i18n: translate abort messages

I found a few places where message given to abort is
not translated, I don't find any reason to not translate
them.

mercurial/bundlerepo.py

@@ -1,542 +1,542 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[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.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from __future__ import absolute_import
 
 import os
 import shutil
 import tempfile
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     node as nodemod,
     pathutil,
     phases,
     revlog,
     scmutil,
     util,
 )
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, bundle, linkmapper):
         # How it works:
         # To retrieve a revision, we need to know the offset of the revision in
         # the bundle (an unbundle object). We store this offset in the index
         # (start). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = scmutil.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = bundle
         n = len(self)
         self.repotiprev = n - 1
         chain = None
         self.bundlerevs = set() # used by 'bundle()' revset expression
         while True:
             chunkdata = bundle.deltachunk(chain)
             if not chunkdata:
                 break
             node = chunkdata['node']
             p1 = chunkdata['p1']
             p2 = chunkdata['p2']
             cs = chunkdata['cs']
             deltabase = chunkdata['deltabase']
             delta = chunkdata['delta']
 
             size = len(delta)
             start = bundle.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 chain = node
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             for p in (p1, p2):
                 if p not in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
 
             if deltabase not in self.nodemap:
                 raise LookupError(deltabase, self.indexfile,
                                   _('unknown delta base'))
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, 0), size, -1, baserev, link,
                  self.rev(p1), self.rev(p2), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             chain = node
             n += 1
 
     def _chunk(self, rev):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                               self.revision(self.node(rev2)))
 
     def revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if node == nullid:
             return ""
 
         text = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._cache and self._cache[1] == iterrev:
                 text = self._cache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if text is None:
             text = self.baserevision(iterrev)
 
         while chain:
             delta = self._chunk(chain.pop())
             text = mdiff.patches(text, [delta])
 
         self._checkhash(text, node, rev)
         self._cache = (node, rev, text)
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use bundlerevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev)
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, bundle):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
 
         # This bypasses filtering on changelog.node() and rev() because we need
         # revision text of the bundle base even if it is hidden.
         oldfilter = self.filteredrevs
         try:
             self.filteredrevs = ()
             return changelog.changelog.revision(self, nodeorrev)
         finally:
             self.filteredrevs = oldfilter
 
 class bundlemanifest(bundlerevlog, manifest.manifest):
     def __init__(self, opener, bundle, linkmapper):
         manifest.manifest.__init__(self, opener)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         node = nodeorrev
         if isinstance(node, int):
             node = self.node(node)
 
         if node in self._mancache:
             result = self._mancache[node][0].text()
         else:
             result = manifest.manifest.revision(self, nodeorrev)
         return result
 
 class bundlefilelog(bundlerevlog, filelog.filelog):
     def __init__(self, opener, path, bundle, linkmapper):
         filelog.filelog.__init__(self, opener, path)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev)
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
         if util.safehasattr(self, 'opener'):
             self.opener = scmutil.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 class bundlerepository(localrepo.localrepository):
     def __init__(self, ui, path, bundlename):
         def _writetempbundle(read, suffix, header=''):
             """Write a temporary file to disk
 
             This is closure because we need to make sure this tracked by
             self.tempfile for cleanup purposes."""
             fdtemp, temp = self.vfs.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un")
             self.tempfile = temp
 
             with os.fdopen(fdtemp, 'wb') as fptemp:
                 fptemp.write(header)
                 while True:
                     chunk = read(2**18)
                     if not chunk:
                         break
                     fptemp.write(chunk)
 
             return self.vfs.open(self.tempfile, mode="rb")
         self._tempparent = None
         try:
             localrepo.localrepository.__init__(self, ui, path)
         except error.RepoError:
             self._tempparent = tempfile.mkdtemp()
             localrepo.instance(ui, self._tempparent, 1)
             localrepo.localrepository.__init__(self, ui, self._tempparent)
         self.ui.setconfig('phases', 'publish', False, 'bundlerepo')
 
         if path:
             self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
         else:
             self._url = 'bundle:' + bundlename
 
         self.tempfile = None
         f = util.posixfile(bundlename, "rb")
         self.bundlefile = self.bundle = exchange.readbundle(ui, f, bundlename)
 
         if isinstance(self.bundle, bundle2.unbundle20):
             cgstream = None
             for part in self.bundle.iterparts():
                 if part.type == 'changegroup':
                     if cgstream is not None:
                         raise NotImplementedError("can't process "
                                                   "multiple changegroups")
                     cgstream = part
                     version = part.params.get('version', '01')
                     if version not in changegroup.allsupportedversions(ui):
                         msg = _('Unsupported changegroup version: %s')
                         raise error.Abort(msg % version)
                     if self.bundle.compressed():
                         cgstream = _writetempbundle(part.read,
                                                     ".cg%sun" % version)
 
             if cgstream is None:
-                raise error.Abort('No changegroups found')
+                raise error.Abort(_('No changegroups found'))
             cgstream.seek(0)
 
             self.bundle = changegroup.getunbundler(version, cgstream, 'UN')
 
         elif self.bundle.compressed():
             f = _writetempbundle(self.bundle.read, '.hg10un', header='HG10UN')
             self.bundlefile = self.bundle = exchange.readbundle(ui, f,
                                                                 bundlename,
                                                                 self.vfs)
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(self, None, phases.draft,
                                [ctx.node() for ctx in self[self.firstnewrev:]])
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self.bundle.changelogheader()
         c = bundlechangelog(self.svfs, self.bundle)
         self.manstart = self.bundle.tell()
         return c
 
     @localrepo.unfilteredpropertycache
     def manifest(self):
         self.bundle.seek(self.manstart)
         # consume the header if it exists
         self.bundle.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         m = bundlemanifest(self.svfs, self.bundle, linkmapper)
         # XXX: hack to work with changegroup3, but we still don't handle
         # tree manifests correctly
         if self.bundle.version == "03":
             self.bundle.filelogheader()
         self.filestart = self.bundle.tell()
         return m
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifest
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self.bundlefilespos:
             self.bundle.seek(self.filestart)
             while True:
                 chunkdata = self.bundle.filelogheader()
                 if not chunkdata:
                     break
                 fname = chunkdata['filename']
                 self.bundlefilespos[fname] = self.bundle.tell()
                 while True:
                     c = self.bundle.deltachunk(None)
                     if not c:
                         break
 
         if f in self.bundlefilespos:
             self.bundle.seek(self.bundlefilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self.bundle, linkmapper)
         else:
             return filelog.filelog(self.svfs, f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self.bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return os.getcwd() # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=nullid):
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _("setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % nodemod.hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % nodemod.hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config("bundle", "mainreporoot", "")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(os.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = os.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == 'bundle':
         s = path.split("+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
     return bundlerepository(ui, repopath, bundlename)
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                      force=False):
     '''obtains a bundle of changes incoming from other
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "other" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "other" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                        force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], other.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = other.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if other repo is not local)
 
         canbundle2 = (ui.configbool('experimental', 'bundle2-exp', True)
                       and other.capable('getbundle')
                       and other.capable('bundle2'))
         if canbundle2:
             kwargs = {}
             kwargs['common'] = common
             kwargs['heads'] = rheads
             kwargs['bundlecaps'] = exchange.caps20to10(repo)
             kwargs['cg'] = True
             b2 = other.getbundle('incoming', **kwargs)
             fname = bundle = changegroup.writechunks(ui, b2._forwardchunks(),
                                                      bundlename)
         else:
             if other.capable('getbundle'):
                 cg = other.getbundle('incoming', common=common, heads=rheads)
             elif onlyheads is None and not other.capable('changegroupsubset'):
                 # compat with older servers when pulling all remote heads
                 cg = other.changegroup(incoming, "incoming")
                 rheads = None
             else:
                 cg = other.changegroupsubset(incoming, rheads, 'incoming')
             if localrepo:
                 bundletype = "HG10BZ"
             else:
                 bundletype = "HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename,
                                                      bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root,
                                                       fname)
             # this repo contains local and other now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev:]]
         remotephases = other.listkeys('phases')
 
         pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         other.close()
 
     return (localrepo, csets, cleanup)

mercurial/exchange.py

@@ -1,1932 +1,1932 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 __future__ import absolute_import
 
 import errno
 import hashlib
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
 )
 from . import (
     base85,
     bookmarks as bookmod,
     bundle2,
     changegroup,
     discovery,
     error,
     lock as lockmod,
     obsolete,
     phases,
     pushkey,
     scmutil,
     sslutil,
     streamclone,
     tags,
     url as urlmod,
     util,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # 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 = urlreq.unquote(key)
             value = urlreq.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 getbundlespec(ui, fh):
     """Infer the bundlespec from a bundle file handle.
 
     The input file handle is seeked and the original seek position is not
     restored.
     """
     def speccompression(alg):
         for k, v in _bundlespeccompressions.items():
             if v == alg:
                 return k
         return None
 
     b = readbundle(ui, fh, None)
     if isinstance(b, changegroup.cg1unpacker):
         alg = b._type
         if alg == '_truncatedBZ':
             alg = 'BZ'
         comp = speccompression(alg)
         if not comp:
             raise error.Abort(_('unknown compression algorithm: %s') % alg)
         return '%s-v1' % comp
     elif isinstance(b, bundle2.unbundle20):
         if 'Compression' in b.params:
             comp = speccompression(b.params['Compression'])
             if not comp:
                 raise error.Abort(_('unknown compression algorithm: %s') % comp)
         else:
             comp = 'none'
 
         version = None
         for part in b.iterparts():
             if part.type == 'changegroup':
                 version = part.params['version']
                 if version in ('01', '02'):
                     version = 'v2'
                 else:
                     raise error.Abort(_('changegroup version %s does not have '
                                         'a known bundlespec') % version,
                                       hint=_('try upgrading your Mercurial '
                                               'client'))
 
         if not version:
             raise error.Abort(_('could not identify changegroup version in '
                                 'bundle'))
 
         return '%s-%s' % (comp, version)
     elif isinstance(b, streamclone.streamcloneapplier):
         requirements = streamclone.readbundle1header(fh)[2]
         params = 'requirements=%s' % ','.join(sorted(requirements))
         return 'none-packed1;%s' % urlreq.quote(params)
     else:
         raise error.Abort(_('unknown bundle type: %s') % b)
 
 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 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
 
     Its purpose is to carry push related state and very common operations.
 
     A new pushoperation 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([repo._bookmarks.expandname(bookmark)
                     for bookmark in 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)
 
         discovery.checkheads(pushop)
     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 independent 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)
 
     _pushb2ctxcheckheads(pushop, bundler)
 
     b2caps = bundle2.bundle2caps(pushop.remote)
     version = '01'
     cgversions = b2caps.get('changegroup')
     if cgversions:  # 3.1 and 3.2 ship with an empty value
         cgversions = [v for v in cgversions
                       if v in changegroup.supportedoutgoingversions(
                           pushop.repo)]
         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 cgversions:
         cgpart.addparam('version', version)
     if 'treemanifest' in pushop.repo.requirements:
         cgpart.addparam('treemanifest', '1')
     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)
+            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)
+            raise error.Abort(_('missing support for %s') % exc)
         except bundle2.AbortFromPart as exc:
             pushop.ui.status(_('remote: %s\n') % exc)
             raise error.Abort(_('push failed on remote'), hint=exc.hint)
     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)
     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 = [repo._bookmarks.expandname(bookmark)
                                   for bookmark in 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'] = ['phases']
         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)
+        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()
             markers = []
             for key in sorted(remoteobs, reverse=True):
                 if key.startswith('dump'):
                     data = base85.b85decode(remoteobs[key])
                     version, newmarks = obsolete._readmarkers(data)
                     markers += newmarks
             if markers:
                 pullop.repo.obsstore.add(tr, markers)
             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=' + urlreq.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 bundle2requested(bundlecaps):
     if bundlecaps is not None:
         return any(cap.startswith('HG2') for cap in bundlecaps)
     return False
 
 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.
     """
     usebundle2 = bundle2requested(bundlecaps)
     # bundle10 case
     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 = urlreq.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 = '01'
         cgversions = b2caps.get('changegroup')
         if cgversions:  # 3.1 and 3.2 ship with an empty value
             cgversions = [v for v in cgversions
                           if v in changegroup.supportedoutgoingversions(repo)]
             if not cgversions:
                 raise ValueError(_('no common changegroup version'))
             version = max(cgversions)
         outgoing = changegroup.computeoutgoing(repo, heads, common)
         cg = changegroup.getlocalchangegroupraw(repo, source, outgoing,
                                                 bundlecaps=bundlecaps,
                                                 version=version)
 
     if cg:
         part = bundler.newpart('changegroup', data=cg)
         if cgversions:
             part.addparam('version', version)
         part.addparam('nbchanges', str(len(outgoing.missing)), mandatory=False)
         if 'treemanifest' in repo.requirements:
             part.addparam('treemanifest', '1')
 
 @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 = hashlib.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('ui', 'clonebundles', True):
         return
 
     # Only run if local repo is empty.
     if len(repo):
         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 ui.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 = urlreq.unquote(key)
             value = urlreq.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):
     prefers = ui.configlist('ui', '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 urlerr.httperror as e:
                 ui.warn(_('HTTP error fetching bundle: %s\n') % str(e))
             except urlerr.urlerror as e:
                 ui.warn(_('error fetching bundle: %s\n') % e.reason[1])
 
             return False
         finally:
             tr.release()
     finally:
         lock.release()

mercurial/hg.py

@@ -1,1014 +1,1015 b''
 # hg.py - repository classes for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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 __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import shutil
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     bookmarks,
     bundlerepo,
     cmdutil,
     destutil,
     discovery,
     error,
     exchange,
     extensions,
     httppeer,
     localrepo,
     lock,
     merge as mergemod,
     node,
     phases,
     repoview,
     scmutil,
     sshpeer,
     statichttprepo,
     ui as uimod,
     unionrepo,
     url,
     util,
     verify as verifymod,
 )
 
 release = lock.release
 
 def _local(path):
     path = util.expandpath(util.urllocalpath(path))
     return (os.path.isfile(path) and bundlerepo or localrepo)
 
 def addbranchrevs(lrepo, other, branches, revs):
     peer = other.peer() # a courtesy to callers using a localrepo for other
     hashbranch, branches = branches
     if not hashbranch and not branches:
         x = revs or None
         if util.safehasattr(revs, 'first'):
             y = revs.first()
         elif revs:
             y = revs[0]
         else:
             y = None
         return x, y
     if revs:
         revs = list(revs)
     else:
         revs = []
 
     if not peer.capable('branchmap'):
         if branches:
             raise error.Abort(_("remote branch lookup not supported"))
         revs.append(hashbranch)
         return revs, revs[0]
     branchmap = peer.branchmap()
 
     def primary(branch):
         if branch == '.':
             if not lrepo:
                 raise error.Abort(_("dirstate branch not accessible"))
             branch = lrepo.dirstate.branch()
         if branch in branchmap:
             revs.extend(node.hex(r) for r in reversed(branchmap[branch]))
             return True
         else:
             return False
 
     for branch in branches:
         if not primary(branch):
             raise error.RepoLookupError(_("unknown branch '%s'") % branch)
     if hashbranch:
         if not primary(hashbranch):
             revs.append(hashbranch)
     return revs, revs[0]
 
 def parseurl(path, branches=None):
     '''parse url#branch, returning (url, (branch, branches))'''
 
     u = util.url(path)
     branch = None
     if u.fragment:
         branch = u.fragment
         u.fragment = None
     return str(u), (branch, branches or [])
 
 schemes = {
     'bundle': bundlerepo,
     'union': unionrepo,
     'file': _local,
     'http': httppeer,
     'https': httppeer,
     'ssh': sshpeer,
     'static-http': statichttprepo,
 }
 
 def _peerlookup(path):
     u = util.url(path)
     scheme = u.scheme or 'file'
     thing = schemes.get(scheme) or schemes['file']
     try:
         return thing(path)
     except TypeError:
         # we can't test callable(thing) because 'thing' can be an unloaded
         # module that implements __call__
         if not util.safehasattr(thing, 'instance'):
             raise
         return thing
 
 def islocal(repo):
     '''return true if repo (or path pointing to repo) is local'''
     if isinstance(repo, str):
         try:
             return _peerlookup(repo).islocal(repo)
         except AttributeError:
             return False
     return repo.local()
 
 def openpath(ui, path):
     '''open path with open if local, url.open if remote'''
     pathurl = util.url(path, parsequery=False, parsefragment=False)
     if pathurl.islocal():
         return util.posixfile(pathurl.localpath(), 'rb')
     else:
         return url.open(ui, path)
 
 # a list of (ui, repo) functions called for wire peer initialization
 wirepeersetupfuncs = []
 
 def _peerorrepo(ui, path, create=False):
     """return a repository object for the specified path"""
     obj = _peerlookup(path).instance(ui, path, create)
     ui = getattr(obj, "ui", ui)
     for name, module in extensions.extensions(ui):
         hook = getattr(module, 'reposetup', None)
         if hook:
             hook(ui, obj)
     if not obj.local():
         for f in wirepeersetupfuncs:
             f(ui, obj)
     return obj
 
 def repository(ui, path='', create=False):
     """return a repository object for the specified path"""
     peer = _peerorrepo(ui, path, create)
     repo = peer.local()
     if not repo:
         raise error.Abort(_("repository '%s' is not local") %
                          (path or peer.url()))
     return repo.filtered('visible')
 
 def peer(uiorrepo, opts, path, create=False):
     '''return a repository peer for the specified path'''
     rui = remoteui(uiorrepo, opts)
     return _peerorrepo(rui, path, create).peer()
 
 def defaultdest(source):
     '''return default destination of clone if none is given
 
     >>> defaultdest('foo')
     'foo'
     >>> defaultdest('/foo/bar')
     'bar'
     >>> defaultdest('/')
     ''
     >>> defaultdest('')
     ''
     >>> defaultdest('http://example.org/')
     ''
     >>> defaultdest('http://example.org/foo/')
     'foo'
     '''
     path = util.url(source).path
     if not path:
         return ''
     return os.path.basename(os.path.normpath(path))
 
 def share(ui, source, dest=None, update=True, bookmarks=True):
     '''create a shared repository'''
 
     if not islocal(source):
         raise error.Abort(_('can only share local repositories'))
 
     if not dest:
         dest = defaultdest(source)
     else:
         dest = ui.expandpath(dest)
 
     if isinstance(source, str):
         origsource = ui.expandpath(source)
         source, branches = parseurl(origsource)
         srcrepo = repository(ui, source)
         rev, checkout = addbranchrevs(srcrepo, srcrepo, branches, None)
     else:
         srcrepo = source.local()
         origsource = source = srcrepo.url()
         checkout = None
 
     sharedpath = srcrepo.sharedpath # if our source is already sharing
 
     destwvfs = scmutil.vfs(dest, realpath=True)
     destvfs = scmutil.vfs(os.path.join(destwvfs.base, '.hg'), realpath=True)
 
     if destvfs.lexists():
         raise error.Abort(_('destination already exists'))
 
     if not destwvfs.isdir():
         destwvfs.mkdir()
     destvfs.makedir()
 
     requirements = ''
     try:
         requirements = srcrepo.vfs.read('requires')
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
 
     requirements += 'shared\n'
     destvfs.write('requires', requirements)
     destvfs.write('sharedpath', sharedpath)
 
     r = repository(ui, destwvfs.base)
     postshare(srcrepo, r, bookmarks=bookmarks)
     _postshareupdate(r, update, checkout=checkout)
 
 def postshare(sourcerepo, destrepo, bookmarks=True):
     """Called after a new shared repo is created.
 
