grammar: use does instead of do where appropriate

hgext/convert/bzr.py

@@ -1,287 +1,287 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, error
 # these do not work with demandimport, blacklist
 demandimport.ignore.extend([
         'bzrlib.transactions',
         'bzrlib.urlutils',
         'ElementPath',
     ])
 
 from mercurial.i18n import _
 from mercurial import error
 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, revs=None):
         super(bzr_source, self).__init__(ui, path, revs=revs)
 
         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.revs:
             # 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.revs[0])
                     info = r.in_history(branch)
                 except errors.BzrError:
                     pass
                 revid = info.rev_id
             if revid is None:
                 raise error.Abort(_('%s is not a valid revision')
                                   % self.revs[0])
             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
             return None, None
         mode = self._modecache[(name, rev)]
         if kind == 'symlink':
             target = revtree.get_symlink_target(fileid)
             if target is None:
                 raise error.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, full):
         if full:
-            raise error.Abort(_("convert from cvs do not support --full"))
+            raise error.Abort(_("convert from cvs does not support --full"))
         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])
         files, changes = self._gettreechanges(self._revtree, prevtree)
         return files, changes, set()
 
     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/cvs.py

@@ -1,280 +1,280 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, error
 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, revs=None):
         super(convert_cvs, self).__init__(ui, path, revs=revs)
 
         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.revs:
             if len(self.revs) > 1:
                 raise error.Abort(_('cvs source does not support specifying '
                                    'multiple revs'))
             # TODO: handle tags
             try:
                 # patchset number?
                 maxrev = int(self.revs[0])
             except ValueError:
                 raise error.Abort(_('revision %s is not a patchset number')
                                  % self.revs[0])
 
         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 as 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 error.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 error.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 error.Abort(_("%d bytes missing from remote file")
                                      % count)
                 count -= len(data)
                 output.write(data)
             return output.getvalue()
 
         self._parse()
         if rev.endswith("(DEAD)"):
             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 error.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 error.Abort(_("unknown CVS response: %s") % line)
 
     def getchanges(self, rev, full):
         if full:
-            raise error.Abort(_("convert from cvs do not support --full"))
+            raise error.Abort(_("convert from cvs does not support --full"))
         self._parse()
         return sorted(self.files[rev].iteritems()), {}, set()
 
     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

@@ -1,208 +1,208 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, error
 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, revs=None):
         converter_source.__init__(self, ui, path, revs=revs)
         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 error.Abort(_('darcs version 2.1 or newer needed (found %r)')
                               % version)
 
         if "ElementTree" not in globals():
             raise error.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, full):
         if full:
-            raise error.Abort(_("convert from darcs do not support --full"))
+            raise error.Abort(_("convert from darcs does not support --full"))
         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, set()
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise error.Abort(_('internal calling inconsistency'))
         path = os.path.join(self.tmppath, name)
         try:
             data = util.readfile(path)
             mode = os.lstat(path).st_mode
         except IOError as inst:
             if inst.errno == errno.ENOENT:
                 return None, None
             raise
         mode = (mode & 0o111) and 'x' or ''
         return data, mode
 
     def gettags(self):
         return self.tags

hgext/convert/git.py

@@ -1,416 +1,416 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, error
 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, revs=None):
         super(convert_git, self).__init__(ui, path, revs=revs)
 
         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)
 
         # The default value (50) is based on the default for 'git diff'.
         similarity = ui.configint('convert', 'git.similarity', default=50)
         if similarity < 0 or similarity > 100:
             raise error.Abort(_('similarity must be between 0 and 100'))
         if similarity > 0:
             self.simopt = '-C%d%%' % similarity
             findcopiesharder = ui.configbool('convert', 'git.findcopiesharder',
                                              False)
             if findcopiesharder:
                 self.simopt += ' --find-copies-harder'
         else:
             self.simopt = ''
 
         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.revs:
             heads, ret = self.gitread('git rev-parse --branches --remotes')
             heads = heads.splitlines()
             if ret:
                 raise error.Abort(_('cannot retrieve git heads'))
         else:
             heads = []
             for rev in self.revs:
                 rawhead, ret = self.gitread("git rev-parse --verify %s" % rev)
                 heads.append(rawhead[:-1])
                 if ret:
                     raise error.Abort(_('cannot retrieve git head "%s"') % rev)
         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 error.Abort(_('cannot read %r object at %s') % (type, rev))
         size = int(info[2])
         data = self.catfilepipe[1].read(size)
         if len(data) < size:
             raise error.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):
             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 whitespace that cant be parsed
         c.parse('.gitmodules', '\n'.join(line.strip() for line in
                                content.split('\n')))
         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:
             # This can happen if a file is in the repo that has permissions
             # 160000, but there is no .gitmodules file.
             self.ui.warn(_("warning: cannot read submodules config file in "
                            "%s\n") % version)
             return
 
         try:
             self.parsegitmodules(modules)
         except error.ParseError:
             self.ui.warn(_("warning: unable to parse .gitmodules in %s\n")
                          % version)
             return
 
         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, full):
         if full:
-            raise error.Abort(_("convert from git do not support --full"))
+            raise error.Abort(_("convert from git does not support --full"))
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s %s" % (
             self.simopt, version))
         changes = []
         copies = {}
         seen = set()
         entry = None
         subexists = [False]
         subdeleted = [False]
         difftree = fh.read().split('\x00')
         lcount = len(difftree)
         i = 0
 
         skipsubmodules = self.ui.configbool('convert', 'git.skipsubmodules',
                                             False)
         def add(entry, f, isdest):
             seen.add(f)
             h = entry[3]
             p = (entry[1] == "100755")
             s = (entry[1] == "120000")
             renamesource = (not isdest and entry[4][0] == 'R')
 
             if f == '.gitmodules':
                 if skipsubmodules:
                     return
 
                 subexists[0] = True
                 if entry[4] == 'D' or renamesource:
                     subdeleted[0] = True
                     changes.append(('.hgsub', hex(nullid)))
                 else:
                     changes.append(('.hgsub', ''))
             elif entry[1] == '160000' or entry[0] == ':160000':
                 if not skipsubmodules:
                     subexists[0] = True
             else:
                 if renamesource:
                     h = hex(nullid)
                 self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                 changes.append((f, h))
 
         while i < lcount:
             l = difftree[i]
             i += 1
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l.split()
                 continue
             f = l
             if entry[4][0] == 'C':
                 copysrc = f
                 copydest = difftree[i]
                 i += 1
                 f = copydest
                 copies[copydest] = copysrc
             if f not in seen:
                 add(entry, f, False)
             # A file can be copied multiple times, or modified and copied
             # simultaneously. So f can be repeated even if fdest isn't.
             if entry[4][0] == 'R':
                 # rename: next line is the destination
                 fdest = difftree[i]
                 i += 1
                 if fdest not in seen:
                     add(entry, fdest, True)
                     # .gitmodules isn't imported at all, so it being copied to
                     # and fro doesn't really make sense
                     if f != '.gitmodules' and fdest != '.gitmodules':
                         copies[fdest] = f
             entry = None
         if fh.close():
             raise error.Abort(_('cannot read changes in %s') % version)
 
         if subexists[0]:
             if subdeleted[0]:
                 changes.append(('.hgsubstate', hex(nullid)))
             else:
                 self.retrievegitmodules(version)
                 changes.append(('.hgsubstate', ''))
         return (changes, copies, set())
 
     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 numcommits(self):
         return len([None for _ in self.gitopen('git rev-list --all')])
 
     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 error.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 error.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 error.Abort(_('cannot read changes in %s') % version)
 
         return changes
 
     def getbookmarks(self):
         bookmarks = {}
 
         # Handle local and remote branches
         remoteprefix = self.ui.config('convert', 'git.remoteprefix', 'remote')
         reftypes = [
             # (git prefix, hg prefix)
             ('refs/remotes/origin/', remoteprefix + '/'),
             ('refs/heads/', '')
         ]
 
         exclude = set([
             'refs/remotes/origin/HEAD',
         ])
 
         try:
             fh = self.gitopen('git show-ref', err=subprocess.PIPE)
             for line in fh:
                 line = line.strip()
                 rev, name = line.split(None, 1)
                 # Process each type of branch
                 for gitprefix, hgprefix in reftypes:
                     if not name.startswith(gitprefix) or name in exclude:
                         continue
                     name = '%s%s' % (hgprefix, name[len(gitprefix):])
                     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

@@ -1,342 +1,342 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, error
 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, revs=None):
         super(gnuarch_source, self).__init__(ui, path, revs=revs)
 
         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 error.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 error.Abort(_('internal calling inconsistency'))
 
         if not os.path.lexists(os.path.join(self.tmppath, name)):
             return None, None
 
         return self._getfile(name, rev)
 
     def getchanges(self, rev, full):
         if full:
-            raise error.Abort(_("convert from arch do not support --full"))
+            raise error.Abort(_("convert from arch does not support --full"))
         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, set()
 
     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))
             if mode:
                 mode = 'l'
             else:
                 mode = ''
         else:
             data = open(os.path.join(self.tmppath, name), 'rb').read()
             mode = (mode & 0o111) 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 error.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/monotone.py

@@ -1,364 +1,365 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, error
 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, revs=None):
         converter_source.__init__(self, ui, path, revs)
         if revs and len(revs) > 1:
             raise error.Abort(_('monotone source does not support specifying '
                                'multiple revs'))
         commandline.__init__(self, ui, 'mtn')
 
         self.ui = ui
         self.path = path
         self.automatestdio = False
         self.revs = revs
 
