core.svn_node_file)
 
     def getrelpath(self, path, module=None):
         if module is None:
             module = self.module
         # Given the repository url of this wc, say
         #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
         # extract the "entry" portion (a relative path) from what
         # svn log --xml says, i.e.
         #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
         # that is to say "tests/PloneTestCase.py"
         if path.startswith(module):
             relative = path.rstrip('/')[len(module):]
             if relative.startswith('/'):
                 return relative[1:]
             elif relative == '':
                 return relative
 
         # The path is outside our tracked tree...
         self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
         return None
 
     def _checkpath(self, path, revnum, module=None):
         if module is not None:
             prevmodule = self.reparent('')
             path = module + '/' + path
         try:
             # ra.check_path does not like leading slashes very much, it leads
             # to PROPFIND subversion errors
             return svn.ra.check_path(self.ra, path.strip('/'), revnum)
         finally:
             if module is not None:
                 self.reparent(prevmodule)
 
     def _getlog(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
         # Normalize path names, svn >= 1.5 only wants paths relative to
         # supplied URL
         relpaths = []
         for p in paths:
             if not p.startswith('/'):
                 p = self.module + '/' + p
             relpaths.append(p.strip('/'))
         args = [self.baseurl, relpaths, start, end, limit,
                 discover_changed_paths, strict_node_history]
         # undocumented feature: debugsvnlog can be disabled
         if not self.ui.configbool('convert', 'svn.debugsvnlog', True):
             return directlogstream(*args)
         arg = encodeargs(args)
         hgexe = util.hgexecutable()
         cmd = '%s debugsvnlog' % util.shellquote(hgexe)
         stdin, stdout = util.popen2(util.quotecommand(cmd))
         stdin.write(arg)
         try:
             stdin.close()
         except IOError:
             raise util.Abort(_('Mercurial failed to run itself, check'
                                ' hg executable is in PATH'))
         return logstream(stdout)
 
 pre_revprop_change = '''#!/bin/sh
 
 REPOS="$1"
 REV="$2"
 USER="$3"
 PROPNAME="$4"
 ACTION="$5"
 
 if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
 
 echo "Changing prohibited revision property" >&2
 exit 1
 '''
 
 class svn_sink(converter_sink, commandline):
     commit_re = re.compile(r'Committed revision (\d+).', re.M)
     uuid_re = re.compile(r'Repository UUID:\s*(\S+)', re.M)
 
     def prerun(self):
         if self.wc:
             os.chdir(self.wc)
 
     def postrun(self):
         if self.wc:
             os.chdir(self.cwd)
 
     def join(self, name):
         return os.path.join(self.wc, '.svn', name)
 
     def revmapfile(self):
         return self.join('hg-shamap')
 
     def authorfile(self):
         return self.join('hg-authormap')
 
     def __init__(self, ui, path):
 
         converter_sink.__init__(self, ui, path)
         commandline.__init__(self, ui, 'svn')
         self.delete = []
         self.setexec = []
         self.delexec = []
         self.copies = []
         self.wc = None
         self.cwd = os.getcwd()
 
         created = False
         if os.path.isfile(os.path.join(path, '.svn', 'entries')):
             self.wc = os.path.realpath(path)
             self.run0('update')
         else:
             if not re.search(r'^(file|http|https|svn|svn\+ssh)\://', path):
                 path = os.path.realpath(path)
                 if os.path.isdir(os.path.dirname(path)):
                     if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
                         ui.status(_('initializing svn repository %r\n') %
                                   os.path.basename(path))
                         commandline(ui, 'svnadmin').run0('create', path)
                         created = path
                     path = util.normpath(path)
                     if not path.startswith('/'):
                         path = '/' + path
                     path = 'file://' + path
 
             wcpath = os.path.join(os.getcwd(), os.path.basename(path) + '-wc')
             ui.status(_('initializing svn working copy %r\n')
                       % os.path.basename(wcpath))
             self.run0('checkout', path, wcpath)
 
             self.wc = wcpath
         self.opener = scmutil.opener(self.wc)
         self.wopener = scmutil.opener(self.wc)
         self.childmap = mapfile(ui, self.join('hg-childmap'))
         self.is_exec = util.checkexec(self.wc) and util.isexec or None
 
         if created:
             hook = os.path.join(created, 'hooks', 'pre-revprop-change')
             fp = open(hook, 'w')
             fp.write(pre_revprop_change)
             fp.close()
             util.setflags(hook, False, True)
 
         output = self.run0('info')
         self.uuid = self.uuid_re.search(output).group(1).strip()
 
     def wjoin(self, *names):
         return os.path.join(self.wc, *names)
 
     @propertycache
     def manifest(self):
         # As of svn 1.7, the "add" command fails when receiving
         # already tracked entries, so we have to track and filter them
         # ourselves.
         m = set()
         output = self.run0('ls', recursive=True, xml=True)
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             for n in e.childNodes:
                 if n.nodeType != n.ELEMENT_NODE or n.tagName != 'name':
                     continue
                 name = ''.join(c.data for c in n.childNodes
                                if c.nodeType == c.TEXT_NODE)
                 # Entries are compared with names coming from
                 # mercurial, so bytes with undefined encoding. Our
                 # best bet is to assume they are in local
                 # encoding. They will be passed to command line calls
                 # later anyway, so they better be.
                 m.add(encoding.tolocal(name.encode('utf-8')))
                 break
         return m
 
     def putfile(self, filename, flags, data):
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             try:
                 if os.path.islink(self.wjoin(filename)):
                     os.unlink(filename)
             except OSError:
                 pass
             self.wopener.write(filename, data)
 
             if self.is_exec:
                 if self.is_exec(self.wjoin(filename)):
                     if 'x' not in flags:
                         self.delexec.append(filename)
                 else:
                     if 'x' in flags:
                         self.setexec.append(filename)
                 util.setflags(self.wjoin(filename), False, 'x' in flags)
 
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
         # already occurred.  Cross the semantic gap.
         wdest = self.wjoin(dest)
         exists = os.path.lexists(wdest)
         if exists:
             fd, tempname = tempfile.mkstemp(
                 prefix='hg-copy-', dir=os.path.dirname(wdest))
             os.close(fd)
             os.unlink(tempname)
             os.rename(wdest, tempname)
         try:
             self.run0('copy', source, dest)
         finally:
             self.manifest.add(dest)
             if exists:
                 try:
                     os.unlink(wdest)
                 except OSError:
                     pass
                 os.rename(tempname, wdest)
 
     def dirs_of(self, files):
         dirs = set()
         for f in files:
             if os.path.isdir(self.wjoin(f)):
                 dirs.add(f)
             for i in strutil.rfindall(f, '/'):
                 dirs.add(f[:i])
         return dirs
 
     def add_dirs(self, files):
         add_dirs = [d for d in sorted(self.dirs_of(files))
                     if d not in self.manifest]
         if add_dirs:
             self.manifest.update(add_dirs)
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
     def add_files(self, files):
         files = [f for f in files if f not in self.manifest]
         if files:
             self.manifest.update(files)
             self.xargs(files, 'add', quiet=True)
         return files
 
     def tidy_dirs(self, names):
         deleted = []
         for d in sorted(self.dirs_of(names), reverse=True):
             wd = self.wjoin(d)
             if os.listdir(wd) == '.svn':
                 self.run0('delete', d)
                 self.manifest.remove(d)
                 deleted.append(d)
         return deleted
 
     def addchild(self, parent, child):
         self.childmap[parent] = child
 
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
             except KeyError:
                 pass
 
         # Apply changes to working copy
         for f, v in files:
-            try:
-                data, mode = source.getfile(f, v)
-            except IOError:
+            data, mode = source.getfile(f, v)
+            if data is None:
                 self.delete.append(f)
             else:
                 self.putfile(f, mode, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
         files = [f[0] for f in files]
 
         entries = set(self.delete)
         files = frozenset(files)
         entries.update(self.add_dirs(files.difference(entries)))
         if self.copies:
             for s, d in self.copies:
                 self._copyfile(s, d)
             self.copies = []
         if self.delete:
             self.xargs(self.delete, 'delete')
             for f in self.delete:
                 self.manifest.remove(f)
             self.delete = []
         entries.update(self.add_files(files.difference(entries)))
         entries.update(self.tidy_dirs(entries))
         if self.delexec:
             self.xargs(self.delexec, 'propdel', 'svn:executable')
             self.delexec = []
         if self.setexec:
             self.xargs(self.setexec, 'propset', 'svn:executable', '*')
             self.setexec = []
 
         fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
         fp = os.fdopen(fd, 'w')
         fp.write(commit.desc)
         fp.close()
         try:
             output = self.run0('commit',
                                username=util.shortuser(commit.author),
                                file=messagefile,
                                encoding='utf-8')
             try:
                 rev = self.commit_re.search(output).group(1)
             except AttributeError:
                 if not files:
                     return parents[0]
                 self.ui.warn(_('unexpected svn output:\n'))
                 self.ui.warn(output)
                 raise util.Abort(_('unable to cope with svn output'))
             if commit.rev:
                 self.run('propset', 'hg:convert-rev', commit.rev,
                          revprop=True, revision=rev)
             if commit.branch and commit.branch != 'default':
                 self.run('propset', 'hg:convert-branch', commit.branch,
                          revprop=True, revision=rev)
             for parent in parents:
                 self.addchild(parent, rev)
             return self.revid(rev)
         finally:
             os.unlink(messagefile)
 
     def puttags(self, tags):
         self.ui.warn(_('writing Subversion tags is not yet implemented\n'))
         return None, None
 
     def hascommitfrommap(self, rev):
         # We trust that revisions referenced in a map still is present
         # TODO: implement something better if necessary and feasible
         return True
 
     def hascommitforsplicemap(self, rev):
         # This is not correct as one can convert to an existing subversion
         # repository and childmap would not list all revisions. Too bad.
         if rev in self.childmap:
             return True
         raise util.Abort(_('splice map revision %s not found in subversion '
                            'child map (revision lookups are not implemented)')
                          % rev)

hgext/histedit.py

@@ -1,944 +1,944 b''
 # histedit.py - interactive history editing for mercurial
 #
 # Copyright 2009 Augie Fackler <[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.
 """interactive history editing
 
 With this extension installed, Mercurial gains one new command: histedit. Usage
 is as follows, assuming the following history::
 
  @  3[tip]   7c2fd3b9020c   2009-04-27 18:04 -0500   durin42
  |    Add delta
  |
  o  2   030b686bedc4   2009-04-27 18:04 -0500   durin42
  |    Add gamma
  |
  o  1   c561b4e977df   2009-04-27 18:04 -0500   durin42
  |    Add beta
  |
  o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
       Add alpha
 
 If you were to run ``hg histedit c561b4e977df``, you would see the following
 file open in your editor::
 
  pick c561b4e977df Add beta
  pick 030b686bedc4 Add gamma
  pick 7c2fd3b9020c Add delta
 
  # Edit history between c561b4e977df and 7c2fd3b9020c
  #
  # Commits are listed from least to most recent
  #
  # Commands:
  #  p, pick = use commit
  #  e, edit = use commit, but stop for amending
  #  f, fold = use commit, but combine it with the one above
  #  r, roll = like fold, but discard this commit's description
  #  d, drop = remove commit from history
  #  m, mess = edit message without changing commit content
  #
 
 In this file, lines beginning with ``#`` are ignored. You must specify a rule
 for each revision in your history. For example, if you had meant to add gamma
 before beta, and then wanted to add delta in the same revision as beta, you
 would reorganize the file to look like this::
 
  pick 030b686bedc4 Add gamma
  pick c561b4e977df Add beta
  fold 7c2fd3b9020c Add delta
 
  # Edit history between c561b4e977df and 7c2fd3b9020c
  #
  # Commits are listed from least to most recent
  #
  # Commands:
  #  p, pick = use commit
  #  e, edit = use commit, but stop for amending
  #  f, fold = use commit, but combine it with the one above
  #  r, roll = like fold, but discard this commit's description
  #  d, drop = remove commit from history
  #  m, mess = edit message without changing commit content
  #
 
 At which point you close the editor and ``histedit`` starts working. When you
 specify a ``fold`` operation, ``histedit`` will open an editor when it folds
 those revisions together, offering you a chance to clean up the commit message::
 
  Add beta
  ***
  Add delta
 
 Edit the commit message to your liking, then close the editor. For
 this example, let's assume that the commit message was changed to
 ``Add beta and delta.`` After histedit has run and had a chance to
 remove any old or temporary revisions it needed, the history looks
 like this::
 
  @  2[tip]   989b4d060121   2009-04-27 18:04 -0500   durin42
  |    Add beta and delta.
  |
  o  1   081603921c3f   2009-04-27 18:04 -0500   durin42
  |    Add gamma
  |
  o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
       Add alpha
 
 Note that ``histedit`` does *not* remove any revisions (even its own temporary
 ones) until after it has completed all the editing operations, so it will
 probably perform several strip operations when it's done. For the above example,
 it had to run strip twice. Strip can be slow depending on a variety of factors,
 so you might need to be a little patient. You can choose to keep the original
 revisions by passing the ``--keep`` flag.
 
 The ``edit`` operation will drop you back to a command prompt,
 allowing you to edit files freely, or even use ``hg record`` to commit
 some changes as a separate commit. When you're done, any remaining
 uncommitted changes will be committed as well. When done, run ``hg
 histedit --continue`` to finish this step. You'll be prompted for a
 new commit message, but the default commit message will be the
 original message for the ``edit`` ed revision.
 
 The ``message`` operation will give you a chance to revise a commit
 message without changing the contents. It's a shortcut for doing
 ``edit`` immediately followed by `hg histedit --continue``.
 
 If ``histedit`` encounters a conflict when moving a revision (while
 handling ``pick`` or ``fold``), it'll stop in a similar manner to
 ``edit`` with the difference that it won't prompt you for a commit
 message when done. If you decide at this point that you don't like how
 much work it will be to rearrange history, or that you made a mistake,
 you can use ``hg histedit --abort`` to abandon the new changes you
 have made and return to the state before you attempted to edit your
 history.
 
 If we clone the histedit-ed example repository above and add four more
 changes, such that we have the following history::
 
    @  6[tip]   038383181893   2009-04-27 18:04 -0500   stefan
    |    Add theta
    |
    o  5   140988835471   2009-04-27 18:04 -0500   stefan
    |    Add eta
    |
    o  4   122930637314   2009-04-27 18:04 -0500   stefan
    |    Add zeta
    |
    o  3   836302820282   2009-04-27 18:04 -0500   stefan
    |    Add epsilon
    |
    o  2   989b4d060121   2009-04-27 18:04 -0500   durin42
    |    Add beta and delta.
    |
    o  1   081603921c3f   2009-04-27 18:04 -0500   durin42
    |    Add gamma
    |
    o  0   d8d2fcd0e319   2009-04-27 18:04 -0500   durin42
         Add alpha
 
 If you run ``hg histedit --outgoing`` on the clone then it is the same
 as running ``hg histedit 836302820282``. If you need plan to push to a
 repository that Mercurial does not detect to be related to the source
 repo, you can add a ``--force`` option.
 """
 
 try:
     import cPickle as pickle
     pickle.dump # import now
 except ImportError:
     import pickle
 import os
 import sys
 
 from mercurial import cmdutil
 from mercurial import discovery
 from mercurial import error
 from mercurial import copies
 from mercurial import context
 from mercurial import hg
 from mercurial import node
 from mercurial import repair
 from mercurial import scmutil
 from mercurial import util
 from mercurial import obsolete
 from mercurial import merge as mergemod
 from mercurial.lock import release
 from mercurial.i18n import _
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 testedwith = 'internal'
 
 # i18n: command names and abbreviations must remain untranslated
 editcomment = _("""# Edit history between %s and %s
 #
 # Commits are listed from least to most recent
 #
 # Commands:
 #  p, pick = use commit
 #  e, edit = use commit, but stop for amending
 #  f, fold = use commit, but combine it with the one above
 #  r, roll = like fold, but discard this commit's description
 #  d, drop = remove commit from history
 #  m, mess = edit message without changing commit content
 #
 """)
 
 def commitfuncfor(repo, src):
     """Build a commit function for the replacement of <src>
 
     This function ensure we apply the same treatment to all changesets.
 
     - Add a 'histedit_source' entry in extra.
 
     Note that fold have its own separated logic because its handling is a bit
     different and not easily factored out of the fold method.
     """
     phasemin = src.phase()
     def commitfunc(**kwargs):
         phasebackup = repo.ui.backupconfig('phases', 'new-commit')
         try:
             repo.ui.setconfig('phases', 'new-commit', phasemin,
                               'histedit')
             extra = kwargs.get('extra', {}).copy()
             extra['histedit_source'] = src.hex()
             kwargs['extra'] = extra
             return repo.commit(**kwargs)
         finally:
             repo.ui.restoreconfig(phasebackup)
     return commitfunc
 
 def applychanges(ui, repo, ctx, opts):
     """Merge changeset from ctx (only) in the current working directory"""
     wcpar = repo.dirstate.parents()[0]
     if ctx.p1().node() == wcpar:
         # edition ar "in place" we do not need to make any merge,
         # just applies changes on parent for edition
         cmdutil.revert(ui, repo, ctx, (wcpar, node.nullid), all=True)
         stats = None
     else:
         try:
             # ui.forcemerge is an internal variable, do not document
             repo.ui.setconfig('ui', 'forcemerge', opts.get('tool', ''),
                               'histedit')
             stats = mergemod.update(repo, ctx.node(), True, True, False,
                                     ctx.p1().node())
         finally:
             repo.ui.setconfig('ui', 'forcemerge', '', 'histedit')
         repo.setparents(wcpar, node.nullid)
         repo.dirstate.write()
         # fix up dirstate for copies and renames
     cmdutil.duplicatecopies(repo, ctx.rev(), ctx.p1().rev())
     return stats
 
 def collapse(repo, first, last, commitopts):
     """collapse the set of revisions from first to last as new one.
 
     Expected commit options are:
         - message
         - date
         - username
     Commit message is edited in all cases.
 
     This function works in memory."""
     ctxs = list(repo.set('%d::%d', first, last))
     if not ctxs:
         return None
     base = first.parents()[0]
 
     # commit a new version of the old changeset, including the update
     # collect all files which might be affected
     files = set()
     for ctx in ctxs:
         files.update(ctx.files())
 
     # Recompute copies (avoid recording a -> b -> a)
     copied = copies.pathcopies(base, last)
 
     # prune files which were reverted by the updates
     def samefile(f):
         if f in last.manifest():
             a = last.filectx(f)
             if f in base.manifest():
                 b = base.filectx(f)
                 return (a.data() == b.data()
                         and a.flags() == b.flags())
             else:
                 return False
         else:
             return f not in base.manifest()
     files = [f for f in files if not samefile(f)]
     # commit version of these files as defined by head
     headmf = last.manifest()
     def filectxfn(repo, ctx, path):
         if path in headmf:
             fctx = last[path]
             flags = fctx.flags()
             mctx = context.memfilectx(repo,
                                       fctx.path(), fctx.data(),
                                       islink='l' in flags,
                                       isexec='x' in flags,
                                       copied=copied.get(path))
             return mctx
-        raise IOError()
+        return None
 
     if commitopts.get('message'):
         message = commitopts['message']
     else:
         message = first.description()
     user = commitopts.get('user')
     date = commitopts.get('date')
     extra = commitopts.get('extra')
 
     parents = (first.p1().node(), first.p2().node())
     editor = None
     if not commitopts.get('rollup'):
         editor = cmdutil.getcommiteditor(edit=True, editform='histedit.fold')
     new = context.memctx(repo,
                          parents=parents,
                          text=message,
                          files=files,
                          filectxfn=filectxfn,
                          user=user,
                          date=date,
                          extra=extra,
                          editor=editor)
     return repo.commitctx(new)
 
 def pick(ui, repo, ctx, ha, opts):
     oldctx = repo[ha]
     if oldctx.parents()[0] == ctx:
         ui.debug('node %s unchanged\n' % ha)
         return oldctx, []
     hg.update(repo, ctx.node())
     stats = applychanges(ui, repo, oldctx, opts)
     if stats and stats[3] > 0:
         raise error.InterventionRequired(_('Fix up the change and run '
                                            'hg histedit --continue'))
     # drop the second merge parent
     commit = commitfuncfor(repo, oldctx)
     n = commit(text=oldctx.description(), user=oldctx.user(),
                date=oldctx.date(), extra=oldctx.extra())
     if n is None:
         ui.warn(_('%s: empty changeset\n')
                      % node.hex(ha))
         return ctx, []
     new = repo[n]
     return new, [(oldctx.node(), (n,))]
 
 
 def edit(ui, repo, ctx, ha, opts):
     oldctx = repo[ha]
     hg.update(repo, ctx.node())
     applychanges(ui, repo, oldctx, opts)
     raise error.InterventionRequired(
         _('Make changes as needed, you may commit or record as needed now.\n'
           'When you are finished, run hg histedit --continue to resume.'))
 
 def rollup(ui, repo, ctx, ha, opts):
     rollupopts = opts.copy()
     rollupopts['rollup'] = True
     return fold(ui, repo, ctx, ha, rollupopts)
 
 def fold(ui, repo, ctx, ha, opts):
     oldctx = repo[ha]
     hg.update(repo, ctx.node())
     stats = applychanges(ui, repo, oldctx, opts)
     if stats and stats[3] > 0:
         raise error.InterventionRequired(
             _('Fix up the change and run hg histedit --continue'))
     n = repo.commit(text='fold-temp-revision %s' % ha, user=oldctx.user(),
                     date=oldctx.date(), extra=oldctx.extra())
     if n is None:
         ui.warn(_('%s: empty changeset')
                      % node.hex(ha))
         return ctx, []
     return finishfold(ui, repo, ctx, oldctx, n, opts, [])
 
 def finishfold(ui, repo, ctx, oldctx, newnode, opts, internalchanges):
     parent = ctx.parents()[0].node()
     hg.update(repo, parent)
     ### prepare new commit data
     commitopts = opts.copy()
     commitopts['user'] = ctx.user()
     # commit message
     if opts.get('rollup'):
         newmessage = ctx.description()
     else:
         newmessage = '\n***\n'.join(
             [ctx.description()] +
             [repo[r].description() for r in internalchanges] +
             [oldctx.description()]) + '\n'
     commitopts['message'] = newmessage
     # date
     commitopts['date'] = max(ctx.date(), oldctx.date())
     extra = ctx.extra().copy()
     # histedit_source
     # note: ctx is likely a temporary commit but that the best we can do here
     #       This is sufficient to solve issue3681 anyway
     extra['histedit_source'] = '%s,%s' % (ctx.hex(), oldctx.hex())
     commitopts['extra'] = extra
     phasebackup = repo.ui.backupconfig('phases', 'new-commit')
     try:
         phasemin = max(ctx.phase(), oldctx.phase())
         repo.ui.setconfig('phases', 'new-commit', phasemin, 'histedit')
         n = collapse(repo, ctx, repo[newnode], commitopts)
     finally:
         repo.ui.restoreconfig(phasebackup)
     if n is None:
         return ctx, []
     hg.update(repo, n)
     replacements = [(oldctx.node(), (newnode,)),
                      (ctx.node(), (n,)),
                      (newnode, (n,)),
                     ]
     for ich in internalchanges:
         replacements.append((ich, (n,)))
     return repo[n], replacements
 
 def drop(ui, repo, ctx, ha, opts):
     return ctx, [(repo[ha].node(), ())]
 
 
 def message(ui, repo, ctx, ha, opts):
     oldctx = repo[ha]
     hg.update(repo, ctx.node())
     stats = applychanges(ui, repo, oldctx, opts)
     if stats and stats[3] > 0:
         raise error.InterventionRequired(
             _('Fix up the change and run hg histedit --continue'))
     message = oldctx.description()
     commit = commitfuncfor(repo, oldctx)
     editor = cmdutil.getcommiteditor(edit=True, editform='histedit.mess')
     new = commit(text=message, user=oldctx.user(), date=oldctx.date(),
                  extra=oldctx.extra(),
                  editor=editor)
     newctx = repo[new]
     if oldctx.node() != newctx.node():
         return newctx, [(oldctx.node(), (new,))]
     # We didn't make an edit, so just indicate no replaced nodes
     return newctx, []
 
 def findoutgoing(ui, repo, remote=None, force=False, opts={}):
     """utility function to find the first outgoing changeset
 
     Used by initialisation code"""
     dest = ui.expandpath(remote or 'default-push', remote or 'default')
     dest, revs = hg.parseurl(dest, None)[:2]
     ui.status(_('comparing with %s\n') % util.hidepassword(dest))
 
     revs, checkout = hg.addbranchrevs(repo, repo, revs, None)
     other = hg.peer(repo, opts, dest)
 
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
 
     outgoing = discovery.findcommonoutgoing(repo, other, revs, force=force)
     if not outgoing.missing:
         raise util.Abort(_('no outgoing ancestors'))
     roots = list(repo.revs("roots(%ln)", outgoing.missing))
     if 1 < len(roots):
         msg = _('there are ambiguous outgoing revisions')
         hint = _('see "hg help histedit" for more detail')
         raise util.Abort(msg, hint=hint)
     return repo.lookup(roots[0])
 
 actiontable = {'p': pick,
                'pick': pick,
                'e': edit,
                'edit': edit,
                'f': fold,
                'fold': fold,
                'r': rollup,
                'roll': rollup,
                'd': drop,
                'drop': drop,
                'm': message,
                'mess': message,
                }
 
 @command('histedit',
     [('', 'commands', '',
       _('Read history edits from the specified file.')),
      ('c', 'continue', False, _('continue an edit already in progress')),
      ('k', 'keep', False,
       _("don't strip old nodes after edit is complete")),
      ('', 'abort', False, _('abort an edit in progress')),
      ('o', 'outgoing', False, _('changesets not found in destination')),
      ('f', 'force', False,
       _('force outgoing even for unrelated repositories')),
      ('r', 'rev', [], _('first revision to be edited'))],
      _("ANCESTOR | --outgoing [URL]"))
 def histedit(ui, repo, *freeargs, **opts):
     """interactively edit changeset history
 
     This command edits changesets between ANCESTOR and the parent of
     the working directory.
 