     The new repo only has a requirements file and pointer to the source.
     This function configures additional shared data.
 
     Extensions can wrap this function and write additional entries to
     destrepo/.hg/shared to indicate additional pieces of data to be shared.
     """
     default = sourcerepo.ui.config('paths', 'default')
     if default:
         fp = destrepo.vfs("hgrc", "w", text=True)
         fp.write("[paths]\n")
         fp.write("default = %s\n" % default)
         fp.close()
 
     if bookmarks:
         fp = destrepo.vfs('shared', 'w')
         fp.write('bookmarks\n')
         fp.close()
 
 def _postshareupdate(repo, update, checkout=None):
     """Maybe perform a working directory update after a shared repo is created.
 
     ``update`` can be a boolean or a revision to update to.
     """
     if not update:
         return
 
     repo.ui.status(_("updating working directory\n"))
     if update is not True:
         checkout = update
     for test in (checkout, 'default', 'tip'):
         if test is None:
             continue
         try:
             uprev = repo.lookup(test)
             break
         except error.RepoLookupError:
             continue
     _update(repo, uprev)
 
 def copystore(ui, srcrepo, destpath):
     '''copy files from store of srcrepo in destpath
 
     returns destlock
     '''
     destlock = None
     try:
         hardlink = None
         num = 0
         closetopic = [None]
         def prog(topic, pos):
             if pos is None:
                 closetopic[0] = topic
             else:
                 ui.progress(topic, pos + num)
         srcpublishing = srcrepo.publishing()
         srcvfs = scmutil.vfs(srcrepo.sharedpath)
         dstvfs = scmutil.vfs(destpath)
         for f in srcrepo.store.copylist():
             if srcpublishing and f.endswith('phaseroots'):
                 continue
             dstbase = os.path.dirname(f)
             if dstbase and not dstvfs.exists(dstbase):
                 dstvfs.mkdir(dstbase)
             if srcvfs.exists(f):
                 if f.endswith('data'):
                     # 'dstbase' may be empty (e.g. revlog format 0)
                     lockfile = os.path.join(dstbase, "lock")
                     # lock to avoid premature writing to the target
                     destlock = lock.lock(dstvfs, lockfile)
                 hardlink, n = util.copyfiles(srcvfs.join(f), dstvfs.join(f),
                                              hardlink, progress=prog)
                 num += n
         if hardlink:
             ui.debug("linked %d files\n" % num)
             if closetopic[0]:
                 ui.progress(closetopic[0], None)
         else:
             ui.debug("copied %d files\n" % num)
             if closetopic[0]:
                 ui.progress(closetopic[0], None)
         return destlock
     except: # re-raises
         release(destlock)
         raise
 
 def clonewithshare(ui, peeropts, sharepath, source, srcpeer, dest, pull=False,
                    rev=None, update=True, stream=False):
     """Perform a clone using a shared repo.
 
     The store for the repository will be located at <sharepath>/.hg. The
     specified revisions will be cloned or pulled from "source". A shared repo
     will be created at "dest" and a working copy will be created if "update" is
     True.
     """
     revs = None
     if rev:
         if not srcpeer.capable('lookup'):
             raise error.Abort(_("src repository does not support "
                                "revision lookup and so doesn't "
                                "support clone by revision"))
         revs = [srcpeer.lookup(r) for r in rev]
 
     # Obtain a lock before checking for or cloning the pooled repo otherwise
     # 2 clients may race creating or populating it.
     pooldir = os.path.dirname(sharepath)
     # lock class requires the directory to exist.
     try:
         util.makedir(pooldir, False)
     except OSError as e:
         if e.errno != errno.EEXIST:
             raise
 
     poolvfs = scmutil.vfs(pooldir)
     basename = os.path.basename(sharepath)
 
     with lock.lock(poolvfs, '%s.lock' % basename):
         if os.path.exists(sharepath):
             ui.status(_('(sharing from existing pooled repository %s)\n') %
                       basename)
         else:
             ui.status(_('(sharing from new pooled repository %s)\n') % basename)
             # Always use pull mode because hardlinks in share mode don't work
             # well. Never update because working copies aren't necessary in
             # share mode.
             clone(ui, peeropts, source, dest=sharepath, pull=True,
                   rev=rev, update=False, stream=stream)
 
     sharerepo = repository(ui, path=sharepath)
     share(ui, sharerepo, dest=dest, update=False, bookmarks=False)
 
     # We need to perform a pull against the dest repo to fetch bookmarks
     # and other non-store data that isn't shared by default. In the case of
     # non-existing shared repo, this means we pull from the remote twice. This
     # is a bit weird. But at the time it was implemented, there wasn't an easy
     # way to pull just non-changegroup data.
     destrepo = repository(ui, path=dest)
     exchange.pull(destrepo, srcpeer, heads=revs)
 
     _postshareupdate(destrepo, update)
 
     return srcpeer, peer(ui, peeropts, dest)
 
 def clone(ui, peeropts, source, dest=None, pull=False, rev=None,
           update=True, stream=False, branch=None, shareopts=None):
     """Make a copy of an existing repository.
 
     Create a copy of an existing repository in a new directory.  The
     source and destination are URLs, as passed to the repository
     function.  Returns a pair of repository peers, the source and
     newly created destination.
 
     The location of the source is added to the new repository's
     .hg/hgrc file, as the default to be used for future pulls and
     pushes.
 
     If an exception is raised, the partly cloned/updated destination
     repository will be deleted.
 
     Arguments:
 
     source: repository object or URL
 
     dest: URL of destination repository to create (defaults to base
     name of source repository)
 
     pull: always pull from source repository, even in local case or if the
     server prefers streaming
 
     stream: stream raw data uncompressed from repository (fast over
     LAN, slow over WAN)
 
     rev: revision to clone up to (implies pull=True)
 
     update: update working directory after clone completes, if
     destination is local repository (True means update to default rev,
     anything else is treated as a revision)
 
     branch: branches to clone
 
     shareopts: dict of options to control auto sharing behavior. The "pool" key
     activates auto sharing mode and defines the directory for stores. The
     "mode" key determines how to construct the directory name of the shared
     repository. "identity" means the name is derived from the node of the first
     changeset in the repository. "remote" means the name is derived from the
     remote's path/URL. Defaults to "identity."
     """
 
     if isinstance(source, str):
         origsource = ui.expandpath(source)
         source, branch = parseurl(origsource, branch)
         srcpeer = peer(ui, peeropts, source)
     else:
         srcpeer = source.peer() # in case we were called with a localrepo
         branch = (None, branch or [])
         origsource = source = srcpeer.url()
     rev, checkout = addbranchrevs(srcpeer, srcpeer, branch, rev)
 
     if dest is None:
         dest = defaultdest(source)
         if dest:
             ui.status(_("destination directory: %s\n") % dest)
     else:
         dest = ui.expandpath(dest)
 
     dest = util.urllocalpath(dest)
     source = util.urllocalpath(source)
 
     if not dest:
         raise error.Abort(_("empty destination path is not valid"))
 
     destvfs = scmutil.vfs(dest, expandpath=True)
     if destvfs.lexists():
         if not destvfs.isdir():
             raise error.Abort(_("destination '%s' already exists") % dest)
         elif destvfs.listdir():
             raise error.Abort(_("destination '%s' is not empty") % dest)
 
     shareopts = shareopts or {}
     sharepool = shareopts.get('pool')
     sharenamemode = shareopts.get('mode')
     if sharepool and islocal(dest):
         sharepath = None
         if sharenamemode == 'identity':
             # Resolve the name from the initial changeset in the remote
             # repository. This returns nullid when the remote is empty. It
             # raises RepoLookupError if revision 0 is filtered or otherwise
             # not available. If we fail to resolve, sharing is not enabled.
             try:
                 rootnode = srcpeer.lookup('0')
                 if rootnode != node.nullid:
                     sharepath = os.path.join(sharepool, node.hex(rootnode))
                 else:
                     ui.status(_('(not using pooled storage: '
                                 'remote appears to be empty)\n'))
             except error.RepoLookupError:
                 ui.status(_('(not using pooled storage: '
                             'unable to resolve identity of remote)\n'))
         elif sharenamemode == 'remote':
             sharepath = os.path.join(
                 sharepool, hashlib.sha1(source).hexdigest())
         else:
-            raise error.Abort('unknown share naming mode: %s' % sharenamemode)
+            raise error.Abort(_('unknown share naming mode: %s') %
+                              sharenamemode)
 
         if sharepath:
             return clonewithshare(ui, peeropts, sharepath, source, srcpeer,
                                   dest, pull=pull, rev=rev, update=update,
                                   stream=stream)
 
     srclock = destlock = cleandir = None
     srcrepo = srcpeer.local()
     try:
         abspath = origsource
         if islocal(origsource):
             abspath = os.path.abspath(util.urllocalpath(origsource))
 
         if islocal(dest):
             cleandir = dest
 
         copy = False
         if (srcrepo and srcrepo.cancopy() and islocal(dest)
             and not phases.hassecret(srcrepo)):
             copy = not pull and not rev
 
         if copy:
             try:
                 # we use a lock here because if we race with commit, we
                 # can end up with extra data in the cloned revlogs that's
                 # not pointed to by changesets, thus causing verify to
                 # fail
                 srclock = srcrepo.lock(wait=False)
             except error.LockError:
                 copy = False
 
         if copy:
             srcrepo.hook('preoutgoing', throw=True, source='clone')
             hgdir = os.path.realpath(os.path.join(dest, ".hg"))
             if not os.path.exists(dest):
                 os.mkdir(dest)
             else:
                 # only clean up directories we create ourselves
                 cleandir = hgdir
             try:
                 destpath = hgdir
                 util.makedir(destpath, notindexed=True)
             except OSError as inst:
                 if inst.errno == errno.EEXIST:
                     cleandir = None
                     raise error.Abort(_("destination '%s' already exists")
                                      % dest)
                 raise
 
             destlock = copystore(ui, srcrepo, destpath)
             # copy bookmarks over
             srcbookmarks = srcrepo.join('bookmarks')
             dstbookmarks = os.path.join(destpath, 'bookmarks')
             if os.path.exists(srcbookmarks):
                 util.copyfile(srcbookmarks, dstbookmarks)
 
             # Recomputing branch cache might be slow on big repos,
             # so just copy it
             def copybranchcache(fname):
                 srcbranchcache = srcrepo.join('cache/%s' % fname)
                 dstbranchcache = os.path.join(dstcachedir, fname)
                 if os.path.exists(srcbranchcache):
                     if not os.path.exists(dstcachedir):
                         os.mkdir(dstcachedir)
                     util.copyfile(srcbranchcache, dstbranchcache)
 
             dstcachedir = os.path.join(destpath, 'cache')
             # In local clones we're copying all nodes, not just served
             # ones. Therefore copy all branch caches over.
             copybranchcache('branch2')
             for cachename in repoview.filtertable:
                 copybranchcache('branch2-%s' % cachename)
 
             # we need to re-init the repo after manually copying the data
             # into it
             destpeer = peer(srcrepo, peeropts, dest)
             srcrepo.hook('outgoing', source='clone',
                           node=node.hex(node.nullid))
         else:
             try:
                 destpeer = peer(srcrepo or ui, peeropts, dest, create=True)
                                 # only pass ui when no srcrepo
             except OSError as inst:
                 if inst.errno == errno.EEXIST:
                     cleandir = None
                     raise error.Abort(_("destination '%s' already exists")
                                      % dest)
                 raise
 
             revs = None
             if rev:
                 if not srcpeer.capable('lookup'):
                     raise error.Abort(_("src repository does not support "
                                        "revision lookup and so doesn't "
                                        "support clone by revision"))
                 revs = [srcpeer.lookup(r) for r in rev]
                 checkout = revs[0]
             local = destpeer.local()
             if local:
                 if not stream:
                     if pull:
                         stream = False
                     else:
                         stream = None
                 # internal config: ui.quietbookmarkmove
                 quiet = local.ui.backupconfig('ui', 'quietbookmarkmove')
                 try:
                     local.ui.setconfig(
                         'ui', 'quietbookmarkmove', True, 'clone')
                     exchange.pull(local, srcpeer, revs,
                                   streamclonerequested=stream)
                 finally:
                     local.ui.restoreconfig(quiet)
             elif srcrepo:
                 exchange.push(srcrepo, destpeer, revs=revs,
                               bookmarks=srcrepo._bookmarks.keys())
             else:
                 raise error.Abort(_("clone from remote to remote not supported")
                                  )
 
         cleandir = None
 
         destrepo = destpeer.local()
         if destrepo:
             template = uimod.samplehgrcs['cloned']
             fp = destrepo.vfs("hgrc", "w", text=True)
             u = util.url(abspath)
             u.passwd = None
             defaulturl = str(u)
             fp.write(template % defaulturl)
             fp.close()
 
             destrepo.ui.setconfig('paths', 'default', defaulturl, 'clone')
 
             if update:
                 if update is not True:
                     checkout = srcpeer.lookup(update)
                 uprev = None
                 status = None
                 if checkout is not None:
                     try:
                         uprev = destrepo.lookup(checkout)
                     except error.RepoLookupError:
                         if update is not True:
                             try:
                                 uprev = destrepo.lookup(update)
                             except error.RepoLookupError:
                                 pass
                 if uprev is None:
                     try:
                         uprev = destrepo._bookmarks['@']
                         update = '@'
                         bn = destrepo[uprev].branch()
                         if bn == 'default':
                             status = _("updating to bookmark @\n")
                         else:
                             status = (_("updating to bookmark @ on branch %s\n")
                                       % bn)
                     except KeyError:
                         try:
                             uprev = destrepo.branchtip('default')
                         except error.RepoLookupError:
                             uprev = destrepo.lookup('tip')
                 if not status:
                     bn = destrepo[uprev].branch()
                     status = _("updating to branch %s\n") % bn
                 destrepo.ui.status(status)
                 _update(destrepo, uprev)
                 if update in destrepo._bookmarks:
                     bookmarks.activate(destrepo, update)
     finally:
         release(srclock, destlock)
         if cleandir is not None:
             shutil.rmtree(cleandir, True)
         if srcpeer is not None:
             srcpeer.close()
     return srcpeer, destpeer
 
 def _showstats(repo, stats, quietempty=False):
     if quietempty and not any(stats):
         return
     repo.ui.status(_("%d files updated, %d files merged, "
                      "%d files removed, %d files unresolved\n") % stats)
 
 def updaterepo(repo, node, overwrite):
     """Update the working directory to node.
 
     When overwrite is set, changes are clobbered, merged else
 
     returns stats (see pydoc mercurial.merge.applyupdates)"""
     return mergemod.update(repo, node, False, overwrite,
                            labels=['working copy', 'destination'])
 
 def update(repo, node, quietempty=False):
     """update the working directory to node, merging linear changes"""
     stats = updaterepo(repo, node, False)
     _showstats(repo, stats, quietempty)
     if stats[3]:
         repo.ui.status(_("use 'hg resolve' to retry unresolved file merges\n"))
     return stats[3] > 0
 
 # naming conflict in clone()
 _update = update
 
 def clean(repo, node, show_stats=True, quietempty=False):
     """forcibly switch the working directory to node, clobbering changes"""
     stats = updaterepo(repo, node, True)
     util.unlinkpath(repo.join('graftstate'), ignoremissing=True)
     if show_stats:
         _showstats(repo, stats, quietempty)
     return stats[3] > 0
 
 # naming conflict in updatetotally()
 _clean = clean
 
 def updatetotally(ui, repo, checkout, brev, clean=False, check=False):
     """Update the working directory with extra care for non-file components
 
     This takes care of non-file components below:
 
     :bookmark: might be advanced or (in)activated
 
     This takes arguments below:
 
     :checkout: to which revision the working directory is updated
     :brev: a name, which might be a bookmark to be activated after updating
     :clean: whether changes in the working directory can be discarded
     :check: whether changes in the working directory should be checked
 