         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 error.Abort(_('bad mtn packet - no end of commandnbr'))
             commandnbr += read
         commandnbr = commandnbr[:-1]
 
         stream = self.mtnreadfp.read(1)
         if stream not in 'mewptl':
             raise error.Abort(_('bad mtn packet - bad stream type %s') % stream)
 
         read = self.mtnreadfp.read(1)
         if read != ':':
             raise error.Abort(_('bad mtn packet - no divider before size'))
 
         read = None
         lengthstr = ''
         while read != ':':
             read = self.mtnreadfp.read(1)
             if not read:
                 raise error.Abort(_('bad mtn packet - no end of packet size'))
             lengthstr += read
         try:
             length = long(lengthstr[:-1])
         except TypeError:
             raise error.Abort(_('bad mtn packet - bad packet size %s')
                 % lengthstr)
 
         read = self.mtnreadfp.read(length)
         if len(read) != length:
             raise error.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 error.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.revs:
             return self.mtnrun("leaves").splitlines()
         else:
             return self.revs
 
     def getchanges(self, rev, full):
         if full:
-            raise error.Abort(_("convert from monotone do not support --full"))
+            raise error.Abort(_("convert from monotone does not support "
+                              "--full"))
         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, set())
 
     def getfile(self, name, rev):
         if not self.mtnisfile(name, rev):
             return None, None
         try:
             data = self.mtnrun("get_file_of", name, r=rev)
         except Exception:
             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 error.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 error.Abort(_('mtn automate stdio header unexpected: %s')
                     % read)
             while read != '\n':
                 read = self.mtnreadfp.readline()
                 if not read:
                     raise error.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

@@ -1,290 +1,290 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, error
 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
 
 def decodefilename(filename):
     """Perforce escapes special characters @, #, *, or %
     with %40, %23, %2A, or %25 respectively
 
     >>> decodefilename('portable-net45%252Bnetcore45%252Bwp8%252BMonoAndroid')
     'portable-net45%2Bnetcore45%2Bwp8%2BMonoAndroid'
     >>> decodefilename('//Depot/Directory/%2525/%2523/%23%40.%2A')
     '//Depot/Directory/%25/%23/#@.*'
     """
     replacements = [('%2A', '*'), ('%23', '#'), ('%40', '@'), ('%25', '%')]
     for k, v in replacements:
         filename = filename.replace(k, v)
     return filename
 
 class p4_source(converter_source):
     def __init__(self, ui, path, revs=None):
         # avoid import cycle
         import convcmd
 
         super(p4_source, self).__init__(ui, path, revs=revs)
 
         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.copies = {}
         self.tags = {}
         self.lastbranch = {}
         self.parent = {}
         self.encoding = self.ui.config('convert', 'p4.encoding',
                                        default=convcmd.orig_encoding)
         self.depotname = {}           # mapping from local name to depot name
         self.localname = {} # mapping from depot name to local 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]*\$")
 
         if revs and len(revs) > 1:
             raise error.Abort(_("p4 source does not support specifying "
                                "multiple revisions"))
         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.revs or int(x) <= int(self.revs[0])))]
 
         # 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=None,
                        extra={"p4": change})
 
             files = []
             copies = {}
             copiedfiles = []
             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.lower().startswith(v.lower()):
                         filename = decodefilename(views[v] + oldname[len(v):])
                         break
                 if filename:
                     files.append((filename, d["rev%d" % i]))
                     self.depotname[filename] = oldname
                     if (d.get("action%d" % i) == "move/add"):
                         copiedfiles.append(filename)
                     self.localname[oldname] = filename
                 i += 1
 
             # Collect information about copied files
             for filename in copiedfiles:
                 oldname = self.depotname[filename]
 
                 flcmd = 'p4 -G filelog %s' \
                       % util.shellquote(oldname)
                 flstdout = util.popen(flcmd, mode='rb')
 
                 copiedfilename = None
                 for d in loaditer(flstdout):
                     copiedoldname = None
 
                     i = 0
                     while ("change%d" % i) in d:
                         if (d["change%d" % i] == change and
                             d["action%d" % i] == "move/add"):
                             j = 0
                             while ("file%d,%d" % (i, j)) in d:
                                 if d["how%d,%d" % (i, j)] == "moved from":
                                     copiedoldname = d["file%d,%d" % (i, j)]
                                     break
                                 j += 1
                         i += 1
 
                     if copiedoldname and copiedoldname in self.localname:
                         copiedfilename = self.localname[copiedoldname]
                         break
 
                 if copiedfilename:
                     copies[filename] = copiedfilename
                 else:
                     ui.warn(_("cannot find source for copied file: %s@%s\n")
                             % (filename, change))
 
             self.changeset[change] = c
             self.files[change] = files
             self.copies[change] = copies
             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))
 
         lasterror = None
         while True:
             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":
                     # if this is the first time error happened
                     # re-attempt getting the file
                     if not lasterror:
                         lasterror = IOError(d["generic"], data)
                         # this will exit inner-most for-loop
                         break
                     else:
                         raise lasterror
 
                 elif code == "stat":
                     action = d.get("action")
                     if action in ["purge", "delete", "move/delete"]:
                         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.append(data)
 
                 lasterror = None
 
             if not lasterror:
                 break
 
         if mode is None:
             return None, None
 
         contents = ''.join(contents)
 
         if keywords:
             contents = keywords.sub("$\\1$", contents)
         if mode == "l" and contents.endswith("\n"):
             contents = contents[:-1]
 
         return contents, mode
 
     def getchanges(self, rev, full):
         if full:
-            raise error.Abort(_("convert from p4 do not support --full"))
+            raise error.Abort(_("convert from p4 does not support --full"))
         return self.files[rev], self.copies[rev], set()
 
     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]])

mercurial/exchange.py

@@ -1,1850 +1,1850 b''
 # exchange.py - utility to exchange data between repos.
 #
 # 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 i18n import _
 from node import hex, nullid
 import errno, urllib, urllib2
 import util, scmutil, changegroup, base85, error
 import discovery, phases, obsolete, bookmarks as bookmod, bundle2, pushkey
 import lock as lockmod
 import streamclone
 import sslutil
 import tags
 import url as urlmod
 
 # Maps bundle compression human names to internal representation.
 _bundlespeccompressions = {'none': None,
                            'bzip2': 'BZ',
                            'gzip': 'GZ',
                           }
 
 # Maps bundle version human names to changegroup versions.
 _bundlespeccgversions = {'v1': '01',
                          'v2': '02',
                          'packed1': 's1',
                          'bundle2': '02', #legacy
                         }
 
 def parsebundlespec(repo, spec, strict=True, externalnames=False):
     """Parse a bundle string specification into parts.
 
     Bundle specifications denote a well-defined bundle/exchange format.
     The content of a given specification should not change over time in
     order to ensure that bundles produced by a newer version of Mercurial are
     readable from an older version.
 
     The string currently has the form:
 
        <compression>-<type>[;<parameter0>[;<parameter1>]]
 
     Where <compression> is one of the supported compression formats
     and <type> is (currently) a version string. A ";" can follow the type and
     all text afterwards is interpretted as URI encoded, ";" delimited key=value
     pairs.
 
     If ``strict`` is True (the default) <compression> is required. Otherwise,
     it is optional.
 
     If ``externalnames`` is False (the default), the human-centric names will
     be converted to their internal representation.
 
     Returns a 3-tuple of (compression, version, parameters). Compression will
     be ``None`` if not in strict mode and a compression isn't defined.
 
     An ``InvalidBundleSpecification`` is raised when the specification is
     not syntactically well formed.
 
     An ``UnsupportedBundleSpecification`` is raised when the compression or
     bundle type/version is not recognized.
 
     Note: this function will likely eventually return a more complex data
     structure, including bundle2 part information.
     """
     def parseparams(s):
         if ';' not in s:
             return s, {}
 
         params = {}
         version, paramstr = s.split(';', 1)
 
         for p in paramstr.split(';'):
             if '=' not in p:
                 raise error.InvalidBundleSpecification(
                     _('invalid bundle specification: '
                       'missing "=" in parameter: %s') % p)
 
             key, value = p.split('=', 1)
             key = urllib.unquote(key)
             value = urllib.unquote(value)
             params[key] = value
 
         return version, params
 
 
     if strict and '-' not in spec:
         raise error.InvalidBundleSpecification(
                 _('invalid bundle specification; '
                   'must be prefixed with compression: %s') % spec)
 
     if '-' in spec:
         compression, version = spec.split('-', 1)
 
         if compression not in _bundlespeccompressions:
             raise error.UnsupportedBundleSpecification(
                     _('%s compression is not supported') % compression)
 
         version, params = parseparams(version)
 
         if version not in _bundlespeccgversions:
             raise error.UnsupportedBundleSpecification(
                     _('%s is not a recognized bundle version') % version)
     else:
         # Value could be just the compression or just the version, in which
         # case some defaults are assumed (but only when not in strict mode).
         assert not strict
 
         spec, params = parseparams(spec)
 
         if spec in _bundlespeccompressions:
             compression = spec
             version = 'v1'
             if 'generaldelta' in repo.requirements:
                 version = 'v2'
         elif spec in _bundlespeccgversions:
             if spec == 'packed1':
                 compression = 'none'
             else:
                 compression = 'bzip2'
             version = spec
         else:
             raise error.UnsupportedBundleSpecification(
                     _('%s is not a recognized bundle specification') % spec)
 