     With --outgoing, this edits changesets not found in the
     destination repository. If URL of the destination is omitted, the
     'default-push' (or 'default') path will be used.
 
     For safety, this command is aborted, also if there are ambiguous
     outgoing revisions which may confuse users: for example, there are
     multiple branches containing outgoing revisions.
 
     Use "min(outgoing() and ::.)" or similar revset specification
     instead of --outgoing to specify edit target revision exactly in
     such ambiguous situation. See :hg:`help revsets` for detail about
     selecting revisions.
 
     Returns 0 on success, 1 if user intervention is required (not only
     for intentional "edit" command, but also for resolving unexpected
     conflicts).
     """
     lock = wlock = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         _histedit(ui, repo, *freeargs, **opts)
     finally:
         release(lock, wlock)
 
 def _histedit(ui, repo, *freeargs, **opts):
     # TODO only abort if we try and histedit mq patches, not just
     # blanket if mq patches are applied somewhere
     mq = getattr(repo, 'mq', None)
     if mq and mq.applied:
         raise util.Abort(_('source has mq patches applied'))
 
     # basic argument incompatibility processing
     outg = opts.get('outgoing')
     cont = opts.get('continue')
     abort = opts.get('abort')
     force = opts.get('force')
     rules = opts.get('commands', '')
     revs = opts.get('rev', [])
     goal = 'new' # This invocation goal, in new, continue, abort
     if force and not outg:
         raise util.Abort(_('--force only allowed with --outgoing'))
     if cont:
         if util.any((outg, abort, revs, freeargs, rules)):
             raise util.Abort(_('no arguments allowed with --continue'))
         goal = 'continue'
     elif abort:
         if util.any((outg, revs, freeargs, rules)):
             raise util.Abort(_('no arguments allowed with --abort'))
         goal = 'abort'
     else:
         if os.path.exists(os.path.join(repo.path, 'histedit-state')):
             raise util.Abort(_('history edit already in progress, try '
                                '--continue or --abort'))
         if outg:
             if revs:
                 raise util.Abort(_('no revisions allowed with --outgoing'))
             if len(freeargs) > 1:
                 raise util.Abort(
                     _('only one repo argument allowed with --outgoing'))
         else:
             revs.extend(freeargs)
             if len(revs) != 1:
                 raise util.Abort(
                     _('histedit requires exactly one ancestor revision'))
 
 
     if goal == 'continue':
         (parentctxnode, rules, keep, topmost, replacements) = readstate(repo)
         parentctx = repo[parentctxnode]
         parentctx, repl = bootstrapcontinue(ui, repo, parentctx, rules, opts)
         replacements.extend(repl)
     elif goal == 'abort':
         (parentctxnode, rules, keep, topmost, replacements) = readstate(repo)
         mapping, tmpnodes, leafs, _ntm = processreplacement(repo, replacements)
         ui.debug('restore wc to old parent %s\n' % node.short(topmost))
         # check whether we should update away
         parentnodes = [c.node() for c in repo[None].parents()]
         for n in leafs | set([parentctxnode]):
             if n in parentnodes:
                 hg.clean(repo, topmost)
                 break
         else:
             pass
         cleanupnode(ui, repo, 'created', tmpnodes)
         cleanupnode(ui, repo, 'temp', leafs)
         os.unlink(os.path.join(repo.path, 'histedit-state'))
         return
     else:
         cmdutil.checkunfinished(repo)
         cmdutil.bailifchanged(repo)
 
         topmost, empty = repo.dirstate.parents()
         if outg:
             if freeargs:
                 remote = freeargs[0]
             else:
                 remote = None
             root = findoutgoing(ui, repo, remote, force, opts)
         else:
             rr = list(repo.set('roots(%ld)', scmutil.revrange(repo, revs)))
             if len(rr) != 1:
                 raise util.Abort(_('The specified revisions must have '
                     'exactly one common root'))
             root = rr[0].node()
 
         keep = opts.get('keep', False)
         revs = between(repo, root, topmost, keep)
         if not revs:
             raise util.Abort(_('%s is not an ancestor of working directory') %
                              node.short(root))
 
         ctxs = [repo[r] for r in revs]
         if not rules:
             rules = '\n'.join([makedesc(c) for c in ctxs])
             rules += '\n\n'
             rules += editcomment % (node.short(root), node.short(topmost))
             rules = ui.edit(rules, ui.username())
             # Save edit rules in .hg/histedit-last-edit.txt in case
             # the user needs to ask for help after something
             # surprising happens.
             f = open(repo.join('histedit-last-edit.txt'), 'w')
             f.write(rules)
             f.close()
         else:
             if rules == '-':
                 f = sys.stdin
             else:
                 f = open(rules)
             rules = f.read()
             f.close()
         rules = [l for l in (r.strip() for r in rules.splitlines())
                  if l and not l.startswith('#')]
         rules = verifyrules(rules, repo, ctxs)
 
         parentctx = repo[root].parents()[0]
         replacements = []
 
 
     while rules:
         writestate(repo, parentctx.node(), rules, keep, topmost, replacements)
         action, ha = rules.pop(0)
         ui.debug('histedit: processing %s %s\n' % (action, ha))
         actfunc = actiontable[action]
         parentctx, replacement_ = actfunc(ui, repo, parentctx, ha, opts)
         replacements.extend(replacement_)
 
     hg.update(repo, parentctx.node())
 
     mapping, tmpnodes, created, ntm = processreplacement(repo, replacements)
     if mapping:
         for prec, succs in mapping.iteritems():
             if not succs:
                 ui.debug('histedit: %s is dropped\n' % node.short(prec))
             else:
                 ui.debug('histedit: %s is replaced by %s\n' % (
                     node.short(prec), node.short(succs[0])))
                 if len(succs) > 1:
                     m = 'histedit:                            %s'
                     for n in succs[1:]:
                         ui.debug(m % node.short(n))
 
     if not keep:
         if mapping:
             movebookmarks(ui, repo, mapping, topmost, ntm)
             # TODO update mq state
         if obsolete._enabled:
             markers = []
             # sort by revision number because it sound "right"
             for prec in sorted(mapping, key=repo.changelog.rev):
                 succs = mapping[prec]
                 markers.append((repo[prec],
                                 tuple(repo[s] for s in succs)))
             if markers:
                 obsolete.createmarkers(repo, markers)
         else:
             cleanupnode(ui, repo, 'replaced', mapping)
 
     cleanupnode(ui, repo, 'temp', tmpnodes)
     os.unlink(os.path.join(repo.path, 'histedit-state'))
     if os.path.exists(repo.sjoin('undo')):
         os.unlink(repo.sjoin('undo'))
 
 def gatherchildren(repo, ctx):
     # is there any new commit between the expected parent and "."
     #
     # note: does not take non linear new change in account (but previous
     #       implementation didn't used them anyway (issue3655)
     newchildren = [c.node() for c in repo.set('(%d::.)', ctx)]
     if ctx.node() != node.nullid:
         if not newchildren:
             # `ctx` should match but no result. This means that
             # currentnode is not a descendant from ctx.
             msg = _('%s is not an ancestor of working directory')
             hint = _('use "histedit --abort" to clear broken state')
             raise util.Abort(msg % ctx, hint=hint)
         newchildren.pop(0)  # remove ctx
     return newchildren
 
 def bootstrapcontinue(ui, repo, parentctx, rules, opts):
     action, currentnode = rules.pop(0)
     ctx = repo[currentnode]
 
     newchildren = gatherchildren(repo, parentctx)
 
     # Commit dirty working directory if necessary
     new = None
     m, a, r, d = repo.status()[:4]
     if m or a or r or d:
         # prepare the message for the commit to comes
         if action in ('f', 'fold', 'r', 'roll'):
             message = 'fold-temp-revision %s' % currentnode
         else:
             message = ctx.description()
         editopt = action in ('e', 'edit', 'm', 'mess')
         canonaction = {'e': 'edit', 'm': 'mess', 'p': 'pick'}
         editform = 'histedit.%s' % canonaction.get(action, action)
         editor = cmdutil.getcommiteditor(edit=editopt, editform=editform)
         commit = commitfuncfor(repo, ctx)
         new = commit(text=message, user=ctx.user(),
                      date=ctx.date(), extra=ctx.extra(),
                      editor=editor)
         if new is not None:
             newchildren.append(new)
 
     replacements = []
     # track replacements
     if ctx.node() not in newchildren:
         # note: new children may be empty when the changeset is dropped.
         # this happen e.g during conflicting pick where we revert content
         # to parent.
         replacements.append((ctx.node(), tuple(newchildren)))
 
     if action in ('f', 'fold', 'r', 'roll'):
         if newchildren:
             # finalize fold operation if applicable
             if new is None:
                 new = newchildren[-1]
             else:
                 newchildren.pop()  # remove new from internal changes
             foldopts = opts
             if action in ('r', 'roll'):
                 foldopts = foldopts.copy()
                 foldopts['rollup'] = True
             parentctx, repl = finishfold(ui, repo, parentctx, ctx, new,
                                          foldopts, newchildren)
             replacements.extend(repl)
         else:
             # newchildren is empty if the fold did not result in any commit
             # this happen when all folded change are discarded during the
             # merge.
             replacements.append((ctx.node(), (parentctx.node(),)))
     elif newchildren:
         # otherwise update "parentctx" before proceeding to further operation
         parentctx = repo[newchildren[-1]]
     return parentctx, replacements
 
 
 def between(repo, old, new, keep):
     """select and validate the set of revision to edit
 
     When keep is false, the specified set can't have children."""
     ctxs = list(repo.set('%n::%n', old, new))
     if ctxs and not keep:
         if (not obsolete._enabled and
             repo.revs('(%ld::) - (%ld)', ctxs, ctxs)):
             raise util.Abort(_('cannot edit history that would orphan nodes'))
         if repo.revs('(%ld) and merge()', ctxs):
             raise util.Abort(_('cannot edit history that contains merges'))
         root = ctxs[0] # list is already sorted by repo.set
         if not root.phase():
             raise util.Abort(_('cannot edit immutable changeset: %s') % root)
     return [c.node() for c in ctxs]
 
 
 def writestate(repo, parentnode, rules, keep, topmost, replacements):
     fp = open(os.path.join(repo.path, 'histedit-state'), 'w')
     pickle.dump((parentnode, rules, keep, topmost, replacements), fp)
     fp.close()
 
 def readstate(repo):
     """Returns a tuple of (parentnode, rules, keep, topmost, replacements).
     """
     fp = open(os.path.join(repo.path, 'histedit-state'))
     return pickle.load(fp)
 
 
 def makedesc(c):
     """build a initial action line for a ctx `c`
 
     line are in the form:
 
       pick <hash> <rev> <summary>
     """
     summary = ''
     if c.description():
         summary = c.description().splitlines()[0]
     line = 'pick %s %d %s' % (c, c.rev(), summary)
     # trim to 80 columns so it's not stupidly wide in my editor
     return util.ellipsis(line, 80)
 
 def verifyrules(rules, repo, ctxs):
     """Verify that there exists exactly one edit rule per given changeset.
 
     Will abort if there are to many or too few rules, a malformed rule,
     or a rule on a changeset outside of the user-given range.
     """
     parsed = []
     expected = set(str(c) for c in ctxs)
     seen = set()
     for r in rules:
         if ' ' not in r:
             raise util.Abort(_('malformed line "%s"') % r)
         action, rest = r.split(' ', 1)
         ha = rest.strip().split(' ', 1)[0]
         try:
             ha = str(repo[ha])  # ensure its a short hash
         except error.RepoError:
             raise util.Abort(_('unknown changeset %s listed') % ha)
         if ha not in expected:
             raise util.Abort(
                 _('may not use changesets other than the ones listed'))
         if ha in seen:
             raise util.Abort(_('duplicated command for changeset %s') % ha)
         seen.add(ha)
         if action not in actiontable:
             raise util.Abort(_('unknown action "%s"') % action)
         parsed.append([action, ha])
     missing = sorted(expected - seen)  # sort to stabilize output
     if missing:
         raise util.Abort(_('missing rules for changeset %s') % missing[0],
                          hint=_('do you want to use the drop action?'))
     return parsed
 
 def processreplacement(repo, replacements):
     """process the list of replacements to return
 
     1) the final mapping between original and created nodes
     2) the list of temporary node created by histedit
     3) the list of new commit created by histedit"""
     allsuccs = set()
     replaced = set()
     fullmapping = {}
     # initialise basic set
     # fullmapping record all operation recorded in replacement
     for rep in replacements:
         allsuccs.update(rep[1])
         replaced.add(rep[0])
         fullmapping.setdefault(rep[0], set()).update(rep[1])
     new = allsuccs - replaced
     tmpnodes = allsuccs & replaced
     # Reduce content fullmapping  into direct relation between original nodes
     # and final node created during history edition
     # Dropped changeset are replaced by an empty list
     toproceed = set(fullmapping)
     final = {}
     while toproceed:
         for x in list(toproceed):
             succs = fullmapping[x]
             for s in list(succs):
                 if s in toproceed:
                     # non final node with unknown closure
                     # We can't process this now
                     break
                 elif s in final:
                     # non final node, replace with closure
                     succs.remove(s)
                     succs.update(final[s])
             else:
                 final[x] = succs
                 toproceed.remove(x)
     # remove tmpnodes from final mapping
     for n in tmpnodes:
         del final[n]
     # we expect all changes involved in final to exist in the repo
     # turn `final` into list (topologically sorted)
     nm = repo.changelog.nodemap
     for prec, succs in final.items():
         final[prec] = sorted(succs, key=nm.get)
 
     # computed topmost element (necessary for bookmark)
     if new:
         newtopmost = sorted(new, key=repo.changelog.rev)[-1]
     elif not final:
         # Nothing rewritten at all. we won't need `newtopmost`
         # It is the same as `oldtopmost` and `processreplacement` know it
         newtopmost = None
     else:
         # every body died. The newtopmost is the parent of the root.
         newtopmost = repo[sorted(final, key=repo.changelog.rev)[0]].p1().node()
 
     return final, tmpnodes, new, newtopmost
 
 def movebookmarks(ui, repo, mapping, oldtopmost, newtopmost):
     """Move bookmark from old to newly created node"""
     if not mapping:
         # if nothing got rewritten there is not purpose for this function
         return
     moves = []
     for bk, old in sorted(repo._bookmarks.iteritems()):
         if old == oldtopmost:
             # special case ensure bookmark stay on tip.
             #
             # This is arguably a feature and we may only want that for the
             # active bookmark. But the behavior is kept compatible with the old
             # version for now.
             moves.append((bk, newtopmost))
             continue
         base = old
         new = mapping.get(base, None)
         if new is None:
             continue
         while not new:
             # base is killed, trying with parent
             base = repo[base].p1().node()
             new = mapping.get(base, (base,))
             # nothing to move
         moves.append((bk, new[-1]))
     if moves:
         marks = repo._bookmarks
         for mark, new in moves:
             old = marks[mark]
             ui.note(_('histedit: moving bookmarks %s from %s to %s\n')
                     % (mark, node.short(old), node.short(new)))
             marks[mark] = new
         marks.write()
 
 def cleanupnode(ui, repo, name, nodes):
     """strip a group of nodes from the repository
 
     The set of node to strip may contains unknown nodes."""
     ui.debug('should strip %s nodes %s\n' %
              (name, ', '.join([node.short(n) for n in nodes])))
     lock = None
     try:
         lock = repo.lock()
         # Find all node that need to be stripped
         # (we hg %lr instead of %ln to silently ignore unknown item
         nm = repo.changelog.nodemap
         nodes = [n for n in nodes if n in nm]
         roots = [c.node() for c in repo.set("roots(%ln)", nodes)]
         for c in roots:
             # We should process node in reverse order to strip tip most first.
             # but this trigger a bug in changegroup hook.
             # This would reduce bundle overhead
             repair.strip(ui, repo, c)
     finally:
         release(lock)
 
 def summaryhook(ui, repo):
     if not os.path.exists(repo.join('histedit-state')):
         return
     (parentctxnode, rules, keep, topmost, replacements) = readstate(repo)
     if rules:
         # i18n: column positioning for "hg summary"
         ui.write(_('hist:   %s (histedit --continue)\n') %
                  (ui.label(_('%d remaining'), 'histedit.remaining') %
                   len(rules)))
 
 def extsetup(ui):
     cmdutil.summaryhooks.add('histedit', summaryhook)
     cmdutil.unfinishedstates.append(
         ['histedit-state', False, True, _('histedit in progress'),
          _("use 'hg histedit --continue' or 'hg histedit --abort'")])

hgext/largefiles/lfcommands.py

@@ -1,573 +1,573 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''High-level command function for lfconvert, plus the cmdtable.'''
 
 import os, errno
 import shutil
 
 from mercurial import util, match as match_, hg, node, context, error, \
     cmdutil, scmutil, commands
 from mercurial.i18n import _
 from mercurial.lock import release
 
 import lfutil
 import basestore
 
 # -- Commands ----------------------------------------------------------
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 @command('lfconvert',
     [('s', 'size', '',
       _('minimum size (MB) for files to be converted as largefiles'), 'SIZE'),
     ('', 'to-normal', False,
      _('convert from a largefiles repo to a normal repo')),
     ],
     _('hg lfconvert SOURCE DEST [FILE ...]'),
     norepo=True,
     inferrepo=True)
 def lfconvert(ui, src, dest, *pats, **opts):
     '''convert a normal repository to a largefiles repository
 
     Convert repository SOURCE to a new repository DEST, identical to
     SOURCE except that certain files will be converted as largefiles:
     specifically, any file that matches any PATTERN *or* whose size is
     above the minimum size threshold is converted as a largefile. The
     size used to determine whether or not to track a file as a
     largefile is the size of the first version of the file. The
     minimum size can be specified either with --size or in
     configuration as ``largefiles.size``.
 
     After running this command you will need to make sure that
     largefiles is enabled anywhere you intend to push the new
     repository.
 