     This returns whether conflict is detected at updating or not.
     """
     with repo.wlock():
         movemarkfrom = None
         warndest = False
         if checkout is None:
             updata = destutil.destupdate(repo, clean=clean, check=check)
             checkout, movemarkfrom, brev = updata
             warndest = True
 
         if clean:
             ret = _clean(repo, checkout)
         else:
             ret = _update(repo, checkout)
 
         if not ret and movemarkfrom:
             if movemarkfrom == repo['.'].node():
                 pass # no-op update
             elif bookmarks.update(repo, [movemarkfrom], repo['.'].node()):
                 ui.status(_("updating bookmark %s\n") % repo._activebookmark)
             else:
                 # this can happen with a non-linear update
                 ui.status(_("(leaving bookmark %s)\n") %
                           repo._activebookmark)
                 bookmarks.deactivate(repo)
         elif brev in repo._bookmarks:
             if brev != repo._activebookmark:
                 ui.status(_("(activating bookmark %s)\n") % brev)
             bookmarks.activate(repo, brev)
         elif brev:
             if repo._activebookmark:
                 ui.status(_("(leaving bookmark %s)\n") %
                           repo._activebookmark)
             bookmarks.deactivate(repo)
 
         if warndest:
             destutil.statusotherdests(ui, repo)
 
     return ret
 
 def merge(repo, node, force=None, remind=True, mergeforce=False):
     """Branch merge with node, resolving changes. Return true if any
     unresolved conflicts."""
     stats = mergemod.update(repo, node, True, force, mergeforce=mergeforce)
     _showstats(repo, stats)
     if stats[3]:
         repo.ui.status(_("use 'hg resolve' to retry unresolved file merges "
                          "or 'hg update -C .' to abandon\n"))
     elif remind:
         repo.ui.status(_("(branch merge, don't forget to commit)\n"))
     return stats[3] > 0
 
 def _incoming(displaychlist, subreporecurse, ui, repo, source,
         opts, buffered=False):
     """
     Helper for incoming / gincoming.
     displaychlist gets called with
         (remoterepo, incomingchangesetlist, displayer) parameters,
     and is supposed to contain only code that can't be unified.
     """
     source, branches = parseurl(ui.expandpath(source), opts.get('branch'))
     other = peer(repo, opts, source)
     ui.status(_('comparing with %s\n') % util.hidepassword(source))
     revs, checkout = addbranchrevs(repo, other, branches, opts.get('rev'))
 
     if revs:
         revs = [other.lookup(rev) for rev in revs]
     other, chlist, cleanupfn = bundlerepo.getremotechanges(ui, repo, other,
                                 revs, opts["bundle"], opts["force"])
     try:
         if not chlist:
             ui.status(_("no changes found\n"))
             return subreporecurse()
 
         displayer = cmdutil.show_changeset(ui, other, opts, buffered)
         displaychlist(other, chlist, displayer)
         displayer.close()
     finally:
         cleanupfn()
     subreporecurse()
     return 0 # exit code is zero since we found incoming changes
 
 def incoming(ui, repo, source, opts):
     def subreporecurse():
         ret = 1
         if opts.get('subrepos'):
             ctx = repo[None]
             for subpath in sorted(ctx.substate):
                 sub = ctx.sub(subpath)
                 ret = min(ret, sub.incoming(ui, source, opts))
         return ret
 
     def display(other, chlist, displayer):
         limit = cmdutil.loglimit(opts)
         if opts.get('newest_first'):
             chlist.reverse()
         count = 0
         for n in chlist:
             if limit is not None and count >= limit:
                 break
             parents = [p for p in other.changelog.parents(n) if p != nullid]
             if opts.get('no_merges') and len(parents) == 2:
                 continue
             count += 1
             displayer.show(other[n])
     return _incoming(display, subreporecurse, ui, repo, source, opts)
 
 def _outgoing(ui, repo, dest, opts):
     dest = ui.expandpath(dest or 'default-push', dest or 'default')
     dest, branches = parseurl(dest, opts.get('branch'))
     ui.status(_('comparing with %s\n') % util.hidepassword(dest))
     revs, checkout = addbranchrevs(repo, repo, branches, opts.get('rev'))
     if revs:
         revs = [repo.lookup(rev) for rev in scmutil.revrange(repo, revs)]
 
     other = peer(repo, opts, dest)
     outgoing = discovery.findcommonoutgoing(repo.unfiltered(), other, revs,
                                             force=opts.get('force'))
     o = outgoing.missing
     if not o:
         scmutil.nochangesfound(repo.ui, repo, outgoing.excluded)
     return o, other
 
 def outgoing(ui, repo, dest, opts):
     def recurse():
         ret = 1
         if opts.get('subrepos'):
             ctx = repo[None]
             for subpath in sorted(ctx.substate):
                 sub = ctx.sub(subpath)
                 ret = min(ret, sub.outgoing(ui, dest, opts))
         return ret
 
     limit = cmdutil.loglimit(opts)
     o, other = _outgoing(ui, repo, dest, opts)
     if not o:
         cmdutil.outgoinghooks(ui, repo, other, opts, o)
         return recurse()
 
     if opts.get('newest_first'):
         o.reverse()
     displayer = cmdutil.show_changeset(ui, repo, opts)
     count = 0
     for n in o:
         if limit is not None and count >= limit:
             break
         parents = [p for p in repo.changelog.parents(n) if p != nullid]
         if opts.get('no_merges') and len(parents) == 2:
             continue
         count += 1
         displayer.show(repo[n])
     displayer.close()
     cmdutil.outgoinghooks(ui, repo, other, opts, o)
     recurse()
     return 0 # exit code is zero since we found outgoing changes
 
 def verify(repo):
     """verify the consistency of a repository"""
     ret = verifymod.verify(repo)
 
     # Broken subrepo references in hidden csets don't seem worth worrying about,
     # since they can't be pushed/pulled, and --hidden can be used if they are a
     # concern.
 
     # pathto() is needed for -R case
     revs = repo.revs("filelog(%s)",
                      util.pathto(repo.root, repo.getcwd(), '.hgsubstate'))
 
     if revs:
         repo.ui.status(_('checking subrepo links\n'))
         for rev in revs:
             ctx = repo[rev]
             try:
                 for subpath in ctx.substate:
                     try:
                         ret = (ctx.sub(subpath, allowcreate=False).verify()
                                or ret)
                     except error.RepoError as e:
                         repo.ui.warn(_('%s: %s\n') % (rev, e))
             except Exception:
                 repo.ui.warn(_('.hgsubstate is corrupt in revision %s\n') %
                              node.short(ctx.node()))
 
     return ret
 
 def remoteui(src, opts):
     'build a remote ui from ui or repo and opts'
     if util.safehasattr(src, 'baseui'): # looks like a repository
         dst = src.baseui.copy() # drop repo-specific config
         src = src.ui # copy target options from repo
     else: # assume it's a global ui object
         dst = src.copy() # keep all global options
 
     # copy ssh-specific options
     for o in 'ssh', 'remotecmd':
         v = opts.get(o) or src.config('ui', o)
         if v:
             dst.setconfig("ui", o, v, 'copied')
 
     # copy bundle-specific options
     r = src.config('bundle', 'mainreporoot')
     if r:
         dst.setconfig('bundle', 'mainreporoot', r, 'copied')
 
     # copy selected local settings to the remote ui
     for sect in ('auth', 'hostfingerprints', 'http_proxy'):
         for key, val in src.configitems(sect):
             dst.setconfig(sect, key, val, 'copied')
     v = src.config('web', 'cacerts')
     if v == '!':
         dst.setconfig('web', 'cacerts', v, 'copied')
     elif v:
         dst.setconfig('web', 'cacerts', util.expandpath(v), 'copied')
 
     return dst
 
 # Files of interest
 # Used to check if the repository has changed looking at mtime and size of
 # these files.
 foi = [('spath', '00changelog.i'),
        ('spath', 'phaseroots'), # ! phase can change content at the same size
        ('spath', 'obsstore'),
        ('path', 'bookmarks'), # ! bookmark can change content at the same size
       ]
 
 class cachedlocalrepo(object):
     """Holds a localrepository that can be cached and reused."""
 
     def __init__(self, repo):
         """Create a new cached repo from an existing repo.
 
         We assume the passed in repo was recently created. If the
         repo has changed between when it was created and when it was
         turned into a cache, it may not refresh properly.
         """
         assert isinstance(repo, localrepo.localrepository)
         self._repo = repo
         self._state, self.mtime = self._repostate()
         self._filtername = repo.filtername
 
     def fetch(self):
         """Refresh (if necessary) and return a repository.
 
         If the cached instance is out of date, it will be recreated
         automatically and returned.
 
         Returns a tuple of the repo and a boolean indicating whether a new
         repo instance was created.
         """
         # We compare the mtimes and sizes of some well-known files to
         # determine if the repo changed. This is not precise, as mtimes
         # are susceptible to clock skew and imprecise filesystems and
         # file content can change while maintaining the same size.
 
         state, mtime = self._repostate()
         if state == self._state:
             return self._repo, False
 
         repo = repository(self._repo.baseui, self._repo.url())
         if self._filtername:
             self._repo = repo.filtered(self._filtername)
         else:
             self._repo = repo.unfiltered()
         self._state = state
         self.mtime = mtime
 
         return self._repo, True
 
     def _repostate(self):
         state = []
         maxmtime = -1
         for attr, fname in foi:
             prefix = getattr(self._repo, attr)
             p = os.path.join(prefix, fname)
             try:
                 st = os.stat(p)
             except OSError:
                 st = os.stat(prefix)
             state.append((st.st_mtime, st.st_size))
             maxmtime = max(maxmtime, st.st_mtime)
 
         return tuple(state), maxmtime
 
     def copy(self):
         """Obtain a copy of this class instance.
 
         A new localrepository instance is obtained. The new instance should be
         completely independent of the original.
         """
         repo = repository(self._repo.baseui, self._repo.origroot)
         if self._filtername:
             repo = repo.filtered(self._filtername)
         else:
             repo = repo.unfiltered()
         c = cachedlocalrepo(repo)
         c._state = self._state
         c.mtime = self.mtime
         return c

mercurial/manifest.py

@@ -1,1096 +1,1096 b''
 # manifest.py - manifest revision class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import array
 import heapq
 import os
 import struct
 
 from .i18n import _
 from . import (
     error,
     mdiff,
     parsers,
     revlog,
     util,
 )
 
 propertycache = util.propertycache
 
 def _parsev1(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1] != '\n':
         raise ValueError('Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError('Manifest lines not in sorted order.')
         prev = l
         f, n = l.split('\0')
         if len(n) > 40:
             yield f, revlog.bin(n[:40]), n[40:]
         else:
             yield f, revlog.bin(n), ''
 
 def _parsev2(data):
     metadataend = data.find('\n')
     # Just ignore metadata for now
     pos = metadataend + 1
     prevf = ''
     while pos < len(data):
         end = data.find('\n', pos + 1) # +1 to skip stem length byte
         if end == -1:
             raise ValueError('Manifest ended with incomplete file entry.')
         stemlen = ord(data[pos])
         items = data[pos + 1:end].split('\0')
         f = prevf[:stemlen] + items[0]
         if prevf > f:
             raise ValueError('Manifest entries not in sorted order.')
         fl = items[1]
         # Just ignore metadata (items[2:] for now)
         n = data[end + 1:end + 21]
         yield f, n, fl
         pos = end + 22
         prevf = f
 
 def _parse(data):
     """Generates (path, node, flags) tuples from a manifest text"""
     if data.startswith('\0'):
         return iter(_parsev2(data))
     else:
         return iter(_parsev1(data))
 
 def _text(it, usemanifestv2):
     """Given an iterator over (path, node, flags) tuples, returns a manifest
     text"""
     if usemanifestv2:
         return _textv2(it)
     else:
         return _textv1(it)
 
 def _textv1(it):
     files = []
     lines = []
     _hex = revlog.hex
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append("%s\0%s%s\n" % (f, _hex(n), fl))
 
     _checkforbidden(files)
     return ''.join(lines)
 
 def _textv2(it):
     files = []
     lines = ['\0\n']
     prevf = ''
     for f, n, fl in it:
         files.append(f)
         stem = os.path.commonprefix([prevf, f])
         stemlen = min(len(stem), 255)
         lines.append("%c%s\0%s\n%s\n" % (stemlen, f[stemlen:], fl, n))
         prevf = f
     _checkforbidden(files)
     return ''.join(lines)
 
 class _lazymanifest(dict):
     """This is the pure implementation of lazymanifest.
 
     It has not been optimized *at all* and is not lazy.
     """
 
     def __init__(self, data):
         dict.__init__(self)
         for f, n, fl in _parse(data):
             self[f] = n, fl
 
     def __setitem__(self, k, v):
         node, flag = v
         assert node is not None
         if len(node) > 21:
             node = node[:21] # match c implementation behavior
         dict.__setitem__(self, k, (node, flag))
 
     def __iter__(self):
         return iter(sorted(dict.keys(self)))
 
     def iterkeys(self):
         return iter(sorted(dict.keys(self)))
 
     def iterentries(self):
         return ((f, e[0], e[1]) for f, e in sorted(self.iteritems()))
 
     def copy(self):
         c = _lazymanifest('')
         c.update(self)
         return c
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         diff = {}
 
         for fn, e1 in self.iteritems():
             if fn not in m2:
                 diff[fn] = e1, (None, '')
             else:
                 e2 = m2[fn]
                 if e1 != e2:
                     diff[fn] = e1, e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2 in m2.iteritems():
             if fn not in self:
                 diff[fn] = (None, ''), e2
 
         return diff
 
     def filtercopy(self, filterfn):
         c = _lazymanifest('')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
     def text(self):
         """Get the full data of this manifest as a bytestring."""
         return _textv1(self.iterentries())
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 class manifestdict(object):
     def __init__(self, data=''):
         if data.startswith('\0'):
             #_lazymanifest can not parse v2
             self._lm = _lazymanifest('')
             for f, n, fl in _parsev2(data):
                 self._lm[f] = n, fl
         else:
             self._lm = _lazymanifest(data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key, '')
 
     def __contains__(self, key):
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2):
         '''Set of files in this manifest that are not in the other'''
         diff = self.diff(m2)
         files = set(filepath
                     for filepath, hashflags in diff.iteritems()
                     if hashflags[1][0] is None)
         return files
 
     @propertycache
     def _dirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         '''Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files.'''
         files = match.files()
         return (len(files) < 100 and (match.isexact() or
             (match.prefix() and all(fn in self for fn in files))))
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict()
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict()
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key, default=''):
         try:
             return self._lm[key][1]
         except KeyError:
             return default
 
     def copy(self):
         c = manifestdict()
         c._lm = self._lm.copy()
         return c
 
     def iteritems(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self):
         return self._lm.iterentries()
 
     def text(self, usemanifestv2=False):
         if usemanifestv2:
             return _textv2(self._lm.iterentries())
         else:
             # use (probably) native version for v1
             return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as an array.array and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < 1000:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = "%s\0%s%s\n" % (f, revlog.hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                                 _("failed to remove %s from manifest") % f)
                     l = ""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, "".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, "".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = array.array('c', self.text())
             deltatext = mdiff.textdiff(base, arraytext)
 
         return arraytext, deltatext
 
 def _msearch(m, s, lo=0, hi=None):
     '''return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer or a string
     s is a string'''
     def advance(i, c):
         while i < lenm and m[i] != c:
             i += 1
         return i
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1] != '\n':
             start -= 1
         end = advance(start, '\0')
         if m[start:end] < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, '\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, '\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, '\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if '\n' in f or '\r' in f:
             raise error.RevlogError(
                 _("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = array.array('c')
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += array.array('c', content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = "".join(struct.pack(">lll", start, end, len(content))
                    + content for start, end, content in x)
     return deltatext, newaddlist
 
 def _splittopdir(f):
     if '/' in f:
         dir, subpath = f.split('/', 1)
         return dir + '/', subpath
     else:
         return '', f
 
 _noop = lambda s: None
 
 class treemanifest(object):
     def __init__(self, dir='', text=''):
         self._dir = dir
         self._node = revlog.nullid
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
             def readsubtree(subdir, subm):
                 raise AssertionError('treemanifest constructor only accepts '
                                      'flat manifests')
             self.parse(text, readsubtree)
             self._dirty = True # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def __len__(self):
         self._load()
         size = len(self._files)
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def _isempty(self):
         self._load() # for consistency; already loaded by all callers
         return (not self._files and (not self._dirs or
                 all(m._isempty() for m in self._dirs.values())))
 
     def __repr__(self):
         return ('<treemanifest dir=%s, node=%s, loaded=%s, dirty=%s at 0x%x>' %
                 (self._dir, revlog.hex(self._node),
                  bool(self._loadfunc is _noop),
                  self._dirty, id(self)))
 
     def dir(self):
         '''The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory.'''
         return self._dir
 
     def node(self):
         '''This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         '''
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         for p, n in sorted(self._dirs.items() + self._files.items()):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, '')
             else:
                 for x in n.iterentries():
                     yield x
 
     def iteritems(self):
         self._load()
         for p, n in sorted(self._dirs.items() + self._files.items()):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in n.iteritems():
                     yield f, sn
 
     def iterkeys(self):
         self._load()
         for p in sorted(self._dirs.keys() + self._files.keys()):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p].iterkeys():
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return False
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return ''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._dirs:
                 return ''
             return self._flags.get(f, '')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, '')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].__setitem__(subpath, n)
         else:
             self._files[f] = n[:21] # to match manifestdict's behavior
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
             def _copyfunc(s):
                 self._load()
                 for d in self._dirs:
                     s._dirs[d] = self._dirs[d].copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2):
         '''Set of files in this manifest that are not in the other'''
         files = set()
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files.iterkeys():
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         return (dir + '/') in self._dirs
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         if not match.visitdir(self._dir[:-1] or '.'):
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         for p in sorted(self._dirs.keys() + self._files.keys()):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 for f in self._dirs[p]._walk(match):
                     yield f
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         return self._matches(match)
 
     def _matches(self, match):
         '''recursively generate a new manifest filtered by the match argument.
         '''
 
         visit = match.visitdir(self._dir[:-1] or '.')
         if visit == 'all':
             return self.copy()
         ret = treemanifest(self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             fullp = self._subpath(fn)
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         for dir, subm in self._dirs.iteritems():
             m = subm._matches(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         result = {}
         emptytree = treemanifest()
         def _diff(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 m2 = t2._dirs.get(d, emptytree)
                 _diff(m1, m2)
 
             for d, m2 in t2._dirs.iteritems():
                 if d not in t1._dirs:
                     _diff(emptytree, m2)
 
             for fn, n1 in t1._files.iteritems():
                 fl1 = t1._flags.get(fn, '')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, '')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in t2._files.iteritems():
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, '')
                     result[t2._subpath(fn)] = ((None, ''), (n2, fl2))
 
         _diff(self, m2)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         for f, n, fl in _parse(text):
             if fl == 't':
                 f = f + '/'
                 self._dirs[f] = readsubtree(self._subpath(f), n)
             elif '/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self, usemanifestv2=False):
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries(), usemanifestv2)
 
     def dirtext(self, usemanifestv2=False):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         dirs = [(d[:-1], self._dirs[d]._node, 't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files), usemanifestv2)
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree):
         self._load() # for consistency; should never have any effect here
         emptytree = treemanifest()
         for d, subm in self._dirs.iteritems():
             subp1 = m1._dirs.get(d, emptytree)._node
             subp2 = m2._dirs.get(d, emptytree)._node
             if subp1 == revlog.nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2)
 
 class manifest(revlog.revlog):
     def __init__(self, opener, dir='', dirlogcache=None):
         '''The 'dir' and 'dirlogcache' arguments are for internal use by
         manifest.manifest only. External users should create a root manifest
         log with manifest.manifest(opener) and call dirlog() on it.
         '''
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         usetreemanifest = False
         usemanifestv2 = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get('manifestcachesize', cachesize)
             usetreemanifest = opts.get('treemanifest', usetreemanifest)
             usemanifestv2 = opts.get('manifestv2', usemanifestv2)
         self._mancache = util.lrucachedict(cachesize)
         self._treeinmem = usetreemanifest
         self._treeondisk = usetreemanifest
         self._usemanifestv2 = usemanifestv2
         indexfile = "00manifest.i"
         if dir:
             assert self._treeondisk
             if not dir.endswith('/'):
                 dir = dir + '/'
             indexfile = "meta/" + dir + "00manifest.i"
         revlog.revlog.__init__(self, opener, indexfile)
         self._dir = dir
         # The dirlogcache is kept on the root manifest log
         if dir:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {'': self}
 
     def _newmanifest(self, data=''):
         if self._treeinmem:
             return treemanifest(self._dir, data)
         return manifestdict(data)
 
     def dirlog(self, dir):
         if dir:
             assert self._treeondisk
         if dir not in self._dirlogcache:
             self._dirlogcache[dir] = manifest(self.opener, dir,
                                               self._dirlogcache)
         return self._dirlogcache[dir]
 
     def _slowreaddelta(self, node):
         r0 = self.deltaparent(self.rev(node))
         m0 = self.read(self.node(r0))
         m1 = self.read(node)
         md = self._newmanifest()
         for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
             if n1:
                 md[f] = n1
                 if fl1:
                     md.setflag(f, fl1)
         return md
 
     def readdelta(self, node):
         if self._usemanifestv2 or self._treeondisk:
             return self._slowreaddelta(node)
         r = self.rev(node)
         d = mdiff.patchtext(self.revdiff(self.deltaparent(r), r))
         return self._newmanifest(d)
 