     # The specification for packed1 can optionally declare the data formats
     # required to apply it. If we see this metadata, compare against what the
     # repo supports and error if the bundle isn't compatible.
     if version == 'packed1' and 'requirements' in params:
         requirements = set(params['requirements'].split(','))
         missingreqs = requirements - repo.supportedformats
         if missingreqs:
             raise error.UnsupportedBundleSpecification(
                     _('missing support for repository features: %s') %
                       ', '.join(sorted(missingreqs)))
 
     if not externalnames:
         compression = _bundlespeccompressions[compression]
         version = _bundlespeccgversions[version]
     return compression, version, params
 
 def readbundle(ui, fh, fname, vfs=None):
     header = changegroup.readexactly(fh, 4)
 
     alg = None
     if not fname:
         fname = "stream"
         if not header.startswith('HG') and header.startswith('\0'):
             fh = changegroup.headerlessfixup(fh, header)
             header = "HG10"
             alg = 'UN'
     elif vfs:
         fname = vfs.join(fname)
 
     magic, version = header[0:2], header[2:4]
 
     if magic != 'HG':
         raise error.Abort(_('%s: not a Mercurial bundle') % fname)
     if version == '10':
         if alg is None:
             alg = changegroup.readexactly(fh, 2)
         return changegroup.cg1unpacker(fh, alg)
     elif version.startswith('2'):
         return bundle2.getunbundler(ui, fh, magicstring=magic + version)
     elif version == 'S1':
         return streamclone.streamcloneapplier(fh)
     else:
         raise error.Abort(_('%s: unknown bundle version %s') % (fname, version))
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if markers:
         remoteversions = bundle2.obsmarkersversion(bundler.capabilities)
         version = obsolete.commonversion(remoteversions)
         if version is None:
-            raise ValueError('bundler do not support common obsmarker format')
+            raise ValueError('bundler does not support common obsmarker format')
         stream = obsolete.encodemarkers(markers, True, version=version)
         return bundler.newpart('obsmarkers', data=stream)
     return None
 
 def _canusebundle2(op):
     """return true if a pull/push can use bundle2
 
     Feel free to nuke this function when we drop the experimental option"""
     return (op.repo.ui.configbool('experimental', 'bundle2-exp', True)
             and op.remote.capable('bundle2'))
 
 
 class pushoperation(object):
     """A object that represent a single push operation
 
     It purpose is to carry push related state and very common operation.
 
     A new should be created at the beginning of each push and discarded
     afterward.
     """
 
     def __init__(self, repo, remote, force=False, revs=None, newbranch=False,
                  bookmarks=()):
         # repo we push from
         self.repo = repo
         self.ui = repo.ui
         # repo we push to
         self.remote = remote
         # force option provided
         self.force = force
         # revs to be pushed (None is "all")
         self.revs = revs
         # bookmark explicitly pushed
         self.bookmarks = bookmarks
         # allow push of new branch
         self.newbranch = newbranch
         # did a local lock get acquired?
         self.locallocked = None
         # step already performed
         # (used to check what steps have been already performed through bundle2)
         self.stepsdone = set()
         # Integer version of the changegroup push result
         # - None means nothing to push
         # - 0 means HTTP error
         # - 1 means we pushed and remote head count is unchanged *or*
         #   we have outgoing changesets but refused to push
         # - other values as described by addchangegroup()
         self.cgresult = None
         # Boolean value for the bookmark push
         self.bkresult = None
         # discover.outgoing object (contains common and outgoing data)
         self.outgoing = None
         # all remote heads before the push
         self.remoteheads = None
         # testable as a boolean indicating if any nodes are missing locally.
         self.incoming = None
         # phases changes that must be pushed along side the changesets
         self.outdatedphases = None
         # phases changes that must be pushed if changeset push fails
         self.fallbackoutdatedphases = None
         # outgoing obsmarkers
         self.outobsmarkers = set()
         # outgoing bookmarks
         self.outbookmarks = []
         # transaction manager
         self.trmanager = None
         # map { pushkey partid -> callback handling failure}
         # used to handle exception from mandatory pushkey part failure
         self.pkfailcb = {}
 
     @util.propertycache
     def futureheads(self):
         """future remote heads if the changeset push succeeds"""
         return self.outgoing.missingheads
 
     @util.propertycache
     def fallbackheads(self):
         """future remote heads if the changeset push fails"""
         if self.revs is None:
             # not target to push, all common are relevant
             return self.outgoing.commonheads
         unfi = self.repo.unfiltered()
         # I want cheads = heads(::missingheads and ::commonheads)
         # (missingheads is revs with secret changeset filtered out)
         #
         # This can be expressed as:
         #     cheads = ( (missingheads and ::commonheads)
         #              + (commonheads and ::missingheads))"
         #              )
         #
         # while trying to push we already computed the following:
         #     common = (::commonheads)
         #     missing = ((commonheads::missingheads) - commonheads)
         #
         # We can pick:
         # * missingheads part of common (::commonheads)
         common = self.outgoing.common
         nm = self.repo.changelog.nodemap
         cheads = [node for node in self.revs if nm[node] in common]
         # and
         # * commonheads parents on missing
         revset = unfi.set('%ln and parents(roots(%ln))',
                          self.outgoing.commonheads,
                          self.outgoing.missing)
         cheads.extend(c.node() for c in revset)
         return cheads
 
     @property
     def commonheads(self):
         """set of all common heads after changeset bundle push"""
         if self.cgresult:
             return self.futureheads
         else:
             return self.fallbackheads
 
 # mapping of message used when pushing bookmark
 bookmsgmap = {'update': (_("updating bookmark %s\n"),
                          _('updating bookmark %s failed!\n')),
               'export': (_("exporting bookmark %s\n"),
                          _('exporting bookmark %s failed!\n')),
               'delete': (_("deleting remote bookmark %s\n"),
                          _('deleting remote bookmark %s failed!\n')),
               }
 
 
 def push(repo, remote, force=False, revs=None, newbranch=False, bookmarks=(),
          opargs=None):
     '''Push outgoing changesets (limited by revs) from a local
     repository to remote. Return an integer:
       - None means nothing to push
       - 0 means HTTP error
       - 1 means we pushed and remote head count is unchanged *or*
         we have outgoing changesets but refused to push
       - other values as described by addchangegroup()
     '''
     if opargs is None:
         opargs = {}
     pushop = pushoperation(repo, remote, force, revs, newbranch, bookmarks,
                            **opargs)
     if pushop.remote.local():
         missing = (set(pushop.repo.requirements)
                    - pushop.remote.local().supported)
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise error.Abort(msg)
 
     # there are two ways to push to remote repo:
     #
     # addchangegroup assumes local user can lock remote
     # repo (local filesystem, old ssh servers).
     #
     # unbundle assumes local user cannot lock remote repo (new ssh
     # servers, http servers).
 
     if not pushop.remote.canpush():
         raise error.Abort(_("destination does not support push"))
     # get local lock as we might write phase data
     localwlock = locallock = None
     try:
         # bundle2 push may receive a reply bundle touching bookmarks or other
         # things requiring the wlock. Take it now to ensure proper ordering.
         maypushback = pushop.ui.configbool('experimental', 'bundle2.pushback')
         if _canusebundle2(pushop) and maypushback:
             localwlock = pushop.repo.wlock()
         locallock = pushop.repo.lock()
         pushop.locallocked = True
     except IOError as err:
         pushop.locallocked = False
         if err.errno != errno.EACCES:
             raise
         # source repo cannot be locked.
         # We do not abort the push, but just disable the local phase
         # synchronisation.
         msg = 'cannot lock source repository: %s\n' % err
         pushop.ui.debug(msg)
     try:
         if pushop.locallocked:
             pushop.trmanager = transactionmanager(pushop.repo,
                                                   'push-response',
                                                   pushop.remote.url())
         pushop.repo.checkpush(pushop)
         lock = None
         unbundle = pushop.remote.capable('unbundle')
         if not unbundle:
             lock = pushop.remote.lock()
         try:
             _pushdiscovery(pushop)
             if _canusebundle2(pushop):
                 _pushbundle2(pushop)
             _pushchangeset(pushop)
             _pushsyncphase(pushop)
             _pushobsolete(pushop)
             _pushbookmark(pushop)
         finally:
             if lock is not None:
                 lock.release()
         if pushop.trmanager:
             pushop.trmanager.close()
     finally:
         if pushop.trmanager:
             pushop.trmanager.release()
         if locallock is not None:
             locallock.release()
         if localwlock is not None:
             localwlock.release()
 
     return pushop
 
 # list of steps to perform discovery before push
 pushdiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pushdiscoverymapping = {}
 
 def pushdiscovery(stepname):
     """decorator for function performing discovery before push
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pushdiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pushdiscoverymapping
         pushdiscoverymapping[stepname] = func
         pushdiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pushdiscovery(pushop):
     """Run all discovery steps"""
     for stepname in pushdiscoveryorder:
         step = pushdiscoverymapping[stepname]
         step(pushop)
 
 @pushdiscovery('changeset')
 def _pushdiscoverychangeset(pushop):
     """discover the changeset that need to be pushed"""
     fci = discovery.findcommonincoming
     commoninc = fci(pushop.repo, pushop.remote, force=pushop.force)
     common, inc, remoteheads = commoninc
     fco = discovery.findcommonoutgoing
     outgoing = fco(pushop.repo, pushop.remote, onlyheads=pushop.revs,
                    commoninc=commoninc, force=pushop.force)
     pushop.outgoing = outgoing
     pushop.remoteheads = remoteheads
     pushop.incoming = inc
 