     Use --to-normal to convert largefiles back to normal files; after
     this, the DEST repository can be used without largefiles at all.'''
 
     if opts['to_normal']:
         tolfile = False
     else:
         tolfile = True
         size = lfutil.getminsize(ui, True, opts.get('size'), default=None)
 
     if not hg.islocal(src):
         raise util.Abort(_('%s is not a local Mercurial repo') % src)
     if not hg.islocal(dest):
         raise util.Abort(_('%s is not a local Mercurial repo') % dest)
 
     rsrc = hg.repository(ui, src)
     ui.status(_('initializing destination %s\n') % dest)
     rdst = hg.repository(ui, dest, create=True)
 
     success = False
     dstwlock = dstlock = None
     try:
         # Lock destination to prevent modification while it is converted to.
         # Don't need to lock src because we are just reading from its history
         # which can't change.
         dstwlock = rdst.wlock()
         dstlock = rdst.lock()
 
         # Get a list of all changesets in the source.  The easy way to do this
         # is to simply walk the changelog, using changelog.nodesbetween().
         # Take a look at mercurial/revlog.py:639 for more details.
         # Use a generator instead of a list to decrease memory usage
         ctxs = (rsrc[ctx] for ctx in rsrc.changelog.nodesbetween(None,
             rsrc.heads())[0])
         revmap = {node.nullid: node.nullid}
         if tolfile:
             lfiles = set()
             normalfiles = set()
             if not pats:
                 pats = ui.configlist(lfutil.longname, 'patterns', default=[])
             if pats:
                 matcher = match_.match(rsrc.root, '', list(pats))
             else:
                 matcher = None
 
             lfiletohash = {}
             for ctx in ctxs:
                 ui.progress(_('converting revisions'), ctx.rev(),
                     unit=_('revision'), total=rsrc['tip'].rev())
                 _lfconvert_addchangeset(rsrc, rdst, ctx, revmap,
                     lfiles, normalfiles, matcher, size, lfiletohash)
             ui.progress(_('converting revisions'), None)
 
             if os.path.exists(rdst.wjoin(lfutil.shortname)):
                 shutil.rmtree(rdst.wjoin(lfutil.shortname))
 
             for f in lfiletohash.keys():
                 if os.path.isfile(rdst.wjoin(f)):
                     os.unlink(rdst.wjoin(f))
                 try:
                     os.removedirs(os.path.dirname(rdst.wjoin(f)))
                 except OSError:
                     pass
 
             # If there were any files converted to largefiles, add largefiles
             # to the destination repository's requirements.
             if lfiles:
                 rdst.requirements.add('largefiles')
                 rdst._writerequirements()
         else:
             for ctx in ctxs:
                 ui.progress(_('converting revisions'), ctx.rev(),
                     unit=_('revision'), total=rsrc['tip'].rev())
                 _addchangeset(ui, rsrc, rdst, ctx, revmap)
 
             ui.progress(_('converting revisions'), None)
         success = True
     finally:
         rdst.dirstate.clear()
         release(dstlock, dstwlock)
         if not success:
             # we failed, remove the new directory
             shutil.rmtree(rdst.root)
 
 def _addchangeset(ui, rsrc, rdst, ctx, revmap):
     # Convert src parents to dst parents
     parents = _convertparents(ctx, revmap)
 
     # Generate list of changed files
     files = _getchangedfiles(ctx, parents)
 
     def getfilectx(repo, memctx, f):
         if lfutil.standin(f) in files:
             # if the file isn't in the manifest then it was removed
             # or renamed, raise IOError to indicate this
             try:
                 fctx = ctx.filectx(lfutil.standin(f))
             except error.LookupError:
-                raise IOError
+                return None
             renamed = fctx.renamed()
             if renamed:
                 renamed = lfutil.splitstandin(renamed[0])
 
             hash = fctx.data().strip()
             path = lfutil.findfile(rsrc, hash)
 
             # If one file is missing, likely all files from this rev are
             if path is None:
                 cachelfiles(ui, rsrc, ctx.node())
                 path = lfutil.findfile(rsrc, hash)
 
                 if path is None:
                     raise util.Abort(
                         _("missing largefile \'%s\' from revision %s")
                          % (f, node.hex(ctx.node())))
 
             data = ''
             fd = None
             try:
                 fd = open(path, 'rb')
                 data = fd.read()
             finally:
                 if fd:
                     fd.close()
             return context.memfilectx(repo, f, data, 'l' in fctx.flags(),
                                       'x' in fctx.flags(), renamed)
         else:
             return _getnormalcontext(repo, ctx, f, revmap)
 
     dstfiles = []
     for file in files:
         if lfutil.isstandin(file):
             dstfiles.append(lfutil.splitstandin(file))
         else:
             dstfiles.append(file)
     # Commit
     _commitcontext(rdst, parents, ctx, dstfiles, getfilectx, revmap)
 
 def _lfconvert_addchangeset(rsrc, rdst, ctx, revmap, lfiles, normalfiles,
         matcher, size, lfiletohash):
     # Convert src parents to dst parents
     parents = _convertparents(ctx, revmap)
 
     # Generate list of changed files
     files = _getchangedfiles(ctx, parents)
 
     dstfiles = []
     for f in files:
         if f not in lfiles and f not in normalfiles:
             islfile = _islfile(f, ctx, matcher, size)
             # If this file was renamed or copied then copy
             # the largefile-ness of its predecessor
             if f in ctx.manifest():
                 fctx = ctx.filectx(f)
                 renamed = fctx.renamed()
                 renamedlfile = renamed and renamed[0] in lfiles
                 islfile |= renamedlfile
                 if 'l' in fctx.flags():
                     if renamedlfile:
                         raise util.Abort(
                             _('renamed/copied largefile %s becomes symlink')
                             % f)
                     islfile = False
             if islfile:
                 lfiles.add(f)
             else:
                 normalfiles.add(f)
 
         if f in lfiles:
             dstfiles.append(lfutil.standin(f))
             # largefile in manifest if it has not been removed/renamed
             if f in ctx.manifest():
                 fctx = ctx.filectx(f)
                 if 'l' in fctx.flags():
                     renamed = fctx.renamed()
                     if renamed and renamed[0] in lfiles:
                         raise util.Abort(_('largefile %s becomes symlink') % f)
 
                 # largefile was modified, update standins
                 m = util.sha1('')
                 m.update(ctx[f].data())
                 hash = m.hexdigest()
                 if f not in lfiletohash or lfiletohash[f] != hash:
                     rdst.wwrite(f, ctx[f].data(), ctx[f].flags())
                     executable = 'x' in ctx[f].flags()
                     lfutil.writestandin(rdst, lfutil.standin(f), hash,
                         executable)
                     lfiletohash[f] = hash
         else:
             # normal file
             dstfiles.append(f)
 
     def getfilectx(repo, memctx, f):
         if lfutil.isstandin(f):
             # if the file isn't in the manifest then it was removed
             # or renamed, raise IOError to indicate this
             srcfname = lfutil.splitstandin(f)
             try:
                 fctx = ctx.filectx(srcfname)
             except error.LookupError:
-                raise IOError
+                return None
             renamed = fctx.renamed()
             if renamed:
                 # standin is always a largefile because largefile-ness
                 # doesn't change after rename or copy
                 renamed = lfutil.standin(renamed[0])
 
             return context.memfilectx(repo, f, lfiletohash[srcfname] + '\n',
                                       'l' in fctx.flags(), 'x' in fctx.flags(),
                                       renamed)
         else:
             return _getnormalcontext(repo, ctx, f, revmap)
 
     # Commit
     _commitcontext(rdst, parents, ctx, dstfiles, getfilectx, revmap)
 
 def _commitcontext(rdst, parents, ctx, dstfiles, getfilectx, revmap):
     mctx = context.memctx(rdst, parents, ctx.description(), dstfiles,
                           getfilectx, ctx.user(), ctx.date(), ctx.extra())
     ret = rdst.commitctx(mctx)
     rdst.setparents(ret)
     revmap[ctx.node()] = rdst.changelog.tip()
 
 # Generate list of changed files
 def _getchangedfiles(ctx, parents):
     files = set(ctx.files())
     if node.nullid not in parents:
         mc = ctx.manifest()
         mp1 = ctx.parents()[0].manifest()
         mp2 = ctx.parents()[1].manifest()
         files |= (set(mp1) | set(mp2)) - set(mc)
         for f in mc:
             if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                 files.add(f)
     return files
 
 # Convert src parents to dst parents
 def _convertparents(ctx, revmap):
     parents = []
     for p in ctx.parents():
         parents.append(revmap[p.node()])
     while len(parents) < 2:
         parents.append(node.nullid)
     return parents
 
 # Get memfilectx for a normal file
 def _getnormalcontext(repo, ctx, f, revmap):
     try:
         fctx = ctx.filectx(f)
     except error.LookupError:
-        raise IOError
+        return None
     renamed = fctx.renamed()
     if renamed:
         renamed = renamed[0]
 
     data = fctx.data()
     if f == '.hgtags':
         data = _converttags (repo.ui, revmap, data)
     return context.memfilectx(repo, f, data, 'l' in fctx.flags(),
                               'x' in fctx.flags(), renamed)
 
 # Remap tag data using a revision map
 def _converttags(ui, revmap, data):
     newdata = []
     for line in data.splitlines():
         try:
             id, name = line.split(' ', 1)
         except ValueError:
             ui.warn(_('skipping incorrectly formatted tag %s\n')
                 % line)
             continue
         try:
             newid = node.bin(id)
         except TypeError:
             ui.warn(_('skipping incorrectly formatted id %s\n')
                 % id)
             continue
         try:
             newdata.append('%s %s\n' % (node.hex(revmap[newid]),
                 name))
         except KeyError:
             ui.warn(_('no mapping for id %s\n') % id)
             continue
     return ''.join(newdata)
 
 def _islfile(file, ctx, matcher, size):
     '''Return true if file should be considered a largefile, i.e.
     matcher matches it or it is larger than size.'''
     # never store special .hg* files as largefiles
     if file == '.hgtags' or file == '.hgignore' or file == '.hgsigs':
         return False
     if matcher and matcher(file):
         return True
     try:
         return ctx.filectx(file).size() >= size * 1024 * 1024
     except error.LookupError:
         return False
 
 def uploadlfiles(ui, rsrc, rdst, files):
     '''upload largefiles to the central store'''
 
     if not files:
         return
 
     store = basestore._openstore(rsrc, rdst, put=True)
 
     at = 0
     ui.debug("sending statlfile command for %d largefiles\n" % len(files))
     retval = store.exists(files)
     files = filter(lambda h: not retval[h], files)
     ui.debug("%d largefiles need to be uploaded\n" % len(files))
 
     for hash in files:
         ui.progress(_('uploading largefiles'), at, unit='largefile',
                     total=len(files))
         source = lfutil.findfile(rsrc, hash)
         if not source:
             raise util.Abort(_('largefile %s missing from store'
                                ' (needs to be uploaded)') % hash)
         # XXX check for errors here
         store.put(source, hash)
         at += 1
     ui.progress(_('uploading largefiles'), None)
 
 def verifylfiles(ui, repo, all=False, contents=False):
     '''Verify that every largefile revision in the current changeset
     exists in the central store.  With --contents, also verify that
     the contents of each local largefile file revision are correct (SHA-1 hash
     matches the revision ID).  With --all, check every changeset in
     this repository.'''
     if all:
         # Pass a list to the function rather than an iterator because we know a
         # list will work.
         revs = range(len(repo))
     else:
         revs = ['.']
 
     store = basestore._openstore(repo)
     return store.verify(revs, contents=contents)
 
 def cachelfiles(ui, repo, node, filelist=None):
     '''cachelfiles ensures that all largefiles needed by the specified revision
     are present in the repository's largefile cache.
 
     returns a tuple (cached, missing).  cached is the list of files downloaded
     by this operation; missing is the list of files that were needed but could
     not be found.'''
     lfiles = lfutil.listlfiles(repo, node)
     if filelist:
         lfiles = set(lfiles) & set(filelist)
     toget = []
 
     for lfile in lfiles:
         try:
             expectedhash = repo[node][lfutil.standin(lfile)].data().strip()
         except IOError, err:
             if err.errno == errno.ENOENT:
                 continue # node must be None and standin wasn't found in wctx
             raise
         if not lfutil.findfile(repo, expectedhash):
             toget.append((lfile, expectedhash))
 
     if toget:
         store = basestore._openstore(repo)
         ret = store.get(toget)
         return ret
 
     return ([], [])
 
 def downloadlfiles(ui, repo, rev=None):
     matchfn = scmutil.match(repo[None],
                             [repo.wjoin(lfutil.shortname)], {})
     def prepare(ctx, fns):
         pass
     totalsuccess = 0
     totalmissing = 0
     if rev != []: # walkchangerevs on empty list would return all revs
         for ctx in cmdutil.walkchangerevs(repo, matchfn, {'rev' : rev},
                                           prepare):
             success, missing = cachelfiles(ui, repo, ctx.node())
             totalsuccess += len(success)
             totalmissing += len(missing)
     ui.status(_("%d additional largefiles cached\n") % totalsuccess)
     if totalmissing > 0:
         ui.status(_("%d largefiles failed to download\n") % totalmissing)
     return totalsuccess, totalmissing
 
 def updatelfiles(ui, repo, filelist=None, printmessage=True,
                  normallookup=False):
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         lfiles = set(lfutil.listlfiles(repo)) | set(lfdirstate)
 
         if filelist is not None:
             filelist = set(filelist)
             lfiles = [f for f in lfiles if f in filelist]
 
         update = {}
         updated, removed = 0, 0
         for lfile in lfiles:
             abslfile = repo.wjoin(lfile)
             absstandin = repo.wjoin(lfutil.standin(lfile))
             if os.path.exists(absstandin):
                 if (os.path.exists(absstandin + '.orig') and
                     os.path.exists(abslfile)):
                     shutil.copyfile(abslfile, abslfile + '.orig')
                     util.unlinkpath(absstandin + '.orig')
                 expecthash = lfutil.readstandin(repo, lfile)
                 if (expecthash != '' and
                     (not os.path.exists(abslfile) or
                      expecthash != lfutil.hashfile(abslfile))):
                     if lfile not in repo[None]: # not switched to normal file
                         util.unlinkpath(abslfile, ignoremissing=True)
                     # use normallookup() to allocate entry in largefiles
                     # dirstate, because lack of it misleads
                     # lfilesrepo.status() into recognition that such cache
                     # missing files are REMOVED.
                     lfdirstate.normallookup(lfile)
                     update[lfile] = expecthash
             else:
                 # Remove lfiles for which the standin is deleted, unless the
                 # lfile is added to the repository again. This happens when a
                 # largefile is converted back to a normal file: the standin
                 # disappears, but a new (normal) file appears as the lfile.
                 if (os.path.exists(abslfile) and
                     repo.dirstate.normalize(lfile) not in repo[None]):
                     util.unlinkpath(abslfile)
                     removed += 1
 
         # largefile processing might be slow and be interrupted - be prepared
         lfdirstate.write()
 
         if lfiles:
             if printmessage:
                 ui.status(_('getting changed largefiles\n'))
             cachelfiles(ui, repo, None, lfiles)
 
         for lfile in lfiles:
             update1 = 0
 
             expecthash = update.get(lfile)
             if expecthash:
                 if not lfutil.copyfromcache(repo, expecthash, lfile):
                     # failed ... but already removed and set to normallookup
                     continue
                 # Synchronize largefile dirstate to the last modified
                 # time of the file
                 lfdirstate.normal(lfile)
                 update1 = 1
 
             # copy the state of largefile standin from the repository's
             # dirstate to its state in the lfdirstate.
             abslfile = repo.wjoin(lfile)
             absstandin = repo.wjoin(lfutil.standin(lfile))
             if os.path.exists(absstandin):
                 mode = os.stat(absstandin).st_mode
                 if mode != os.stat(abslfile).st_mode:
                     os.chmod(abslfile, mode)
                     update1 = 1
 
             updated += update1
 
             lfutil.synclfdirstate(repo, lfdirstate, lfile, normallookup)
 
         if filelist is not None:
             # If "local largefile" is chosen at file merging, it is
             # not listed in "filelist" (= dirstate syncing is
             # omitted), because the standin file is not changed before and
             # after merging.
             # But the status of such files may have to be changed by
             # merging. For example, locally modified ("M") largefile
             # has to become re-added("A"), if it is "normal" file in
             # the target revision of linear-merging.
             for lfile in lfdirstate:
                 if lfile not in filelist:
                     lfutil.synclfdirstate(repo, lfdirstate, lfile, True)
 
         lfdirstate.write()
         if printmessage and lfiles:
             ui.status(_('%d largefiles updated, %d removed\n') % (updated,
                 removed))
     finally:
         wlock.release()
 
 @command('lfpull',
     [('r', 'rev', [], _('pull largefiles for these revisions'))
     ] + commands.remoteopts,
     _('-r REV... [-e CMD] [--remotecmd CMD] [SOURCE]'))
 def lfpull(ui, repo, source="default", **opts):
     """pull largefiles for the specified revisions from the specified source
 
     Pull largefiles that are referenced from local changesets but missing
     locally, pulling from a remote repository to the local cache.
 
     If SOURCE is omitted, the 'default' path will be used.
     See :hg:`help urls` for more information.
 
     .. container:: verbose
 
       Some examples:
 
       - pull largefiles for all branch heads::
 
           hg lfpull -r "head() and not closed()"
 
       - pull largefiles on the default branch::
 
           hg lfpull -r "branch(default)"
     """
     repo.lfpullsource = source
 
     revs = opts.get('rev', [])
     if not revs:
         raise util.Abort(_('no revisions specified'))
     revs = scmutil.revrange(repo, revs)
 
     numcached = 0
     for rev in revs:
         ui.note(_('pulling largefiles for revision %s\n') % rev)
         (cached, missing) = cachelfiles(ui, repo, rev)
         numcached += len(cached)
     ui.status(_("%d largefiles cached\n") % numcached)

mercurial/cmdutil.py

@@ -1,2725 +1,2725 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # 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 node import hex, nullid, nullrev, short
 from i18n import _
 import os, sys, errno, re, tempfile
 import util, scmutil, templater, patch, error, templatekw, revlog, copies
 import match as matchmod
 import context, repair, graphmod, revset, phases, obsolete, pathutil
 import changelog
 import bookmarks
 import lock as lockmod
 
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "^log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     for e in keys:
         aliases = parsealiases(e)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith("debug") or found.startswith("debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = choice.keys()
         clist.sort()
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return choice.values()[0]
 
     raise error.UnknownCommand(cmd)
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def bailifchanged(repo):
     if repo.dirstate.p2() != nullid:
         raise util.Abort(_('outstanding uncommitted merge'))
     modified, added, removed, deleted = repo.status()[:4]
     if modified or added or removed or deleted:
         raise util.Abort(_('uncommitted changes'))
     ctx = repo[None]
     for s in sorted(ctx.substate):
         if ctx.sub(s).dirty():
             raise util.Abort(_("uncommitted changes in subrepo %s") % s)
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
     message = opts.get('message')
     logfile = opts.get('logfile')
 
     if message and logfile:
         raise util.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if logfile == '-':
                 message = ui.fin.read()
             else:
                 message = '\n'.join(util.readfile(logfile).splitlines())
         except IOError, inst:
             raise util.Abort(_("can't read commit message '%s': %s") %
                              (logfile, inst.strerror))
     return message
 
 def mergeeditform(ctxorbool, baseform):
     """build appropriate editform from ctxorbool and baseform
 
     'cxtorbool' is one of a ctx to be committed, or a bool whether
     merging is committed.
 
     This returns editform 'baseform' with '.merge' if merging is
     committed, or one with '.normal' suffix otherwise.
     """
     if isinstance(ctxorbool, bool):
         if ctxorbool:
             return baseform + ".merge"
     elif 1 < len(ctxorbool.parents()):
         return baseform + ".merge"
 
     return baseform + ".normal"
 
 def getcommiteditor(edit=False, finishdesc=None, extramsg=None,
                     editform='', **opts):
     """get appropriate commit message editor according to '--edit' option
 
     'finishdesc' is a function to be called with edited commit message
     (= 'description' of the new changeset) just after editing, but
     before checking empty-ness. It should return actual text to be
     stored into history. This allows to change description before
     storing.
 
     'extramsg' is a extra message to be shown in the editor instead of
     'Leave message empty to abort commit' line. 'HG: ' prefix and EOL
     is automatically added.
 
     'editform' is a dot-separated list of names, to distinguish
     the purpose of commit text editing.
 
     'getcommiteditor' returns 'commitforceeditor' regardless of
     'edit', if one of 'finishdesc' or 'extramsg' is specified, because
     they are specific for usage in MQ.
     """
     if edit or finishdesc or extramsg:
         return lambda r, c, s: commitforceeditor(r, c, s,
                                                  finishdesc=finishdesc,
                                                  extramsg=extramsg,
                                                  editform=editform)
     elif editform:
         return lambda r, c, s: commiteditor(r, c, s, editform=editform)
     else:
         return commiteditor
 
 def loglimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get('limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise util.Abort(_('limit must be a positive integer'))
         if limit <= 0:
             raise util.Abort(_('limit must be positive'))
     else:
         limit = None
     return limit
 
 def makefilename(repo, pat, node, desc=None,
                   total=None, seqno=None, revwidth=None, pathname=None):
     node_expander = {
         'H': lambda: hex(node),
         'R': lambda: str(repo.changelog.rev(node)),
         'h': lambda: short(node),
         'm': lambda: re.sub('[^\w]', '_', str(desc))
         }
     expander = {
         '%': lambda: '%',
         'b': lambda: os.path.basename(repo.root),
         }
 
     try:
         if node:
             expander.update(node_expander)
         if node:
             expander['r'] = (lambda:
                     str(repo.changelog.rev(node)).zfill(revwidth or 0))
         if total is not None:
             expander['N'] = lambda: str(total)
         if seqno is not None:
             expander['n'] = lambda: str(seqno)
         if total is not None and seqno is not None:
             expander['n'] = lambda: str(seqno).zfill(len(str(total)))
         if pathname is not None:
             expander['s'] = lambda: os.path.basename(pathname)
             expander['d'] = lambda: os.path.dirname(pathname) or '.'
             expander['p'] = lambda: pathname
 
         newname = []
         patlen = len(pat)
         i = 0
         while i < patlen:
             c = pat[i]
             if c == '%':
                 i += 1
                 c = pat[i]
                 c = expander[c]()
             newname.append(c)
             i += 1
         return ''.join(newname)
     except KeyError, inst:
         raise util.Abort(_("invalid format spec '%%%s' in output filename") %
                          inst.args[0])
 
 def makefileobj(repo, pat, node=None, desc=None, total=None,
                 seqno=None, revwidth=None, mode='wb', modemap=None,
                 pathname=None):
 
     writable = mode not in ('r', 'rb')
 
     if not pat or pat == '-':
         fp = writable and repo.ui.fout or repo.ui.fin
         if util.safehasattr(fp, 'fileno'):
             return os.fdopen(os.dup(fp.fileno()), mode)
         else:
             # if this fp can't be duped properly, return
             # a dummy object that can be closed
             class wrappedfileobj(object):
                 noop = lambda x: None
                 def __init__(self, f):
                     self.f = f
                 def __getattr__(self, attr):
                     if attr == 'close':
                         return self.noop
                     else:
                         return getattr(self.f, attr)
 
             return wrappedfileobj(fp)
     if util.safehasattr(pat, 'write') and writable:
         return pat
     if util.safehasattr(pat, 'read') and 'r' in mode:
         return pat
     fn = makefilename(repo, pat, node, desc, total, seqno, revwidth, pathname)
     if modemap is not None:
         mode = modemap.get(fn, mode)
         if mode == 'wb':
             modemap[fn] = 'ab'
     return open(fn, mode)
 
 def openrevlog(repo, cmd, file_, opts):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts['changelog']
     mf = opts['manifest']
     msg = None
     if cl and mf:
         msg = _('cannot specify --changelog and --manifest at the same time')
     elif cl or mf:
         if file_:
             msg = _('cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _('cannot specify --changelog or --manifest '
                     'without a repository')
     if msg:
         raise util.Abort(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.unfiltered().changelog
         elif mf:
             r = repo.manifest
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
     if not r:
         if not file_:
             raise error.CommandError(cmd, _('invalid arguments'))
         if not os.path.isfile(file_):
             raise util.Abort(_("revlog '%s' not found") % file_)
         r = revlog.revlog(scmutil.opener(os.getcwd(), audit=False),
                           file_[:-2] + ".i")
     return r
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get("after")
     dryrun = opts.get("dry_run")
     wctx = repo[None]
 
     def walkpat(pat):
         srcs = []
         badstates = after and '?' or '?r'
         m = scmutil.match(repo[None], [pat], opts, globbed=True)
         for abs in repo.walk(m):
             state = repo.dirstate[abs]
             rel = m.rel(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
                 if exact and state == 'r':
                     ui.warn(_('%s: not copying - file has been marked for'
                               ' remove\n') % rel)
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if '/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit('/', 1)
             abstarget = repo.dirstate.normalize(abspath) + '/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(_('%s: not overwriting - %s collides with %s\n') %
                     (reltarget, repo.pathto(abssrc, cwd),
                      repo.pathto(prevsrc, cwd)))
             return
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if (repo.dirstate.normalize(abssrc) ==
                 repo.dirstate.normalize(abstarget)):
                 if not rename:
                     ui.warn(_("%s: can't copy - same file\n") % reltarget)
                     return
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in 'mn':
             if not opts['force']:
                 ui.warn(_('%s: not overwriting - file exists\n') %
                         reltarget)
                 return
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(_('%s: not recording move - %s does not exist\n') %
                             (relsrc, reltarget))
                 else:
                     ui.warn(_('%s: not recording copy - %s does not exist\n') %
                             (relsrc, reltarget))
                 return
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or '.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + "~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     util.copyfile(src, target)
                 srcexists = True
             except IOError, inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working copy\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, inst.strerror))
                     return True # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_('moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_('copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(ui, repo, wctx, abssrc, abstarget,
                              dryrun=dryrun, cwd=cwd)
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 util.unlinkpath(repo.wjoin(abssrc))
             wctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(os.sep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(os.sep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(os.sep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest,
                                              util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(dest,
                                         os.path.basename(util.localpath(p)))
                 else:
                     res = lambda p: dest
         return res
 
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise util.Abort(_('no source or destination specified'))
     if len(pats) == 1:
         raise util.Abort(_('no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise util.Abort(_('with multiple sources, destination must be an '
                                'existing directory'))
         if util.endswithsep(dest):
             raise util.Abort(_('destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise util.Abort(_('no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     if errors:
         ui.warn(_('(consider using --after)\n'))
 
     return errors != 0
 
 def service(opts, parentfn=None, initfn=None, runfn=None, logfile=None,
     runargs=None, appendpid=False):
     '''Run a command as a service.'''
 
     def writepid(pid):
         if opts['pid_file']:
             mode = appendpid and 'a' or 'w'
             fp = open(opts['pid_file'], mode)
             fp.write(str(pid) + '\n')
             fp.close()
 
     if opts['daemon'] and not opts['daemon_pipefds']:
         # Signal child process startup with file removal
         lockfd, lockpath = tempfile.mkstemp(prefix='hg-service-')
         os.close(lockfd)
         try:
             if not runargs:
                 runargs = util.hgcmd() + sys.argv[1:]
             runargs.append('--daemon-pipefds=%s' % lockpath)
             # Don't pass --cwd to the child process, because we've already
             # changed directory.
             for i in xrange(1, len(runargs)):
                 if runargs[i].startswith('--cwd='):
                     del runargs[i]
                     break
                 elif runargs[i].startswith('--cwd'):
                     del runargs[i:i + 2]
                     break
             def condfn():
                 return not os.path.exists(lockpath)
             pid = util.rundetached(runargs, condfn)
             if pid < 0:
                 raise util.Abort(_('child process failed to start'))
             writepid(pid)
         finally:
             try:
                 os.unlink(lockpath)
             except OSError, e:
                 if e.errno != errno.ENOENT:
                     raise
         if parentfn:
             return parentfn(pid)
         else:
             return
 
     if initfn:
         initfn()
 
     if not opts['daemon']:
         writepid(os.getpid())
 
     if opts['daemon_pipefds']:
         lockpath = opts['daemon_pipefds']
         try:
             os.setsid()
         except AttributeError:
             pass
         os.unlink(lockpath)
         util.hidewindow()
         sys.stdout.flush()
         sys.stderr.flush()
 
         nullfd = os.open(os.devnull, os.O_RDWR)
         logfilefd = nullfd
         if logfile:
             logfilefd = os.open(logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND)
         os.dup2(nullfd, 0)
         os.dup2(logfilefd, 1)
         os.dup2(logfilefd, 2)
         if nullfd not in (0, 1, 2):
             os.close(nullfd)
         if logfile and logfilefd not in (0, 1, 2):
             os.close(logfilefd)
 
     if runfn:
         return runfn()
 
 def tryimportone(ui, repo, hunk, parents, opts, msgs, updatefunc):
     """Utility function used by commands.import to import a single patch
 
     This function is explicitly defined here to help the evolve extension to
     wrap this part of the import logic.
 