     def readshallowdelta(self, node):
         '''For flat manifests, this is the same as readdelta(). For
         treemanifests, this will read the delta for this revlog's directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifests, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.'''
         if not self._treeondisk:
             return self.readdelta(node)
         if self._usemanifestv2:
             raise error.Abort(
-                "readshallowdelta() not implemented for manifestv2")
+                _("readshallowdelta() not implemented for manifestv2"))
         r = self.rev(node)
         d = mdiff.patchtext(self.revdiff(self.deltaparent(r), r))
         return manifestdict(d)
 
     def readfast(self, node):
         '''use the faster of readdelta or read
 
         This will return a manifest which is either only the files
         added/modified relative to p1, or all files in the
         manifest. Which one is returned depends on the codepath used
         to retrieve the data.
         '''
         r = self.rev(node)
         deltaparent = self.deltaparent(r)
         if deltaparent != revlog.nullrev and deltaparent in self.parentrevs(r):
             return self.readdelta(node)
         return self.read(node)
 
     def readshallowfast(self, node):
         '''like readfast(), but calls readshallowdelta() instead of readdelta()
         '''
         r = self.rev(node)
         deltaparent = self.deltaparent(r)
         if deltaparent != revlog.nullrev and deltaparent in self.parentrevs(r):
             return self.readshallowdelta(node)
         return self.readshallow(node)
 
     def read(self, node):
         if node == revlog.nullid:
             return self._newmanifest() # don't upset local cache
         if node in self._mancache:
             return self._mancache[node][0]
         if self._treeondisk:
             def gettext():
                 return self.revision(node)
             def readsubtree(dir, subm):
                 return self.dirlog(dir).read(subm)
             m = self._newmanifest()
             m.read(gettext, readsubtree)
             m.setnode(node)
             arraytext = None
         else:
             text = self.revision(node)
             m = self._newmanifest(text)
             arraytext = array.array('c', text)
         self._mancache[node] = (m, arraytext)
         return m
 
     def readshallow(self, node):
         '''Reads the manifest in this directory. When using flat manifests,
         this manifest will generally have files in subdirectories in it. Does
         not cache the manifest as the callers generally do not read the same
         version twice.'''
         return manifestdict(self.revision(node))
 
     def find(self, node, f):
         '''look up entry for a single file efficiently.
         return (node, flags) pair if found, (None, None) if not.'''
         m = self.read(node)
         try:
             return m.find(f)
         except KeyError:
             return None, None
 
     def add(self, m, transaction, link, p1, p2, added, removed):
         if (p1 in self._mancache and not self._treeinmem
             and not self._usemanifestv2):
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge([(x, False) for x in added],
                                [(x, True) for x in removed])
 
             arraytext, deltatext = m.fastdelta(self._mancache[p1][1], work)
             cachedelta = self.rev(p1), deltatext
             text = util.buffer(arraytext)
             n = self.addrevision(text, transaction, link, p1, p2, cachedelta)
         else:
             # The first parent manifest isn't already loaded, so we'll
             # just encode a fulltext of the manifest and pass that
             # through to the revlog layer, and let it handle the delta
             # process.
             if self._treeondisk:
                 m1 = self.read(p1)
                 m2 = self.read(p2)
                 n = self._addtree(m, transaction, link, m1, m2)
                 arraytext = None
             else:
                 text = m.text(self._usemanifestv2)
                 n = self.addrevision(text, transaction, link, p1, p2)
                 arraytext = array.array('c', text)
 
         self._mancache[n] = (m, arraytext)
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if m.unmodifiedsince(m1) or m.unmodifiedsince(m2):
             return m.node()
         def writesubtree(subm, subp1, subp2):
             sublog = self.dirlog(subm.dir())
             sublog.add(subm, transaction, link, subp1, subp2, None, None)
         m.writesubtrees(m1, m2, writesubtree)
         text = m.dirtext(self._usemanifestv2)
         # Double-check whether contents are unchanged to one parent
         if text == m1.dirtext(self._usemanifestv2):
             n = m1.node()
         elif text == m2.dirtext(self._usemanifestv2):
             n = m2.node()
         else:
             n = self.addrevision(text, transaction, link, m1.node(), m2.node())
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
     def clearcaches(self):
         super(manifest, self).clearcaches()
         self._mancache.clear()
         self._dirlogcache = {'': self}

mercurial/match.py

@@ -1,712 +1,712 b''
 # match.py - filename matching
 #
 #  Copyright 2008, 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 __future__ import absolute_import
 
 import copy
 import os
 import re
 
 from .i18n import _
 from . import (
     error,
     pathutil,
     util,
 )
 
 propertycache = util.propertycache
 
 def _rematcher(regex):
     '''compile the regexp with the best available regexp engine and return a
     matcher function'''
     m = util.re.compile(regex)
     try:
         # slightly faster, provided by facebook's re2 bindings
         return m.test_match
     except AttributeError:
         return m.match
 
 def _expandsets(kindpats, ctx, listsubrepos):
     '''Returns the kindpats list with the 'set' patterns expanded.'''
     fset = set()
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'set':
             if not ctx:
-                raise error.Abort("fileset expression with no context")
+                raise error.Abort(_("fileset expression with no context"))
             s = ctx.getfileset(pat)
             fset.update(s)
 
             if listsubrepos:
                 for subpath in ctx.substate:
                     s = ctx.sub(subpath).getfileset(pat)
                     fset.update(subpath + '/' + f for f in s)
 
             continue
         other.append((kind, pat, source))
     return fset, other
 
 def _expandsubinclude(kindpats, root):
     '''Returns the list of subinclude matchers and the kindpats without the
     subincludes in it.'''
     relmatchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'subinclude':
             sourceroot = pathutil.dirname(util.normpath(source))
             pat = util.pconvert(pat)
             path = pathutil.join(sourceroot, pat)
 
             newroot = pathutil.dirname(path)
             relmatcher = match(newroot, '', [], ['include:%s' % path])
 
             prefix = pathutil.canonpath(root, root, newroot)
             if prefix:
                 prefix += '/'
             relmatchers.append((prefix, relmatcher))
         else:
             other.append((kind, pat, source))
 
     return relmatchers, other
 
 def _kindpatsalwaysmatch(kindpats):
     """"Checks whether the kindspats match everything, as e.g.
     'relpath:.' does.
     """
     for kind, pat, source in kindpats:
         if pat != '' or kind not in ['relpath', 'glob']:
             return False
     return True
 
 class match(object):
     def __init__(self, root, cwd, patterns, include=[], exclude=[],
                  default='glob', exact=False, auditor=None, ctx=None,
                  listsubrepos=False, warn=None, badfn=None):
         """build an object to match a set of file patterns
 
         arguments:
         root - the canonical root of the tree you're matching against
         cwd - the current working directory, if relevant
         patterns - patterns to find
         include - patterns to include (unless they are excluded)
         exclude - patterns to exclude (even if they are included)
         default - if a pattern in patterns has no explicit type, assume this one
         exact - patterns are actually filenames (include/exclude still apply)
         warn - optional function used for printing warnings
         badfn - optional bad() callback for this matcher instead of the default
 
         a pattern is one of:
         'glob:<glob>' - a glob relative to cwd
         're:<regexp>' - a regular expression
         'path:<path>' - a path relative to repository root
         'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
         'relpath:<path>' - a path relative to cwd
         'relre:<regexp>' - a regexp that needn't match the start of a name
         'set:<fileset>' - a fileset expression
         'include:<path>' - a file of patterns to read and include
         'subinclude:<path>' - a file of patterns to match against files under
                               the same directory
         '<something>' - a pattern of the specified default type
         """
 
         self._root = root
         self._cwd = cwd
         self._files = [] # exact files and roots of patterns
         self._anypats = bool(include or exclude)
         self._always = False
         self._pathrestricted = bool(include or exclude or patterns)
         self._warn = warn
         self._includeroots = set()
         self._includedirs = set(['.'])
         self._excluderoots = set()
 
         if badfn is not None:
             self.bad = badfn
 
         matchfns = []
         if include:
             kindpats = self._normalize(include, 'glob', root, cwd, auditor)
             self.includepat, im = _buildmatch(ctx, kindpats, '(?:/|$)',
                                               listsubrepos, root)
             self._includeroots.update(_roots(kindpats))
             self._includedirs.update(util.dirs(self._includeroots))
             matchfns.append(im)
         if exclude:
             kindpats = self._normalize(exclude, 'glob', root, cwd, auditor)
             self.excludepat, em = _buildmatch(ctx, kindpats, '(?:/|$)',
                                               listsubrepos, root)
             if not _anypats(kindpats):
                 self._excluderoots.update(_roots(kindpats))
             matchfns.append(lambda f: not em(f))
         if exact:
             if isinstance(patterns, list):
                 self._files = patterns
             else:
                 self._files = list(patterns)
             matchfns.append(self.exact)
         elif patterns:
             kindpats = self._normalize(patterns, default, root, cwd, auditor)
             if not _kindpatsalwaysmatch(kindpats):
                 self._files = _roots(kindpats)
                 self._anypats = self._anypats or _anypats(kindpats)
                 self.patternspat, pm = _buildmatch(ctx, kindpats, '$',
                                                    listsubrepos, root)
                 matchfns.append(pm)
 
         if not matchfns:
             m = util.always
             self._always = True
         elif len(matchfns) == 1:
             m = matchfns[0]
         else:
             def m(f):
                 for matchfn in matchfns:
                     if not matchfn(f):
                         return False
                 return True
 
         self.matchfn = m
         self._fileroots = set(self._files)
 
     def __call__(self, fn):
         return self.matchfn(fn)
     def __iter__(self):
         for f in self._files:
             yield f
 
     # Callbacks related to how the matcher is used by dirstate.walk.
     # Subscribers to these events must monkeypatch the matcher object.
     def bad(self, f, msg):
         '''Callback from dirstate.walk for each explicit file that can't be
         found/accessed, with an error message.'''
         pass
 
     # If an explicitdir is set, it will be called when an explicitly listed
     # directory is visited.
     explicitdir = None
 
     # If an traversedir is set, it will be called when a directory discovered
     # by recursive traversal is visited.
     traversedir = None
 
     def abs(self, f):
         '''Convert a repo path back to path that is relative to the root of the
         matcher.'''
         return f
 
     def rel(self, f):
         '''Convert repo path back to path that is relative to cwd of matcher.'''
         return util.pathto(self._root, self._cwd, f)
 
     def uipath(self, f):
         '''Convert repo path to a display path.  If patterns or -I/-X were used
         to create this matcher, the display path will be relative to cwd.
         Otherwise it is relative to the root of the repo.'''
         return (self._pathrestricted and self.rel(f)) or self.abs(f)
 
     def files(self):
         '''Explicitly listed files or patterns or roots:
         if no patterns or .always(): empty list,
         if exact: list exact files,
         if not .anypats(): list all files and dirs,
         else: optimal roots'''
         return self._files
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileroots)) | set(['.'])
 
     def visitdir(self, dir):
         '''Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories. This is
         based on the match's primary, included, and excluded patterns.
 
         Returns the string 'all' if the given directory and all subdirectories
         should be visited. Otherwise returns True or False indicating whether
         the given directory should be visited.
 
         This function's behavior is undefined if it has returned False for
         one of the dir's parent directories.
         '''
         if self.prefix() and dir in self._fileroots:
             return 'all'
         if dir in self._excluderoots:
             return False
         if (self._includeroots and
             '.' not in self._includeroots and
             dir not in self._includeroots and
             dir not in self._includedirs and
             not any(parent in self._includeroots
                     for parent in util.finddirs(dir))):
             return False
         return (not self._fileroots or
                 '.' in self._fileroots or
                 dir in self._fileroots or
                 dir in self._dirs or
                 any(parentdir in self._fileroots
                     for parentdir in util.finddirs(dir)))
 
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fileroots
 
     def anypats(self):
         '''Matcher uses patterns or include/exclude.'''
         return self._anypats
 
     def always(self):
         '''Matcher will match everything and .files() will be empty
         - optimization might be possible and necessary.'''
         return self._always
 
     def ispartial(self):
         '''True if the matcher won't always match.
 
         Although it's just the inverse of _always in this implementation,
         an extension such as narrowhg might make it return something
         slightly different.'''
         return not self._always
 
     def isexact(self):
         return self.matchfn == self.exact
 
     def prefix(self):
         return not self.always() and not self.isexact() and not self.anypats()
 
     def _normalize(self, patterns, default, root, cwd, auditor):
         '''Convert 'kind:pat' from the patterns list to tuples with kind and
         normalized and rooted patterns and with listfiles expanded.'''
         kindpats = []
         for kind, pat in [_patsplit(p, default) for p in patterns]:
             if kind in ('glob', 'relpath'):
                 pat = pathutil.canonpath(root, cwd, pat, auditor)
             elif kind in ('relglob', 'path'):
                 pat = util.normpath(pat)
             elif kind in ('listfile', 'listfile0'):
                 try:
                     files = util.readfile(pat)
                     if kind == 'listfile0':
                         files = files.split('\0')
                     else:
                         files = files.splitlines()
                     files = [f for f in files if f]
                 except EnvironmentError:
                     raise error.Abort(_("unable to read file list (%s)") % pat)
                 for k, p, source in self._normalize(files, default, root, cwd,
                                                     auditor):
                     kindpats.append((k, p, pat))
                 continue
             elif kind == 'include':
                 try:
                     fullpath = os.path.join(root, util.localpath(pat))
                     includepats = readpatternfile(fullpath, self._warn)
                     for k, p, source in self._normalize(includepats, default,
                                                         root, cwd, auditor):
                         kindpats.append((k, p, source or pat))
                 except error.Abort as inst:
                     raise error.Abort('%s: %s' % (pat, inst[0]))
                 except IOError as inst:
                     if self._warn:
                         self._warn(_("skipping unreadable pattern file "
                                      "'%s': %s\n") % (pat, inst.strerror))
                 continue
             # else: re or relre - which cannot be normalized
             kindpats.append((kind, pat, ''))
         return kindpats
 
 def exact(root, cwd, files, badfn=None):
     return match(root, cwd, files, exact=True, badfn=badfn)
 
 def always(root, cwd):
     return match(root, cwd, [])
 
 def badmatch(match, badfn):
     """Make a copy of the given matcher, replacing its bad method with the given
     one.
     """
     m = copy.copy(match)
     m.bad = badfn
     return m
 
 class subdirmatcher(match):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> m1 = match('root', '', ['a.txt', 'sub/b.txt'])
     >>> m2 = subdirmatcher('sub', m1)
     >>> bool(m2('a.txt'))
     False
     >>> bool(m2('b.txt'))
     True
     >>> bool(m2.matchfn('a.txt'))
     False
     >>> bool(m2.matchfn('b.txt'))
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact('b.txt')
     True
     >>> util.pconvert(m2.rel('b.txt'))
     'sub/b.txt'
     >>> def bad(f, msg):
     ...     print "%s: %s" % (f, msg)
     >>> m1.bad = bad
     >>> m2.bad('x.txt', 'No such file')
     sub/x.txt: No such file
     >>> m2.abs('c.txt')
     'sub/c.txt'
     """
 
     def __init__(self, path, matcher):
         self._root = matcher._root
         self._cwd = matcher._cwd
         self._path = path
         self._matcher = matcher
         self._always = matcher._always
         self._pathrestricted = matcher._pathrestricted
 
         self._files = [f[len(path) + 1:] for f in matcher._files
                        if f.startswith(path + "/")]
 
         # If the parent repo had a path to this subrepo and no patterns are
         # specified, this submatcher always matches.
         if not self._always and not matcher._anypats:
             self._always = any(f == path for f in matcher._files)
 
         self._anypats = matcher._anypats
         # Some information is lost in the superclass's constructor, so we
         # can not accurately create the matching function for the subdirectory
         # from the inputs. Instead, we override matchfn() and visitdir() to
         # call the original matcher with the subdirectory path prepended.
         self.matchfn = lambda fn: matcher.matchfn(self._path + "/" + fn)
         def visitdir(dir):
             if dir == '.':
                 return matcher.visitdir(self._path)
             return matcher.visitdir(self._path + "/" + dir)
         self.visitdir = visitdir
         self._fileroots = set(self._files)
 
     def abs(self, f):
         return self._matcher.abs(self._path + "/" + f)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + "/" + f, msg)
 
     def rel(self, f):
         return self._matcher.rel(self._path + "/" + f)
 
 class icasefsmatcher(match):
     """A matcher for wdir on case insensitive filesystems, which normalizes the
     given patterns to the case in the filesystem.
     """
 
     def __init__(self, root, cwd, patterns, include, exclude, default, auditor,
                  ctx, listsubrepos=False, badfn=None):
         init = super(icasefsmatcher, self).__init__
         self._dirstate = ctx.repo().dirstate
         self._dsnormalize = self._dirstate.normalize
 
         init(root, cwd, patterns, include, exclude, default, auditor=auditor,
              ctx=ctx, listsubrepos=listsubrepos, badfn=badfn)
 
         # m.exact(file) must be based off of the actual user input, otherwise
         # inexact case matches are treated as exact, and not noted without -v.
         if self._files:
             self._fileroots = set(_roots(self._kp))
 
     def _normalize(self, patterns, default, root, cwd, auditor):
         self._kp = super(icasefsmatcher, self)._normalize(patterns, default,
                                                           root, cwd, auditor)
         kindpats = []
         for kind, pats, source in self._kp:
             if kind not in ('re', 'relre'):  # regex can't be normalized
                 p = pats
                 pats = self._dsnormalize(pats)
 
                 # Preserve the original to handle a case only rename.
                 if p != pats and p in self._dirstate:
                     kindpats.append((kind, p, source))
 
             kindpats.append((kind, pats, source))
         return kindpats
 
 def patkind(pattern, default=None):
     '''If pattern is 'kind:pat' with a known kind, return kind.'''
     return _patsplit(pattern, default)[0]
 
 def _patsplit(pattern, default):
     """Split a string into the optional pattern kind prefix and the actual
     pattern."""
     if ':' in pattern:
         kind, pat = pattern.split(':', 1)
         if kind in ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                     'listfile', 'listfile0', 'set', 'include', 'subinclude'):
             return kind, pat
     return default, pattern
 
 def _globre(pat):
     r'''Convert an extended glob string to a regexp string.
 