 @pushdiscovery('phase')
 def _pushdiscoveryphase(pushop):
     """discover the phase that needs to be pushed
 
     (computed for both success and failure case for changesets push)"""
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     remotephases = pushop.remote.listkeys('phases')
     publishing = remotephases.get('publishing', False)
     if (pushop.ui.configbool('ui', '_usedassubrepo', False)
         and remotephases    # server supports phases
         and not pushop.outgoing.missing # no changesets to be pushed
         and publishing):
         # When:
         # - this is a subrepo push
         # - and remote support phase
         # - and no changeset are to be pushed
         # - and remote is publishing
         # We may be in issue 3871 case!
         # We drop the possible phase synchronisation done by
         # courtesy to publish changesets possibly locally draft
         # on the remote.
         remotephases = {'publishing': 'True'}
     ana = phases.analyzeremotephases(pushop.repo,
                                      pushop.fallbackheads,
                                      remotephases)
     pheads, droots = ana
     extracond = ''
     if not publishing:
         extracond = ' and public()'
     revset = 'heads((%%ln::%%ln) %s)' % extracond
     # Get the list of all revs draft on remote by public here.
     # XXX Beware that revset break if droots is not strictly
     # XXX root we may want to ensure it is but it is costly
     fallback = list(unfi.set(revset, droots, pushop.fallbackheads))
     if not outgoing.missing:
         future = fallback
     else:
         # adds changeset we are going to push as draft
         #
         # should not be necessary for publishing server, but because of an
         # issue fixed in xxxxx we have to do it anyway.
         fdroots = list(unfi.set('roots(%ln  + %ln::)',
                        outgoing.missing, droots))
         fdroots = [f.node() for f in fdroots]
         future = list(unfi.set(revset, fdroots, pushop.futureheads))
     pushop.outdatedphases = future
     pushop.fallbackoutdatedphases = fallback
 
 @pushdiscovery('obsmarker')
 def _pushdiscoveryobsmarkers(pushop):
     if (obsolete.isenabled(pushop.repo, obsolete.exchangeopt)
         and pushop.repo.obsstore
         and 'obsolete' in pushop.remote.listkeys('namespaces')):
         repo = pushop.repo
         # very naive computation, that can be quite expensive on big repo.
         # However: evolution is currently slow on them anyway.
         nodes = (c.node() for c in repo.set('::%ln', pushop.futureheads))
         pushop.outobsmarkers = pushop.repo.obsstore.relevantmarkers(nodes)
 
 @pushdiscovery('bookmarks')
 def _pushdiscoverybookmarks(pushop):
     ui = pushop.ui
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     ui.debug("checking for updated bookmarks\n")
     ancestors = ()
     if pushop.revs:
         revnums = map(repo.changelog.rev, pushop.revs)
         ancestors = repo.changelog.ancestors(revnums, inclusive=True)
     remotebookmark = remote.listkeys('bookmarks')
 
     explicit = set(pushop.bookmarks)
 
     comp = bookmod.compare(repo, repo._bookmarks, remotebookmark, srchex=hex)
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = comp
     for b, scid, dcid in advsrc:
         if b in explicit:
             explicit.remove(b)
         if not ancestors or repo[scid].rev() in ancestors:
             pushop.outbookmarks.append((b, dcid, scid))
     # search added bookmark
     for b, scid, dcid in addsrc:
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, '', scid))
     # search for overwritten bookmark
     for b, scid, dcid in advdst + diverge + differ:
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, dcid, scid))
     # search for bookmark to delete
     for b, scid, dcid in adddst:
         if b in explicit:
             explicit.remove(b)
             # treat as "deleted locally"
             pushop.outbookmarks.append((b, dcid, ''))
     # identical bookmarks shouldn't get reported
     for b, scid, dcid in same:
         if b in explicit:
             explicit.remove(b)
 
     if explicit:
         explicit = sorted(explicit)
         # we should probably list all of them
         ui.warn(_('bookmark %s does not exist on the local '
                   'or remote repository!\n') % explicit[0])
         pushop.bkresult = 2
 
     pushop.outbookmarks.sort()
 
 def _pushcheckoutgoing(pushop):
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     if not outgoing.missing:
         # nothing to push
         scmutil.nochangesfound(unfi.ui, unfi, outgoing.excluded)
         return False
     # something to push
     if not pushop.force:
         # if repo.obsstore == False --> no obsolete
         # then, save the iteration
         if unfi.obsstore:
             # this message are here for 80 char limit reason
             mso = _("push includes obsolete changeset: %s!")
             mst = {"unstable": _("push includes unstable changeset: %s!"),
                    "bumped": _("push includes bumped changeset: %s!"),
                    "divergent": _("push includes divergent changeset: %s!")}
             # If we are to push if there is at least one
             # obsolete or unstable changeset in missing, at
             # least one of the missinghead will be obsolete or
             # unstable. So checking heads only is ok
             for node in outgoing.missingheads:
                 ctx = unfi[node]
                 if ctx.obsolete():
                     raise error.Abort(mso % ctx)
                 elif ctx.troubled():
                     raise error.Abort(mst[ctx.troubles()[0]] % ctx)
 
         # internal config: bookmarks.pushing
         newbm = pushop.ui.configlist('bookmarks', 'pushing')
         discovery.checkheads(unfi, pushop.remote, outgoing,
                              pushop.remoteheads,
                              pushop.newbranch,
                              bool(pushop.incoming),
                              newbm)
     return True
 
 # List of names of steps to perform for an outgoing bundle2, order matters.
 b2partsgenorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 b2partsgenmapping = {}
 
 def b2partsgenerator(stepname, idx=None):
     """decorator for function generating bundle2 part
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the b2partsgenmapping dictionary directly."""
     def dec(func):
         assert stepname not in b2partsgenmapping
         b2partsgenmapping[stepname] = func
         if idx is None:
             b2partsgenorder.append(stepname)
         else:
             b2partsgenorder.insert(idx, stepname)
         return func
     return dec
 
 def _pushb2ctxcheckheads(pushop, bundler):
     """Generate race condition checking parts
 
     Exists as an indepedent function to aid extensions
     """
     if not pushop.force:
         bundler.newpart('check:heads', data=iter(pushop.remoteheads))
 
 @b2partsgenerator('changeset')
 def _pushb2ctx(pushop, bundler):
     """handle changegroup push through bundle2
 
     addchangegroup result is stored in the ``pushop.cgresult`` attribute.
     """
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     # Send known heads to the server for race detection.
     if not _pushcheckoutgoing(pushop):
         return
     pushop.repo.prepushoutgoinghooks(pushop.repo,
                                      pushop.remote,
                                      pushop.outgoing)
 
     _pushb2ctxcheckheads(pushop, bundler)
 
     b2caps = bundle2.bundle2caps(pushop.remote)
     version = None
     cgversions = b2caps.get('changegroup')
     if not cgversions:  # 3.1 and 3.2 ship with an empty value
         cg = changegroup.getlocalchangegroupraw(pushop.repo, 'push',
                                                 pushop.outgoing)
     else:
         cgversions = [v for v in cgversions if v in changegroup.packermap]
         if not cgversions:
             raise ValueError(_('no common changegroup version'))
         version = max(cgversions)
         cg = changegroup.getlocalchangegroupraw(pushop.repo, 'push',
                                                 pushop.outgoing,
                                                 version=version)
     cgpart = bundler.newpart('changegroup', data=cg)
     if version is not None:
         cgpart.addparam('version', version)
     def handlereply(op):
         """extract addchangegroup returns from server reply"""
         cgreplies = op.records.getreplies(cgpart.id)
         assert len(cgreplies['changegroup']) == 1
         pushop.cgresult = cgreplies['changegroup'][0]['return']
     return handlereply
 
 @b2partsgenerator('phase')
 def _pushb2phases(pushop, bundler):
     """handle phase push through bundle2"""
     if 'phases' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     if not 'pushkey' in b2caps:
         return
     pushop.stepsdone.add('phases')
     part2node = []
 
     def handlefailure(pushop, exc):
         targetid = int(exc.partid)
         for partid, node in part2node:
             if partid == targetid:
                 raise error.Abort(_('updating %s to public failed') % node)
 
     enc = pushkey.encode
     for newremotehead in pushop.outdatedphases:
         part = bundler.newpart('pushkey')
         part.addparam('namespace', enc('phases'))
         part.addparam('key', enc(newremotehead.hex()))
         part.addparam('old', enc(str(phases.draft)))
         part.addparam('new', enc(str(phases.public)))
         part2node.append((part.id, newremotehead))
         pushop.pkfailcb[part.id] = handlefailure
 
     def handlereply(op):
         for partid, node in part2node:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             msg = None
             if not results:
                 msg = _('server ignored update of %s to public!\n') % node
             elif not int(results[0]['return']):
                 msg = _('updating %s to public failed!\n') % node
             if msg is not None:
                 pushop.ui.warn(msg)
     return handlereply
 
 @b2partsgenerator('obsmarkers')
 def _pushb2obsmarkers(pushop, bundler):
     if 'obsmarkers' in pushop.stepsdone:
         return
     remoteversions = bundle2.obsmarkersversion(bundler.capabilities)
     if obsolete.commonversion(remoteversions) is None:
         return
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         markers = sorted(pushop.outobsmarkers)
         buildobsmarkerspart(bundler, markers)
 