     The API is currently a bit ugly because it a simple code translation from
     the import command. Feel free to make it better.
 
     :hunk: a patch (as a binary string)
     :parents: nodes that will be parent of the created commit
     :opts: the full dict of option passed to the import command
     :msgs: list to save commit message to.
            (used in case we need to save it when failing)
     :updatefunc: a function that update a repo to a given node
                  updatefunc(<repo>, <node>)
     """
     tmpname, message, user, date, branch, nodeid, p1, p2 = \
         patch.extract(ui, hunk)
 
     update = not opts.get('bypass')
     strip = opts["strip"]
     sim = float(opts.get('similarity') or 0)
     if not tmpname:
         return (None, None, False)
     msg = _('applied to working directory')
 
     rejects = False
 
     try:
         cmdline_message = logmessage(ui, opts)
         if cmdline_message:
             # pickup the cmdline msg
             message = cmdline_message
         elif message:
             # pickup the patch msg
             message = message.strip()
         else:
             # launch the editor
             message = None
         ui.debug('message:\n%s\n' % message)
 
         if len(parents) == 1:
             parents.append(repo[nullid])
         if opts.get('exact'):
             if not nodeid or not p1:
                 raise util.Abort(_('not a Mercurial patch'))
             p1 = repo[p1]
             p2 = repo[p2 or nullid]
         elif p2:
             try:
                 p1 = repo[p1]
                 p2 = repo[p2]
                 # Without any options, consider p2 only if the
                 # patch is being applied on top of the recorded
                 # first parent.
                 if p1 != parents[0]:
                     p1 = parents[0]
                     p2 = repo[nullid]
             except error.RepoError:
                 p1, p2 = parents
         else:
             p1, p2 = parents
 
         n = None
         if update:
             if p1 != parents[0]:
                 updatefunc(repo, p1.node())
             if p2 != parents[1]:
                 repo.setparents(p1.node(), p2.node())
 
             if opts.get('exact') or opts.get('import_branch'):
                 repo.dirstate.setbranch(branch or 'default')
 
             partial = opts.get('partial', False)
             files = set()
             try:
                 patch.patch(ui, repo, tmpname, strip=strip, files=files,
                             eolmode=None, similarity=sim / 100.0)
             except patch.PatchError, e:
                 if not partial:
                     raise util.Abort(str(e))
                 if partial:
                     rejects = True
 
             files = list(files)
             if opts.get('no_commit'):
                 if message:
                     msgs.append(message)
             else:
                 if opts.get('exact') or p2:
                     # If you got here, you either use --force and know what
                     # you are doing or used --exact or a merge patch while
                     # being updated to its first parent.
                     m = None
                 else:
                     m = scmutil.matchfiles(repo, files or [])
                 editform = mergeeditform(repo[None], 'import.normal')
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform=editform, **opts)
                 n = repo.commit(message, opts.get('user') or user,
                                 opts.get('date') or date, match=m,
                                 editor=editor, force=partial)
         else:
             if opts.get('exact') or opts.get('import_branch'):
                 branch = branch or 'default'
             else:
                 branch = p1.branch()
             store = patch.filestore()
             try:
                 files = set()
                 try:
                     patch.patchrepo(ui, repo, p1, store, tmpname, strip,
                                     files, eolmode=None)
                 except patch.PatchError, e:
                     raise util.Abort(str(e))
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform='import.bypass')
                 memctx = context.makememctx(repo, (p1.node(), p2.node()),
                                             message,
                                             opts.get('user') or user,
                                             opts.get('date') or date,
                                             branch, files, store,
                                             editor=editor)
                 n = memctx.commit()
             finally:
                 store.close()
         if opts.get('exact') and hex(n) != nodeid:
             raise util.Abort(_('patch is damaged or loses information'))
         if n:
             # i18n: refers to a short changeset id
             msg = _('created %s') % short(n)
         return (msg, n, rejects)
     finally:
         os.unlink(tmpname)
 
 def export(repo, revs, template='hg-%h.patch', fp=None, switch_parent=False,
            opts=None):
     '''export changesets as hg patches.'''
 
     total = len(revs)
     revwidth = max([len(str(rev)) for rev in revs])
     filemode = {}
 
     def single(rev, seqno, fp):
         ctx = repo[rev]
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()
         if switch_parent:
             parents.reverse()
         prev = (parents and parents[0]) or nullid
 
         shouldclose = False
         if not fp and len(template) > 0:
             desc_lines = ctx.description().rstrip().split('\n')
             desc = desc_lines[0]    #Commit always has a first line.
             fp = makefileobj(repo, template, node, desc=desc, total=total,
                              seqno=seqno, revwidth=revwidth, mode='wb',
                              modemap=filemode)
             if fp != template:
                 shouldclose = True
         if fp and fp != sys.stdout and util.safehasattr(fp, 'name'):
             repo.ui.note("%s\n" % fp.name)
 
         if not fp:
             write = repo.ui.write
         else:
             def write(s, **kw):
                 fp.write(s)
 
 
         write("# HG changeset patch\n")
         write("# User %s\n" % ctx.user())
         write("# Date %d %d\n" % ctx.date())
         write("#      %s\n" % util.datestr(ctx.date()))
         if branch and branch != 'default':
             write("# Branch %s\n" % branch)
         write("# Node ID %s\n" % hex(node))
         write("# Parent  %s\n" % hex(prev))
         if len(parents) > 1:
             write("# Parent  %s\n" % hex(parents[1]))
         write(ctx.description().rstrip())
         write("\n\n")
 
         for chunk, label in patch.diffui(repo, prev, node, opts=opts):
             write(chunk, label=label)
 
         if shouldclose:
             fp.close()
 
     for seqno, rev in enumerate(revs):
         single(rev, seqno + 1, fp)
 
 def diffordiffstat(ui, repo, diffopts, node1, node2, match,
                    changes=None, stat=False, fp=None, prefix='',
                    listsubrepos=False):
     '''show diff or diffstat.'''
     if fp is None:
         write = ui.write
     else:
         def write(s, **kw):
             fp.write(s)
 
     if stat:
         diffopts = diffopts.copy(context=0)
         width = 80
         if not ui.plain():
             width = ui.termwidth()
         chunks = patch.diff(repo, node1, node2, match, changes, diffopts,
                             prefix=prefix)
         for chunk, label in patch.diffstatui(util.iterlines(chunks),
                                              width=width,
                                              git=diffopts.git):
             write(chunk, label=label)
     else:
         for chunk, label in patch.diffui(repo, node1, node2, match,
                                          changes, diffopts, prefix=prefix):
             write(chunk, label=label)
 
     if listsubrepos:
         ctx1 = repo[node1]
         ctx2 = repo[node2]
         for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
             tempnode2 = node2
             try:
                 if node2 is not None:
                     tempnode2 = ctx2.substate[subpath][1]
             except KeyError:
                 # A subrepo that existed in node1 was deleted between node1 and
                 # node2 (inclusive). Thus, ctx2's substate won't contain that
                 # subpath. The best we can do is to ignore it.
                 tempnode2 = None
             submatch = matchmod.narrowmatcher(subpath, match)
             sub.diff(ui, diffopts, tempnode2, submatch, changes=changes,
                      stat=stat, fp=fp, prefix=prefix)
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, patch, diffopts, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.patch = patch
         self.diffopts = diffopts
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
 
     def flush(self, rev):
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
             return 1
         return 0
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, matchfn=None, **props):
         if self.buffered:
             self.ui.pushbuffer()
             self._show(ctx, copies, matchfn, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer(labeled=True)
         else:
             self._show(ctx, copies, matchfn, props)
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         rev = ctx.rev()
 
         if self.ui.quiet:
             self.ui.write("%d:%s\n" % (rev, short(changenode)),
                           label='log.node')
             return
 
         log = self.repo.changelog
         date = util.datestr(ctx.date())
 
         hexfunc = self.ui.debugflag and hex or short
 
         parents = [(p, hexfunc(log.node(p)))
                    for p in self._meaningful_parentrevs(log, rev)]
 
         # i18n: column positioning for "hg log"
         self.ui.write(_("changeset:   %d:%s\n") % (rev, hexfunc(changenode)),
                       label='log.changeset changeset.%s' % ctx.phasestr())
 
         branch = ctx.branch()
         # don't show the default branch name
         if branch != 'default':
             # i18n: column positioning for "hg log"
             self.ui.write(_("branch:      %s\n") % branch,
                           label='log.branch')
         for bookmark in self.repo.nodebookmarks(changenode):
             # i18n: column positioning for "hg log"
             self.ui.write(_("bookmark:    %s\n") % bookmark,
                     label='log.bookmark')
         for tag in self.repo.nodetags(changenode):
             # i18n: column positioning for "hg log"
             self.ui.write(_("tag:         %s\n") % tag,
                           label='log.tag')
         if self.ui.debugflag and ctx.phase():
             # i18n: column positioning for "hg log"
             self.ui.write(_("phase:       %s\n") % _(ctx.phasestr()),
                           label='log.phase')
         for parent in parents:
             # i18n: column positioning for "hg log"
             self.ui.write(_("parent:      %d:%s\n") % parent,
                           label='log.parent changeset.%s' % ctx.phasestr())
 
         if self.ui.debugflag:
             mnode = ctx.manifestnode()
             # i18n: column positioning for "hg log"
             self.ui.write(_("manifest:    %d:%s\n") %
                           (self.repo.manifest.rev(mnode), hex(mnode)),
                           label='ui.debug log.manifest')
         # i18n: column positioning for "hg log"
         self.ui.write(_("user:        %s\n") % ctx.user(),
                       label='log.user')
         # i18n: column positioning for "hg log"
         self.ui.write(_("date:        %s\n") % date,
                       label='log.date')
 
         if self.ui.debugflag:
             files = self.repo.status(log.parents(changenode)[0], changenode)[:3]
             for key, value in zip([# i18n: column positioning for "hg log"
                                    _("files:"),
                                    # i18n: column positioning for "hg log"
                                    _("files+:"),
                                    # i18n: column positioning for "hg log"
                                    _("files-:")], files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)),
                                   label='ui.debug log.files')
         elif ctx.files() and self.ui.verbose:
             # i18n: column positioning for "hg log"
             self.ui.write(_("files:       %s\n") % " ".join(ctx.files()),
                           label='ui.note log.files')
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             # i18n: column positioning for "hg log"
             self.ui.write(_("copies:      %s\n") % ' '.join(copies),
                           label='ui.note log.copies')
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')),
                               label='ui.debug log.extra')
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"),
                               label='ui.note log.description')
                 self.ui.write(description,
                               label='ui.note log.description')
                 self.ui.write("\n\n")
             else:
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0],
                               label='log.summary')
         self.ui.write("\n")
 
         self.showpatch(changenode, matchfn)
 
     def showpatch(self, node, matchfn):
         if not matchfn:
             matchfn = self.patch
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.diffopts(self.ui, self.diffopts)
             prev = self.repo.changelog.parents(node)[0]
             if stat:
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
             if diff:
                 if stat:
                     self.ui.write("\n")
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
             self.ui.write("\n")
 
     def _meaningful_parentrevs(self, log, rev):
         """Return list of meaningful (or all if debug) parentrevs for rev.
 
         For merges (two non-nullrev revisions) both parents are meaningful.
         Otherwise the first parent revision is considered meaningful if it
         is not the preceding revision.
         """
         parents = log.parentrevs(rev)
         if not self.ui.debugflag and parents[1] == nullrev:
             if parents[0] >= rev - 1:
                 parents = []
             else:
                 parents = [parents[0]]
         return parents
 
 
 class changeset_templater(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, patch, diffopts, tmpl, mapfile, buffered):
         changeset_printer.__init__(self, ui, repo, patch, diffopts, buffered)
         formatnode = ui.debugflag and (lambda x: x) or (lambda x: x[:12])
         defaulttempl = {
             'parent': '{rev}:{node|formatnode} ',
             'manifest': '{rev}:{node|formatnode}',
             'file_copy': '{name} ({source})',
             'extra': '{key}={value|stringescape}'
             }
         # filecopy is preserved for compatibility reasons
         defaulttempl['filecopy'] = defaulttempl['file_copy']
         self.t = templater.templater(mapfile, {'formatnode': formatnode},
                                      cache=defaulttempl)
         if tmpl:
             self.t.cache['changeset'] = tmpl
 
         self.cache = {}
 
     def _meaningful_parentrevs(self, ctx):
         """Return list of meaningful (or all if debug) parentrevs for rev.
         """
         parents = ctx.parents()
         if len(parents) > 1:
             return parents
         if self.ui.debugflag:
             return [parents[0], self.repo['null']]
         if parents[0].rev() >= ctx.rev() - 1:
             return []
         return parents
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
 
         showlist = templatekw.showlist
 
         # showparents() behaviour depends on ui trace level which
         # causes unexpected behaviours at templating level and makes
         # it harder to extract it in a standalone function. Its
         # behaviour cannot be changed so leave it here for now.
         def showparents(**args):
             ctx = args['ctx']
             parents = [[('rev', p.rev()), ('node', p.hex())]
                        for p in self._meaningful_parentrevs(ctx)]
             return showlist('parent', parents, **args)
 
         props = props.copy()
         props.update(templatekw.keywords)
         props['parents'] = showparents
         props['templ'] = self.t
         props['ctx'] = ctx
         props['repo'] = self.repo
         props['revcache'] = {'copies': copies}
         props['cache'] = self.cache
 
         # find correct templates for current mode
 
         tmplmodes = [
             (True, None),
             (self.ui.verbose, 'verbose'),
             (self.ui.quiet, 'quiet'),
             (self.ui.debugflag, 'debug'),
         ]
 
         types = {'header': '', 'footer':'', 'changeset': 'changeset'}
         for mode, postfix  in tmplmodes:
             for type in types:
                 cur = postfix and ('%s_%s' % (type, postfix)) or type
                 if mode and cur in self.t:
                     types[type] = cur
 
         try:
 
             # write header
             if types['header']:
                 h = templater.stringify(self.t(types['header'], **props))
                 if self.buffered:
                     self.header[ctx.rev()] = h
                 else:
                     if self.lastheader != h:
                         self.lastheader = h
                         self.ui.write(h)
 
             # write changeset metadata, then patch if requested
             key = types['changeset']
             self.ui.write(templater.stringify(self.t(key, **props)))
             self.showpatch(ctx.node(), matchfn)
 
             if types['footer']:
                 if not self.footer:
                     self.footer = templater.stringify(self.t(types['footer'],
                                                       **props))
 
         except KeyError, inst:
             msg = _("%s: no key named '%s'")
             raise util.Abort(msg % (self.t.mapfile, inst.args[0]))
         except SyntaxError, inst:
             raise util.Abort('%s: %s' % (self.t.mapfile, inst.args[0]))
 
 def gettemplate(ui, tmpl, style):
     """
     Find the template matching the given template spec or style.
     """
 
     # ui settings
     if not tmpl and not style:
         tmpl = ui.config('ui', 'logtemplate')
         if tmpl:
             try:
                 tmpl = templater.parsestring(tmpl)
             except SyntaxError:
                 tmpl = templater.parsestring(tmpl, quoted=False)
             return tmpl, None
         else:
             style = util.expandpath(ui.config('ui', 'style', ''))
 
     if style:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = (templater.templatepath('map-cmdline.' + mapfile)
                        or templater.templatepath(mapfile))
             if mapname:
                 mapfile = mapname
         return None, mapfile
 
     if not tmpl:
         return None, None
 
     # looks like a literal template?
     if '{' in tmpl:
         return tmpl, None
 
     # perhaps a stock style?
     if not os.path.split(tmpl)[0]:
         mapname = (templater.templatepath('map-cmdline.' + tmpl)
                    or templater.templatepath(tmpl))
         if mapname and os.path.isfile(mapname):
             return None, mapname
 
     # perhaps it's a reference to [templates]
     t = ui.config('templates', tmpl)
     if t:
         try:
             tmpl = templater.parsestring(t)
         except SyntaxError:
             tmpl = templater.parsestring(t, quoted=False)
         return tmpl, None
 
     if tmpl == 'list':
         ui.write(_("available styles: %s\n") % templater.stylelist())
         raise util.Abort(_("specify a template"))
 
     # perhaps it's a path to a map or a template
     if ('/' in tmpl or '\\' in tmpl) and os.path.isfile(tmpl):
         # is it a mapfile for a style?
         if os.path.basename(tmpl).startswith("map-"):
             return None, os.path.realpath(tmpl)
         tmpl = open(tmpl).read()
         return tmpl, None
 
     # constant string?
     return tmpl, None
 
 def show_changeset(ui, repo, opts, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changeset_printer() is done.
     """
     # options
     patch = None
     if opts.get('patch') or opts.get('stat'):
         patch = scmutil.matchall(repo)
 
     tmpl, mapfile = gettemplate(ui, opts.get('template'), opts.get('style'))
 
     if not tmpl and not mapfile:
         return changeset_printer(ui, repo, patch, opts, buffered)
 
     try:
         t = changeset_templater(ui, repo, patch, opts, tmpl, mapfile, buffered)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
     return t
 
 def showmarker(ui, marker):
     """utility function to display obsolescence marker in a readable way
 
     To be used by debug function."""
     ui.write(hex(marker.precnode()))
     for repl in marker.succnodes():
         ui.write(' ')
         ui.write(hex(repl))
     ui.write(' %X ' % marker.flags())
     parents = marker.parentnodes()
     if parents is not None:
         ui.write('{%s} ' % ', '.join(hex(p) for p in parents))
     ui.write('(%s) ' % util.datestr(marker.date()))
     ui.write('{%s}' % (', '.join('%r: %r' % t for t in
                                  sorted(marker.metadata().items())
                                  if t[0] != 'date')))
     ui.write('\n')
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = util.matchdate(date)
     m = scmutil.matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(_("found revision %s from %s\n") %
                       (rev, util.datestr(results[rev])))
             return str(rev)
 
     raise util.Abort(_("revision matching date not found"))
 
 def increasingwindows(windowsize=8, sizelimit=512):
     while True:
         yield windowsize
         if windowsize < sizelimit:
             windowsize *= 2
 
 class FileWalkError(Exception):
     pass
 
 def walkfilerevs(repo, match, follow, revs, fncache):
     '''Walks the file history for the matched files.
 
     Returns the changeset revs that are involved in the file history.
 
     Throws FileWalkError if the file history can't be walked using
     filelogs alone.
     '''
     wanted = set()
     copies = []
     minrev, maxrev = min(revs), max(revs)
     def filerevgen(filelog, last):
         """
         Only files, no patterns.  Check the history of each file.
 