     >>> print _globre(r'?')
     .
     >>> print _globre(r'*')
     [^/]*
     >>> print _globre(r'**')
     .*
     >>> print _globre(r'**/a')
     (?:.*/)?a
     >>> print _globre(r'a/**/b')
     a\/(?:.*/)?b
     >>> print _globre(r'[a*?!^][^b][!c]')
     [a*?!^][\^b][^c]
     >>> print _globre(r'{a,b}')
     (?:a|b)
     >>> print _globre(r'.\*\?')
     \.\*\?
     '''
     i, n = 0, len(pat)
     res = ''
     group = 0
     escape = util.re.escape
     def peek():
         return i < n and pat[i]
     while i < n:
         c = pat[i]
         i += 1
         if c not in '*?[{},\\':
             res += escape(c)
         elif c == '*':
             if peek() == '*':
                 i += 1
                 if peek() == '/':
                     i += 1
                     res += '(?:.*/)?'
                 else:
                     res += '.*'
             else:
                 res += '[^/]*'
         elif c == '?':
             res += '.'
         elif c == '[':
             j = i
             if j < n and pat[j] in '!]':
                 j += 1
             while j < n and pat[j] != ']':
                 j += 1
             if j >= n:
                 res += '\\['
             else:
                 stuff = pat[i:j].replace('\\','\\\\')
                 i = j + 1
                 if stuff[0] == '!':
                     stuff = '^' + stuff[1:]
                 elif stuff[0] == '^':
                     stuff = '\\' + stuff
                 res = '%s[%s]' % (res, stuff)
         elif c == '{':
             group += 1
             res += '(?:'
         elif c == '}' and group:
             res += ')'
             group -= 1
         elif c == ',' and group:
             res += '|'
         elif c == '\\':
             p = peek()
             if p:
                 i += 1
                 res += escape(p)
             else:
                 res += escape(c)
         else:
             res += escape(c)
     return res
 
 def _regex(kind, pat, globsuffix):
     '''Convert a (normalized) pattern of any kind into a regular expression.
     globsuffix is appended to the regexp of globs.'''
     if not pat:
         return ''
     if kind == 're':
         return pat
     if kind == 'path':
         if pat == '.':
             return ''
         return '^' + util.re.escape(pat) + '(?:/|$)'
     if kind == 'relglob':
         return '(?:|.*/)' + _globre(pat) + globsuffix
     if kind == 'relpath':
         return util.re.escape(pat) + '(?:/|$)'
     if kind == 'relre':
         if pat.startswith('^'):
             return pat
         return '.*' + pat
     return _globre(pat) + globsuffix
 
 def _buildmatch(ctx, kindpats, globsuffix, listsubrepos, root):
     '''Return regexp string and a matcher function for kindpats.
     globsuffix is appended to the regexp of globs.'''
     matchfuncs = []
 
     subincludes, kindpats = _expandsubinclude(kindpats, root)
     if subincludes:
         def matchsubinclude(f):
             for prefix, mf in subincludes:
                 if f.startswith(prefix) and mf(f[len(prefix):]):
                     return True
             return False
         matchfuncs.append(matchsubinclude)
 
     fset, kindpats = _expandsets(kindpats, ctx, listsubrepos)
     if fset:
         matchfuncs.append(fset.__contains__)
 
     regex = ''
     if kindpats:
         regex, mf = _buildregexmatch(kindpats, globsuffix)
         matchfuncs.append(mf)
 
     if len(matchfuncs) == 1:
         return regex, matchfuncs[0]
     else:
         return regex, lambda f: any(mf(f) for mf in matchfuncs)
 
 def _buildregexmatch(kindpats, globsuffix):
     """Build a match function from a list of kinds and kindpats,
     return regexp string and a matcher function."""
     try:
         regex = '(?:%s)' % '|'.join([_regex(k, p, globsuffix)
                                      for (k, p, s) in kindpats])
         if len(regex) > 20000:
             raise OverflowError
         return regex, _rematcher(regex)
     except OverflowError:
         # We're using a Python with a tiny regex engine and we
         # made it explode, so we'll divide the pattern list in two
         # until it works
         l = len(kindpats)
         if l < 2:
             raise
         regexa, a = _buildregexmatch(kindpats[:l//2], globsuffix)
         regexb, b = _buildregexmatch(kindpats[l//2:], globsuffix)
         return regex, lambda s: a(s) or b(s)
     except re.error:
         for k, p, s in kindpats:
             try:
                 _rematcher('(?:%s)' % _regex(k, p, globsuffix))
             except re.error:
                 if s:
                     raise error.Abort(_("%s: invalid pattern (%s): %s") %
                                      (s, k, p))
                 else:
                     raise error.Abort(_("invalid pattern (%s): %s") % (k, p))
         raise error.Abort(_("invalid pattern"))
 
 def _roots(kindpats):
     '''return roots and exact explicitly listed files from patterns
 
     >>> _roots([('glob', 'g/*', ''), ('glob', 'g', ''), ('glob', 'g*', '')])
     ['g', 'g', '.']
     >>> _roots([('relpath', 'r', ''), ('path', 'p/p', ''), ('path', '', '')])
     ['r', 'p/p', '.']
     >>> _roots([('relglob', 'rg*', ''), ('re', 're/', ''), ('relre', 'rr', '')])
     ['.', '.', '.']
     '''
     r = []
     for kind, pat, source in kindpats:
         if kind == 'glob': # find the non-glob prefix
             root = []
             for p in pat.split('/'):
                 if '[' in p or '{' in p or '*' in p or '?' in p:
                     break
                 root.append(p)
             r.append('/'.join(root) or '.')
         elif kind in ('relpath', 'path'):
             r.append(pat or '.')
         else: # relglob, re, relre
             r.append('.')
     return r
 
 def _anypats(kindpats):
     for kind, pat, source in kindpats:
         if kind in ('glob', 're', 'relglob', 'relre', 'set'):
             return True
 
 _commentre = None
 
 def readpatternfile(filepath, warn, sourceinfo=False):
     '''parse a pattern file, returning a list of
     patterns. These patterns should be given to compile()
     to be validated and converted into a match function.
 
     trailing white space is dropped.
     the escape character is backslash.
     comments start with #.
     empty lines are skipped.
 
     lines can be of the following formats:
 
     syntax: regexp # defaults following lines to non-rooted regexps
     syntax: glob   # defaults following lines to non-rooted globs
     re:pattern     # non-rooted regular expression
     glob:pattern   # non-rooted glob
     pattern        # pattern of the current default type
 
     if sourceinfo is set, returns a list of tuples:
     (pattern, lineno, originalline). This is useful to debug ignore patterns.
     '''
 
     syntaxes = {'re': 'relre:', 'regexp': 'relre:', 'glob': 'relglob:',
                 'include': 'include', 'subinclude': 'subinclude'}
     syntax = 'relre:'
     patterns = []
 
     fp = open(filepath)
     for lineno, line in enumerate(fp, start=1):
         if "#" in line:
             global _commentre
             if not _commentre:
                 _commentre = util.re.compile(r'((?:^|[^\\])(?:\\\\)*)#.*')
             # remove comments prefixed by an even number of escapes
             m = _commentre.search(line)
             if m:
                 line = line[:m.end(1)]
             # fixup properly escaped comments that survived the above
             line = line.replace("\\#", "#")
         line = line.rstrip()
         if not line:
             continue
 
         if line.startswith('syntax:'):
             s = line[7:].strip()
             try:
                 syntax = syntaxes[s]
             except KeyError:
                 if warn:
                     warn(_("%s: ignoring invalid syntax '%s'\n") %
                          (filepath, s))
             continue
 
         linesyntax = syntax
         for s, rels in syntaxes.iteritems():
             if line.startswith(rels):
                 linesyntax = rels
                 line = line[len(rels):]
                 break
             elif line.startswith(s+':'):
                 linesyntax = rels
                 line = line[len(s) + 1:]
                 break
         if sourceinfo:
             patterns.append((linesyntax + line, lineno, line))
         else:
             patterns.append(linesyntax + line)
     fp.close()
     return patterns

mercurial/obsolete.py

@@ -1,1282 +1,1283 b''
 # obsolete.py - obsolete markers handling
 #
 # Copyright 2012 Pierre-Yves David <[e-mail]>
 #                Logilab SA        <[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.
 
 """Obsolete marker handling
 
 An obsolete marker maps an old changeset to a list of new
 changesets. If the list of new changesets is empty, the old changeset
 is said to be "killed". Otherwise, the old changeset is being
 "replaced" by the new changesets.
 
 Obsolete markers can be used to record and distribute changeset graph
 transformations performed by history rewrite operations, and help
 building new tools to reconcile conflicting rewrite actions. To
 facilitate conflict resolution, markers include various annotations
 besides old and news changeset identifiers, such as creation date or
 author name.
 
 The old obsoleted changeset is called a "precursor" and possible
 replacements are called "successors". Markers that used changeset X as
 a precursor are called "successor markers of X" because they hold
 information about the successors of X. Markers that use changeset Y as
 a successors are call "precursor markers of Y" because they hold
 information about the precursors of Y.
 
 Examples:
 
 - When changeset A is replaced by changeset A', one marker is stored:
 
     (A, (A',))
 
 - When changesets A and B are folded into a new changeset C, two markers are
   stored:
 
     (A, (C,)) and (B, (C,))
 
 - When changeset A is simply "pruned" from the graph, a marker is created:
 
     (A, ())
 
 - When changeset A is split into B and C, a single marker are used:
 
     (A, (C, C))
 
   We use a single marker to distinguish the "split" case from the "divergence"
   case. If two independent operations rewrite the same changeset A in to A' and
   A'', we have an error case: divergent rewriting. We can detect it because
   two markers will be created independently:
 
   (A, (B,)) and (A, (C,))
 
 Format
 ------
 
 Markers are stored in an append-only file stored in
 '.hg/store/obsstore'.
 
 The file starts with a version header:
 
 - 1 unsigned byte: version number, starting at zero.
 
 The header is followed by the markers. Marker format depend of the version. See
 comment associated with each format for details.
 
 """
 from __future__ import absolute_import
 
 import errno
 import struct
 
 from .i18n import _
 from . import (
     base85,
     error,
     node,
     parsers,
     phases,
     util,
 )
 
 _pack = struct.pack
 _unpack = struct.unpack
 _calcsize = struct.calcsize
 propertycache = util.propertycache
 
 # the obsolete feature is not mature enough to be enabled by default.
 # you have to rely on third party extension extension to enable this.
 _enabled = False
 
 # Options for obsolescence
 createmarkersopt = 'createmarkers'
 allowunstableopt = 'allowunstable'
 exchangeopt = 'exchange'
 
 ### obsolescence marker flag
 
 ## bumpedfix flag
 #
 # When a changeset A' succeed to a changeset A which became public, we call A'
 # "bumped" because it's a successors of a public changesets
 #
 # o    A' (bumped)
 # |`:
 # | o  A
 # |/
 # o    Z
 #
 # The way to solve this situation is to create a new changeset Ad as children
 # of A. This changeset have the same content than A'. So the diff from A to A'
 # is the same than the diff from A to Ad. Ad is marked as a successors of A'
 #
 # o   Ad
 # |`:
 # | x A'
 # |'|
 # o | A
 # |/
 # o Z
 #
 # But by transitivity Ad is also a successors of A. To avoid having Ad marked
 # as bumped too, we add the `bumpedfix` flag to the marker. <A', (Ad,)>.
 # This flag mean that the successors express the changes between the public and
 # bumped version and fix the situation, breaking the transitivity of
 # "bumped" here.
 bumpedfix = 1
 usingsha256 = 2
 
 ## Parsing and writing of version "0"
 #
 # The header is followed by the markers. Each marker is made of:
 #
 # - 1 uint8 : number of new changesets "N", can be zero.
 #
 # - 1 uint32: metadata size "M" in bytes.
 #
 # - 1 byte: a bit field. It is reserved for flags used in common
 #   obsolete marker operations, to avoid repeated decoding of metadata
 #   entries.
 #
 # - 20 bytes: obsoleted changeset identifier.
 #
 # - N*20 bytes: new changesets identifiers.
 #
 # - M bytes: metadata as a sequence of nul-terminated strings. Each
 #   string contains a key and a value, separated by a colon ':', without
 #   additional encoding. Keys cannot contain '\0' or ':' and values
 #   cannot contain '\0'.
 _fm0version = 0
 _fm0fixed   = '>BIB20s'
 _fm0node = '20s'
 _fm0fsize = _calcsize(_fm0fixed)
 _fm0fnodesize = _calcsize(_fm0node)
 
 def _fm0readmarkers(data, off):
     # Loop on markers
     l = len(data)
     while off + _fm0fsize <= l:
         # read fixed part
         cur = data[off:off + _fm0fsize]
         off += _fm0fsize
         numsuc, mdsize, flags, pre = _unpack(_fm0fixed, cur)
         # read replacement
         sucs = ()
         if numsuc:
             s = (_fm0fnodesize * numsuc)
             cur = data[off:off + s]
             sucs = _unpack(_fm0node * numsuc, cur)
             off += s
         # read metadata
         # (metadata will be decoded on demand)
         metadata = data[off:off + mdsize]
         if len(metadata) != mdsize:
             raise error.Abort(_('parsing obsolete marker: metadata is too '
                                'short, %d bytes expected, got %d')
                              % (mdsize, len(metadata)))
         off += mdsize
         metadata = _fm0decodemeta(metadata)
         try:
             when, offset = metadata.pop('date', '0 0').split(' ')
             date = float(when), int(offset)
         except ValueError:
             date = (0., 0)
         parents = None
         if 'p2' in metadata:
             parents = (metadata.pop('p1', None), metadata.pop('p2', None))
         elif 'p1' in metadata:
             parents = (metadata.pop('p1', None),)
         elif 'p0' in metadata:
             parents = ()
         if parents is not None:
             try:
                 parents = tuple(node.bin(p) for p in parents)
                 # if parent content is not a nodeid, drop the data
                 for p in parents:
                     if len(p) != 20:
                         parents = None
                         break
             except TypeError:
                 # if content cannot be translated to nodeid drop the data.
                 parents = None
 
         metadata = tuple(sorted(metadata.iteritems()))
 
         yield (pre, sucs, flags, metadata, date, parents)
 
 def _fm0encodeonemarker(marker):
     pre, sucs, flags, metadata, date, parents = marker
     if flags & usingsha256:
         raise error.Abort(_('cannot handle sha256 with old obsstore format'))
     metadata = dict(metadata)
     time, tz = date
     metadata['date'] = '%r %i' % (time, tz)
     if parents is not None:
         if not parents:
             # mark that we explicitly recorded no parents
             metadata['p0'] = ''
         for i, p in enumerate(parents):
             metadata['p%i' % (i + 1)] = node.hex(p)
     metadata = _fm0encodemeta(metadata)
     numsuc = len(sucs)
     format = _fm0fixed + (_fm0node * numsuc)
     data = [numsuc, len(metadata), flags, pre]
     data.extend(sucs)
     return _pack(format, *data) + metadata
 
 def _fm0encodemeta(meta):
     """Return encoded metadata string to string mapping.
 
     Assume no ':' in key and no '\0' in both key and value."""
     for key, value in meta.iteritems():
         if ':' in key or '\0' in key:
             raise ValueError("':' and '\0' are forbidden in metadata key'")
         if '\0' in value:
             raise ValueError("':' is forbidden in metadata value'")
     return '\0'.join(['%s:%s' % (k, meta[k]) for k in sorted(meta)])
 
 def _fm0decodemeta(data):
     """Return string to string dictionary from encoded version."""
     d = {}
     for l in data.split('\0'):
         if l:
             key, value = l.split(':')
             d[key] = value
     return d
 
 ## Parsing and writing of version "1"
 #
 # The header is followed by the markers. Each marker is made of:
 #
 # - uint32: total size of the marker (including this field)
 #
 # - float64: date in seconds since epoch
 #
 # - int16: timezone offset in minutes
 #
 # - uint16: a bit field. It is reserved for flags used in common
 #   obsolete marker operations, to avoid repeated decoding of metadata
 #   entries.
 #
 # - uint8: number of successors "N", can be zero.
 #
 # - uint8: number of parents "P", can be zero.
 #
 #     0: parents data stored but no parent,
 #     1: one parent stored,
 #     2: two parents stored,
 #     3: no parent data stored
 #
 # - uint8: number of metadata entries M
 #
 # - 20 or 32 bytes: precursor changeset identifier.
 #
 # - N*(20 or 32) bytes: successors changesets identifiers.
 #
 # - P*(20 or 32) bytes: parents of the precursors changesets.
 #
 # - M*(uint8, uint8): size of all metadata entries (key and value)
 #
 # - remaining bytes: the metadata, each (key, value) pair after the other.
 _fm1version = 1
 _fm1fixed = '>IdhHBBB20s'
 _fm1nodesha1 = '20s'
 _fm1nodesha256 = '32s'
 _fm1nodesha1size = _calcsize(_fm1nodesha1)
 _fm1nodesha256size = _calcsize(_fm1nodesha256)
 _fm1fsize = _calcsize(_fm1fixed)
 _fm1parentnone = 3
 _fm1parentshift = 14
 _fm1parentmask = (_fm1parentnone << _fm1parentshift)
 _fm1metapair = 'BB'
 _fm1metapairsize = _calcsize('BB')
 
 def _fm1purereadmarkers(data, off):
     # make some global constants local for performance
     noneflag = _fm1parentnone
     sha2flag = usingsha256
     sha1size = _fm1nodesha1size
     sha2size = _fm1nodesha256size
     sha1fmt = _fm1nodesha1
     sha2fmt = _fm1nodesha256
     metasize = _fm1metapairsize
     metafmt = _fm1metapair
     fsize = _fm1fsize
     unpack = _unpack
 
     # Loop on markers
     stop = len(data) - _fm1fsize
     ufixed = struct.Struct(_fm1fixed).unpack
 
     while off <= stop:
         # read fixed part
         o1 = off + fsize
         t, secs, tz, flags, numsuc, numpar, nummeta, prec = ufixed(data[off:o1])
 
         if flags & sha2flag:
             # FIXME: prec was read as a SHA1, needs to be amended
 
             # read 0 or more successors
             if numsuc == 1:
                 o2 = o1 + sha2size
                 sucs = (data[o1:o2],)
             else:
                 o2 = o1 + sha2size * numsuc
                 sucs = unpack(sha2fmt * numsuc, data[o1:o2])
 
             # read parents
             if numpar == noneflag:
                 o3 = o2
                 parents = None
             elif numpar == 1:
                 o3 = o2 + sha2size
                 parents = (data[o2:o3],)
             else:
                 o3 = o2 + sha2size * numpar
                 parents = unpack(sha2fmt * numpar, data[o2:o3])
         else:
             # read 0 or more successors
             if numsuc == 1:
                 o2 = o1 + sha1size
                 sucs = (data[o1:o2],)
             else:
                 o2 = o1 + sha1size * numsuc
                 sucs = unpack(sha1fmt * numsuc, data[o1:o2])
 
             # read parents
             if numpar == noneflag:
                 o3 = o2
                 parents = None
             elif numpar == 1:
                 o3 = o2 + sha1size
                 parents = (data[o2:o3],)
             else:
                 o3 = o2 + sha1size * numpar
                 parents = unpack(sha1fmt * numpar, data[o2:o3])
 