 @b2partsgenerator('bookmarks')
 def _pushb2bookmarks(pushop, bundler):
     """handle bookmark push through bundle2"""
     if 'bookmarks' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     if 'pushkey' not in b2caps:
         return
     pushop.stepsdone.add('bookmarks')
     part2book = []
     enc = pushkey.encode
 
     def handlefailure(pushop, exc):
         targetid = int(exc.partid)
         for partid, book, action in part2book:
             if partid == targetid:
                 raise error.Abort(bookmsgmap[action][1].rstrip() % book)
         # we should not be called for part we did not generated
         assert False
 
     for book, old, new in pushop.outbookmarks:
         part = bundler.newpart('pushkey')
         part.addparam('namespace', enc('bookmarks'))
         part.addparam('key', enc(book))
         part.addparam('old', enc(old))
         part.addparam('new', enc(new))
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
         part2book.append((part.id, book, action))
         pushop.pkfailcb[part.id] = handlefailure
 
     def handlereply(op):
         ui = pushop.ui
         for partid, book, action in part2book:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             if not results:
                 pushop.ui.warn(_('server ignored bookmark %s update\n') % book)
             else:
                 ret = int(results[0]['return'])
                 if ret:
                     ui.status(bookmsgmap[action][0] % book)
                 else:
                     ui.warn(bookmsgmap[action][1] % book)
                     if pushop.bkresult is not None:
                         pushop.bkresult = 1
     return handlereply
 
 
 def _pushbundle2(pushop):
     """push data to the remote using bundle2
 
     The only currently supported type of data is changegroup but this will
     evolve in the future."""
     bundler = bundle2.bundle20(pushop.ui, bundle2.bundle2caps(pushop.remote))
     pushback = (pushop.trmanager
                 and pushop.ui.configbool('experimental', 'bundle2.pushback'))
 
     # create reply capability
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(pushop.repo,
                                                       allowpushback=pushback))
     bundler.newpart('replycaps', data=capsblob)
     replyhandlers = []
     for partgenname in b2partsgenorder:
         partgen = b2partsgenmapping[partgenname]
         ret = partgen(pushop, bundler)
         if callable(ret):
             replyhandlers.append(ret)
     # do not push if nothing to push
     if bundler.nbparts <= 1:
         return
     stream = util.chunkbuffer(bundler.getchunks())
     try:
         try:
             reply = pushop.remote.unbundle(stream, ['force'], 'push')
         except error.BundleValueError as exc:
             raise error.Abort('missing support for %s' % exc)
         try:
             trgetter = None
             if pushback:
                 trgetter = pushop.trmanager.transaction
             op = bundle2.processbundle(pushop.repo, reply, trgetter)
         except error.BundleValueError as exc:
             raise error.Abort('missing support for %s' % exc)
     except error.PushkeyFailed as exc:
         partid = int(exc.partid)
         if partid not in pushop.pkfailcb:
             raise
         pushop.pkfailcb[partid](pushop, exc)
     for rephand in replyhandlers:
         rephand(op)
 
 def _pushchangeset(pushop):
     """Make the actual push of changeset bundle to remote repo"""
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     if not _pushcheckoutgoing(pushop):
         return
     pushop.repo.prepushoutgoinghooks(pushop.repo,
                                      pushop.remote,
                                      pushop.outgoing)
     outgoing = pushop.outgoing
     unbundle = pushop.remote.capable('unbundle')
     # TODO: get bundlecaps from remote
     bundlecaps = None
     # create a changegroup from local
     if pushop.revs is None and not (outgoing.excluded
                             or pushop.repo.changelog.filteredrevs):
         # push everything,
         # use the fast path, no race possible on push
         bundler = changegroup.cg1packer(pushop.repo, bundlecaps)
         cg = changegroup.getsubset(pushop.repo,
                                    outgoing,
                                    bundler,
                                    'push',
                                    fastpath=True)
     else:
         cg = changegroup.getlocalchangegroup(pushop.repo, 'push', outgoing,
                                         bundlecaps)
 
     # apply changegroup to remote
     if unbundle:
         # local repo finds heads on server, finds out what
         # revs it must push. once revs transferred, if server
         # finds it has different heads (someone else won
         # commit/push race), server aborts.
         if pushop.force:
             remoteheads = ['force']
         else:
             remoteheads = pushop.remoteheads
         # ssh: return remote's addchangegroup()
         # http: return remote's addchangegroup() or 0 for error
         pushop.cgresult = pushop.remote.unbundle(cg, remoteheads,
                                             pushop.repo.url())
     else:
         # we return an integer indicating remote head count
         # change
         pushop.cgresult = pushop.remote.addchangegroup(cg, 'push',
                                                        pushop.repo.url())
 
 def _pushsyncphase(pushop):
     """synchronise phase information locally and remotely"""
     cheads = pushop.commonheads
     # even when we don't push, exchanging phase data is useful
     remotephases = pushop.remote.listkeys('phases')
     if (pushop.ui.configbool('ui', '_usedassubrepo', False)
         and remotephases    # server supports phases
         and pushop.cgresult is None # nothing was pushed
         and remotephases.get('publishing', False)):
         # When:
         # - this is a subrepo push
         # - and remote support phase
         # - and no changeset was pushed
         # - and remote is publishing
         # We may be in issue 3871 case!
         # We drop the possible phase synchronisation done by
         # courtesy to publish changesets possibly locally draft
         # on the remote.
         remotephases = {'publishing': 'True'}
     if not remotephases: # old server or public only reply from non-publishing
         _localphasemove(pushop, cheads)
         # don't push any phase data as there is nothing to push
     else:
         ana = phases.analyzeremotephases(pushop.repo, cheads,
                                          remotephases)
         pheads, droots = ana
         ### Apply remote phase on local
         if remotephases.get('publishing', False):
             _localphasemove(pushop, cheads)
         else: # publish = False
             _localphasemove(pushop, pheads)
             _localphasemove(pushop, cheads, phases.draft)
         ### Apply local phase on remote
 
         if pushop.cgresult:
             if 'phases' in pushop.stepsdone:
                 # phases already pushed though bundle2
                 return
             outdated = pushop.outdatedphases
         else:
             outdated = pushop.fallbackoutdatedphases
 
         pushop.stepsdone.add('phases')
 
         # filter heads already turned public by the push
         outdated = [c for c in outdated if c.node() not in pheads]
         # fallback to independent pushkey command
         for newremotehead in outdated:
             r = pushop.remote.pushkey('phases',
                                       newremotehead.hex(),
                                       str(phases.draft),
                                       str(phases.public))
             if not r:
                 pushop.ui.warn(_('updating %s to public failed!\n')
                                % newremotehead)
 
 def _localphasemove(pushop, nodes, phase=phases.public):
     """move <nodes> to <phase> in the local source repo"""
     if pushop.trmanager:
         phases.advanceboundary(pushop.repo,
                                pushop.trmanager.transaction(),
                                phase,
                                nodes)
     else:
         # repo is not locked, do not change any phases!
         # Informs the user that phases should have been moved when
         # applicable.
         actualmoves = [n for n in nodes if phase < pushop.repo[n].phase()]
         phasestr = phases.phasenames[phase]
         if actualmoves:
             pushop.ui.status(_('cannot lock source repo, skipping '
                                'local %s phase update\n') % phasestr)
 
 def _pushobsolete(pushop):
     """utility function to push obsolete markers to a remote"""
     if 'obsmarkers' in pushop.stepsdone:
         return
     repo = pushop.repo
     remote = pushop.remote
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         pushop.ui.debug('try to push obsolete markers to remote\n')
         rslts = []
         remotedata = obsolete._pushkeyescape(sorted(pushop.outobsmarkers))
         for key in sorted(remotedata, reverse=True):
             # reverse sort to ensure we end with dump0
             data = remotedata[key]
             rslts.append(remote.pushkey('obsolete', key, '', data))
         if [r for r in rslts if not r]:
             msg = _('failed to push some obsolete markers!\n')
             repo.ui.warn(msg)
 
 def _pushbookmark(pushop):
     """Update bookmark position on remote"""
     if pushop.cgresult == 0 or 'bookmarks' in pushop.stepsdone:
         return
     pushop.stepsdone.add('bookmarks')
     ui = pushop.ui
     remote = pushop.remote
 
     for b, old, new in pushop.outbookmarks:
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
         if remote.pushkey('bookmarks', b, old, new):
             ui.status(bookmsgmap[action][0] % b)
         else:
             ui.warn(bookmsgmap[action][1] % b)
             # discovery can have set the value form invalid entry
             if pushop.bkresult is not None:
                 pushop.bkresult = 1
 
 class pulloperation(object):
     """A object that represent a single pull operation
 
     It purpose is to carry pull related state and very common operation.
 