         Examines filelog entries within minrev, maxrev linkrev range
         Returns an iterator yielding (linkrev, parentlinkrevs, copied)
         tuples in backwards order
         """
         cl_count = len(repo)
         revs = []
         for j in xrange(0, last + 1):
             linkrev = filelog.linkrev(j)
             if linkrev < minrev:
                 continue
             # only yield rev for which we have the changelog, it can
             # happen while doing "hg log" during a pull or commit
             if linkrev >= cl_count:
                 break
 
             parentlinkrevs = []
             for p in filelog.parentrevs(j):
                 if p != nullrev:
                     parentlinkrevs.append(filelog.linkrev(p))
             n = filelog.node(j)
             revs.append((linkrev, parentlinkrevs,
                          follow and filelog.renamed(n)))
 
         return reversed(revs)
     def iterfiles():
         pctx = repo['.']
         for filename in match.files():
             if follow:
                 if filename not in pctx:
                     raise util.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % filename)
                 yield filename, pctx[filename].filenode()
             else:
                 yield filename, None
         for filename_node in copies:
             yield filename_node
 
     for file_, node in iterfiles():
         filelog = repo.file(file_)
         if not len(filelog):
             if node is None:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise util.Abort(
                         _('cannot follow nonexistent file: "%s"') % file_)
                 raise FileWalkError("Cannot walk via filelog")
             else:
                 continue
 
         if node is None:
             last = len(filelog) - 1
         else:
             last = filelog.rev(node)
 
 
         # keep track of all ancestors of the file
         ancestors = set([filelog.linkrev(last)])
 
         # iterate from latest to oldest revision
         for rev, flparentlinkrevs, copied in filerevgen(filelog, last):
             if not follow:
                 if rev > maxrev:
                     continue
             else:
                 # Note that last might not be the first interesting
                 # rev to us:
                 # if the file has been changed after maxrev, we'll
                 # have linkrev(last) > maxrev, and we still need
                 # to explore the file graph
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
             fncache.setdefault(rev, []).append(file_)
             wanted.add(rev)
             if copied:
                 copies.append(copied)
 
     return wanted
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     follow = opts.get('follow') or opts.get('follow_first')
 
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts.get('rev'))
     elif follow:
         revs = repo.revs('reverse(:.)')
     else:
         revs = revset.spanset(repo)
         revs.reverse()
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or (match.files() and opts.get('removed'))
     fncache = {}
     change = repo.changectx
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if not slowpath and not match.files():
         # No files, no patterns.  Display all revs.
         wanted = revs
 
     if not slowpath and match.files():
         # We only have to read through the filelog to find wanted revisions
 
         try:
             wanted = walkfilerevs(repo, match, follow, revs, fncache)
         except FileWalkError:
             slowpath = True
 
             # We decided to fall back to the slowpath because at least one
             # of the paths was not a file. Check to see if at least one of them
             # existed in history, otherwise simply return
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 return []
 
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise util.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
 
         # The slow path checks files modified in every changeset.
         # This is really slow on large repos, so compute the set lazily.
         class lazywantedset(object):
             def __init__(self):
                 self.set = set()
                 self.revs = set(revs)
 
             # No need to worry about locality here because it will be accessed
             # in the same order as the increasing window below.
             def __contains__(self, value):
                 if value in self.set:
                     return True
                 elif not value in self.revs:
                     return False
                 else:
                     self.revs.discard(value)
                     ctx = change(value)
                     matches = filter(match, ctx.files())
                     if matches:
                         fncache[value] = matches
                         self.set.add(value)
                         return True
                     return False
 
             def discard(self, value):
                 self.revs.discard(value)
                 self.set.discard(value)
 
         wanted = lazywantedset()
 
     class followfilter(object):
         def __init__(self, onlyfirst=False):
             self.startrev = nullrev
             self.roots = set()
             self.onlyfirst = onlyfirst
 
         def match(self, rev):
             def realparents(rev):
                 if self.onlyfirst:
                     return repo.changelog.parentrevs(rev)[0:1]
                 else:
                     return filter(lambda x: x != nullrev,
                                   repo.changelog.parentrevs(rev))
 
             if self.startrev == nullrev:
                 self.startrev = rev
                 return True
 
             if rev > self.startrev:
                 # forward: all descendants
                 if not self.roots:
                     self.roots.add(self.startrev)
                 for parent in realparents(rev):
                     if parent in self.roots:
                         self.roots.add(rev)
                         return True
             else:
                 # backwards: all parents
                 if not self.roots:
                     self.roots.update(realparents(self.startrev))
                 if rev in self.roots:
                     self.roots.remove(rev)
                     self.roots.update(realparents(rev))
                     return True
 
             return False
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get('prune', ()):
         rev = repo[rev].rev()
         ff = followfilter()
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted = wanted - [x]
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and not match.files():
             ff = followfilter(onlyfirst=opts.get('follow_first'))
             def want(rev):
                 return ff.match(rev) and rev in wanted
         else:
             def want(rev):
                 return rev in wanted
 
         it = iter(revs)
         stopiteration = False
         for windowsize in increasingwindows():
             nrevs = []
             for i in xrange(windowsize):
                 try:
                     rev = it.next()
                     if want(rev):
                         nrevs.append(rev)
                 except (StopIteration):
                     stopiteration = True
                     break
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
                     def fns_generator():
                         for f in ctx.files():
                             if match(f):
                                 yield f
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
 
             if stopiteration:
                 break
 
     return iterate()
 
 def _makefollowlogfilematcher(repo, files, followfirst):
     # When displaying a revision with --patch --follow FILE, we have
     # to know which file of the revision must be diffed. With
     # --follow, we want the names of the ancestors of FILE in the
     # revision, stored in "fcache". "fcache" is populated by
     # reproducing the graph traversal already done by --follow revset
     # and relating linkrevs to file names (which is not "correct" but
     # good enough).
     fcache = {}
     fcacheready = [False]
     pctx = repo['.']
 
     def populate():
         for fn in files:
             for i in ((pctx[fn],), pctx[fn].ancestors(followfirst=followfirst)):
                 for c in i:
                     fcache.setdefault(c.linkrev(), set()).add(c.path())
 
     def filematcher(rev):
         if not fcacheready[0]:
             # Lazy initialization
             fcacheready[0] = True
             populate()
         return scmutil.matchfiles(repo, fcache.get(rev, []))
 
     return filematcher
 
 def _makenofollowlogfilematcher(repo, pats, opts):
     '''hook for extensions to override the filematcher for non-follow cases'''
     return None
 
 def _makelogrevset(repo, pats, opts, revs):
     """Return (expr, filematcher) where expr is a revset string built
     from log options and file patterns or None. If --stat or --patch
     are not passed filematcher is None. Otherwise it is a callable
     taking a revision number and returning a match objects filtering
     the files to be detailed when displaying the revision.
     """
     opt2revset = {
         'no_merges':        ('not merge()', None),
         'only_merges':      ('merge()', None),
         '_ancestors':       ('ancestors(%(val)s)', None),
         '_fancestors':      ('_firstancestors(%(val)s)', None),
         '_descendants':     ('descendants(%(val)s)', None),
         '_fdescendants':    ('_firstdescendants(%(val)s)', None),
         '_matchfiles':      ('_matchfiles(%(val)s)', None),
         'date':             ('date(%(val)r)', None),
         'branch':           ('branch(%(val)r)', ' or '),
         '_patslog':         ('filelog(%(val)r)', ' or '),
         '_patsfollow':      ('follow(%(val)r)', ' or '),
         '_patsfollowfirst': ('_followfirst(%(val)r)', ' or '),
         'keyword':          ('keyword(%(val)r)', ' or '),
         'prune':            ('not (%(val)r or ancestors(%(val)r))', ' and '),
         'user':             ('user(%(val)r)', ' or '),
         }
 
     opts = dict(opts)
     # follow or not follow?
     follow = opts.get('follow') or opts.get('follow_first')
     followfirst = opts.get('follow_first') and 1 or 0
     # --follow with FILE behaviour depends on revs...
     it = iter(revs)
     startrev = it.next()
     try:
         followdescendants = startrev < it.next()
     except (StopIteration):
         followdescendants = False
 
     # branch and only_branch are really aliases and must be handled at
     # the same time
     opts['branch'] = opts.get('branch', []) + opts.get('only_branch', [])
     opts['branch'] = [repo.lookupbranch(b) for b in opts['branch']]
     # pats/include/exclude are passed to match.match() directly in
     # _matchfiles() revset but walkchangerevs() builds its matcher with
     # scmutil.match(). The difference is input pats are globbed on
     # platforms without shell expansion (windows).
     pctx = repo[None]
     match, pats = scmutil.matchandpats(pctx, pats, opts)
     slowpath = match.anypats() or (match.files() and opts.get('removed'))
     if not slowpath:
         for f in match.files():
             if follow and f not in pctx:
                 # If the file exists, it may be a directory, so let it
                 # take the slow path.
                 if os.path.exists(repo.wjoin(f)):
                     slowpath = True
                     continue
                 else:
                     raise util.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % f)
             filelog = repo.file(f)
             if not filelog:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise util.Abort(
                         _('cannot follow nonexistent file: "%s"') % f)
                 slowpath = True
 
         # We decided to fall back to the slowpath because at least one
         # of the paths was not a file. Check to see if at least one of them
         # existed in history - in that case, we'll continue down the
         # slowpath; otherwise, we can turn off the slowpath
         if slowpath:
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 slowpath = False
 
     if slowpath:
         # See walkchangerevs() slow path.
         #
         # pats/include/exclude cannot be represented as separate
         # revset expressions as their filtering logic applies at file
         # level. For instance "-I a -X a" matches a revision touching
         # "a" and "b" while "file(a) and not file(b)" does
         # not. Besides, filesets are evaluated against the working
         # directory.
         matchargs = ['r:', 'd:relpath']
         for p in pats:
             matchargs.append('p:' + p)
         for p in opts.get('include', []):
             matchargs.append('i:' + p)
         for p in opts.get('exclude', []):
             matchargs.append('x:' + p)
         matchargs = ','.join(('%r' % p) for p in matchargs)
         opts['_matchfiles'] = matchargs
     else:
         if follow:
             fpats = ('_patsfollow', '_patsfollowfirst')
             fnopats = (('_ancestors', '_fancestors'),
                        ('_descendants', '_fdescendants'))
             if pats:
                 # follow() revset interprets its file argument as a
                 # manifest entry, so use match.files(), not pats.
                 opts[fpats[followfirst]] = list(match.files())
             else:
                 opts[fnopats[followdescendants][followfirst]] = str(startrev)
         else:
             opts['_patslog'] = list(pats)
 
     filematcher = None
     if opts.get('patch') or opts.get('stat'):
         # When following files, track renames via a special matcher.
         # If we're forced to take the slowpath it means we're following
         # at least one pattern/directory, so don't bother with rename tracking.
         if follow and not match.always() and not slowpath:
             # _makelogfilematcher expects its files argument to be relative to
             # the repo root, so use match.files(), not pats.
             filematcher = _makefollowlogfilematcher(repo, match.files(),
                                                     followfirst)
         else:
             filematcher = _makenofollowlogfilematcher(repo, pats, opts)
             if filematcher is None:
                 filematcher = lambda rev: match
 
     expr = []
     for op, val in opts.iteritems():
         if not val:
             continue
         if op not in opt2revset:
             continue
         revop, andor = opt2revset[op]
         if '%(val)' not in revop:
             expr.append(revop)
         else:
             if not isinstance(val, list):
                 e = revop % {'val': val}
             else:
                 e = '(' + andor.join((revop % {'val': v}) for v in val) + ')'
             expr.append(e)
 
     if expr:
         expr = '(' + ' and '.join(expr) + ')'
     else:
         expr = None
     return expr, filematcher
 
 def getgraphlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     if not len(repo):
         return [], None, None
     limit = loglimit(opts)
     # Default --rev value depends on --follow but --follow behaviour
     # depends on revisions resolved from --rev...
     follow = opts.get('follow') or opts.get('follow_first')
     possiblyunsorted = False # whether revs might need sorting
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts['rev'])
         # Don't sort here because _makelogrevset might depend on the
         # order of revs
         possiblyunsorted = True
     else:
         if follow and len(repo) > 0:
             revs = repo.revs('reverse(:.)')
         else:
             revs = revset.spanset(repo)
             revs.reverse()
     if not revs:
         return revset.baseset(), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if possiblyunsorted:
         revs.sort(reverse=True)
     if expr:
         # Revset matchers often operate faster on revisions in changelog
         # order, because most filters deal with the changelog.
         revs.reverse()
         matcher = revset.match(repo.ui, expr)
         # Revset matches can reorder revisions. "A or B" typically returns
         # returns the revision matching A then the revision matching B. Sort
         # again to fix that.
         revs = matcher(repo, revs)
         revs.sort(reverse=True)
     if limit is not None:
         limitedrevs = revset.baseset()
         for idx, rev in enumerate(revs):
             if idx >= limit:
                 break
             limitedrevs.append(rev)
         revs = limitedrevs
 
     return revs, expr, filematcher
 
 def getlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     limit = loglimit(opts)
     # Default --rev value depends on --follow but --follow behaviour
     # depends on revisions resolved from --rev...
     follow = opts.get('follow') or opts.get('follow_first')
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts['rev'])
     elif follow:
         revs = repo.revs('reverse(:.)')
     else:
         revs = revset.spanset(repo)
         revs.reverse()
     if not revs:
         return revset.baseset([]), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if expr:
         # Revset matchers often operate faster on revisions in changelog
         # order, because most filters deal with the changelog.
         if not opts.get('rev'):
             revs.reverse()
         matcher = revset.match(repo.ui, expr)
         # Revset matches can reorder revisions. "A or B" typically returns
         # returns the revision matching A then the revision matching B. Sort
         # again to fix that.
         revs = matcher(repo, revs)
         if not opts.get('rev'):
             revs.sort(reverse=True)
     if limit is not None:
         count = 0
         limitedrevs = revset.baseset([])
         it = iter(revs)
         while count < limit:
             try:
                 limitedrevs.append(it.next())
             except (StopIteration):
                 break
             count += 1
         revs = limitedrevs
 
     return revs, expr, filematcher
 
 def displaygraph(ui, dag, displayer, showparents, edgefn, getrenamed=None,
                  filematcher=None):
     seen, state = [], graphmod.asciistate()
     for rev, type, ctx, parents in dag:
         char = 'o'
         if ctx.node() in showparents:
             char = '@'
         elif ctx.obsolete():
             char = 'x'
         copies = None
         if getrenamed and ctx.rev():
             copies = []
             for fn in ctx.files():
                 rename = getrenamed(fn, ctx.rev())
                 if rename:
                     copies.append((fn, rename[0]))
         revmatchfn = None
         if filematcher is not None:
             revmatchfn = filematcher(ctx.rev())
         displayer.show(ctx, copies=copies, matchfn=revmatchfn)
         lines = displayer.hunk.pop(rev).split('\n')
         if not lines[-1]:
             del lines[-1]
         displayer.flush(rev)
         edges = edgefn(type, char, lines, seen, rev, parents)
         for type, char, lines, coldata in edges:
             graphmod.ascii(ui, state, type, char, lines, coldata)
     displayer.close()
 
 def graphlog(ui, repo, *pats, **opts):
     # Parameters are identical to log command ones
     revs, expr, filematcher = getgraphlogrevs(repo, pats, opts)
     revdag = graphmod.dagwalker(repo, revs)
 
     getrenamed = None
     if opts.get('copies'):
         endrev = None
         if opts.get('rev'):
             endrev = scmutil.revrange(repo, opts.get('rev')).max() + 1
         getrenamed = templatekw.getrenamedfn(repo, endrev=endrev)
     displayer = show_changeset(ui, repo, opts, buffered=True)
     showparents = [ctx.node() for ctx in repo[None].parents()]
     displaygraph(ui, revdag, displayer, showparents,
                  graphmod.asciiedges, getrenamed, filematcher)
 
 def checkunsupportedgraphflags(pats, opts):
     for op in ["newest_first"]:
         if op in opts and opts[op]:
             raise util.Abort(_("-G/--graph option is incompatible with --%s")
                              % op.replace("_", "-"))
 
 def graphrevs(repo, nodes, opts):
     limit = loglimit(opts)
     nodes.reverse()
     if limit is not None:
         nodes = nodes[:limit]
     return graphmod.nodes(repo, nodes)
 
 def add(ui, repo, match, dryrun, listsubrepos, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     oldbad = match.bad
     match.bad = lambda x, y: bad.append(x) or oldbad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
     for f in repo.walk(match):
         exact = match.exact(f)
         if exact or not explicitonly and f not in repo.dirstate:
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(_('adding %s\n') % match.rel(join(f)))
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.narrowmatcher(subpath, match)
             if listsubrepos:
                 bad.extend(sub.add(ui, submatch, dryrun, listsubrepos, prefix,
                                    False))
             else:
                 bad.extend(sub.add(ui, submatch, dryrun, listsubrepos, prefix,
                                    True))
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not dryrun:
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 def forget(ui, repo, match, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     oldbad = match.bad
     match.bad = lambda x, y: bad.append(x) or oldbad(x, y)
     wctx = repo[None]
     forgot = []
     s = repo.status(match=match, clean=True)
     forget = sorted(s[0] + s[1] + s[3] + s[6])
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.narrowmatcher(subpath, match)
             subbad, subforgot = sub.forget(ui, submatch, prefix)
             bad.extend([subpath + '/' + f for f in subbad])
             forgot.extend([subpath + '/' + f for f in subforgot])
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not os.path.isdir(match.rel(join(f))):
                 if f not in forgot:
                     if os.path.exists(match.rel(join(f))):
                         ui.warn(_('not removing %s: '
                                   'file is already untracked\n')
                                 % match.rel(join(f)))
                     bad.append(f)
 
     for f in forget:
         if ui.verbose or not match.exact(f):
             ui.status(_('removing %s\n') % match.rel(join(f)))
 
     rejected = wctx.forget(forget, prefix)
     bad.extend(f for f in rejected if f in match.files())
     forgot.extend(forget)
     return bad, forgot
 
 def cat(ui, repo, ctx, matcher, prefix, **opts):
     err = 1
 
     def write(path):
         fp = makefileobj(repo, opts.get('output'), ctx.node(),
                          pathname=os.path.join(prefix, path))
         data = ctx[path].data()
         if opts.get('decode'):
             data = repo.wwritedata(path, data)
         fp.write(data)
         fp.close()
 
     # Automation often uses hg cat on single files, so special case it
     # for performance to avoid the cost of parsing the manifest.
     if len(matcher.files()) == 1 and not matcher.anypats():
         file = matcher.files()[0]
         mf = repo.manifest
         mfnode = ctx._changeset[0]
         if mf.find(mfnode, file)[0]:
             write(file)
             return 0
 
     # Don't warn about "missing" files that are really in subrepos
     bad = matcher.bad
 
     def badfn(path, msg):
         for subpath in ctx.substate:
             if path.startswith(subpath):
                 return
         bad(path, msg)
 
     matcher.bad = badfn
 
     for abs in ctx.walk(matcher):
         write(abs)
         err = 0
 
     matcher.bad = bad
 
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         try:
             submatch = matchmod.narrowmatcher(subpath, matcher)
 
             if not sub.cat(ui, submatch, os.path.join(prefix, sub._path),
                            **opts):
                 err = 0
         except error.RepoLookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % os.path.join(prefix, subpath))
 
     return err
 
 def duplicatecopies(repo, rev, fromrev, skiprev=None):
     '''reproduce copies from fromrev to rev in the dirstate
 
     If skiprev is specified, it's a revision that should be used to
     filter copy records. Any copies that occur between fromrev and
     skiprev will not be duplicated, even if they appear in the set of
     copies between fromrev and rev.
     '''
     exclude = {}
     if skiprev is not None:
         exclude = copies.pathcopies(repo[fromrev], repo[skiprev])
     for dst, src in copies.pathcopies(repo[fromrev], repo[rev]).iteritems():
         # copies.pathcopies returns backward renames, so dst might not
         # actually be in the dirstate
         if dst in exclude:
             continue
         if repo.dirstate[dst] in "nma":
             repo.dirstate.copy(src, dst)
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
     message = logmessage(ui, opts)
 
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         scmutil.addremove(repo, pats, opts)
 
     return commitfunc(ui, repo, message,
                       scmutil.match(repo[None], pats, opts), opts)
 
 def amend(ui, repo, commitfunc, old, extra, pats, opts):
     ui.note(_('amending changeset %s\n') % old)
     base = old.p1()
 
     wlock = lock = newid = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         tr = repo.transaction('amend')
         try:
             # See if we got a message from -m or -l, if not, open the editor
             # with the message of the changeset to amend
             message = logmessage(ui, opts)
             # ensure logfile does not conflict with later enforcement of the
             # message. potential logfile content has been processed by
             # `logmessage` anyway.
             opts.pop('logfile')
             # First, do a regular commit to record all changes in the working
             # directory (if there are any)
             ui.callhooks = False
             currentbookmark = repo._bookmarkcurrent
             try:
                 repo._bookmarkcurrent = None
                 opts['message'] = 'temporary amend commit for %s' % old
                 node = commit(ui, repo, commitfunc, pats, opts)
             finally:
                 repo._bookmarkcurrent = currentbookmark
                 ui.callhooks = True
             ctx = repo[node]
 
             # Participating changesets:
             #
             # node/ctx o - new (intermediate) commit that contains changes
             #          |   from working dir to go into amending commit
             #          |   (or a workingctx if there were no changes)
             #          |
             # old      o - changeset to amend
             #          |
             # base     o - parent of amending changeset
 
             # Update extra dict from amended commit (e.g. to preserve graft
             # source)
             extra.update(old.extra())
 
             # Also update it from the intermediate commit or from the wctx
             extra.update(ctx.extra())
 
             if len(old.parents()) > 1:
                 # ctx.files() isn't reliable for merges, so fall back to the
                 # slower repo.status() method
                 files = set([fn for st in repo.status(base, old)[:3]
                              for fn in st])
             else:
                 files = set(old.files())
 
             # Second, we use either the commit we just did, or if there were no
             # changes the parent of the working directory as the version of the
             # files in the final amend commit
             if node:
                 ui.note(_('copying changeset %s to %s\n') % (ctx, base))
 
                 user = ctx.user()
                 date = ctx.date()
                 # Recompute copies (avoid recording a -> b -> a)
                 copied = copies.pathcopies(base, ctx)
 
                 # Prune files which were reverted by the updates: if old
                 # introduced file X and our intermediate commit, node,
                 # renamed that file, then those two files are the same and
                 # we can discard X from our list of files. Likewise if X
                 # was deleted, it's no longer relevant
                 files.update(ctx.files())
 
                 def samefile(f):
                     if f in ctx.manifest():
                         a = ctx.filectx(f)
                         if f in base.manifest():
                             b = base.filectx(f)
                             return (not a.cmp(b)
                                     and a.flags() == b.flags())
                         else:
                             return False
                     else:
                         return f not in base.manifest()
                 files = [f for f in files if not samefile(f)]
 
                 def filectxfn(repo, ctx_, path):
                     try:
                         fctx = ctx[path]
                         flags = fctx.flags()
                         mctx = context.memfilectx(repo,
                                                   fctx.path(), fctx.data(),
                                                   islink='l' in flags,
                                                   isexec='x' in flags,
                                                   copied=copied.get(path))
                         return mctx
                     except KeyError:
-                        raise IOError
+                        return None
             else:
                 ui.note(_('copying changeset %s to %s\n') % (old, base))
 
                 # Use version of files as in the old cset
                 def filectxfn(repo, ctx_, path):
                     try:
                         return old.filectx(path)
                     except KeyError:
-                        raise IOError
+                        return None
 
                 user = opts.get('user') or old.user()
                 date = opts.get('date') or old.date()
             editform = mergeeditform(old, 'commit.amend')
             editor = getcommiteditor(editform=editform, **opts)
             if not message:
                 editor = getcommiteditor(edit=True, editform=editform)
                 message = old.description()
 
             pureextra = extra.copy()
             extra['amend_source'] = old.hex()
 
             new = context.memctx(repo,
                                  parents=[base.node(), old.p2().node()],
                                  text=message,
                                  files=files,
                                  filectxfn=filectxfn,
                                  user=user,
                                  date=date,
                                  extra=extra,
                                  editor=editor)
 
             newdesc =  changelog.stripdesc(new.description())
             if ((not node)
                 and newdesc == old.description()
                 and user == old.user()
                 and date == old.date()
                 and pureextra == old.extra()):
                 # nothing changed. continuing here would create a new node
                 # anyway because of the amend_source noise.
                 #
                 # This not what we expect from amend.
                 return old.node()
 
             ph = repo.ui.config('phases', 'new-commit', phases.draft)
             try:
                 if opts.get('secret'):
                     commitphase = 'secret'
                 else:
                     commitphase = old.phase()
                 repo.ui.setconfig('phases', 'new-commit', commitphase, 'amend')
                 newid = repo.commitctx(new)
             finally:
                 repo.ui.setconfig('phases', 'new-commit', ph, 'amend')
             if newid != old.node():
                 # Reroute the working copy parent to the new changeset
                 repo.setparents(newid, nullid)
 
                 # Move bookmarks from old parent to amend commit
                 bms = repo.nodebookmarks(old.node())
                 if bms:
                     marks = repo._bookmarks
                     for bm in bms:
                         marks[bm] = newid
                     marks.write()
             #commit the whole amend process
             if obsolete._enabled and newid != old.node():
                 # mark the new changeset as successor of the rewritten one
                 new = repo[newid]
                 obs = [(old, (new,))]
                 if node:
                     obs.append((ctx, ()))
 
                 obsolete.createmarkers(repo, obs)
             tr.close()
         finally:
             tr.release()
         if (not obsolete._enabled) and newid != old.node():
             # Strip the intermediate commit (if there was one) and the amended
             # commit
             if node:
                 ui.note(_('stripping intermediate changeset %s\n') % ctx)
             ui.note(_('stripping amended changeset %s\n') % old)
             repair.strip(ui, repo, old.node(), topic='amend-backup')
     finally:
         if newid is None:
             repo.dirstate.invalidate()
         lockmod.release(lock, wlock)
     return newid
 
 def commiteditor(repo, ctx, subs, editform=''):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(repo, ctx, subs, editform=editform)
 
 def commitforceeditor(repo, ctx, subs, finishdesc=None, extramsg=None,
                       editform=''):
     if not extramsg:
         extramsg = _("Leave message empty to abort commit.")
 
     forms = [e for e in editform.split('.') if e]
     forms.insert(0, 'changeset')
     while forms:
         tmpl = repo.ui.config('committemplate', '.'.join(forms))
         if tmpl:
             committext = buildcommittemplate(repo, ctx, subs, extramsg, tmpl)
             break
         forms.pop()
     else:
         committext = buildcommittext(repo, ctx, subs, extramsg)
 
     # run editor in the repository root
     olddir = os.getcwd()
     os.chdir(repo.root)
     text = repo.ui.edit(committext, ctx.user(), ctx.extra(), editform=editform)
     text = re.sub("(?m)^HG:.*(\n|$)", "", text)
     os.chdir(olddir)
 
     if finishdesc:
         text = finishdesc(text)
     if not text.strip():
         raise util.Abort(_("empty commit message"))
 
     return text
 
 def buildcommittemplate(repo, ctx, subs, extramsg, tmpl):
     ui = repo.ui
     tmpl, mapfile = gettemplate(ui, tmpl, None)
 
     try:
         t = changeset_templater(ui, repo, None, {}, tmpl, mapfile, False)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
 
     for k, v in repo.ui.configitems('committemplate'):
         if k != 'changeset':
             t.t.cache[k] = v
 
     if not extramsg:
         extramsg = '' # ensure that extramsg is string
 
     ui.pushbuffer()
     t.show(ctx, extramsg=extramsg)
     return ui.popbuffer()
 
 def buildcommittext(repo, ctx, subs, extramsg):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append("")
     edittext.append("") # Empty line between message and comments.
     edittext.append(_("HG: Enter commit message."
                       "  Lines beginning with 'HG:' are removed."))
     edittext.append("HG: %s" % extramsg)
     edittext.append("HG: --")
     edittext.append(_("HG: user: %s") % ctx.user())
     if ctx.p2():
         edittext.append(_("HG: branch merge"))
     if ctx.branch():
         edittext.append(_("HG: branch '%s'") % ctx.branch())
     if bookmarks.iscurrent(repo):
         edittext.append(_("HG: bookmark '%s'") % repo._bookmarkcurrent)
     edittext.extend([_("HG: subrepo %s") % s for s in subs])
     edittext.extend([_("HG: added %s") % f for f in added])
     edittext.extend([_("HG: changed %s") % f for f in modified])
     edittext.extend([_("HG: removed %s") % f for f in removed])
     if not added and not modified and not removed:
         edittext.append(_("HG: no files changed"))
     edittext.append("")
 
     return "\n".join(edittext)
 
 def commitstatus(repo, node, branch, bheads=None, opts={}):
     ctx = repo[node]
     parents = ctx.parents()
 
     if (not opts.get('amend') and bheads and node not in bheads and not
         [x for x in parents if x.node() in bheads and x.branch() == branch]):
         repo.ui.status(_('created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get('close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(_('reopening closed branch head %d\n') % r)
 
     if repo.ui.debugflag:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx.hex()))
     elif repo.ui.verbose:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx))
 
 def revert(ui, repo, ctx, parents, *pats, **opts):
     parent, p2 = parents
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == p2:
         parent = p2
     if node == parent:
         pmf = mf
     else:
         pmf = None
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other.
 