         # read metadata
         off = o3 + metasize * nummeta
         metapairsize = unpack('>' + (metafmt * nummeta), data[o3:off])
         metadata = []
         for idx in xrange(0, len(metapairsize), 2):
             o1 = off + metapairsize[idx]
             o2 = o1 + metapairsize[idx + 1]
             metadata.append((data[off:o1], data[o1:o2]))
             off = o2
 
         yield (prec, sucs, flags, tuple(metadata), (secs, tz * 60), parents)
 
 def _fm1encodeonemarker(marker):
     pre, sucs, flags, metadata, date, parents = marker
     # determine node size
     _fm1node = _fm1nodesha1
     if flags & usingsha256:
         _fm1node = _fm1nodesha256
     numsuc = len(sucs)
     numextranodes = numsuc
     if parents is None:
         numpar = _fm1parentnone
     else:
         numpar = len(parents)
         numextranodes += numpar
     formatnodes = _fm1node * numextranodes
     formatmeta = _fm1metapair * len(metadata)
     format = _fm1fixed + formatnodes + formatmeta
     # tz is stored in minutes so we divide by 60
     tz = date[1]//60
     data = [None, date[0], tz, flags, numsuc, numpar, len(metadata), pre]
     data.extend(sucs)
     if parents is not None:
         data.extend(parents)
     totalsize = _calcsize(format)
     for key, value in metadata:
         lk = len(key)
         lv = len(value)
         data.append(lk)
         data.append(lv)
         totalsize += lk + lv
     data[0] = totalsize
     data = [_pack(format, *data)]
     for key, value in metadata:
         data.append(key)
         data.append(value)
     return ''.join(data)
 
 def _fm1readmarkers(data, off):
     native = getattr(parsers, 'fm1readmarkers', None)
     if not native:
         return _fm1purereadmarkers(data, off)
     stop = len(data) - _fm1fsize
     return native(data, off, stop)
 
 # mapping to read/write various marker formats
 # <version> -> (decoder, encoder)
 formats = {_fm0version: (_fm0readmarkers, _fm0encodeonemarker),
            _fm1version: (_fm1readmarkers, _fm1encodeonemarker)}
 
 @util.nogc
 def _readmarkers(data):
     """Read and enumerate markers from raw data"""
     off = 0
     diskversion = _unpack('>B', data[off:off + 1])[0]
     off += 1
     if diskversion not in formats:
         raise error.Abort(_('parsing obsolete marker: unknown version %r')
                          % diskversion)
     return diskversion, formats[diskversion][0](data, off)
 
 def encodemarkers(markers, addheader=False, version=_fm0version):
     # Kept separate from flushmarkers(), it will be reused for
     # markers exchange.
     encodeone = formats[version][1]
     if addheader:
         yield _pack('>B', version)
     for marker in markers:
         yield encodeone(marker)
 
 
 class marker(object):
     """Wrap obsolete marker raw data"""
 
     def __init__(self, repo, data):
         # the repo argument will be used to create changectx in later version
         self._repo = repo
         self._data = data
         self._decodedmeta = None
 
     def __hash__(self):
         return hash(self._data)
 
     def __eq__(self, other):
         if type(other) != type(self):
             return False
         return self._data == other._data
 
     def precnode(self):
         """Precursor changeset node identifier"""
         return self._data[0]
 
     def succnodes(self):
         """List of successor changesets node identifiers"""
         return self._data[1]
 
     def parentnodes(self):
         """Parents of the precursors (None if not recorded)"""
         return self._data[5]
 
     def metadata(self):
         """Decoded metadata dictionary"""
         return dict(self._data[3])
 
     def date(self):
         """Creation date as (unixtime, offset)"""
         return self._data[4]
 
     def flags(self):
         """The flags field of the marker"""
         return self._data[2]
 
 @util.nogc
 def _addsuccessors(successors, markers):
     for mark in markers:
         successors.setdefault(mark[0], set()).add(mark)
 
 @util.nogc
 def _addprecursors(precursors, markers):
     for mark in markers:
         for suc in mark[1]:
             precursors.setdefault(suc, set()).add(mark)
 
 @util.nogc
 def _addchildren(children, markers):
     for mark in markers:
         parents = mark[5]
         if parents is not None:
             for p in parents:
                 children.setdefault(p, set()).add(mark)
 
 def _checkinvalidmarkers(markers):
     """search for marker with invalid data and raise error if needed
 
     Exist as a separated function to allow the evolve extension for a more
     subtle handling.
     """
     for mark in markers:
         if node.nullid in mark[1]:
             raise error.Abort(_('bad obsolescence marker detected: '
                                'invalid successors nullid'))
 
 class obsstore(object):
     """Store obsolete markers
 
     Markers can be accessed with two mappings:
     - precursors[x] -> set(markers on precursors edges of x)
     - successors[x] -> set(markers on successors edges of x)
     - children[x]   -> set(markers on precursors edges of children(x)
     """
 
     fields = ('prec', 'succs', 'flag', 'meta', 'date', 'parents')
     # prec:    nodeid, precursor changesets
     # succs:   tuple of nodeid, successor changesets (0-N length)
     # flag:    integer, flag field carrying modifier for the markers (see doc)
     # meta:    binary blob, encoded metadata dictionary
     # date:    (float, int) tuple, date of marker creation
     # parents: (tuple of nodeid) or None, parents of precursors
     #          None is used when no data has been recorded
 
     def __init__(self, svfs, defaultformat=_fm1version, readonly=False):
         # caches for various obsolescence related cache
         self.caches = {}
         self.svfs = svfs
         self._version = defaultformat
         self._readonly = readonly
 
     def __iter__(self):
         return iter(self._all)
 
     def __len__(self):
         return len(self._all)
 
     def __nonzero__(self):
         if not self._cached('_all'):
             try:
                 return self.svfs.stat('obsstore').st_size > 1
             except OSError as inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 # just build an empty _all list if no obsstore exists, which
                 # avoids further stat() syscalls
                 pass
         return bool(self._all)
 
     @property
     def readonly(self):
         """True if marker creation is disabled
 
         Remove me in the future when obsolete marker is always on."""
         return self._readonly
 
     def create(self, transaction, prec, succs=(), flag=0, parents=None,
                date=None, metadata=None):
         """obsolete: add a new obsolete marker
 
         * ensuring it is hashable
         * check mandatory metadata
         * encode metadata
 
         If you are a human writing code creating marker you want to use the
         `createmarkers` function in this module instead.
 
         return True if a new marker have been added, False if the markers
         already existed (no op).
         """
         if metadata is None:
             metadata = {}
         if date is None:
             if 'date' in metadata:
                 # as a courtesy for out-of-tree extensions
                 date = util.parsedate(metadata.pop('date'))
             else:
                 date = util.makedate()
         if len(prec) != 20:
             raise ValueError(prec)
         for succ in succs:
             if len(succ) != 20:
                 raise ValueError(succ)
         if prec in succs:
             raise ValueError(_('in-marker cycle with %s') % node.hex(prec))
 
         metadata = tuple(sorted(metadata.iteritems()))
 
         marker = (str(prec), tuple(succs), int(flag), metadata, date, parents)
         return bool(self.add(transaction, [marker]))
 
     def add(self, transaction, markers):
         """Add new markers to the store
 
         Take care of filtering duplicate.
         Return the number of new marker."""
         if self._readonly:
-            raise error.Abort('creating obsolete markers is not enabled on '
-                              'this repo')
+            raise error.Abort(_('creating obsolete markers is not enabled on '
+                              'this repo'))
         known = set(self._all)
         new = []
         for m in markers:
             if m not in known:
                 known.add(m)
                 new.append(m)
         if new:
             f = self.svfs('obsstore', 'ab')
             try:
                 offset = f.tell()
                 transaction.add('obsstore', offset)
                 # offset == 0: new file - add the version header
                 for bytes in encodemarkers(new, offset == 0, self._version):
                     f.write(bytes)
             finally:
                 # XXX: f.close() == filecache invalidation == obsstore rebuilt.
                 # call 'filecacheentry.refresh()'  here
                 f.close()
             self._addmarkers(new)
             # new marker *may* have changed several set. invalidate the cache.
             self.caches.clear()
         # records the number of new markers for the transaction hooks
         previous = int(transaction.hookargs.get('new_obsmarkers', '0'))
         transaction.hookargs['new_obsmarkers'] = str(previous + len(new))
         return len(new)
 
     def mergemarkers(self, transaction, data):
         """merge a binary stream of markers inside the obsstore
 
         Returns the number of new markers added."""
         version, markers = _readmarkers(data)
         return self.add(transaction, markers)
 
     @propertycache
     def _all(self):
         data = self.svfs.tryread('obsstore')
         if not data:
             return []
         self._version, markers = _readmarkers(data)
         markers = list(markers)
         _checkinvalidmarkers(markers)
         return markers
 
     @propertycache
     def successors(self):
         successors = {}
         _addsuccessors(successors, self._all)
         return successors
 
     @propertycache
     def precursors(self):
         precursors = {}
         _addprecursors(precursors, self._all)
         return precursors
 
     @propertycache
     def children(self):
         children = {}
         _addchildren(children, self._all)
         return children
 
     def _cached(self, attr):
         return attr in self.__dict__
 
     def _addmarkers(self, markers):
         markers = list(markers) # to allow repeated iteration
         self._all.extend(markers)
         if self._cached('successors'):
             _addsuccessors(self.successors, markers)
         if self._cached('precursors'):
             _addprecursors(self.precursors, markers)
         if self._cached('children'):
             _addchildren(self.children, markers)
         _checkinvalidmarkers(markers)
 
     def relevantmarkers(self, nodes):
         """return a set of all obsolescence markers relevant to a set of nodes.
 
         "relevant" to a set of nodes mean:
 
         - marker that use this changeset as successor
         - prune marker of direct children on this changeset
         - recursive application of the two rules on precursors of these markers
 
         It is a set so you cannot rely on order."""
 
         pendingnodes = set(nodes)
         seenmarkers = set()
         seennodes = set(pendingnodes)
         precursorsmarkers = self.precursors
         children = self.children
         while pendingnodes:
             direct = set()
             for current in pendingnodes:
                 direct.update(precursorsmarkers.get(current, ()))
                 pruned = [m for m in children.get(current, ()) if not m[1]]
                 direct.update(pruned)
             direct -= seenmarkers
             pendingnodes = set([m[0] for m in direct])
             seenmarkers |= direct
             pendingnodes -= seennodes
             seennodes |= pendingnodes
         return seenmarkers
 
 def commonversion(versions):
     """Return the newest version listed in both versions and our local formats.
 
     Returns None if no common version exists.
     """
     versions.sort(reverse=True)
     # search for highest version known on both side
     for v in versions:
         if v in formats:
             return v
     return None
 
 # arbitrary picked to fit into 8K limit from HTTP server
 # you have to take in account:
 # - the version header
 # - the base85 encoding
 _maxpayload = 5300
 
 def _pushkeyescape(markers):
     """encode markers into a dict suitable for pushkey exchange
 
     - binary data is base85 encoded
     - split in chunks smaller than 5300 bytes"""
     keys = {}
     parts = []
     currentlen = _maxpayload * 2  # ensure we create a new part
     for marker in markers:
         nextdata = _fm0encodeonemarker(marker)
         if (len(nextdata) + currentlen > _maxpayload):
             currentpart = []
             currentlen = 0
             parts.append(currentpart)
         currentpart.append(nextdata)
         currentlen += len(nextdata)
     for idx, part in enumerate(reversed(parts)):
         data = ''.join([_pack('>B', _fm0version)] + part)
         keys['dump%i' % idx] = base85.b85encode(data)
     return keys
 
 def listmarkers(repo):
     """List markers over pushkey"""
     if not repo.obsstore:
         return {}
     return _pushkeyescape(sorted(repo.obsstore))
 
 def pushmarker(repo, key, old, new):
     """Push markers over pushkey"""
     if not key.startswith('dump'):
         repo.ui.warn(_('unknown key: %r') % key)
         return 0
     if old:
         repo.ui.warn(_('unexpected old value for %r') % key)
         return 0
     data = base85.b85decode(new)
     lock = repo.lock()
     try:
         tr = repo.transaction('pushkey: obsolete markers')
         try:
             repo.obsstore.mergemarkers(tr, data)
             tr.close()
             return 1
         finally:
             tr.release()
     finally:
         lock.release()
 
 def getmarkers(repo, nodes=None):
     """returns markers known in a repository
 
     If <nodes> is specified, only markers "relevant" to those nodes are are
     returned"""
     if nodes is None:
         rawmarkers = repo.obsstore
     else:
         rawmarkers = repo.obsstore.relevantmarkers(nodes)
 
     for markerdata in rawmarkers:
         yield marker(repo, markerdata)
 
 def relevantmarkers(repo, node):
     """all obsolete markers relevant to some revision"""
     for markerdata in repo.obsstore.relevantmarkers(node):
         yield marker(repo, markerdata)
 
 
 def precursormarkers(ctx):
     """obsolete marker marking this changeset as a successors"""
     for data in ctx.repo().obsstore.precursors.get(ctx.node(), ()):
         yield marker(ctx.repo(), data)
 
 def successormarkers(ctx):
     """obsolete marker making this changeset obsolete"""
     for data in ctx.repo().obsstore.successors.get(ctx.node(), ()):
         yield marker(ctx.repo(), data)
 
 def allsuccessors(obsstore, nodes, ignoreflags=0):
     """Yield node for every successor of <nodes>.
 
     Some successors may be unknown locally.
 
     This is a linear yield unsuited to detecting split changesets. It includes
     initial nodes too."""
     remaining = set(nodes)
     seen = set(remaining)
     while remaining:
         current = remaining.pop()
         yield current
         for mark in obsstore.successors.get(current, ()):
             # ignore marker flagged with specified flag
             if mark[2] & ignoreflags:
                 continue
             for suc in mark[1]:
                 if suc not in seen:
                     seen.add(suc)
                     remaining.add(suc)
 
 def allprecursors(obsstore, nodes, ignoreflags=0):
     """Yield node for every precursors of <nodes>.
 
     Some precursors may be unknown locally.
 
     This is a linear yield unsuited to detecting folded changesets. It includes
     initial nodes too."""
 
     remaining = set(nodes)
     seen = set(remaining)
     while remaining:
         current = remaining.pop()
         yield current
         for mark in obsstore.precursors.get(current, ()):
             # ignore marker flagged with specified flag
             if mark[2] & ignoreflags:
                 continue
             suc = mark[0]
             if suc not in seen:
                 seen.add(suc)
                 remaining.add(suc)
 
 def foreground(repo, nodes):
     """return all nodes in the "foreground" of other node
 
     The foreground of a revision is anything reachable using parent -> children
     or precursor -> successor relation. It is very similar to "descendant" but
     augmented with obsolescence information.
 
     Beware that possible obsolescence cycle may result if complex situation.
     """
     repo = repo.unfiltered()
     foreground = set(repo.set('%ln::', nodes))
     if repo.obsstore:
         # We only need this complicated logic if there is obsolescence
         # XXX will probably deserve an optimised revset.
         nm = repo.changelog.nodemap
         plen = -1
         # compute the whole set of successors or descendants
         while len(foreground) != plen:
             plen = len(foreground)
             succs = set(c.node() for c in foreground)
             mutable = [c.node() for c in foreground if c.mutable()]
             succs.update(allsuccessors(repo.obsstore, mutable))
             known = (n for n in succs if n in nm)
             foreground = set(repo.set('%ln::', known))
     return set(c.node() for c in foreground)
 
 
 def successorssets(repo, initialnode, cache=None):
     """Return set of all latest successors of initial nodes
 
     The successors set of a changeset A are the group of revisions that succeed
     A. It succeeds A as a consistent whole, each revision being only a partial
     replacement. The successors set contains non-obsolete changesets only.
 
     This function returns the full list of successor sets which is why it
     returns a list of tuples and not just a single tuple. Each tuple is a valid
     successors set. Note that (A,) may be a valid successors set for changeset A
     (see below).
 
     In most cases, a changeset A will have a single element (e.g. the changeset
     A is replaced by A') in its successors set. Though, it is also common for a
     changeset A to have no elements in its successor set (e.g. the changeset
     has been pruned). Therefore, the returned list of successors sets will be
     [(A',)] or [], respectively.
 
     When a changeset A is split into A' and B', however, it will result in a
     successors set containing more than a single element, i.e. [(A',B')].
     Divergent changesets will result in multiple successors sets, i.e. [(A',),
     (A'')].
 
     If a changeset A is not obsolete, then it will conceptually have no
     successors set. To distinguish this from a pruned changeset, the successor
     set will contain itself only, i.e. [(A,)].
 
     Finally, successors unknown locally are considered to be pruned (obsoleted
     without any successors).
 
     The optional `cache` parameter is a dictionary that may contain precomputed
     successors sets. It is meant to reuse the computation of a previous call to
     `successorssets` when multiple calls are made at the same time. The cache
     dictionary is updated in place. The caller is responsible for its life
     span. Code that makes multiple calls to `successorssets` *must* use this
     cache mechanism or suffer terrible performance.
     """
 
     succmarkers = repo.obsstore.successors
 
     # Stack of nodes we search successors sets for
     toproceed = [initialnode]
     # set version of above list for fast loop detection
     # element added to "toproceed" must be added here
     stackedset = set(toproceed)
     if cache is None:
         cache = {}
 