     A new should be created at the beginning of each pull and discarded
     afterward.
     """
 
     def __init__(self, repo, remote, heads=None, force=False, bookmarks=(),
                  remotebookmarks=None, streamclonerequested=None):
         # repo we pull into
         self.repo = repo
         # repo we pull from
         self.remote = remote
         # revision we try to pull (None is "all")
         self.heads = heads
         # bookmark pulled explicitly
         self.explicitbookmarks = bookmarks
         # do we force pull?
         self.force = force
         # whether a streaming clone was requested
         self.streamclonerequested = streamclonerequested
         # transaction manager
         self.trmanager = None
         # set of common changeset between local and remote before pull
         self.common = None
         # set of pulled head
         self.rheads = None
         # list of missing changeset to fetch remotely
         self.fetch = None
         # remote bookmarks data
         self.remotebookmarks = remotebookmarks
         # result of changegroup pulling (used as return code by pull)
         self.cgresult = None
         # list of step already done
         self.stepsdone = set()
         # Whether we attempted a clone from pre-generated bundles.
         self.clonebundleattempted = False
 
     @util.propertycache
     def pulledsubset(self):
         """heads of the set of changeset target by the pull"""
         # compute target subset
         if self.heads is None:
             # We pulled every thing possible
             # sync on everything common
             c = set(self.common)
             ret = list(self.common)
             for n in self.rheads:
                 if n not in c:
                     ret.append(n)
             return ret
         else:
             # We pulled a specific subset
             # sync on this subset
             return self.heads
 
     @util.propertycache
     def canusebundle2(self):
         return _canusebundle2(self)
 
     @util.propertycache
     def remotebundle2caps(self):
         return bundle2.bundle2caps(self.remote)
 
     def gettransaction(self):
         # deprecated; talk to trmanager directly
         return self.trmanager.transaction()
 
 class transactionmanager(object):
     """An object to manage the life cycle of a transaction
 
     It creates the transaction on demand and calls the appropriate hooks when
     closing the transaction."""
     def __init__(self, repo, source, url):
         self.repo = repo
         self.source = source
         self.url = url
         self._tr = None
 
     def transaction(self):
         """Return an open transaction object, constructing if necessary"""
         if not self._tr:
             trname = '%s\n%s' % (self.source, util.hidepassword(self.url))
             self._tr = self.repo.transaction(trname)
             self._tr.hookargs['source'] = self.source
             self._tr.hookargs['url'] = self.url
         return self._tr
 
     def close(self):
         """close transaction if created"""
         if self._tr is not None:
             self._tr.close()
 
     def release(self):
         """release transaction if created"""
         if self._tr is not None:
             self._tr.release()
 
 def pull(repo, remote, heads=None, force=False, bookmarks=(), opargs=None,
          streamclonerequested=None):
     """Fetch repository data from a remote.
 
     This is the main function used to retrieve data from a remote repository.
 
     ``repo`` is the local repository to clone into.
     ``remote`` is a peer instance.
     ``heads`` is an iterable of revisions we want to pull. ``None`` (the
     default) means to pull everything from the remote.
     ``bookmarks`` is an iterable of bookmarks requesting to be pulled. By
     default, all remote bookmarks are pulled.
     ``opargs`` are additional keyword arguments to pass to ``pulloperation``
     initialization.
     ``streamclonerequested`` is a boolean indicating whether a "streaming
     clone" is requested. A "streaming clone" is essentially a raw file copy
     of revlogs from the server. This only works when the local repository is
     empty. The default value of ``None`` means to respect the server
     configuration for preferring stream clones.
 
     Returns the ``pulloperation`` created for this pull.
     """
     if opargs is None:
         opargs = {}
     pullop = pulloperation(repo, remote, heads, force, bookmarks=bookmarks,
                            streamclonerequested=streamclonerequested, **opargs)
     if pullop.remote.local():
         missing = set(pullop.remote.requirements) - pullop.repo.supported
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise error.Abort(msg)
 
     lock = pullop.repo.lock()
     try:
         pullop.trmanager = transactionmanager(repo, 'pull', remote.url())
         streamclone.maybeperformlegacystreamclone(pullop)
         # This should ideally be in _pullbundle2(). However, it needs to run
         # before discovery to avoid extra work.
         _maybeapplyclonebundle(pullop)
         _pulldiscovery(pullop)
         if pullop.canusebundle2:
             _pullbundle2(pullop)
         _pullchangeset(pullop)
         _pullphase(pullop)
         _pullbookmarks(pullop)
         _pullobsolete(pullop)
         pullop.trmanager.close()
     finally:
         pullop.trmanager.release()
         lock.release()
 
     return pullop
 
 # list of steps to perform discovery before pull
 pulldiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pulldiscoverymapping = {}
 
 def pulldiscovery(stepname):
     """decorator for function performing discovery before pull
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pulldiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pulldiscoverymapping
         pulldiscoverymapping[stepname] = func
         pulldiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pulldiscovery(pullop):
     """Run all discovery steps"""
     for stepname in pulldiscoveryorder:
         step = pulldiscoverymapping[stepname]
         step(pullop)
 
 @pulldiscovery('b1:bookmarks')
 def _pullbookmarkbundle1(pullop):
     """fetch bookmark data in bundle1 case
 
     If not using bundle2, we have to fetch bookmarks before changeset
     discovery to reduce the chance and impact of race conditions."""
     if pullop.remotebookmarks is not None:
         return
     if pullop.canusebundle2 and 'listkeys' in pullop.remotebundle2caps:
         # all known bundle2 servers now support listkeys, but lets be nice with
         # new implementation.
         return
     pullop.remotebookmarks = pullop.remote.listkeys('bookmarks')
 
 
 @pulldiscovery('changegroup')
 def _pulldiscoverychangegroup(pullop):
     """discovery phase for the pull
 
     Current handle changeset discovery only, will change handle all discovery
     at some point."""
     tmp = discovery.findcommonincoming(pullop.repo,
                                        pullop.remote,
                                        heads=pullop.heads,
                                        force=pullop.force)
     common, fetch, rheads = tmp
     nm = pullop.repo.unfiltered().changelog.nodemap
     if fetch and rheads:
         # If a remote heads in filtered locally, lets drop it from the unknown
         # remote heads and put in back in common.
         #
         # This is a hackish solution to catch most of "common but locally
         # hidden situation".  We do not performs discovery on unfiltered
         # repository because it end up doing a pathological amount of round
         # trip for w huge amount of changeset we do not care about.
         #
         # If a set of such "common but filtered" changeset exist on the server
         # but are not including a remote heads, we'll not be able to detect it,
         scommon = set(common)
         filteredrheads = []
         for n in rheads:
             if n in nm:
                 if n not in scommon:
                     common.append(n)
             else:
                 filteredrheads.append(n)
         if not filteredrheads:
             fetch = []
         rheads = filteredrheads
     pullop.common = common
     pullop.fetch = fetch
     pullop.rheads = rheads
 
 def _pullbundle2(pullop):
     """pull data using bundle2
 
     For now, the only supported data are changegroup."""
     kwargs = {'bundlecaps': caps20to10(pullop.repo)}
 
     streaming, streamreqs = streamclone.canperformstreamclone(pullop)
 
     # pulling changegroup
     pullop.stepsdone.add('changegroup')
 
     kwargs['common'] = pullop.common
     kwargs['heads'] = pullop.heads or pullop.rheads
     kwargs['cg'] = pullop.fetch
     if 'listkeys' in pullop.remotebundle2caps:
         kwargs['listkeys'] = ['phase']
         if pullop.remotebookmarks is None:
             # make sure to always includes bookmark data when migrating
             # `hg incoming --bundle` to using this function.
             kwargs['listkeys'].append('bookmarks')
 
     # If this is a full pull / clone and the server supports the clone bundles
     # feature, tell the server whether we attempted a clone bundle. The
     # presence of this flag indicates the client supports clone bundles. This
     # will enable the server to treat clients that support clone bundles
     # differently from those that don't.
     if (pullop.remote.capable('clonebundles')
         and pullop.heads is None and list(pullop.common) == [nullid]):
         kwargs['cbattempted'] = pullop.clonebundleattempted
 
     if streaming:
         pullop.repo.ui.status(_('streaming all changes\n'))
     elif not pullop.fetch:
         pullop.repo.ui.status(_("no changes found\n"))
         pullop.cgresult = 0
     else:
         if pullop.heads is None and list(pullop.common) == [nullid]:
             pullop.repo.ui.status(_("requesting all changes\n"))
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         remoteversions = bundle2.obsmarkersversion(pullop.remotebundle2caps)
         if obsolete.commonversion(remoteversions) is not None:
             kwargs['obsmarkers'] = True
             pullop.stepsdone.add('obsmarkers')
     _pullbundle2extraprepare(pullop, kwargs)
     bundle = pullop.remote.getbundle('pull', **kwargs)
     try:
         op = bundle2.processbundle(pullop.repo, bundle, pullop.gettransaction)
     except error.BundleValueError as exc:
         raise error.Abort('missing support for %s' % exc)
 
     if pullop.fetch:
         results = [cg['return'] for cg in op.records['changegroup']]
         pullop.cgresult = changegroup.combineresults(results)
 
     # processing phases change
     for namespace, value in op.records['listkeys']:
         if namespace == 'phases':
             _pullapplyphases(pullop, value)
 
     # processing bookmark update
     for namespace, value in op.records['listkeys']:
         if namespace == 'bookmarks':
             pullop.remotebookmarks = value
 