     # `names` is a mapping for all elements in working copy and target revision
     # The mapping is in the form:
     #   <asb path in repo> -> (<path from CWD>, <exactly specified by matcher?>)
     names = {}
 
     wlock = repo.wlock()
     try:
         ## filling of the `names` mapping
         # walk dirstate to fill `names`
 
         m = scmutil.match(repo[None], pats, opts)
         m.bad = lambda x, y: False
         for abs in repo.walk(m):
             names[abs] = m.rel(abs), m.exact(abs)
 
         # walk target manifest to fill `names`
 
         def badfn(path, msg):
             if path in names:
                 return
             if path in ctx.substate:
                 return
             path_ = path + '/'
             for f in names:
                 if f.startswith(path_):
                     return
             ui.warn("%s: %s\n" % (m.rel(path), msg))
 
         m = scmutil.match(ctx, pats, opts)
         m.bad = badfn
         for abs in ctx.walk(m):
             if abs not in names:
                 names[abs] = m.rel(abs), m.exact(abs)
 
         # get the list of subrepos that must be reverted
         targetsubs = sorted(s for s in ctx.substate if m(s))
 
         # Find status of all file in `names`.
         m = scmutil.matchfiles(repo, names)
 
         changes = repo.status(node1=node, match=m,
                               unknown=True, ignored=True, clean=True)
         modified = set(changes[0])
         added    = set(changes[1])
         removed  = set(changes[2])
         _deleted = set(changes[3])
         unknown  = set(changes[4])
         unknown.update(changes[5])
         clean    = set(changes[6])
 
         # split between files known in target manifest and the others
         smf = set(mf)
 
         # determine the exact nature of the deleted changesets
         _deletedadded = _deleted - smf
         _deletedmodified = _deleted - _deletedadded
         added |= _deletedadded
         modified |= _deletedmodified
 
         # We need to account for the state of file in the dirstate
         #
         # Even, when we revert agains something else than parent. this will
         # slightly alter the behavior of revert (doing back up or not, delete
         # or just forget etc)
         if parent == node:
             dsmodified = modified
             dsadded = added
             dsremoved = removed
             modified, added, removed = set(), set(), set()
         else:
             changes = repo.status(node1=parent, match=m)
             dsmodified = set(changes[0])
             dsadded    = set(changes[1])
             dsremoved  = set(changes[2])
 
             # only take into account for removes between wc and target
             clean |= dsremoved - removed
             dsremoved &= removed
             # distinct between dirstate remove and other
             removed -= dsremoved
 
             # tell newly modified apart.
             dsmodified &= modified
             dsmodified |= modified & dsadded # dirstate added may needs backup
             modified -= dsmodified
 
             # There are three categories of added files
             #
             # 1. addition that just happened in the dirstate
             #    (should be forgotten)
             # 2. file is added since target revision and has local changes
             #    (should be backed up and removed)
             # 3. file is added since target revision and is clean
             #    (should be removed)
             #
             # However we do not need to split them yet. The current revert code
             # will automatically recognize (1) when performing operation. And
             # the backup system is currently unabled to handle (2).
             #
             # So we just put them all in the same group.
             dsadded = added
 
         # in case of merge, files that are actually added can be reported as
         # modified, we need to post process the result
         if p2 != nullid:
             if pmf is None:
                 # only need parent manifest in the merge case,
                 # so do not read by default
                 pmf = repo[parent].manifest()
             mergeadd = dsmodified - set(pmf)
             dsadded |= mergeadd
             dsmodified -= mergeadd
 
         # if f is a rename, update `names` to also revert the source
         cwd = repo.getcwd()
         for f in dsadded:
             src = repo.dirstate.copied(f)
             # XXX should we check for rename down to target node?
             if src and src not in names and repo.dirstate[src] == 'r':
                 dsremoved.add(src)
                 names[src] = (repo.pathto(src, cwd), True)
 
         ## computation of the action to performs on `names` content.
 
         def removeforget(abs):
             if repo.dirstate[abs] == 'a':
                 return _('forgetting %s\n')
             return _('removing %s\n')
 
         # action to be actually performed by revert
         # (<list of file>, message>) tuple
         actions = {'revert': ([], _('reverting %s\n')),
                    'add': ([], _('adding %s\n')),
                    'remove': ([], removeforget),
                    'undelete': ([], _('undeleting %s\n')),
                    'noop': (None, _('no changes needed to %s\n')),
                    'unknown': (None, _('file not managed: %s\n')),
                   }
 
 
         # should we do a backup?
         backup = not opts.get('no_backup')
         discard = False
 
         disptable = (
             # dispatch table:
             #   file state
             #   action
             #   make backup
             (modified,   actions['revert'],   discard),
             (dsmodified, actions['revert'],   backup),
             (dsadded,    actions['remove'],   backup),
             (removed,    actions['add'],      backup),
             (dsremoved,  actions['undelete'], backup),
             (clean,      actions['noop'],     discard),
             (unknown,    actions['unknown'],  discard),
             )
 
         for abs, (rel, exact) in sorted(names.items()):
             # target file to be touch on disk (relative to cwd)
             target = repo.wjoin(abs)
             # search the entry in the dispatch table.
             # if the file is in any of these sets, it was touched in the working
             # directory parent and we are sure it needs to be reverted.
             for table, (xlist, msg), dobackup in disptable:
                 if abs not in table:
                     continue
                 if xlist is not None:
                     xlist.append(abs)
                     if (dobackup and os.path.lexists(target) and
                         abs in ctx and repo[None][abs].cmp(ctx[abs])):
                         bakname = "%s.orig" % rel
                         ui.note(_('saving current version of %s as %s\n') %
                                 (rel, bakname))
                         if not opts.get('dry_run'):
                             util.rename(target, bakname)
                     if ui.verbose or not exact:
                         if not isinstance(msg, basestring):
                             msg = msg(abs)
                         ui.status(msg % rel)
                 elif exact:
                     ui.warn(msg % rel)
                 break
 
 
         if not opts.get('dry_run'):
             _performrevert(repo, parents, ctx, actions)
 
             if targetsubs:
                 # Revert the subrepos on the revert list
                 for sub in targetsubs:
                     ctx.sub(sub).revert(ui, ctx.substate[sub], *pats, **opts)
     finally:
         wlock.release()
 
 def _performrevert(repo, parents, ctx, actions):
     """function that actually perform all the actions computed for revert
 
     This is an independent function to let extension to plug in and react to
     the imminent revert.
 
     Make sure you have the working directory locked when calling this function.
     """
     parent, p2 = parents
     node = ctx.node()
     def checkout(f):
         fc = ctx[f]
         repo.wwrite(f, fc.data(), fc.flags())
 
     audit_path = pathutil.pathauditor(repo.root)
     for f in actions['remove'][0]:
         if repo.dirstate[f] == 'a':
             repo.dirstate.drop(f)
             continue
         audit_path(f)
         try:
             util.unlinkpath(repo.wjoin(f))
         except OSError:
             pass
         repo.dirstate.remove(f)
 
     normal = None
     if node == parent:
         # We're reverting to our parent. If possible, we'd like status
         # to report the file as clean. We have to use normallookup for
         # merges to avoid losing information about merged/dirty files.
         if p2 != nullid:
             normal = repo.dirstate.normallookup
         else:
             normal = repo.dirstate.normal
     for f in actions['revert'][0]:
         checkout(f)
         if normal:
             normal(f)
 
     for f in actions['add'][0]:
         checkout(f)
         repo.dirstate.add(f)
 
     normal = repo.dirstate.normallookup
     if node == parent and p2 == nullid:
         normal = repo.dirstate.normal
     for f in actions['undelete'][0]:
         checkout(f)
         normal(f)
 
     copied = copies.pathcopies(repo[parent], ctx)
 
     for f in actions['add'][0] + actions['undelete'][0] + actions['revert'][0]:
         if f in copied:
             repo.dirstate.copy(copied[f], f)
 
 def command(table):
     """Returns a function object to be used as a decorator for making commands.
 
     This function receives a command table as its argument. The table should
     be a dict.
 
     The returned function can be used as a decorator for adding commands
     to that command table. This function accepts multiple arguments to define
     a command.
 
     The first argument is the command name.
 
     The options argument is an iterable of tuples defining command arguments.
     See ``mercurial.fancyopts.fancyopts()`` for the format of each tuple.
 
     The synopsis argument defines a short, one line summary of how to use the
     command. This shows up in the help output.
 
     The norepo argument defines whether the command does not require a
     local repository. Most commands operate against a repository, thus the
     default is False.
 
     The optionalrepo argument defines whether the command optionally requires
     a local repository.
 
     The inferrepo argument defines whether to try to find a repository from the
     command line arguments. If True, arguments will be examined for potential
     repository locations. See ``findrepo()``. If a repository is found, it
     will be used.
     """
     def cmd(name, options=(), synopsis=None, norepo=False, optionalrepo=False,
             inferrepo=False):
         def decorator(func):
             if synopsis:
                 table[name] = func, list(options), synopsis
             else:
                 table[name] = func, list(options)
 
             if norepo:
                 # Avoid import cycle.
                 import commands
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
 
             if optionalrepo:
                 import commands
                 commands.optionalrepo += ' %s' % ' '.join(parsealiases(name))
 
             if inferrepo:
                 import commands
                 commands.inferrepo += ' %s' % ' '.join(parsealiases(name))
 
             return func
         return decorator
 
     return cmd
 
 # a list of (ui, repo, otherpeer, opts, missing) functions called by
 # commands.outgoing.  "missing" is "missing" of the result of
 # "findcommonoutgoing()"
 outgoinghooks = util.hooks()
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # a list of (ui, repo, opts, changes) functions called by commands.summary.
 #
 # functions should return tuple of booleans below, if 'changes' is None:
 #  (whether-incomings-are-needed, whether-outgoings-are-needed)
 #
 # otherwise, 'changes' is a tuple of tuples below:
 #  - (sourceurl, sourcebranch, sourcepeer, incoming)
 #  - (desturl,   destbranch,   destpeer,   outgoing)
 summaryremotehooks = util.hooks()
 
 # A list of state files kept by multistep operations like graft.
 # Since graft cannot be aborted, it is considered 'clearable' by update.
 # note: bisect is intentionally excluded
 # (state file, clearable, allowcommit, error, hint)
 unfinishedstates = [
     ('graftstate', True, False, _('graft in progress'),
      _("use 'hg graft --continue' or 'hg update' to abort")),
     ('updatestate', True, False, _('last update was interrupted'),
      _("use 'hg update' to get a consistent checkout"))
     ]
 
 def checkunfinished(repo, commit=False):
     '''Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if commit and allowcommit:
             continue
         if repo.vfs.exists(f):
             raise util.Abort(msg, hint=hint)
 
 def clearunfinished(repo):
     '''Check for unfinished operations (as above), and clear the ones
     that are clearable.
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if not clearable and repo.vfs.exists(f):
             raise util.Abort(msg, hint=hint)
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if clearable and repo.vfs.exists(f):
             util.unlink(repo.join(f))

mercurial/context.py

@@ -1,1694 +1,1699 b''
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 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 node import nullid, nullrev, short, hex, bin
 from i18n import _
 import mdiff, error, util, scmutil, subrepo, patch, encoding, phases
 import match as matchmod
 import os, errno, stat
 import obsolete as obsmod
 import repoview
 import fileset
 import revlog
 
 propertycache = util.propertycache
 
 class basectx(object):
     """A basectx object represents the common logic for its children:
     changectx: read-only context that is already present in the repo,
     workingctx: a context that represents the working directory and can
                 be committed,
     memctx: a context that represents changes in-memory and can also
             be committed."""
     def __new__(cls, repo, changeid='', *args, **kwargs):
         if isinstance(changeid, basectx):
             return changeid
 
         o = super(basectx, cls).__new__(cls)
 
         o._repo = repo
         o._rev = nullrev
         o._node = nullid
 
         return o
 
     def __str__(self):
         return short(self.node())
 
     def __int__(self):
         return self.rev()
 
     def __repr__(self):
         return "<%s %s>" % (type(self).__name__, str(self))
 
     def __eq__(self, other):
         try:
             return type(self) == type(other) and self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         for f in sorted(self._manifest):
             yield f
 
     def _manifestmatches(self, match, s):
         """generate a new manifest filtered by the match argument
 
         This method is for internal use only and mainly exists to provide an
         object oriented way for other contexts to customize the manifest
         generation.
         """
         if match.always():
             return self.manifest().copy()
 
         files = match.files()
         if (match.matchfn == match.exact or
             (not match.anypats() and util.all(fn in self for fn in files))):
             return self.manifest().intersectfiles(files)
 
         mf = self.manifest().copy()
         for fn in mf.keys():
             if not match(fn):
                 del mf[fn]
         return mf
 
     def _matchstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """return match.always if match is none
 
         This internal method provides a way for child objects to override the
         match operator.
         """
         return match or matchmod.always(self._repo.root, self._repo.getcwd())
 
     def _prestatus(self, other, s, match, listignored, listclean, listunknown):
         """provide a hook to allow child objects to preprocess status results
 
         For example, this allows other contexts, such as workingctx, to query
         the dirstate before comparing the manifests.
         """
         # load earliest manifest first for caching reasons
         if self.rev() < other.rev():
             self.manifest()
         return s
 
     def _poststatus(self, other, s, match, listignored, listclean, listunknown):
         """provide a hook to allow child objects to postprocess status results
 
         For example, this allows other contexts, such as workingctx, to filter
         suspect symlinks in the case of FAT32 and NTFS filesytems.
         """
         return s
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context"""
         mf1 = other._manifestmatches(match, s)
         mf2 = self._manifestmatches(match, s)
 
         modified, added, clean = [], [], []
         deleted, unknown, ignored = s[3], s[4], s[5]
         withflags = mf1.withflags() | mf2.withflags()
         for fn, mf2node in mf2.iteritems():
             if fn in mf1:
                 if (fn not in deleted and
                     ((fn in withflags and mf1.flags(fn) != mf2.flags(fn)) or
                      (mf1[fn] != mf2node and
                       (mf2node or self[fn].cmp(other[fn]))))):
                     modified.append(fn)
                 elif listclean:
                     clean.append(fn)
                 del mf1[fn]
             elif fn not in deleted:
                 added.append(fn)
         removed = mf1.keys()
         if removed:
             # need to filter files if they are already reported as removed
             unknown = [fn for fn in unknown if fn not in mf1]
             ignored = [fn for fn in ignored if fn not in mf1]
 
         return [modified, added, removed, deleted, unknown, ignored, clean]
 
     @propertycache
     def substate(self):
         return subrepo.state(self, self._repo.ui)
 
     def subrev(self, subpath):
         return self.substate[subpath][1]
 
     def rev(self):
         return self._rev
     def node(self):
         return self._node
     def hex(self):
         return hex(self.node())
     def manifest(self):
         return self._manifest
     def phasestr(self):
         return phases.phasenames[self.phase()]
     def mutable(self):
         return self.phase() > phases.public
 
     def getfileset(self, expr):
         return fileset.getfileset(self, expr)
 
     def obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, 'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, 'extinct')
 
     def unstable(self):
         """True if the changeset is not obsolete but it's ancestor are"""
         return self.rev() in obsmod.getrevs(self._repo, 'unstable')
 
     def bumped(self):
         """True if the changeset try to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be bumped.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'bumped')
 
     def divergent(self):
         """Is a successors of a changeset with multiple possible successors set
 
         Only non-public and non-obsolete changesets may be divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'divergent')
 
     def troubled(self):
         """True if the changeset is either unstable, bumped or divergent"""
         return self.unstable() or self.bumped() or self.divergent()
 
     def troubles(self):
         """return the list of troubles affecting this changesets.
 
         Troubles are returned as strings. possible values are:
         - unstable,
         - bumped,
         - divergent.
         """
         troubles = []
         if self.unstable():
             troubles.append('unstable')
         if self.bumped():
             troubles.append('bumped')
         if self.divergent():
             troubles.append('divergent')
         return troubles
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         if len(self._parents) == 2:
             return self._parents[1]
         return changectx(self._repo, -1)
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.ManifestLookupError(self._node, path,
                                                 _('not found in manifest'))
         if '_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return (self._manifestdelta[path],
                         self._manifestdelta.flags(path))
         node, flag = self._repo.manifest.find(self._changeset[0], path)
         if not node:
             raise error.ManifestLookupError(self._node, path,
                                             _('not found in manifest'))
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return ''
 
     def sub(self, path):
         return subrepo.subrepo(self, path)
 
     def match(self, pats=[], include=None, exclude=None, default='glob'):
         r = self._repo
         return matchmod.match(r.root, r.getcwd(), pats,
                               include, exclude, default,
                               auditor=r.auditor, ctx=self)
 
     def diff(self, ctx2=None, match=None, **opts):
         """Returns a diff generator for the given contexts and matcher"""
         if ctx2 is None:
             ctx2 = self.p1()
         if ctx2 is not None:
             ctx2 = self._repo[ctx2]
         diffopts = patch.diffopts(self._repo.ui, opts)
         return patch.diff(self._repo, ctx2, self, match=match, opts=diffopts)
 
     @propertycache
     def _dirs(self):
         return scmutil.dirs(self._manifest)
 
     def dirs(self):
         return self._dirs
 
     def dirty(self, missing=False, merge=True, branch=True):
         return False
 
     def status(self, other=None, match=None, listignored=False,
                listclean=False, listunknown=False, listsubrepos=False):
         """return status of files between two nodes or node and working
         directory.
 