     # This while loop is the flattened version of a recursive search for
     # successors sets
     #
     # def successorssets(x):
     #    successors = directsuccessors(x)
     #    ss = [[]]
     #    for succ in directsuccessors(x):
     #        # product as in itertools cartesian product
     #        ss = product(ss, successorssets(succ))
     #    return ss
     #
     # But we can not use plain recursive calls here:
     # - that would blow the python call stack
     # - obsolescence markers may have cycles, we need to handle them.
     #
     # The `toproceed` list act as our call stack. Every node we search
     # successors set for are stacked there.
     #
     # The `stackedset` is set version of this stack used to check if a node is
     # already stacked. This check is used to detect cycles and prevent infinite
     # loop.
     #
     # successors set of all nodes are stored in the `cache` dictionary.
     #
     # After this while loop ends we use the cache to return the successors sets
     # for the node requested by the caller.
     while toproceed:
         # Every iteration tries to compute the successors sets of the topmost
         # node of the stack: CURRENT.
         #
         # There are four possible outcomes:
         #
         # 1) We already know the successors sets of CURRENT:
         #    -> mission accomplished, pop it from the stack.
         # 2) Node is not obsolete:
         #    -> the node is its own successors sets. Add it to the cache.
         # 3) We do not know successors set of direct successors of CURRENT:
         #    -> We add those successors to the stack.
         # 4) We know successors sets of all direct successors of CURRENT:
         #    -> We can compute CURRENT successors set and add it to the
         #       cache.
         #
         current = toproceed[-1]
         if current in cache:
             # case (1): We already know the successors sets
             stackedset.remove(toproceed.pop())
         elif current not in succmarkers:
             # case (2): The node is not obsolete.
             if current in repo:
                 # We have a valid last successors.
                 cache[current] = [(current,)]
             else:
                 # Final obsolete version is unknown locally.
                 # Do not count that as a valid successors
                 cache[current] = []
         else:
             # cases (3) and (4)
             #
             # We proceed in two phases. Phase 1 aims to distinguish case (3)
             # from case (4):
             #
             #     For each direct successors of CURRENT, we check whether its
             #     successors sets are known. If they are not, we stack the
             #     unknown node and proceed to the next iteration of the while
             #     loop. (case 3)
             #
             #     During this step, we may detect obsolescence cycles: a node
             #     with unknown successors sets but already in the call stack.
             #     In such a situation, we arbitrary set the successors sets of
             #     the node to nothing (node pruned) to break the cycle.
             #
             #     If no break was encountered we proceed to phase 2.
             #
             # Phase 2 computes successors sets of CURRENT (case 4); see details
             # in phase 2 itself.
             #
             # Note the two levels of iteration in each phase.
             # - The first one handles obsolescence markers using CURRENT as
             #   precursor (successors markers of CURRENT).
             #
             #   Having multiple entry here means divergence.
             #
             # - The second one handles successors defined in each marker.
             #
             #   Having none means pruned node, multiple successors means split,
             #   single successors are standard replacement.
             #
             for mark in sorted(succmarkers[current]):
                 for suc in mark[1]:
                     if suc not in cache:
                         if suc in stackedset:
                             # cycle breaking
                             cache[suc] = []
                         else:
                             # case (3) If we have not computed successors sets
                             # of one of those successors we add it to the
                             # `toproceed` stack and stop all work for this
                             # iteration.
                             toproceed.append(suc)
                             stackedset.add(suc)
                             break
                 else:
                     continue
                 break
             else:
                 # case (4): we know all successors sets of all direct
                 # successors
                 #
                 # Successors set contributed by each marker depends on the
                 # successors sets of all its "successors" node.
                 #
                 # Each different marker is a divergence in the obsolescence
                 # history. It contributes successors sets distinct from other
                 # markers.
                 #
                 # Within a marker, a successor may have divergent successors
                 # sets. In such a case, the marker will contribute multiple
                 # divergent successors sets. If multiple successors have
                 # divergent successors sets, a Cartesian product is used.
                 #
                 # At the end we post-process successors sets to remove
                 # duplicated entry and successors set that are strict subset of
                 # another one.
                 succssets = []
                 for mark in sorted(succmarkers[current]):
                     # successors sets contributed by this marker
                     markss = [[]]
                     for suc in mark[1]:
                         # cardinal product with previous successors
                         productresult = []
                         for prefix in markss:
                             for suffix in cache[suc]:
                                 newss = list(prefix)
                                 for part in suffix:
                                     # do not duplicated entry in successors set
                                     # first entry wins.
                                     if part not in newss:
                                         newss.append(part)
                                 productresult.append(newss)
                         markss = productresult
                     succssets.extend(markss)
                 # remove duplicated and subset
                 seen = []
                 final = []
                 candidate = sorted(((set(s), s) for s in succssets if s),
                                    key=lambda x: len(x[1]), reverse=True)
                 for setversion, listversion in candidate:
                     for seenset in seen:
                         if setversion.issubset(seenset):
                             break
                     else:
                         final.append(listversion)
                         seen.append(setversion)
                 final.reverse() # put small successors set first
                 cache[current] = final
     return cache[initialnode]
 
 # mapping of 'set-name' -> <function to compute this set>
 cachefuncs = {}
 def cachefor(name):
     """Decorator to register a function as computing the cache for a set"""
     def decorator(func):
         assert name not in cachefuncs
         cachefuncs[name] = func
         return func
     return decorator
 
 def getrevs(repo, name):
     """Return the set of revision that belong to the <name> set
 
     Such access may compute the set and cache it for future use"""
     repo = repo.unfiltered()
     if not repo.obsstore:
         return frozenset()
     if name not in repo.obsstore.caches:
         repo.obsstore.caches[name] = cachefuncs[name](repo)
     return repo.obsstore.caches[name]
 
 # To be simple we need to invalidate obsolescence cache when:
 #
 # - new changeset is added:
 # - public phase is changed
 # - obsolescence marker are added
 # - strip is used a repo
 def clearobscaches(repo):
     """Remove all obsolescence related cache from a repo
 
     This remove all cache in obsstore is the obsstore already exist on the
     repo.
 
     (We could be smarter here given the exact event that trigger the cache
     clearing)"""
     # only clear cache is there is obsstore data in this repo
     if 'obsstore' in repo._filecache:
         repo.obsstore.caches.clear()
 
 @cachefor('obsolete')
 def _computeobsoleteset(repo):
     """the set of obsolete revisions"""
     obs = set()
     getnode = repo.changelog.node
     notpublic = repo.revs("not public()")
     for r in notpublic:
         if getnode(r) in repo.obsstore.successors:
             obs.add(r)
     return obs
 
 @cachefor('unstable')
 def _computeunstableset(repo):
     """the set of non obsolete revisions with obsolete parents"""
     revs = [(ctx.rev(), ctx) for ctx in
             repo.set('(not public()) and (not obsolete())')]
     revs.sort(key=lambda x:x[0])
     unstable = set()
     for rev, ctx in revs:
         # A rev is unstable if one of its parent is obsolete or unstable
         # this works since we traverse following growing rev order
         if any((x.obsolete() or (x.rev() in unstable))
                 for x in ctx.parents()):
             unstable.add(rev)
     return unstable
 
 @cachefor('suspended')
 def _computesuspendedset(repo):
     """the set of obsolete parents with non obsolete descendants"""
     suspended = repo.changelog.ancestors(getrevs(repo, 'unstable'))
     return set(r for r in getrevs(repo, 'obsolete') if r in suspended)
 
 @cachefor('extinct')
 def _computeextinctset(repo):
     """the set of obsolete parents without non obsolete descendants"""
     return getrevs(repo, 'obsolete') - getrevs(repo, 'suspended')
 
 
 @cachefor('bumped')
 def _computebumpedset(repo):
     """the set of revs trying to obsolete public revisions"""
     bumped = set()
     # util function (avoid attribute lookup in the loop)
     phase = repo._phasecache.phase # would be faster to grab the full list
     public = phases.public
     cl = repo.changelog
     torev = cl.nodemap.get
     for ctx in repo.set('(not public()) and (not obsolete())'):
         rev = ctx.rev()
         # We only evaluate mutable, non-obsolete revision
         node = ctx.node()
         # (future) A cache of precursors may worth if split is very common
         for pnode in allprecursors(repo.obsstore, [node],
                                    ignoreflags=bumpedfix):
             prev = torev(pnode) # unfiltered! but so is phasecache
             if (prev is not None) and (phase(repo, prev) <= public):
                 # we have a public precursor
                 bumped.add(rev)
                 break # Next draft!
     return bumped
 
 @cachefor('divergent')
 def _computedivergentset(repo):
     """the set of rev that compete to be the final successors of some revision.
     """
     divergent = set()
     obsstore = repo.obsstore
     newermap = {}
     for ctx in repo.set('(not public()) - obsolete()'):
         mark = obsstore.precursors.get(ctx.node(), ())
         toprocess = set(mark)
         seen = set()
         while toprocess:
             prec = toprocess.pop()[0]
             if prec in seen:
                 continue # emergency cycle hanging prevention
             seen.add(prec)
             if prec not in newermap:
                 successorssets(repo, prec, newermap)
             newer = [n for n in newermap[prec] if n]
             if len(newer) > 1:
                 divergent.add(ctx.rev())
                 break
             toprocess.update(obsstore.precursors.get(prec, ()))
     return divergent
 
 
 def createmarkers(repo, relations, flag=0, date=None, metadata=None):
     """Add obsolete markers between changesets in a repo
 
     <relations> must be an iterable of (<old>, (<new>, ...)[,{metadata}])
     tuple. `old` and `news` are changectx. metadata is an optional dictionary
     containing metadata for this marker only. It is merged with the global
     metadata specified through the `metadata` argument of this function,
 
     Trying to obsolete a public changeset will raise an exception.
 
     Current user and date are used except if specified otherwise in the
     metadata attribute.
 
     This function operates within a transaction of its own, but does
     not take any lock on the repo.
     """
     # prepare metadata
     if metadata is None:
         metadata = {}
     if 'user' not in metadata:
         metadata['user'] = repo.ui.username()
     tr = repo.transaction('add-obsolescence-marker')
     try:
         markerargs = []
         for rel in relations:
             prec = rel[0]
             sucs = rel[1]
             localmetadata = metadata.copy()
             if 2 < len(rel):
                 localmetadata.update(rel[2])
 
             if not prec.mutable():
-                raise error.Abort("cannot obsolete public changeset: %s"
+                raise error.Abort(_("cannot obsolete public changeset: %s")
                                  % prec,
                                  hint='see "hg help phases" for details')
             nprec = prec.node()
             nsucs = tuple(s.node() for s in sucs)
             npare = None
             if not nsucs:
                 npare = tuple(p.node() for p in prec.parents())
             if nprec in nsucs:
-                raise error.Abort("changeset %s cannot obsolete itself" % prec)
+                raise error.Abort(_("changeset %s cannot obsolete itself")
+                                  % prec)
 
             # Creating the marker causes the hidden cache to become invalid,
             # which causes recomputation when we ask for prec.parents() above.
             # Resulting in n^2 behavior.  So let's prepare all of the args
             # first, then create the markers.
             markerargs.append((nprec, nsucs, npare, localmetadata))
 
         for args in markerargs:
             nprec, nsucs, npare, localmetadata = args
             repo.obsstore.create(tr, nprec, nsucs, flag, parents=npare,
                                  date=date, metadata=localmetadata)
             repo.filteredrevcache.clear()
         tr.close()
     finally:
         tr.release()
 
 def isenabled(repo, option):
     """Returns True if the given repository has the given obsolete option
     enabled.
     """
     result = set(repo.ui.configlist('experimental', 'evolution'))
     if 'all' in result:
         return True
 
     # For migration purposes, temporarily return true if the config hasn't been
     # set but _enabled is true.
     if len(result) == 0 and _enabled:
         return True
 
     # createmarkers must be enabled if other options are enabled
     if ((allowunstableopt in result or exchangeopt in result) and
         not createmarkersopt in result):
         raise error.Abort(_("'createmarkers' obsolete option must be enabled "
                            "if other obsolete options are enabled"))
 
     return option in result

mercurial/revset.py

@@ -1,3671 +1,3672 b''
 # revset.py - revision set queries for mercurial
 #
 # Copyright 2010 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 __future__ import absolute_import
 
 import heapq
 import re
 
 from .i18n import _
 from . import (
     destutil,
     encoding,
     error,
     hbisect,
     match as matchmod,
     node,
     obsolete as obsmod,
     parser,
     pathutil,
     phases,
     registrar,
     repoview,
     util,
 )
 
 def _revancestors(repo, revs, followfirst):
     """Like revlog.ancestors(), but supports followfirst."""
     if followfirst:
         cut = 1
     else:
         cut = None
     cl = repo.changelog
 
     def iterate():
         revs.sort(reverse=True)
         irevs = iter(revs)
         h = []
 
         inputrev = next(irevs, None)
         if inputrev is not None:
             heapq.heappush(h, -inputrev)
 
         seen = set()
         while h:
             current = -heapq.heappop(h)
             if current == inputrev:
                 inputrev = next(irevs, None)
                 if inputrev is not None:
                     heapq.heappush(h, -inputrev)
             if current not in seen:
                 seen.add(current)
                 yield current
                 for parent in cl.parentrevs(current)[:cut]:
                     if parent != node.nullrev:
                         heapq.heappush(h, -parent)
 
     return generatorset(iterate(), iterasc=False)
 
 def _revdescendants(repo, revs, followfirst):
     """Like revlog.descendants() but supports followfirst."""
     if followfirst:
         cut = 1
     else:
         cut = None
 
     def iterate():
         cl = repo.changelog
         # XXX this should be 'parentset.min()' assuming 'parentset' is a
         # smartset (and if it is not, it should.)
         first = min(revs)
         nullrev = node.nullrev
         if first == nullrev:
             # Are there nodes with a null first parent and a non-null
             # second one? Maybe. Do we care? Probably not.
             for i in cl:
                 yield i
         else:
             seen = set(revs)
             for i in cl.revs(first + 1):
                 for x in cl.parentrevs(i)[:cut]:
                     if x != nullrev and x in seen:
                         seen.add(i)
                         yield i
                         break
 
     return generatorset(iterate(), iterasc=True)
 
 def _reachablerootspure(repo, minroot, roots, heads, includepath):
     """return (heads(::<roots> and ::<heads>))
 
     If includepath is True, return (<roots>::<heads>)."""
     if not roots:
         return []
     parentrevs = repo.changelog.parentrevs
     roots = set(roots)
     visit = list(heads)
     reachable = set()
     seen = {}
     # prefetch all the things! (because python is slow)
     reached = reachable.add
     dovisit = visit.append
     nextvisit = visit.pop
     # open-code the post-order traversal due to the tiny size of
     # sys.getrecursionlimit()
     while visit:
         rev = nextvisit()
         if rev in roots:
             reached(rev)
             if not includepath:
                 continue
         parents = parentrevs(rev)
         seen[rev] = parents
         for parent in parents:
             if parent >= minroot and parent not in seen:
                 dovisit(parent)
     if not reachable:
         return baseset()
     if not includepath:
         return reachable
     for rev in sorted(seen):
         for parent in seen[rev]:
             if parent in reachable:
                 reached(rev)
     return reachable
 
 def reachableroots(repo, roots, heads, includepath=False):
     """return (heads(::<roots> and ::<heads>))
 
     If includepath is True, return (<roots>::<heads>)."""
     if not roots:
         return baseset()
     minroot = roots.min()
     roots = list(roots)
     heads = list(heads)
     try:
         revs = repo.changelog.reachableroots(minroot, heads, roots, includepath)
     except AttributeError:
         revs = _reachablerootspure(repo, minroot, roots, heads, includepath)
     revs = baseset(revs)
     revs.sort()
     return revs
 
 elements = {
     # token-type: binding-strength, primary, prefix, infix, suffix
     "(": (21, None, ("group", 1, ")"), ("func", 1, ")"), None),
     "##": (20, None, None, ("_concat", 20), None),
     "~": (18, None, None, ("ancestor", 18), None),
     "^": (18, None, None, ("parent", 18), ("parentpost", 18)),
     "-": (5, None, ("negate", 19), ("minus", 5), None),
     "::": (17, None, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     "..": (17, None, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     ":": (15, "rangeall", ("rangepre", 15), ("range", 15), ("rangepost", 15)),
     "not": (10, None, ("not", 10), None, None),
     "!": (10, None, ("not", 10), None, None),
     "and": (5, None, None, ("and", 5), None),
     "&": (5, None, None, ("and", 5), None),
     "%": (5, None, None, ("only", 5), ("onlypost", 5)),
     "or": (4, None, None, ("or", 4), None),
     "|": (4, None, None, ("or", 4), None),
     "+": (4, None, None, ("or", 4), None),
     "=": (3, None, None, ("keyvalue", 3), None),
     ",": (2, None, None, ("list", 2), None),
     ")": (0, None, None, None, None),
     "symbol": (0, "symbol", None, None, None),
     "string": (0, "string", None, None, None),
     "end": (0, None, None, None, None),
 }
 
 keywords = set(['and', 'or', 'not'])
 
 # default set of valid characters for the initial letter of symbols
 _syminitletters = set(c for c in [chr(i) for i in xrange(256)]
                       if c.isalnum() or c in '._@' or ord(c) > 127)
 
 # default set of valid characters for non-initial letters of symbols
 _symletters = set(c for c in  [chr(i) for i in xrange(256)]
                   if c.isalnum() or c in '-._/@' or ord(c) > 127)
 
 def tokenize(program, lookup=None, syminitletters=None, symletters=None):
     '''
     Parse a revset statement into a stream of tokens
 
     ``syminitletters`` is the set of valid characters for the initial
     letter of symbols.
 
     By default, character ``c`` is recognized as valid for initial
     letter of symbols, if ``c.isalnum() or c in '._@' or ord(c) > 127``.
 
     ``symletters`` is the set of valid characters for non-initial
     letters of symbols.
 
     By default, character ``c`` is recognized as valid for non-initial
     letters of symbols, if ``c.isalnum() or c in '-._/@' or ord(c) > 127``.
 
     Check that @ is a valid unquoted token character (issue3686):
     >>> list(tokenize("@::"))
     [('symbol', '@', 0), ('::', None, 1), ('end', None, 3)]
 
     '''
     if syminitletters is None:
         syminitletters = _syminitletters
     if symletters is None:
         symletters = _symletters
 
     if program and lookup:
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         parts = program.split(':', 1)
         if all(lookup(sym) for sym in parts if sym):
             if parts[0]:
                 yield ('symbol', parts[0], 0)
             if len(parts) > 1:
                 s = len(parts[0])
                 yield (':', None, s)
                 if parts[1]:
                     yield ('symbol', parts[1], s + 1)
             yield ('end', None, len(program))
             return
 
     pos, l = 0, len(program)
     while pos < l:
         c = program[pos]
         if c.isspace(): # skip inter-token whitespace
             pass
         elif c == ':' and program[pos:pos + 2] == '::': # look ahead carefully
             yield ('::', None, pos)
             pos += 1 # skip ahead
         elif c == '.' and program[pos:pos + 2] == '..': # look ahead carefully
             yield ('..', None, pos)
             pos += 1 # skip ahead
         elif c == '#' and program[pos:pos + 2] == '##': # look ahead carefully
             yield ('##', None, pos)
             pos += 1 # skip ahead
         elif c in "():=,-|&+!~^%": # handle simple operators
             yield (c, None, pos)
         elif (c in '"\'' or c == 'r' and
               program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
             if c == 'r':
                 pos += 1
                 c = program[pos]
                 decode = lambda x: x
             else:
                 decode = parser.unescapestr
             pos += 1
             s = pos
             while pos < l: # find closing quote
                 d = program[pos]
                 if d == '\\': # skip over escaped characters
                     pos += 2
                     continue
                 if d == c:
                     yield ('string', decode(program[s:pos]), s)
                     break
                 pos += 1
             else:
                 raise error.ParseError(_("unterminated string"), s)
         # gather up a symbol/keyword
         elif c in syminitletters:
             s = pos
             pos += 1
             while pos < l: # find end of symbol
                 d = program[pos]
                 if d not in symletters:
                     break
                 if d == '.' and program[pos - 1] == '.': # special case for ..
                     pos -= 1
                     break
                 pos += 1
             sym = program[s:pos]
             if sym in keywords: # operator keywords
                 yield (sym, None, s)
             elif '-' in sym:
                 # some jerk gave us foo-bar-baz, try to check if it's a symbol
                 if lookup and lookup(sym):
                     # looks like a real symbol
                     yield ('symbol', sym, s)
                 else:
                     # looks like an expression
                     parts = sym.split('-')
                     for p in parts[:-1]:
                         if p: # possible consecutive -
                             yield ('symbol', p, s)
                         s += len(p)
                         yield ('-', None, pos)
                         s += 1
                     if parts[-1]: # possible trailing -
                         yield ('symbol', parts[-1], s)
             else:
                 yield ('symbol', sym, s)
             pos -= 1
         else:
             raise error.ParseError(_("syntax error in revset '%s'") %
                                    program, pos)
         pos += 1
     yield ('end', None, pos)
 