     # bookmark data were either already there or pulled in the bundle
     if pullop.remotebookmarks is not None:
         _pullbookmarks(pullop)
 
 def _pullbundle2extraprepare(pullop, kwargs):
     """hook function so that extensions can extend the getbundle call"""
     pass
 
 def _pullchangeset(pullop):
     """pull changeset from unbundle into the local repo"""
     # We delay the open of the transaction as late as possible so we
     # don't open transaction for nothing or you break future useful
     # rollback call
     if 'changegroup' in pullop.stepsdone:
         return
     pullop.stepsdone.add('changegroup')
     if not pullop.fetch:
         pullop.repo.ui.status(_("no changes found\n"))
         pullop.cgresult = 0
         return
     pullop.gettransaction()
     if pullop.heads is None and list(pullop.common) == [nullid]:
         pullop.repo.ui.status(_("requesting all changes\n"))
     elif pullop.heads is None and pullop.remote.capable('changegroupsubset'):
         # issue1320, avoid a race if remote changed after discovery
         pullop.heads = pullop.rheads
 
     if pullop.remote.capable('getbundle'):
         # TODO: get bundlecaps from remote
         cg = pullop.remote.getbundle('pull', common=pullop.common,
                                      heads=pullop.heads or pullop.rheads)
     elif pullop.heads is None:
         cg = pullop.remote.changegroup(pullop.fetch, 'pull')
     elif not pullop.remote.capable('changegroupsubset'):
         raise error.Abort(_("partial pull cannot be done because "
                            "other repository doesn't support "
                            "changegroupsubset."))
     else:
         cg = pullop.remote.changegroupsubset(pullop.fetch, pullop.heads, 'pull')
     pullop.cgresult = cg.apply(pullop.repo, 'pull', pullop.remote.url())
 
 def _pullphase(pullop):
     # Get remote phases data from remote
     if 'phases' in pullop.stepsdone:
         return
     remotephases = pullop.remote.listkeys('phases')
     _pullapplyphases(pullop, remotephases)
 
 def _pullapplyphases(pullop, remotephases):
     """apply phase movement from observed remote state"""
     if 'phases' in pullop.stepsdone:
         return
     pullop.stepsdone.add('phases')
     publishing = bool(remotephases.get('publishing', False))
     if remotephases and not publishing:
         # remote is new and unpublishing
         pheads, _dr = phases.analyzeremotephases(pullop.repo,
                                                  pullop.pulledsubset,
                                                  remotephases)
         dheads = pullop.pulledsubset
     else:
         # Remote is old or publishing all common changesets
         # should be seen as public
         pheads = pullop.pulledsubset
         dheads = []
     unfi = pullop.repo.unfiltered()
     phase = unfi._phasecache.phase
     rev = unfi.changelog.nodemap.get
     public = phases.public
     draft = phases.draft
 
     # exclude changesets already public locally and update the others
     pheads = [pn for pn in pheads if phase(unfi, rev(pn)) > public]
     if pheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, public, pheads)
 
     # exclude changesets already draft locally and update the others
     dheads = [pn for pn in dheads if phase(unfi, rev(pn)) > draft]
     if dheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, draft, dheads)
 
 def _pullbookmarks(pullop):
     """process the remote bookmark information to update the local one"""
     if 'bookmarks' in pullop.stepsdone:
         return
     pullop.stepsdone.add('bookmarks')
     repo = pullop.repo
     remotebookmarks = pullop.remotebookmarks
     bookmod.updatefromremote(repo.ui, repo, remotebookmarks,
                              pullop.remote.url(),
                              pullop.gettransaction,
                              explicit=pullop.explicitbookmarks)
 
 def _pullobsolete(pullop):
     """utility function to pull obsolete markers from a remote
 
     The `gettransaction` is function that return the pull transaction, creating
     one if necessary. We return the transaction to inform the calling code that
     a new transaction have been created (when applicable).
 
     Exists mostly to allow overriding for experimentation purpose"""
     if 'obsmarkers' in pullop.stepsdone:
         return
     pullop.stepsdone.add('obsmarkers')
     tr = None
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         pullop.repo.ui.debug('fetching remote obsolete markers\n')
         remoteobs = pullop.remote.listkeys('obsolete')
         if 'dump0' in remoteobs:
             tr = pullop.gettransaction()
             for key in sorted(remoteobs, reverse=True):
                 if key.startswith('dump'):
                     data = base85.b85decode(remoteobs[key])
                     pullop.repo.obsstore.mergemarkers(tr, data)
             pullop.repo.invalidatevolatilesets()
     return tr
 
 def caps20to10(repo):
     """return a set with appropriate options to use bundle20 during getbundle"""
     caps = set(['HG20'])
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(repo))
     caps.add('bundle2=' + urllib.quote(capsblob))
     return caps
 
 # List of names of steps to perform for a bundle2 for getbundle, order matters.
 getbundle2partsorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 getbundle2partsmapping = {}
 
 def getbundle2partsgenerator(stepname, idx=None):
     """decorator for function generating bundle2 part for getbundle
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the getbundle2partsmapping dictionary directly."""
     def dec(func):
         assert stepname not in getbundle2partsmapping
         getbundle2partsmapping[stepname] = func
         if idx is None:
             getbundle2partsorder.append(stepname)
         else:
             getbundle2partsorder.insert(idx, stepname)
         return func
     return dec
 
 def getbundle(repo, source, heads=None, common=None, bundlecaps=None,
               **kwargs):
     """return a full bundle (with potentially multiple kind of parts)
 
     Could be a bundle HG10 or a bundle HG20 depending on bundlecaps
     passed. For now, the bundle can contain only changegroup, but this will
     changes when more part type will be available for bundle2.
 
     This is different from changegroup.getchangegroup that only returns an HG10
     changegroup bundle. They may eventually get reunited in the future when we
     have a clearer idea of the API we what to query different data.
 
     The implementation is at a very early stage and will get massive rework
     when the API of bundle is refined.
     """
     # bundle10 case
     usebundle2 = False
     if bundlecaps is not None:
         usebundle2 = any((cap.startswith('HG2') for cap in bundlecaps))
     if not usebundle2:
         if bundlecaps and not kwargs.get('cg', True):
             raise ValueError(_('request for bundle10 must include changegroup'))
 
         if kwargs:
             raise ValueError(_('unsupported getbundle arguments: %s')
                              % ', '.join(sorted(kwargs.keys())))
         return changegroup.getchangegroup(repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps)
 
     # bundle20 case
     b2caps = {}
     for bcaps in bundlecaps:
         if bcaps.startswith('bundle2='):
             blob = urllib.unquote(bcaps[len('bundle2='):])
             b2caps.update(bundle2.decodecaps(blob))
     bundler = bundle2.bundle20(repo.ui, b2caps)
 
     kwargs['heads'] = heads
     kwargs['common'] = common
 
     for name in getbundle2partsorder:
         func = getbundle2partsmapping[name]
         func(bundler, repo, source, bundlecaps=bundlecaps, b2caps=b2caps,
              **kwargs)
 
     return util.chunkbuffer(bundler.getchunks())
 
 @getbundle2partsgenerator('changegroup')
 def _getbundlechangegrouppart(bundler, repo, source, bundlecaps=None,
                               b2caps=None, heads=None, common=None, **kwargs):
     """add a changegroup part to the requested bundle"""
     cg = None
     if kwargs.get('cg', True):
         # build changegroup bundle here.
         version = None
         cgversions = b2caps.get('changegroup')
         getcgkwargs = {}
         if cgversions:  # 3.1 and 3.2 ship with an empty value
             cgversions = [v for v in cgversions if v in changegroup.packermap]
             if not cgversions:
                 raise ValueError(_('no common changegroup version'))
             version = getcgkwargs['version'] = max(cgversions)
         outgoing = changegroup.computeoutgoing(repo, heads, common)
         cg = changegroup.getlocalchangegroupraw(repo, source, outgoing,
                                                 bundlecaps=bundlecaps,
                                                 **getcgkwargs)
 
     if cg:
         part = bundler.newpart('changegroup', data=cg)
         if version is not None:
             part.addparam('version', version)
         part.addparam('nbchanges', str(len(outgoing.missing)), mandatory=False)
 
 @getbundle2partsgenerator('listkeys')
 def _getbundlelistkeysparts(bundler, repo, source, bundlecaps=None,
                             b2caps=None, **kwargs):
     """add parts containing listkeys namespaces to the requested bundle"""
     listkeys = kwargs.get('listkeys', ())
     for namespace in listkeys:
         part = bundler.newpart('listkeys')
         part.addparam('namespace', namespace)
         keys = repo.listkeys(namespace).items()
         part.data = pushkey.encodekeys(keys)
 
 @getbundle2partsgenerator('obsmarkers')
 def _getbundleobsmarkerpart(bundler, repo, source, bundlecaps=None,
                             b2caps=None, heads=None, **kwargs):
     """add an obsolescence markers part to the requested bundle"""
     if kwargs.get('obsmarkers', False):
         if heads is None:
             heads = repo.heads()
         subset = [c.node() for c in repo.set('::%ln', heads)]
         markers = repo.obsstore.relevantmarkers(subset)
         markers = sorted(markers)
         buildobsmarkerspart(bundler, markers)
 
 @getbundle2partsgenerator('hgtagsfnodes')
 def _getbundletagsfnodes(bundler, repo, source, bundlecaps=None,
                          b2caps=None, heads=None, common=None,
                          **kwargs):
     """Transfer the .hgtags filenodes mapping.
 
     Only values for heads in this bundle will be transferred.
 
     The part data consists of pairs of 20 byte changeset node and .hgtags
     filenodes raw values.
     """
     # Don't send unless:
     # - changeset are being exchanged,
     # - the client supports it.
     if not (kwargs.get('cg', True) and 'hgtagsfnodes' in b2caps):
         return
 
     outgoing = changegroup.computeoutgoing(repo, heads, common)
 
     if not outgoing.missingheads:
         return
 
     cache = tags.hgtagsfnodescache(repo.unfiltered())
     chunks = []
 
     # .hgtags fnodes are only relevant for head changesets. While we could
     # transfer values for all known nodes, there will likely be little to
     # no benefit.
     #
     # We don't bother using a generator to produce output data because
     # a) we only have 40 bytes per head and even esoteric numbers of heads
     # consume little memory (1M heads is 40MB) b) we don't want to send the
     # part if we don't have entries and knowing if we have entries requires
     # cache lookups.
     for node in outgoing.missingheads:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode is not None:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart('hgtagsfnodes', data=''.join(chunks))
 
 def check_heads(repo, their_heads, context):
     """check if the heads of a repo have been modified
 
     Used by peer for unbundling.
     """
     heads = repo.heads()
     heads_hash = util.sha1(''.join(sorted(heads))).digest()
     if not (their_heads == ['force'] or their_heads == heads or
             their_heads == ['hashed', heads_hash]):
         # someone else committed/pushed/unbundled while we
         # were transferring data
         raise error.PushRaced('repository changed while %s - '
                               'please try again' % context)
 
 def unbundle(repo, cg, heads, source, url):
     """Apply a bundle to a repo.
 
     this function makes sure the repo is locked during the application and have
     mechanism to check that no push race occurred between the creation of the
     bundle and its application.
 