         If other is None, compare this node with working directory.
 
         returns (modified, added, removed, deleted, unknown, ignored, clean)
         """
 
         ctx1 = self
         ctx2 = self._repo[other]
 
         # This next code block is, admittedly, fragile logic that tests for
         # reversing the contexts and wouldn't need to exist if it weren't for
         # the fast (and common) code path of comparing the working directory
         # with its first parent.
         #
         # What we're aiming for here is the ability to call:
         #
         # workingctx.status(parentctx)
         #
         # If we always built the manifest for each context and compared those,
         # then we'd be done. But the special case of the above call means we
         # just copy the manifest of the parent.
         reversed = False
         if (not isinstance(ctx1, changectx)
             and isinstance(ctx2, changectx)):
             reversed = True
             ctx1, ctx2 = ctx2, ctx1
 
         r = [[], [], [], [], [], [], []]
         match = ctx2._matchstatus(ctx1, r, match, listignored, listclean,
                                   listunknown)
         r = ctx2._prestatus(ctx1, r, match, listignored, listclean, listunknown)
         r = ctx2._buildstatus(ctx1, r, match, listignored, listclean,
                               listunknown)
         r = ctx2._poststatus(ctx1, r, match, listignored, listclean,
                              listunknown)
 
         if reversed:
             # reverse added and removed
             r[1], r[2] = r[2], r[1]
 
         if listsubrepos:
             for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
                 rev2 = ctx2.subrev(subpath)
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self._repo.ui.status(_("skipping missing "
                                            "subrepository: %s\n") % subpath)
 
         for l in r:
             l.sort()
 
         # we return a tuple to signify that this list isn't changing
         return tuple(r)
 
 
 def makememctx(repo, parents, text, user, date, branch, files, store,
                editor=None):
     def getfilectx(repo, memctx, path):
-        data, (islink, isexec), copied = store.getfile(path)
+        data, mode, copied = store.getfile(path)
+        if data is None:
+            return None
+        islink, isexec = mode
         return memfilectx(repo, path, data, islink=islink, isexec=isexec,
                                   copied=copied, memctx=memctx)
     extra = {}
     if branch:
         extra['branch'] = encoding.fromlocal(branch)
     ctx =  memctx(repo, parents, text, files, getfilectx, user,
                           date, extra, editor)
     return ctx
 
 class changectx(basectx):
     """A changecontext object makes access to data related to a particular
     changeset convenient. It represents a read-only context already present in
     the repo."""
     def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
 
         # since basectx.__new__ already took care of copying the object, we
         # don't need to do anything in __init__, so we just exit here
         if isinstance(changeid, basectx):
             return
 
         if changeid == '':
             changeid = '.'
         self._repo = repo
 
         if isinstance(changeid, int):
             try:
                 self._node = repo.changelog.node(changeid)
             except IndexError:
                 raise error.RepoLookupError(
                     _("unknown revision '%s'") % changeid)
             self._rev = changeid
             return
         if isinstance(changeid, long):
             changeid = str(changeid)
         if changeid == '.':
             self._node = repo.dirstate.p1()
             self._rev = repo.changelog.rev(self._node)
             return
         if changeid == 'null':
             self._node = nullid
             self._rev = nullrev
             return
         if changeid == 'tip':
             self._node = repo.changelog.tip()
             self._rev = repo.changelog.rev(self._node)
             return
         if len(changeid) == 20:
             try:
                 self._node = changeid
                 self._rev = repo.changelog.rev(changeid)
                 return
             except LookupError:
                 pass
 
         try:
             r = int(changeid)
             if str(r) != changeid:
                 raise ValueError
             l = len(repo.changelog)
             if r < 0:
                 r += l
             if r < 0 or r >= l:
                 raise ValueError
             self._rev = r
             self._node = repo.changelog.node(r)
             return
         except (ValueError, OverflowError, IndexError):
             pass
 
         if len(changeid) == 40:
             try:
                 self._node = bin(changeid)
                 self._rev = repo.changelog.rev(self._node)
                 return
             except (TypeError, LookupError):
                 pass
 
         if changeid in repo._bookmarks:
             self._node = repo._bookmarks[changeid]
             self._rev = repo.changelog.rev(self._node)
             return
         if changeid in repo._tagscache.tags:
             self._node = repo._tagscache.tags[changeid]
             self._rev = repo.changelog.rev(self._node)
             return
         try:
             self._node = repo.branchtip(changeid)
             self._rev = repo.changelog.rev(self._node)
             return
         except error.RepoLookupError:
             pass
 
         self._node = repo.changelog._partialmatch(changeid)
         if self._node is not None:
             self._rev = repo.changelog.rev(self._node)
             return
 
         # lookup failed
         # check if it might have come from damaged dirstate
         #
         # XXX we could avoid the unfiltered if we had a recognizable exception
         # for filtered changeset access
         if changeid in repo.unfiltered().dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(changeid))
         try:
             if len(changeid) == 20:
                 changeid = hex(changeid)
         except TypeError:
             pass
         raise error.RepoLookupError(
             _("unknown revision '%s'") % changeid)
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.read(self.rev())
 
     @propertycache
     def _manifest(self):
         return self._repo.manifest.read(self._changeset[0])
 
     @propertycache
     def _manifestdelta(self):
         return self._repo.manifest.readdelta(self._changeset[0])
 
     @propertycache
     def _parents(self):
         p = self._repo.changelog.parentrevs(self._rev)
         if p[1] == nullrev:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     def changeset(self):
         return self._changeset
     def manifestnode(self):
         return self._changeset[0]
 
     def user(self):
         return self._changeset[1]
     def date(self):
         return self._changeset[2]
     def files(self):
         return self._changeset[3]
     def description(self):
         return self._changeset[4]
     def branch(self):
         return encoding.tolocal(self._changeset[5].get("branch"))
     def closesbranch(self):
         return 'close' in self._changeset[5]
     def extra(self):
         return self._changeset[5]
     def tags(self):
         return self._repo.nodetags(self._node)
     def bookmarks(self):
         return self._repo.nodebookmarks(self._node)
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, 'visible')
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors([self._rev]):
             yield changectx(self._repo, a)
 
     def descendants(self):
         for d in self._repo.changelog.descendants([self._rev]):
             yield changectx(self._repo, d)
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
     def ancestor(self, c2, warn=False):
         """
         return the "best" ancestor context of self and c2
         """
         # deal with workingctxs
         n2 = c2._node
         if n2 is None:
             n2 = c2._parents[0]._node
         cahs = self._repo.changelog.commonancestorsheads(self._node, n2)
         if not cahs:
             anc = nullid
         elif len(cahs) == 1:
             anc = cahs[0]
         else:
             for r in self._repo.ui.configlist('merge', 'preferancestor'):
                 if r == '*':
                     continue
                 ctx = changectx(self._repo, r)
                 anc = ctx.node()
                 if anc in cahs:
                     break
             else:
                 anc = self._repo.changelog.ancestor(self._node, n2)
             if warn:
                 self._repo.ui.status(
                     (_("note: using %s as ancestor of %s and %s\n") %
                      (short(anc), short(self._node), short(n2))) +
                     ''.join(_("      alternatively, use --config "
                               "merge.preferancestor=%s\n") %
                             short(n) for n in sorted(cahs) if n != anc))
         return changectx(self._repo, anc)
 
     def descendant(self, other):
         """True if other is descendant of this changeset"""
         return self._repo.changelog.descendant(self._rev, other._rev)
 
     def walk(self, match):
         fset = set(match.files())
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         # avoid the entire walk if we're only looking for specific files
         if fset and not match.anypats():
             if util.all([fn in self for fn in fset]):
                 for fn in sorted(fset):
                     if match(fn):
                         yield fn
                 raise StopIteration
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
         for fn in sorted(fset):
             if fn in self._dirs:
                 # specified pattern is a directory
                 continue
             match.bad(fn, _('no such file in rev %s') % self)
 
     def matches(self, match):
         return self.walk(match)
 
 class basefilectx(object):
     """A filecontext object represents the common logic for its children:
     filectx: read-only access to a filerevision that is already present
              in the repo,
     workingfilectx: a filecontext that represents files from the working
                     directory,
     memfilectx: a filecontext that represents files in-memory."""
     def __new__(cls, repo, path, *args, **kwargs):
         return super(basefilectx, cls).__new__(cls)
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if '_changeid' in self.__dict__:
             return self._changeid
         elif '_changectx' in self.__dict__:
             return self._changectx.rev()
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if '_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     def __str__(self):
         return "%s@%s" % (self.path(), self._changectx)
 
     def __repr__(self):
         return "<%s %s>" % (type(self).__name__, str(self))
 
     def __hash__(self):
         try:
             return hash((self._path, self._filenode))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (type(self) == type(other) and self._path == other._path
                     and self._filenode == other._filenode)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filerev(self):
         return self._filerev
     def filenode(self):
         return self._filenode
     def flags(self):
         return self._changectx.flags(self._path)
     def filelog(self):
         return self._filelog
     def rev(self):
         return self._changeid
     def linkrev(self):
         return self._filelog.linkrev(self._filerev)
     def node(self):
         return self._changectx.node()
     def hex(self):
         return self._changectx.hex()
     def user(self):
         return self._changectx.user()
     def date(self):
         return self._changectx.date()
     def files(self):
         return self._changectx.files()
     def description(self):
         return self._changectx.description()
     def branch(self):
         return self._changectx.branch()
     def extra(self):
         return self._changectx.extra()
     def phase(self):
         return self._changectx.phase()
     def phasestr(self):
         return self._changectx.phasestr()
     def manifest(self):
         return self._changectx.manifest()
     def changectx(self):
         return self._changectx
 
     def path(self):
         return self._path
 
     def isbinary(self):
         try:
             return util.binary(self.data())
         except IOError:
             return False
     def isexec(self):
         return 'x' in self.flags()
     def islink(self):
         return 'l' in self.flags()
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         if (fctx._filerev is None
             and (self._repo._encodefilterpats
                  # if file data starts with '\1\n', empty metadata block is
                  # prepended, which adds 4 bytes to filelog.size().
                  or self.size() - 4 == fctx.size())
             or self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
 
         return True
 
     def parents(self):
         _path = self._path
         fl = self._filelog
         pl = [(_path, n, fl) for n in self._filelog.parents(self._filenode)]
 
         r = self._filelog.renamed(self._filenode)
         if r:
             pl[0] = (r[0], r[1], None)
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def p1(self):
         return self.parents()[0]
 
     def p2(self):
         p = self.parents()
         if len(p) == 2:
             return p[1]
         return filectx(self._repo, self._path, fileid=-1, filelog=self._filelog)
 
     def annotate(self, follow=False, linenumber=None, diffopts=None):
         '''returns a list of tuples of (ctx, line) for each line
         in the file, where ctx is the filectx of the node where
         that line was last changed.
         This returns tuples of ((ctx, linenumber), line) for each line,
         if "linenumber" parameter is NOT "None".
         In such tuples, linenumber means one at the first appearance
         in the managed file.
         To reduce annotation cost,
         this returns fixed value(False is used) as linenumber,
         if "linenumber" parameter is "False".'''
 
         if linenumber is None:
             def decorate(text, rev):
                 return ([rev] * len(text.splitlines()), text)
         elif linenumber:
             def decorate(text, rev):
                 size = len(text.splitlines())
                 return ([(rev, i) for i in xrange(1, size + 1)], text)
         else:
             def decorate(text, rev):
                 return ([(rev, False)] * len(text.splitlines()), text)
 
         def pair(parent, child):
             blocks = mdiff.allblocks(parent[1], child[1], opts=diffopts,
                                      refine=True)
             for (a1, a2, b1, b2), t in blocks:
                 # Changed blocks ('!') or blocks made only of blank lines ('~')
                 # belong to the child.
                 if t == '=':
                     child[0][b1:b2] = parent[0][a1:a2]
             return child
 
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
 
         def parents(f):
             pl = f.parents()
 
             # Don't return renamed parents if we aren't following.
             if not follow:
                 pl = [p for p in pl if p.path() == f.path()]
 
             # renamed filectx won't have a filelog yet, so set it
             # from the cache to save time
             for p in pl:
                 if not '_filelog' in p.__dict__:
                     p._filelog = getlog(p.path())
 
             return pl
 
         # use linkrev to find the first changeset where self appeared
         if self.rev() != self.linkrev():
             base = self.filectx(self.filenode())
         else:
             base = self
 
         # This algorithm would prefer to be recursive, but Python is a
         # bit recursion-hostile. Instead we do an iterative
         # depth-first search.
 
         visit = [base]
         hist = {}
         pcache = {}
         needed = {base: 1}
         while visit:
             f = visit[-1]
             pcached = f in pcache
             if not pcached:
                 pcache[f] = parents(f)
 
             ready = True
             pl = pcache[f]
             for p in pl:
                 if p not in hist:
                     ready = False
                     visit.append(p)
                 if not pcached:
                     needed[p] = needed.get(p, 0) + 1
             if ready:
                 visit.pop()
                 reusable = f in hist
                 if reusable:
                     curr = hist[f]
                 else:
                     curr = decorate(f.data(), f)
                 for p in pl:
                     if not reusable:
                         curr = pair(hist[p], curr)
                     if needed[p] == 1:
                         del hist[p]
                         del needed[p]
                     else:
                         needed[p] -= 1
 
                 hist[f] = curr
                 pcache[f] = []
 
         return zip(hist[base][0], hist[base][1].splitlines(True))
 
     def ancestors(self, followfirst=False):
         visit = {}
         c = self
         cut = followfirst and 1 or None
         while True:
             for parent in c.parents()[:cut]:
                 visit[(parent.rev(), parent.node())] = parent
             if not visit:
                 break
             c = visit.pop(max(visit))
             yield c
 
 class filectx(basefilectx):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
     def __init__(self, repo, path, changeid=None, fileid=None,
                  filelog=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (changeid is not None
                 or fileid is not None
                 or changectx is not None), \
                 ("bad args: changeid=%r, fileid=%r, changectx=%r"
                  % (changeid, fileid, changectx))
 
         if filelog is not None:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         try:
             return changectx(self._repo, self._changeid)
         except error.RepoLookupError:
             # Linkrev may point to any revision in the repository.  When the
             # repository is filtered this may lead to `filectx` trying to build
             # `changectx` for filtered revision. In such case we fallback to
             # creating `changectx` on the unfiltered version of the reposition.
             # This fallback should not be an issue because `changectx` from
             # `filectx` are not used in complex operations that care about
             # filtering.
             #
             # This fallback is a cheap and dirty fix that prevent several
             # crashes. It does not ensure the behavior is correct. However the
             # behavior was not correct before filtering either and "incorrect
             # behavior" is seen as better as "crash"
             #
             # Linkrevs have several serious troubles with filtering that are
             # complicated to solve. Proper handling of the issue here should be
             # considered when solving linkrev issue are on the table.
             return changectx(self._repo.unfiltered(), self._changeid)
 
     def filectx(self, fileid):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(self._repo, self._path, fileid=fileid,
                        filelog=self._filelog)
 
     def data(self):
         return self._filelog.read(self._filenode)
     def size(self):
         return self._filelog.size(self._filerev)
 
     def renamed(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return renamed
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [filectx(self._repo, self._path, fileid=x,
                         filelog=self._filelog) for x in c]
 
 class committablectx(basectx):
     """A committablectx object provides common functionality for a context that
     wants the ability to commit, e.g. workingctx or memctx."""
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = util.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = changes
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if 'branch' not in self._extra:
             try:
                 branch = encoding.fromlocal(self._repo.dirstate.branch())
             except UnicodeDecodeError:
                 raise util.Abort(_('branch name not in UTF-8!'))
             self._extra['branch'] = branch
         if self._extra['branch'] == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __nonzero__(self):
         return True
 
     def _buildflagfunc(self):
         # Create a fallback function for getting file flags when the
         # filesystem doesn't support them
 
         copiesget = self._repo.dirstate.copies().get
 
         if len(self._parents) < 2:
             # when we have one parent, it's easy: copy from parent
             man = self._parents[0].manifest()
             def func(f):
                 f = copiesget(f, f)
                 return man.flags(f)
         else:
             # merges are tricky: we try to reconstruct the unstored
             # result from the merge (issue1802)
             p1, p2 = self._parents
             pa = p1.ancestor(p2)
             m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
 
             def func(f):
                 f = copiesget(f, f) # may be wrong for merges with copies
                 fl1, fl2, fla = m1.flags(f), m2.flags(f), ma.flags(f)
                 if fl1 == fl2:
                     return fl1
                 if fl1 == fla:
                     return fl2
                 if fl2 == fla:
                     return fl1
                 return '' # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the values in self._status"""
 
         man = self._parents[0].manifest().copy()
         if len(self._parents) > 1:
             man2 = self.p2().manifest()
             def getman(f):
                 if f in man:
                     return man
                 return man2
         else:
             getman = lambda f: man
 
         copied = self._repo.dirstate.copies()
         ff = self._flagfunc
         modified, added, removed, deleted = self._status[:4]
         for i, l in (("a", added), ("m", modified)):
             for f in l:
                 orig = copied.get(f, f)
                 man[f] = getman(orig).get(orig, nullid) + i
                 try:
                     man.set(f, ff(f))
                 except OSError:
                     pass
 
         for f in deleted + removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         return self._repo.status()
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         return util.makedate()
 
     def subrev(self, subpath):
         return None
 
     def user(self):
         return self._user or self._repo.ui.username()
     def date(self):
         return self._date
     def description(self):
         return self._text
     def files(self):
         return sorted(self._status[0] + self._status[1] + self._status[2])
 
     def modified(self):
         return self._status[0]
     def added(self):
         return self._status[1]
     def removed(self):
         return self._status[2]
     def deleted(self):
         return self._status[3]
     def unknown(self):
         return self._status[4]
     def ignored(self):
         return self._status[5]
     def clean(self):
         return self._status[6]
     def branch(self):
         return encoding.tolocal(self._extra['branch'])
     def closesbranch(self):
         return 'close' in self._extra
     def extra(self):
         return self._extra
 
     def tags(self):
         t = []
         for p in self.parents():
             t.extend(p.tags())
         return t
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.draft # default phase to draft
         for p in self.parents():
             phase = max(phase, p.phase())
         return phase
 
     def hidden(self):
         return False
 
     def children(self):
         return []
 
     def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return ''
 
     def ancestor(self, c2):
         """return the ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
     def walk(self, match):
         return sorted(self._repo.dirstate.walk(match, sorted(self.substate),
                                                True, False))
 
     def matches(self, match):
         return sorted(self._repo.dirstate.matches(match))
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]):
             yield changectx(self._repo, a)
 
     def markcommitted(self, node):
         """Perform post-commit cleanup necessary after committing this ctx
 
         Specifically, this updates backing stores this working context
         wraps to reflect the fact that the changes reflected by this
         workingctx have been committed.  For example, it marks
         modified and added files as normal in the dirstate.
 
         """
 
         for f in self.modified() + self.added():
             self._repo.dirstate.normal(f)
         for f in self.removed():
             self._repo.dirstate.drop(f)
         self._repo.dirstate.setparents(node)
 
     def dirs(self):
         return self._repo.dirstate.dirs()
 
 class workingctx(committablectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         super(workingctx, self).__init__(repo, text, user, date, extra, changes)
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d[f] != 'r':
                 yield f
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(self._repo, path, workingctx=self,
                               filelog=filelog)
 
     def dirty(self, missing=False, merge=True, branch=True):
         "check whether a working directory is modified"
         # check subrepos first
         for s in sorted(self.substate):
             if self.sub(s).dirty():
                 return True
         # check current working dir
         return ((merge and self.p2()) or
                 (branch and self.branch() != self.p1().branch()) or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
     def add(self, list, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         wlock = self._repo.wlock()
         ui, ds = self._repo.ui, self._repo.dirstate
         try:
             rejected = []
             lstat = self._repo.wvfs.lstat
             for f in list:
                 scmutil.checkportable(ui, join(f))
                 try:
                     st = lstat(f)
                 except OSError:
                     ui.warn(_("%s does not exist!\n") % join(f))
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     ui.warn(_("%s: up to %d MB of RAM may be required "
                               "to manage this file\n"
                               "(use 'hg revert %s' to cancel the "
                               "pending addition)\n")
                               % (f, 3 * st.st_size // 1000000, join(f)))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(_("%s not added: only files and symlinks "
                               "supported currently\n") % join(f))
                     rejected.append(f)
                 elif ds[f] in 'amn':
                     ui.warn(_("%s already tracked!\n") % join(f))
                 elif ds[f] == 'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, files, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         wlock = self._repo.wlock()
         try:
             rejected = []
             for f in files:
                 if f not in self._repo.dirstate:
                     self._repo.ui.warn(_("%s not tracked!\n") % join(f))
                     rejected.append(f)
                 elif self._repo.dirstate[f] != 'a':
                     self._repo.dirstate.remove(f)
                 else:
                     self._repo.dirstate.drop(f)
             return rejected
         finally:
             wlock.release()
 
     def undelete(self, list):
         pctxs = self.parents()
         wlock = self._repo.wlock()
         try:
             for f in list:
                 if self._repo.dirstate[f] != 'r':
                     self._repo.ui.warn(_("%s not removed!\n") % f)
                 else:
                     fctx = f in pctxs[0] and pctxs[0][f] or pctxs[1][f]
                     t = fctx.data()
                     self._repo.wwrite(f, t, fctx.flags())
                     self._repo.dirstate.normal(f)
         finally:
             wlock.release()
 
     def copy(self, source, dest):
         try:
             st = self._repo.wvfs.lstat(dest)
         except OSError, err:
             if err.errno != errno.ENOENT:
                 raise
             self._repo.ui.warn(_("%s does not exist!\n") % dest)
             return
         if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
             self._repo.ui.warn(_("copy failed: %s is not a file or a "
                                  "symbolic link\n") % dest)
         else:
             wlock = self._repo.wlock()
             try:
                 if self._repo.dirstate[dest] in '?r':
                     self._repo.dirstate.add(dest)
                 self._repo.dirstate.copy(source, dest)
             finally:
                 wlock.release()
 
     def _filtersuspectsymlink(self, files):
         if not files or self._repo.dirstate._checklink:
             return files
 
         # Symlink placeholders may get non-symlink-like contents
         # via user error or dereferencing by NFS or Samba servers,
         # so we filter out any placeholders that don't look like a
         # symlink
         sane = []
         for f in files:
             if self.flags(f) == 'l':
                 d = self[f].data()
                 if d == '' or len(d) >= 1024 or '\n' in d or util.binary(d):
                     self._repo.ui.debug('ignoring suspect symlink placeholder'
                                         ' "%s"\n' % f)
                     continue
             sane.append(f)
         return sane
 
     def _checklookup(self, files):
         # check for any possibly clean files
         if not files:
             return [], []
 
         modified = []
         fixup = []
         pctx = self._parents[0]
         # do a full compare of any files that might have changed
         for f in sorted(files):
             if (f not in pctx or self.flags(f) != pctx.flags(f)
                 or pctx[f].cmp(self[f])):
                 modified.append(f)
             else:
                 fixup.append(f)
 
         # update dirstate for files that are actually clean
         if fixup:
             try:
                 # updating the dirstate is optional
                 # so we don't wait on the lock
                 # wlock can invalidate the dirstate, so cache normal _after_
                 # taking the lock
                 wlock = self._repo.wlock(False)
                 normal = self._repo.dirstate.normal
                 try:
                     for f in fixup:
                         normal(f)
                 finally:
                     wlock.release()
             except error.LockError:
                 pass
         return modified, fixup
 
     def _manifestmatches(self, match, s):
         """Slow path for workingctx
 
         The fast path is when we compare the working directory to its parent
         which means this function is comparing with a non-parent; therefore we
         need to build a manifest and return what matches.
         """
         mf = self._repo['.']._manifestmatches(match, s)
         modified, added, removed = s[0:3]
         for f in modified + added:
             mf[f] = None
             mf.set(f, self.flags(f))
         for f in removed:
             if f in mf:
                 del mf[f]
         return mf
 
     def _prestatus(self, other, s, match, listignored, listclean, listunknown):
         """override the parent hook with a dirstate query
 
         We use this prestatus hook to populate the status with information from
         the dirstate.
         """
         # doesn't need to call super; if that changes, be aware that super
         # calls self.manifest which would slow down the common case of calling
         # status against a workingctx's parent
         return self._dirstatestatus(match, listignored, listclean, listunknown)
 
     def _poststatus(self, other, s, match, listignored, listclean, listunknown):
         """override the parent hook with a filter for suspect symlinks
 
         We use this poststatus hook to filter out symlinks that might have
         accidentally ended up with the entire contents of the file they are
         susposed to be linking to.
         """
         s[0] = self._filtersuspectsymlink(s[0])
         self._status = s[:]
         return s
 
     def _dirstatestatus(self, match=None, ignored=False, clean=False,
                         unknown=False):
         '''Gets the status from the dirstate -- internal use only.'''
         listignored, listclean, listunknown = ignored, clean, unknown
         match = match or matchmod.always(self._repo.root, self._repo.getcwd())
         subrepos = []
         if '.hgsub' in self:
             subrepos = sorted(self.substate)
         s = self._repo.dirstate.status(match, subrepos, listignored,
                                        listclean, listunknown)
         cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
         # check for any possibly clean files
         if cmp:
             modified2, fixup = self._checklookup(cmp)
             modified += modified2
 
             # update dirstate for files that are actually clean
             if fixup and listclean:
                 clean += fixup
 
         return [modified, added, removed, deleted, unknown, ignored, clean]
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context
 
         This includes logic for maintaining the fast path of status when
         comparing the working directory against its parent, which is to skip
         building a new manifest if self (working directory) is not comparing
         against its parent (repo['.']).
         """
         if other != self._repo['.']:
             s = super(workingctx, self)._buildstatus(other, s, match,
                                                      listignored, listclean,
                                                      listunknown)
         return s
 
     def _matchstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """override the match method with a filter for directory patterns
 
         We use inheritance to customize the match.bad method only in cases of
         workingctx since it belongs only to the working directory when
         comparing against the parent changeset.
 