     If the push was raced as PushRaced exception is raised."""
     r = 0
     # need a transaction when processing a bundle2 stream
     # [wlock, lock, tr] - needs to be an array so nested functions can modify it
     lockandtr = [None, None, None]
     recordout = None
     # quick fix for output mismatch with bundle2 in 3.4
     captureoutput = repo.ui.configbool('experimental', 'bundle2-output-capture',
                                        False)
     if url.startswith('remote:http:') or url.startswith('remote:https:'):
         captureoutput = True
     try:
         check_heads(repo, heads, 'uploading changes')
         # push can proceed
         if util.safehasattr(cg, 'params'):
             r = None
             try:
                 def gettransaction():
                     if not lockandtr[2]:
                         lockandtr[0] = repo.wlock()
                         lockandtr[1] = repo.lock()
                         lockandtr[2] = repo.transaction(source)
                         lockandtr[2].hookargs['source'] = source
                         lockandtr[2].hookargs['url'] = url
                         lockandtr[2].hookargs['bundle2'] = '1'
                     return lockandtr[2]
 
                 # Do greedy locking by default until we're satisfied with lazy
                 # locking.
                 if not repo.ui.configbool('experimental', 'bundle2lazylocking'):
                     gettransaction()
 
                 op = bundle2.bundleoperation(repo, gettransaction,
                                              captureoutput=captureoutput)
                 try:
                     op = bundle2.processbundle(repo, cg, op=op)
                 finally:
                     r = op.reply
                     if captureoutput and r is not None:
                         repo.ui.pushbuffer(error=True, subproc=True)
                         def recordout(output):
                             r.newpart('output', data=output, mandatory=False)
                 if lockandtr[2] is not None:
                     lockandtr[2].close()
             except BaseException as exc:
                 exc.duringunbundle2 = True
                 if captureoutput and r is not None:
                     parts = exc._bundle2salvagedoutput = r.salvageoutput()
                     def recordout(output):
                         part = bundle2.bundlepart('output', data=output,
                                                   mandatory=False)
                         parts.append(part)
                 raise
         else:
             lockandtr[1] = repo.lock()
             r = cg.apply(repo, source, url)
     finally:
         lockmod.release(lockandtr[2], lockandtr[1], lockandtr[0])
         if recordout is not None:
             recordout(repo.ui.popbuffer())
     return r
 
 def _maybeapplyclonebundle(pullop):
     """Apply a clone bundle from a remote, if possible."""
 
     repo = pullop.repo
     remote = pullop.remote
 
     if not repo.ui.configbool('experimental', 'clonebundles', False):
         return
 
     if pullop.heads:
         return
 
     if not remote.capable('clonebundles'):
         return
 
     res = remote._call('clonebundles')
 
     # If we call the wire protocol command, that's good enough to record the
     # attempt.
     pullop.clonebundleattempted = True
 
     entries = parseclonebundlesmanifest(repo, res)
     if not entries:
         repo.ui.note(_('no clone bundles available on remote; '
                        'falling back to regular clone\n'))
         return
 
     entries = filterclonebundleentries(repo, entries)
     if not entries:
         # There is a thundering herd concern here. However, if a server
         # operator doesn't advertise bundles appropriate for its clients,
         # they deserve what's coming. Furthermore, from a client's
         # perspective, no automatic fallback would mean not being able to
         # clone!
         repo.ui.warn(_('no compatible clone bundles available on server; '
                        'falling back to regular clone\n'))
         repo.ui.warn(_('(you may want to report this to the server '
                        'operator)\n'))
         return
 
     entries = sortclonebundleentries(repo.ui, entries)
 
     url = entries[0]['URL']
     repo.ui.status(_('applying clone bundle from %s\n') % url)
     if trypullbundlefromurl(repo.ui, repo, url):
         repo.ui.status(_('finished applying clone bundle\n'))
     # Bundle failed.
     #
     # We abort by default to avoid the thundering herd of
     # clients flooding a server that was expecting expensive
     # clone load to be offloaded.
     elif repo.ui.configbool('ui', 'clonebundlefallback', False):
         repo.ui.warn(_('falling back to normal clone\n'))
     else:
         raise error.Abort(_('error applying bundle'),
                           hint=_('if this error persists, consider contacting '
                                  'the server operator or disable clone '
                                  'bundles via '
                                  '"--config experimental.clonebundles=false"'))
 
 def parseclonebundlesmanifest(repo, s):
     """Parses the raw text of a clone bundles manifest.
 
     Returns a list of dicts. The dicts have a ``URL`` key corresponding
     to the URL and other keys are the attributes for the entry.
     """
     m = []
     for line in s.splitlines():
         fields = line.split()
         if not fields:
             continue
         attrs = {'URL': fields[0]}
         for rawattr in fields[1:]:
             key, value = rawattr.split('=', 1)
             key = urllib.unquote(key)
             value = urllib.unquote(value)
             attrs[key] = value
 
             # Parse BUNDLESPEC into components. This makes client-side
             # preferences easier to specify since you can prefer a single
             # component of the BUNDLESPEC.
             if key == 'BUNDLESPEC':
                 try:
                     comp, version, params = parsebundlespec(repo, value,
                                                             externalnames=True)
                     attrs['COMPRESSION'] = comp
                     attrs['VERSION'] = version
                 except error.InvalidBundleSpecification:
                     pass
                 except error.UnsupportedBundleSpecification:
                     pass
 
         m.append(attrs)
 
     return m
 
 def filterclonebundleentries(repo, entries):
     """Remove incompatible clone bundle manifest entries.
 
     Accepts a list of entries parsed with ``parseclonebundlesmanifest``
     and returns a new list consisting of only the entries that this client
     should be able to apply.
 
     There is no guarantee we'll be able to apply all returned entries because
     the metadata we use to filter on may be missing or wrong.
     """
     newentries = []
     for entry in entries:
         spec = entry.get('BUNDLESPEC')
         if spec:
             try:
                 parsebundlespec(repo, spec, strict=True)
             except error.InvalidBundleSpecification as e:
                 repo.ui.debug(str(e) + '\n')
                 continue
             except error.UnsupportedBundleSpecification as e:
                 repo.ui.debug('filtering %s because unsupported bundle '
                               'spec: %s\n' % (entry['URL'], str(e)))
                 continue
 
         if 'REQUIRESNI' in entry and not sslutil.hassni:
             repo.ui.debug('filtering %s because SNI not supported\n' %
                           entry['URL'])
             continue
 
         newentries.append(entry)
 
     return newentries
 
 def sortclonebundleentries(ui, entries):
     # experimental config: experimental.clonebundleprefers
     prefers = ui.configlist('experimental', 'clonebundleprefers', default=[])
     if not prefers:
         return list(entries)
 
     prefers = [p.split('=', 1) for p in prefers]
 
     # Our sort function.
     def compareentry(a, b):
         for prefkey, prefvalue in prefers:
             avalue = a.get(prefkey)
             bvalue = b.get(prefkey)
 
             # Special case for b missing attribute and a matches exactly.
             if avalue is not None and bvalue is None and avalue == prefvalue:
                 return -1
 
             # Special case for a missing attribute and b matches exactly.
             if bvalue is not None and avalue is None and bvalue == prefvalue:
                 return 1
 
             # We can't compare unless attribute present on both.
             if avalue is None or bvalue is None:
                 continue
 
             # Same values should fall back to next attribute.
             if avalue == bvalue:
                 continue
 
             # Exact matches come first.
             if avalue == prefvalue:
                 return -1
             if bvalue == prefvalue:
                 return 1
 
             # Fall back to next attribute.
             continue
 
         # If we got here we couldn't sort by attributes and prefers. Fall
         # back to index order.
         return 0
 
     return sorted(entries, cmp=compareentry)
 
 def trypullbundlefromurl(ui, repo, url):
     """Attempt to apply a bundle from a URL."""
     lock = repo.lock()
     try:
         tr = repo.transaction('bundleurl')
         try:
             try:
                 fh = urlmod.open(ui, url)
                 cg = readbundle(ui, fh, 'stream')
 
                 if isinstance(cg, bundle2.unbundle20):
                     bundle2.processbundle(repo, cg, lambda: tr)
                 elif isinstance(cg, streamclone.streamcloneapplier):
                     cg.apply(repo)
                 else:
                     cg.apply(repo, 'clonebundles', url)
                 tr.close()
                 return True
             except urllib2.HTTPError as e:
                 ui.warn(_('HTTP error fetching bundle: %s\n') % str(e))
             except urllib2.URLError as e:
                 ui.warn(_('error fetching bundle: %s\n') % e.reason[1])
 
             return False
         finally:
             tr.release()
     finally:
         lock.release()