         If we aren't comparing against the working directory's parent, then we
         just use the default match object sent to us.
         """
         superself = super(workingctx, self)
         match = superself._matchstatus(other, s, match, listignored, listclean,
                                        listunknown)
         if other != self._repo['.']:
             def bad(f, msg):
                 # 'f' may be a directory pattern from 'match.files()',
                 # so 'f not in ctx1' is not enough
                 if f not in other and f not in other.dirs():
                     self._repo.ui.warn('%s: %s\n' %
                                        (self._repo.dirstate.pathto(f), msg))
             match.bad = bad
         return match
 
     def status(self, other='.', match=None, listignored=False,
                listclean=False, listunknown=False, listsubrepos=False):
         # yet to be determined: what to do if 'other' is a 'workingctx' or a
         # 'memctx'?
         s = super(workingctx, self).status(other, match, listignored, listclean,
                                            listunknown, listsubrepos)
         # calling 'super' subtly reveresed the contexts, so we flip the results
         # (s[1] is 'added' and s[2] is 'removed')
         s = list(s)
         s[1], s[2] = s[2], s[1]
         return tuple(s)
 
 class committablefilectx(basefilectx):
     """A committablefilectx provides common functionality for a file context
     that wants the ability to commit, e.g. workingfilectx or memfilectx."""
     def __init__(self, repo, path, filelog=None, ctx=None):
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog is not None:
             self._filelog = filelog
         if ctx:
             self._changectx = ctx
 
     def __nonzero__(self):
         return True
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def children(self):
         return []
 
 class workingfilectx(committablefilectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
     def __init__(self, repo, path, filelog=None, workingctx=None):
         super(workingfilectx, self).__init__(repo, path, filelog, workingctx)
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def data(self):
         return self._repo.wread(self._path)
     def renamed(self):
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def size(self):
         return self._repo.wvfs.lstat(self._path).st_size
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (int(self._repo.wvfs.lstat(self._path).st_mtime), tz)
         except OSError, err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         # fctx should be a filectx (not a workingfilectx)
         # invert comparison to reuse the same code path
         return fctx.cmp(self)
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         util.unlinkpath(self._repo.wjoin(self._path), ignoremissing)
 
     def write(self, data, flags):
         """wraps repo.wwrite"""
         self._repo.wwrite(self._path, data, flags)
 
 class memctx(committablectx):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn raises an
     IOError. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by util.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
     def __init__(self, repo, parents, text, files, filectxfn, user=None,
                  date=None, extra=None, editor=False):
         super(memctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [changectx(self._repo, p) for p in (p1, p2)]
         files = sorted(set(files))
         self._status = [files, [], [], [], []]
         self._filectxfn = filectxfn
         self.substate = {}
 
         # if store is not callable, wrap it in a function
         if not callable(filectxfn):
             def getfilectx(repo, memctx, path):
                 fctx = filectxfn[path]
                 # this is weird but apparently we only keep track of one parent
                 # (why not only store that instead of a tuple?)
                 copied = fctx.renamed()
                 if copied:
                     copied = copied[0]
                 return memfilectx(repo, path, fctx.data(),
                                   islink=fctx.islink(), isexec=fctx.isexec(),
                                   copied=copied, memctx=memctx)
             self._filectxfn = getfilectx
 
         self._extra = extra and extra.copy() or {}
         if self._extra.get('branch', '') == '':
             self._extra['branch'] = 'default'
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def filectx(self, path, filelog=None):
-        """get a file context from the working directory"""
+        """get a file context from the working directory
+
+        Returns None if file doesn't exist and should be removed."""
         return self._filectxfn(self._repo, self, path)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @propertycache
     def _manifest(self):
         """generate a manifest based on the return values of filectxfn"""
 
         # keep this simple for now; just worry about p1
         pctx = self._parents[0]
         man = pctx.manifest().copy()
 
         for f, fnode in man.iteritems():
             p1node = nullid
             p2node = nullid
             p = pctx[f].parents() # if file isn't in pctx, check p2?
             if len(p) > 0:
                 p1node = p[0].node()
                 if len(p) > 1:
                     p2node = p[1].node()
             man[f] = revlog.hash(self[f].data(), p1node, p2node)
 
         return man
 
 
 class memfilectx(committablefilectx):
     """memfilectx represents an in-memory file to commit.
 
     See memctx and commitablefilectx for more details.
     """
     def __init__(self, repo, path, data, islink=False,
                  isexec=False, copied=None, memctx=None):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         super(memfilectx, self).__init__(repo, path, None, memctx)
         self._data = data
         self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
         self._copied = None
         if copied:
             self._copied = (copied, nullid)
 
     def data(self):
         return self._data
     def size(self):
         return len(self.data())
     def flags(self):
         return self._flags
     def renamed(self):
         return self._copied
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         # need to figure out what to do here
         del self._changectx[self._path]
 
     def write(self, data, flags):
         """wraps repo.wwrite"""
         self._data = data

mercurial/localrepo.py

@@ -1,1780 +1,1781 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # 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 node import hex, nullid, short
 from i18n import _
 import urllib
 import peer, changegroup, subrepo, pushkey, obsolete, repoview
 import changelog, dirstate, filelog, manifest, context, bookmarks, phases
 import lock as lockmod
 import transaction, store, encoding, exchange, bundle2
 import scmutil, util, extensions, hook, error, revset
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 from lock import release
 import weakref, errno, os, time, inspect
 import branchmap, pathutil
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
 class repofilecache(filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
 
     def __get__(self, repo, type=None):
         return super(repofilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(repofilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(repofilecache, self).__delete__(repo.unfiltered())
 
 class storecache(repofilecache):
     """filecache for files in the store"""
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 class unfilteredpropertycache(propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 moderncaps = set(('lookup', 'branchmap', 'pushkey', 'known', 'getbundle',
                   'unbundle'))
 legacycaps = moderncaps.union(set(['changegroupsubset']))
 
 class localpeer(peer.peerrepository):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=moderncaps):
         peer.peerrepository.__init__(self)
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
         self.requirements = repo.requirements
         self.supportedformats = repo.supportedformats
 
     def close(self):
         self._repo.close()
 
     def _capabilities(self):
         return self._caps
 
     def local(self):
         return self._repo
 
     def canpush(self):
         return True
 
     def url(self):
         return self._repo.url()
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None,
                   format='HG10', **kwargs):
         cg = exchange.getbundle(self._repo, source, heads=heads,
                                 common=common, bundlecaps=bundlecaps, **kwargs)
         if bundlecaps is not None and 'HG2X' in bundlecaps:
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             cg = bundle2.unbundle20(self.ui, cg)
         return cg
 
     # TODO We might want to move the next two calls into legacypeer and add
     # unbundle instead.
 
     def unbundle(self, cg, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             cg = exchange.readbundle(self.ui, cg, None)
             ret = exchange.unbundle(self._repo, cg, heads, 'push', url)
             if util.safehasattr(ret, 'getchunks'):
                 # This is a bundle20 object, turn it into an unbundler.
                 # This little dance should be dropped eventually when the API
                 # is finally improved.
                 stream = util.chunkbuffer(ret.getchunks())
                 ret = bundle2.unbundle20(self.ui, stream)
             return ret
         except error.PushRaced, exc:
             raise error.ResponseError(_('push failed:'), str(exc))
 
     def lock(self):
         return self._repo.lock()
 
     def addchangegroup(self, cg, source, url):
         return changegroup.addchangegroup(self._repo, cg, source, url)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         localpeer.__init__(self, repo, caps=legacycaps)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def changegroup(self, basenodes, source):
         return changegroup.changegroup(self._repo, basenodes, source)
 
     def changegroupsubset(self, bases, heads, source):
         return changegroup.changegroupsubset(self._repo, bases, heads, source)
 
 class localrepository(object):
 
     supportedformats = set(('revlogv1', 'generaldelta'))
     _basesupported = supportedformats | set(('store', 'fncache', 'shared',
                                              'dotencode'))
     openerreqs = set(('revlogv1', 'generaldelta'))
     requirements = ['revlogv1']
     filtername = None
 
     bundle2caps = {'HG2X': (),
                    'b2x:listkeys': (),
                    'b2x:pushkey': (),
                    'b2x:changegroup': (),
                   }
 
     # a list of (ui, featureset) functions.
     # only functions defined in module of enabled extensions are invoked
     featuresetupfuncs = set()
 
     def _baserequirements(self, create):
         return self.requirements[:]
 
     def __init__(self, baseui, path=None, create=False):
         self.wvfs = scmutil.vfs(path, expandpath=True, realpath=True)
         self.wopener = self.wvfs
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
         self.auditor = pathutil.pathauditor(self.root, self._checknested)
         self.vfs = scmutil.vfs(self.path)
         self.opener = self.vfs
         self.baseui = baseui
         self.ui = baseui.copy()
         self.ui.copy = baseui.copy # prevent copying repo configuration
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if self.featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in self.featuresetupfuncs:
                 if setupfunc.__module__ in extmods:
                     setupfunc(self.ui, self.supported)
         else:
             self.supported = self._basesupported
 
         if not self.vfs.isdir():
             if create:
                 if not self.wvfs.exists():
                     self.wvfs.makedirs()
                 self.vfs.makedir(notindexed=True)
                 requirements = self._baserequirements(create)
                 if self.ui.configbool('format', 'usestore', True):
                     self.vfs.mkdir("store")
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                         if self.ui.configbool('format', 'dotencode', True):
                             requirements.append('dotencode')
                     # create an invalid changelog
                     self.vfs.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'generaldelta', False):
                     requirements.append("generaldelta")
                 requirements = set(requirements)
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 requirements = scmutil.readrequires(self.vfs, self.supported)
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = set()
 
         self.sharedpath = self.path
         try:
             vfs = scmutil.vfs(self.vfs.read("sharedpath").rstrip('\n'),
                               realpath=True)
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, scmutil.vfs)
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sopener = self.svfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self._applyrequirements(requirements)
         if create:
             self._writerequirements()
 
 
         self._branchcaches = {}
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
     def close(self):
         pass
 
     def _restrictcapabilities(self, caps):
         # bundle2 is not ready for prime time, drop it unless explicitly
         # required by the tests (or some brave tester)
         if self.ui.configbool('experimental', 'bundle2-exp', False):
             caps = set(caps)
             capsblob = bundle2.encodecaps(self.bundle2caps)
             caps.add('bundle2-exp=' + urllib.quote(capsblob))
         return caps
 
     def _applyrequirements(self, requirements):
         self.requirements = requirements
         self.sopener.options = dict((r, 1) for r in requirements
                                            if r in self.openerreqs)
         chunkcachesize = self.ui.configint('format', 'chunkcachesize')
         if chunkcachesize is not None:
             self.sopener.options['chunkcachesize'] = chunkcachesize
 
     def _writerequirements(self):
         reqfile = self.opener("requires", "w")
         for r in sorted(self.requirements):
             reqfile.write("%s\n" % r)
         reqfile.close()
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name):
         """Return a filtered version of a repository"""
         # build a new class with the mixin and the current class
         # (possibly subclass of the repo)
         class proxycls(repoview.repoview, self.unfiltered().__class__):
             pass
         return proxycls(self, name)
 
     @repofilecache('bookmarks')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @repofilecache('bookmarks.current')
     def _bookmarkcurrent(self):
         return bookmarks.readcurrent(self)
 
     def bookmarkheads(self, bookmark):
         name = bookmark.split('@', 1)[0]
         heads = []
         for mark, n in self._bookmarks.iteritems():
             if mark.split('@', 1)[0] == name:
                 heads.append(n)
         return heads
 
     @storecache('phaseroots')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         store = obsolete.obsstore(self.sopener)
         if store and not obsolete._enabled:
             # message is rare enough to not be translated
             msg = 'obsolete feature not enabled but %i markers found!\n'
             self.ui.warn(msg % len(list(store)))
         return store
 
     @storecache('00changelog.i')
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         return c
 
     @storecache('00manifest.i')
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @repofilecache('dirstate')
     def dirstate(self):
         warned = [0]
         def validate(node):
             try:
                 self.changelog.rev(node)
                 return node
             except error.LookupError:
                 if not warned[0]:
                     warned[0] = True
                     self.ui.warn(_("warning: ignoring unknown"
                                    " working parent %s!\n") % short(node))
                 return nullid
 
         return dirstate.dirstate(self.opener, self.ui, self.root, validate)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Return a list of revisions matching the given revset'''
         expr = revset.formatspec(expr, *args)
         m = revset.match(None, expr)
         return m(self, revset.spanset(self))
 
     def set(self, expr, *args):
         '''
         Yield a context for each matching revision, after doing arg
         replacement via revset.formatspec
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @unfilteredmethod
     def _tag(self, names, node, message, local, user, date, extra={},
              editor=False):
         if isinstance(names, str):
             names = (names,)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if (self._tagscache.tagtypes and
                     name in self._tagscache.tagtypes):
                     old = self.tags().get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError, e:
             if e.errno != errno.ENOENT:
                 raise
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         fp.close()
 
         self.invalidatecaches()
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m,
                               editor=editor)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date, editor=False):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         if not local:
             for x in self.status()[:5]:
                 if '.hgtags' in x:
                     raise util.Abort(_('working copy of .hgtags is changed '
                                        '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date, editor=editor)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
     def branchtip(self, branch):
         '''return the tip node for a given branch'''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             raise error.RepoLookupError(_("unknown branch '%s'") % branch)
 
     def lookup(self, key):
         return self[key].node()
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def known(self, nodes):
         nm = self.changelog.nodemap
         pc = self._phasecache
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or pc.phase(self, r) >= phases.secret)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.ui.configbool('phases', 'publish', True):
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered('visible').changelog.filteredrevs
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def setparents(self, p1, p2=nullid):
         copies = self.dirstate.setparents(p1, p2)
         pctx = self[p1]
         if copies:
             # Adjust copy records, the dirstate cannot do it, it
             # requires access to parents manifests. Preserve them
             # only for entries added to first parent.
             for f in copies:
                 if f not in pctx and copies[f] in pctx:
                     self.dirstate.copy(copies[f], f)
         if p2 == nullid:
             for f, s in sorted(self.dirstate.copies().items()):
                 if f not in pctx and s not in pctx:
                     self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return self.wvfs.islink(f)
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
         return self.filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wopener.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener.write(filename, data)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def transaction(self, desc, report=None):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found"),
                 hint=_("run 'hg recover' to clean up transaction"))
 
         def onclose():
             self.store.write(self._transref())
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         rp = report and report or self.ui.warn
         tr = transaction.transaction(rp, self.sopener,
                                      "journal",
                                      aftertrans(renames),
                                      self.store.createmode,
                                      onclose)
         self._transref = weakref.ref(tr)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     def _writejournal(self, desc):
         self.opener.write("journal.dirstate",
                           self.opener.tryread("dirstate"))
         self.opener.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.opener.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.opener.write("journal.bookmarks",
                           self.opener.tryread("bookmarks"))
         self.sopener.write("journal.phaseroots",
                            self.sopener.tryread("phaseroots"))
 
     def recover(self):
         lock = self.lock()
         try:
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, "journal",
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 return self._rollback(dryrun, force)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force):
         ui = self.ui
         try:
             args = self.opener.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise util.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         transaction.rollback(self.sopener, 'undo', ui.warn)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks')
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots')
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             self.vfs.rename('undo.dirstate', 'dirstate')
             try:
                 branch = self.opener.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             self.dirstate.invalidate()
             parents = tuple([p.rev() for p in self.parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._branchcaches.clear()
         self.invalidatevolatilesets()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self):
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in self._filecache:
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
 
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     def _lock(self, vfs, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lockmod.lock(vfs, lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lockmod.lock(vfs, lockname,
                              int(self.ui.config("ui", "timeout", "600")),
                              releasefn, desc=desc)
             self.ui.warn(_("got lock after %s seconds\n") % l.delay)
         if acquirefn:
             acquirefn()
         return l
 
     def _afterlock(self, callback):
         """add a callback to the current repository lock.
 
         The callback will be executed on lock release."""
         l = self._lockref and self._lockref()
         if l:
             l.postrelease.append(callback)
         else:
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             for k, ce in self._filecache.items():
                 if k == 'dirstate' or k not in self.__dict__:
                     continue
                 ce.refresh()
 
         l = self._lock(self.svfs, "lock", wait, unlock,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.dirstate.write()
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.vfs, "wlock", wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self[None].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             commitsubs = set()
             newstate = wctx.substate.copy()
             # only manage subrepos and .hgsubstate if .hgsub is present
             if '.hgsub' in wctx:
                 # we'll decide whether to track this ourselves, thanks
                 for c in changes[:3]:
                     if '.hgsubstate' in c:
                         c.remove('.hgsubstate')
 
                 # compare current state to last committed state
                 # build new substate based on last committed state
                 oldstate = wctx.p1().substate
                 for s in sorted(newstate.keys()):
                     if not match(s):
                         # ignore working copy, use old state if present
                         if s in oldstate:
                             newstate[s] = oldstate[s]
                             continue
                         if not force:
                             raise util.Abort(
                                 _("commit with new subrepo %s excluded") % s)
                     if wctx.sub(s).dirty(True):
                         if not self.ui.configbool('ui', 'commitsubrepos'):
                             raise util.Abort(
                                 _("uncommitted changes in subrepo %s") % s,
                                 hint=_("use --subrepos for recursive commit"))
                         subs.append(s)
                         commitsubs.add(s)
                     else:
                         bs = wctx.sub(s).basestate()
                         newstate[s] = (newstate[s][0], bs, newstate[s][2])
                         if oldstate.get(s, (None, None, None))[1] != bs:
                             subs.append(s)
 
                 # check for removed subrepos
                 for p in wctx.parents():
                     r = [s for s in p.substate if s not in newstate]
                     subs += [s for s in r if match(s)]
                 if subs:
                     if (not match('.hgsub') and
                         '.hgsub' in (wctx.modified() + wctx.added())):
                         raise util.Abort(
                             _("can't commit subrepos without .hgsub"))
                     changes[0].insert(0, '.hgsubstate')
 
             elif '.hgsub' in changes[2]:
                 # clean up .hgsubstate when .hgsub is removed
                 if ('.hgsubstate' in wctx and
                     '.hgsubstate' not in changes[0] + changes[1] + changes[2]):
                     changes[2].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     f = self.dirstate.normalize(f)
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
 
             if (not force and not extra.get("close") and not merge
                 and not cctx.files()
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             if merge and cctx.deleted():
                 raise util.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                        "(see hg help resolve)"))
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepo.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
         finally:
             wlock.release()
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             self.hook("commit", node=node, parent1=parent1, parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = list(ctx.removed())
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.files():
                 m1 = p1.manifest().copy()
                 m2 = p2.manifest()
 
                 # check in files
                 new = {}
                 changed = []
                 linkrev = len(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
-                        new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
-                                                  changed)
-                        m1.set(f, fctx.flags())
+                        if fctx is None:
+                            removed.append(f)
+                        else:
+                            new[f] = self._filecommit(fctx, m1, m2, linkrev,
+                                                      trp, changed)
+                            m1.set(f, fctx.flags())
                     except OSError, inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError, inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
-                            raise
-                        else:
-                            removed.append(f)
+                        raise
 
                 # update manifest
                 m1.update(new)
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m1]
                 for f in drop:
                     del m1[f]
                 mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                        p2.manifestnode(), (new, drop))
                 files = changed + removed
             else:
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             # set the new commit is proper phase
             targetphase = subrepo.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.retractboundary(self, tr, targetphase, [n])
             tr.close()
             branchmap.updatecache(self.filtered('served'))
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # update the 'served' branch cache to help read only server process
         # Thanks to branchcache collaboration this is done from the nearest
         # filtered subset and it is expected to be fast.
         branchmap.updatecache(self.filtered('served'))
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(node2, match, ignored, clean, unknown,
                                   listsubrepos)
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def pull(self, remote, heads=None, force=False):
         return exchange.pull (self, remote, heads, force)
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
         pass
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of "(repo, remote, outgoing)"
         functions, which are called before pushing changesets.
         """
         return util.hooks()
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         return exchange.push(self, remote, force, revs, newbranch)
 
     def stream_in(self, remote, requirements):
         lock = self.lock()
         try:
             # Save remote branchmap. We will use it later
             # to speed up branchcache creation
             rbranchmap = None
             if remote.capable("branchmap"):
                 rbranchmap = remote.branchmap()
 
             fp = remote.stream_out()
             l = fp.readline()
             try:
                 resp = int(l)
             except ValueError:
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             if resp == 1:
                 raise util.Abort(_('operation forbidden by server'))
             elif resp == 2:
                 raise util.Abort(_('locking the remote repository failed'))
             elif resp != 0:
                 raise util.Abort(_('the server sent an unknown error code'))
             self.ui.status(_('streaming all changes\n'))
             l = fp.readline()
             try:
                 total_files, total_bytes = map(int, l.split(' ', 1))
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             self.ui.status(_('%d files to transfer, %s of data\n') %
                            (total_files, util.bytecount(total_bytes)))
             handled_bytes = 0
             self.ui.progress(_('clone'), 0, total=total_bytes)
             start = time.time()
 
             tr = self.transaction(_('clone'))
             try:
                 for i in xrange(total_files):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split('\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _('unexpected response from remote server:'), l)
                     if self.ui.debugflag:
                         self.ui.debug('adding %s (%s)\n' %
                                       (name, util.bytecount(size)))
                     # for backwards compat, name was partially encoded
                     ofp = self.sopener(store.decodedir(name), 'w')
                     for chunk in util.filechunkiter(fp, limit=size):
                         handled_bytes += len(chunk)
                         self.ui.progress(_('clone'), handled_bytes,
                                          total=total_bytes)
                         ofp.write(chunk)
                     ofp.close()
                 tr.close()
             finally:
                 tr.release()
 
             # Writing straight to files circumvented the inmemory caches
             self.invalidate()
 
             elapsed = time.time() - start
             if elapsed <= 0:
                 elapsed = 0.001
             self.ui.progress(_('clone'), None)
             self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                            (util.bytecount(total_bytes), elapsed,
                             util.bytecount(total_bytes / elapsed)))
 
             # new requirements = old non-format requirements +
             #                    new format-related
             # requirements from the streamed-in repository
             requirements.update(set(self.requirements) - self.supportedformats)
             self._applyrequirements(requirements)
             self._writerequirements()
 
             if rbranchmap:
                 rbheads = []
                 for bheads in rbranchmap.itervalues():
                     rbheads.extend(bheads)
 
                 if rbheads:
                     rtiprev = max((int(self.changelog.rev(node))
                             for node in rbheads))
                     cache = branchmap.branchcache(rbranchmap,
                                                   self[rtiprev].node(),
                                                   rtiprev)
                     # Try to stick it as low as possible
                     # filter above served are unlikely to be fetch from a clone
                     for candidate in ('base', 'immutable', 'served'):
                         rview = self.filtered(candidate)
                         if cache.validfor(rview):
                             self._branchcaches[candidate] = cache
                             cache.write(rview)
                             break
             self.invalidate()
             return len(self.heads()) + 1
         finally:
             lock.release()
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if not stream:
             # if the server explicitly prefers to stream (for fast LANs)
             stream = remote.capable('stream-preferred')
 
         if stream and not heads:
             # 'stream' means remote revlog format is revlogv1 only
             if remote.capable('stream'):
                 return self.stream_in(remote, set(('revlogv1',)))
             # otherwise, 'streamreqs' contains the remote revlog format
             streamreqs = remote.capable('streamreqs')
             if streamreqs:
                 streamreqs = set(streamreqs.split(','))
                 # if we support it, stream in and adjust our requirements
                 if not streamreqs - self.supportedformats:
                     return self.stream_in(remote, streamreqs)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         self.hook('prepushkey', throw=True, namespace=namespace, key=key,
                   old=old, new=new)
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                   ret=ret)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
     def savecommitmessage(self, text):
         fp = self.opener('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True