 # helpers
 
 def getstring(x, err):
     if x and (x[0] == 'string' or x[0] == 'symbol'):
         return x[1]
     raise error.ParseError(err)
 
 def getlist(x):
     if not x:
         return []
     if x[0] == 'list':
         return list(x[1:])
     return [x]
 
 def getargs(x, min, max, err):
     l = getlist(x)
     if len(l) < min or (max >= 0 and len(l) > max):
         raise error.ParseError(err)
     return l
 
 def getargsdict(x, funcname, keys):
     return parser.buildargsdict(getlist(x), funcname, keys.split(),
                                 keyvaluenode='keyvalue', keynode='symbol')
 
 def getset(repo, subset, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     s = methods[x[0]](repo, subset, *x[1:])
     if util.safehasattr(s, 'isascending'):
         return s
     # else case should not happen, because all non-func are internal,
     # ignoring for now.
     if x[0] == 'func' and x[1][0] == 'symbol' and x[1][1] in symbols:
         repo.ui.deprecwarn('revset "%s" uses list instead of smartset'
                            % x[1][1],
                            '3.9')
     return baseset(s)
 
 def _getrevsource(repo, r):
     extra = repo[r].extra()
     for label in ('source', 'transplant_source', 'rebase_source'):
         if label in extra:
             try:
                 return repo[extra[label]].rev()
             except error.RepoLookupError:
                 pass
     return None
 
 # operator methods
 
 def stringset(repo, subset, x):
     x = repo[x].rev()
     if (x in subset
         or x == node.nullrev and isinstance(subset, fullreposet)):
         return baseset([x])
     return baseset()
 
 def rangeset(repo, subset, x, y):
     m = getset(repo, fullreposet(repo), x)
     n = getset(repo, fullreposet(repo), y)
 
     if not m or not n:
         return baseset()
     m, n = m.first(), n.last()
 
     if m == n:
         r = baseset([m])
     elif n == node.wdirrev:
         r = spanset(repo, m, len(repo)) + baseset([n])
     elif m == node.wdirrev:
         r = baseset([m]) + spanset(repo, len(repo) - 1, n - 1)
     elif m < n:
         r = spanset(repo, m, n + 1)
     else:
         r = spanset(repo, m, n - 1)
     # XXX We should combine with subset first: 'subset & baseset(...)'. This is
     # necessary to ensure we preserve the order in subset.
     #
     # This has performance implication, carrying the sorting over when possible
     # would be more efficient.
     return r & subset
 
 def dagrange(repo, subset, x, y):
     r = fullreposet(repo)
     xs = reachableroots(repo, getset(repo, r, x), getset(repo, r, y),
                          includepath=True)
     return subset & xs
 
 def andset(repo, subset, x, y):
     return getset(repo, getset(repo, subset, x), y)
 
 def differenceset(repo, subset, x, y):
     return getset(repo, subset, x) - getset(repo, subset, y)
 
 def orset(repo, subset, *xs):
     assert xs
     if len(xs) == 1:
         return getset(repo, subset, xs[0])
     p = len(xs) // 2
     a = orset(repo, subset, *xs[:p])
     b = orset(repo, subset, *xs[p:])
     return a + b
 
 def notset(repo, subset, x):
     return subset - getset(repo, subset, x)
 
 def listset(repo, subset, *xs):
     raise error.ParseError(_("can't use a list in this context"),
                            hint=_('see hg help "revsets.x or y"'))
 
 def keyvaluepair(repo, subset, k, v):
     raise error.ParseError(_("can't use a key-value pair in this context"))
 
 def func(repo, subset, a, b):
     if a[0] == 'symbol' and a[1] in symbols:
         return symbols[a[1]](repo, subset, b)
 
     keep = lambda fn: getattr(fn, '__doc__', None) is not None
 
     syms = [s for (s, fn) in symbols.items() if keep(fn)]
     raise error.UnknownIdentifier(a[1], syms)
 
 # functions
 
 # symbols are callables like:
 #   fn(repo, subset, x)
 # with:
 #   repo - current repository instance
 #   subset - of revisions to be examined
 #   x - argument in tree form
 symbols = {}
 
 # symbols which can't be used for a DoS attack for any given input
 # (e.g. those which accept regexes as plain strings shouldn't be included)
 # functions that just return a lot of changesets (like all) don't count here
 safesymbols = set()
 
 predicate = registrar.revsetpredicate()
 
 @predicate('_destupdate')
 def _destupdate(repo, subset, x):
     # experimental revset for update destination
     args = getargsdict(x, 'limit', 'clean check')
     return subset & baseset([destutil.destupdate(repo, **args)[0]])
 
 @predicate('_destmerge')
 def _destmerge(repo, subset, x):
     # experimental revset for merge destination
     sourceset = None
     if x is not None:
         sourceset = getset(repo, fullreposet(repo), x)
     return subset & baseset([destutil.destmerge(repo, sourceset=sourceset)])
 
 @predicate('adds(pattern)', safe=True)
 def adds(repo, subset, x):
     """Changesets that add a file matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "adds" is a keyword
     pat = getstring(x, _("adds requires a pattern"))
     return checkstatus(repo, subset, pat, 1)
 
 @predicate('ancestor(*changeset)', safe=True)
 def ancestor(repo, subset, x):
     """A greatest common ancestor of the changesets.
 
     Accepts 0 or more changesets.
     Will return empty list when passed no args.
     Greatest common ancestor of a single changeset is that changeset.
     """
     # i18n: "ancestor" is a keyword
     l = getlist(x)
     rl = fullreposet(repo)
     anc = None
 
     # (getset(repo, rl, i) for i in l) generates a list of lists
     for revs in (getset(repo, rl, i) for i in l):
         for r in revs:
             if anc is None:
                 anc = repo[r]
             else:
                 anc = anc.ancestor(repo[r])
 
     if anc is not None and anc.rev() in subset:
         return baseset([anc.rev()])
     return baseset()
 
 def _ancestors(repo, subset, x, followfirst=False):
     heads = getset(repo, fullreposet(repo), x)
     if not heads:
         return baseset()
     s = _revancestors(repo, heads, followfirst)
     return subset & s
 
 @predicate('ancestors(set)', safe=True)
 def ancestors(repo, subset, x):
     """Changesets that are ancestors of a changeset in set.
     """
     return _ancestors(repo, subset, x)
 
 @predicate('_firstancestors', safe=True)
 def _firstancestors(repo, subset, x):
     # ``_firstancestors(set)``
     # Like ``ancestors(set)`` but follows only the first parents.
     return _ancestors(repo, subset, x, followfirst=True)
 
 def ancestorspec(repo, subset, x, n):
     """``set~n``
     Changesets that are the Nth ancestor (first parents only) of a changeset
     in set.
     """
     try:
         n = int(n[1])
     except (TypeError, ValueError):
         raise error.ParseError(_("~ expects a number"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         for i in range(n):
             r = cl.parentrevs(r)[0]
         ps.add(r)
     return subset & ps
 
 @predicate('author(string)', safe=True)
 def author(repo, subset, x):
     """Alias for ``user(string)``.
     """
     # i18n: "author" is a keyword
     n = encoding.lower(getstring(x, _("author requires a string")))
     kind, pattern, matcher = _substringmatcher(n)
     return subset.filter(lambda x: matcher(encoding.lower(repo[x].user())),
                          condrepr=('<user %r>', n))
 
 @predicate('bisect(string)', safe=True)
 def bisect(repo, subset, x):
     """Changesets marked in the specified bisect status:
 
     - ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
     - ``goods``, ``bads``      : csets topologically good/bad
     - ``range``              : csets taking part in the bisection
     - ``pruned``             : csets that are goods, bads or skipped
     - ``untested``           : csets whose fate is yet unknown
     - ``ignored``            : csets ignored due to DAG topology
     - ``current``            : the cset currently being bisected
     """
     # i18n: "bisect" is a keyword
     status = getstring(x, _("bisect requires a string")).lower()
     state = set(hbisect.get(repo, status))
     return subset & state
 
 # Backward-compatibility
 # - no help entry so that we do not advertise it any more
 @predicate('bisected', safe=True)
 def bisected(repo, subset, x):
     return bisect(repo, subset, x)
 
 @predicate('bookmark([name])', safe=True)
 def bookmark(repo, subset, x):
     """The named bookmark or all bookmarks.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a bookmark that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "bookmark" is a keyword
     args = getargs(x, 0, 1, _('bookmark takes one or no arguments'))
     if args:
         bm = getstring(args[0],
                        # i18n: "bookmark" is a keyword
                        _('the argument to bookmark must be a string'))
         kind, pattern, matcher = util.stringmatcher(bm)
         bms = set()
         if kind == 'literal':
             bmrev = repo._bookmarks.get(pattern, None)
             if not bmrev:
                 raise error.RepoLookupError(_("bookmark '%s' does not exist")
                                             % pattern)
             bms.add(repo[bmrev].rev())
         else:
             matchrevs = set()
             for name, bmrev in repo._bookmarks.iteritems():
                 if matcher(name):
                     matchrevs.add(bmrev)
             if not matchrevs:
                 raise error.RepoLookupError(_("no bookmarks exist"
                                               " that match '%s'") % pattern)
             for bmrev in matchrevs:
                 bms.add(repo[bmrev].rev())
     else:
         bms = set([repo[r].rev()
                    for r in repo._bookmarks.values()])
     bms -= set([node.nullrev])
     return subset & bms
 
 @predicate('branch(string or set)', safe=True)
 def branch(repo, subset, x):
     """
     All changesets belonging to the given branch or the branches of the given
     changesets.
 
     If `string` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a branch that actually starts with `re:`,
     use the prefix `literal:`.
     """
     getbi = repo.revbranchcache().branchinfo
 
     try:
         b = getstring(x, '')
     except error.ParseError:
         # not a string, but another revspec, e.g. tip()
         pass
     else:
         kind, pattern, matcher = util.stringmatcher(b)
         if kind == 'literal':
             # note: falls through to the revspec case if no branch with
             # this name exists and pattern kind is not specified explicitly
             if pattern in repo.branchmap():
                 return subset.filter(lambda r: matcher(getbi(r)[0]),
                                      condrepr=('<branch %r>', b))
             if b.startswith('literal:'):
                 raise error.RepoLookupError(_("branch '%s' does not exist")
                                             % pattern)
         else:
             return subset.filter(lambda r: matcher(getbi(r)[0]),
                                  condrepr=('<branch %r>', b))
 
     s = getset(repo, fullreposet(repo), x)
     b = set()
     for r in s:
         b.add(getbi(r)[0])
     c = s.__contains__
     return subset.filter(lambda r: c(r) or getbi(r)[0] in b,
                          condrepr=lambda: '<branch %r>' % sorted(b))
 
 @predicate('bumped()', safe=True)
 def bumped(repo, subset, x):
     """Mutable changesets marked as successors of public changesets.
 
     Only non-public and non-obsolete changesets can be `bumped`.
     """
     # i18n: "bumped" is a keyword
     getargs(x, 0, 0, _("bumped takes no arguments"))
     bumped = obsmod.getrevs(repo, 'bumped')
     return subset & bumped
 
 @predicate('bundle()', safe=True)
 def bundle(repo, subset, x):
     """Changesets in the bundle.
 
     Bundle must be specified by the -R option."""
 
     try:
         bundlerevs = repo.changelog.bundlerevs
     except AttributeError:
         raise error.Abort(_("no bundle provided - specify with -R"))
     return subset & bundlerevs
 
 def checkstatus(repo, subset, pat, field):
     hasset = matchmod.patkind(pat) == 'set'
 
     mcache = [None]
     def matches(x):
         c = repo[x]
         if not mcache[0] or hasset:
             mcache[0] = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
         m = mcache[0]
         fname = None
         if not m.anypats() and len(m.files()) == 1:
             fname = m.files()[0]
         if fname is not None:
             if fname not in c.files():
                 return False
         else:
             for f in c.files():
                 if m(f):
                     break
             else:
                 return False
         files = repo.status(c.p1().node(), c.node())[field]
         if fname is not None:
             if fname in files:
                 return True
         else:
             for f in files:
                 if m(f):
                     return True
 
     return subset.filter(matches, condrepr=('<status[%r] %r>', field, pat))
 
 def _children(repo, narrow, parentset):
     if not parentset:
         return baseset()
     cs = set()
     pr = repo.changelog.parentrevs
     minrev = parentset.min()
     for r in narrow:
         if r <= minrev:
             continue
         for p in pr(r):
             if p in parentset:
                 cs.add(r)
     # XXX using a set to feed the baseset is wrong. Sets are not ordered.
     # This does not break because of other fullreposet misbehavior.
     return baseset(cs)
 
 @predicate('children(set)', safe=True)
 def children(repo, subset, x):
     """Child changesets of changesets in set.
     """
     s = getset(repo, fullreposet(repo), x)
     cs = _children(repo, subset, s)
     return subset & cs
 
 @predicate('closed()', safe=True)
 def closed(repo, subset, x):
     """Changeset is closed.
     """
     # i18n: "closed" is a keyword
     getargs(x, 0, 0, _("closed takes no arguments"))
     return subset.filter(lambda r: repo[r].closesbranch(),
                          condrepr='<branch closed>')
 
 @predicate('contains(pattern)')
 def contains(repo, subset, x):
     """The revision's manifest contains a file matching pattern (but might not
     modify it). See :hg:`help patterns` for information about file patterns.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
     """
     # i18n: "contains" is a keyword
     pat = getstring(x, _("contains requires a pattern"))
 
     def matches(x):
         if not matchmod.patkind(pat):
             pats = pathutil.canonpath(repo.root, repo.getcwd(), pat)
             if pats in repo[x]:
                 return True
         else:
             c = repo[x]
             m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
             for f in c.manifest():
                 if m(f):
                     return True
         return False
 
     return subset.filter(matches, condrepr=('<contains %r>', pat))
 
 @predicate('converted([id])', safe=True)
 def converted(repo, subset, x):
     """Changesets converted from the given identifier in the old repository if
     present, or all converted changesets if no identifier is specified.
     """
 
     # There is exactly no chance of resolving the revision, so do a simple
     # string compare and hope for the best
 
     rev = None
     # i18n: "converted" is a keyword
     l = getargs(x, 0, 1, _('converted takes one or no arguments'))
     if l:
         # i18n: "converted" is a keyword
         rev = getstring(l[0], _('converted requires a revision'))
 
     def _matchvalue(r):
         source = repo[r].extra().get('convert_revision', None)
         return source is not None and (rev is None or source.startswith(rev))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<converted %r>', rev))
 
 @predicate('date(interval)', safe=True)
 def date(repo, subset, x):
     """Changesets within the interval, see :hg:`help dates`.
     """
     # i18n: "date" is a keyword
     ds = getstring(x, _("date requires a string"))
     dm = util.matchdate(ds)
     return subset.filter(lambda x: dm(repo[x].date()[0]),
                          condrepr=('<date %r>', ds))
 
 @predicate('desc(string)', safe=True)
 def desc(repo, subset, x):
     """Search commit message for string. The match is case-insensitive.
     """
     # i18n: "desc" is a keyword
     ds = encoding.lower(getstring(x, _("desc requires a string")))
 
     def matches(x):
         c = repo[x]
         return ds in encoding.lower(c.description())
 
     return subset.filter(matches, condrepr=('<desc %r>', ds))
 
 def _descendants(repo, subset, x, followfirst=False):
     roots = getset(repo, fullreposet(repo), x)
     if not roots:
         return baseset()
     s = _revdescendants(repo, roots, followfirst)
 
     # Both sets need to be ascending in order to lazily return the union
     # in the correct order.
     base = subset & roots
     desc = subset & s
     result = base + desc
     if subset.isascending():
         result.sort()
     elif subset.isdescending():
         result.sort(reverse=True)
     else:
         result = subset & result
     return result
 
 @predicate('descendants(set)', safe=True)
 def descendants(repo, subset, x):
     """Changesets which are descendants of changesets in set.
     """
     return _descendants(repo, subset, x)
 
 @predicate('_firstdescendants', safe=True)
 def _firstdescendants(repo, subset, x):
     # ``_firstdescendants(set)``
     # Like ``descendants(set)`` but follows only the first parents.
     return _descendants(repo, subset, x, followfirst=True)
 
 @predicate('destination([set])', safe=True)
 def destination(repo, subset, x):
     """Changesets that were created by a graft, transplant or rebase operation,
     with the given revisions specified as the source.  Omitting the optional set
     is the same as passing all().
     """
     if x is not None:
         sources = getset(repo, fullreposet(repo), x)
     else:
         sources = fullreposet(repo)
 
     dests = set()
 
     # subset contains all of the possible destinations that can be returned, so
     # iterate over them and see if their source(s) were provided in the arg set.
     # Even if the immediate src of r is not in the arg set, src's source (or
     # further back) may be.  Scanning back further than the immediate src allows
     # transitive transplants and rebases to yield the same results as transitive
     # grafts.
     for r in subset:
         src = _getrevsource(repo, r)
         lineage = None
 
         while src is not None:
             if lineage is None:
                 lineage = list()
 
             lineage.append(r)
 
             # The visited lineage is a match if the current source is in the arg
             # set.  Since every candidate dest is visited by way of iterating
             # subset, any dests further back in the lineage will be tested by a
             # different iteration over subset.  Likewise, if the src was already
             # selected, the current lineage can be selected without going back
             # further.
             if src in sources or src in dests:
                 dests.update(lineage)
                 break
 
             r = src
             src = _getrevsource(repo, r)
 
     return subset.filter(dests.__contains__,
                          condrepr=lambda: '<destination %r>' % sorted(dests))
 
 @predicate('divergent()', safe=True)
 def divergent(repo, subset, x):
     """
     Final successors of changesets with an alternative set of final successors.
     """
     # i18n: "divergent" is a keyword
     getargs(x, 0, 0, _("divergent takes no arguments"))
     divergent = obsmod.getrevs(repo, 'divergent')
     return subset & divergent
 
 @predicate('extinct()', safe=True)
 def extinct(repo, subset, x):
     """Obsolete changesets with obsolete descendants only.
     """
     # i18n: "extinct" is a keyword
     getargs(x, 0, 0, _("extinct takes no arguments"))
     extincts = obsmod.getrevs(repo, 'extinct')
     return subset & extincts
 
 @predicate('extra(label, [value])', safe=True)
 def extra(repo, subset, x):
     """Changesets with the given label in the extra metadata, with the given
     optional value.
 
     If `value` starts with `re:`, the remainder of the value is treated as
     a regular expression. To match a value that actually starts with `re:`,
     use the prefix `literal:`.
     """
     args = getargsdict(x, 'extra', 'label value')
     if 'label' not in args:
         # i18n: "extra" is a keyword
         raise error.ParseError(_('extra takes at least 1 argument'))
     # i18n: "extra" is a keyword
     label = getstring(args['label'], _('first argument to extra must be '
                                        'a string'))
     value = None
 
     if 'value' in args:
         # i18n: "extra" is a keyword
         value = getstring(args['value'], _('second argument to extra must be '
                                            'a string'))
         kind, value, matcher = util.stringmatcher(value)
 
     def _matchvalue(r):
         extra = repo[r].extra()
         return label in extra and (value is None or matcher(extra[label]))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<extra[%r] %r>', label, value))
 
 @predicate('filelog(pattern)', safe=True)
 def filelog(repo, subset, x):
     """Changesets connected to the specified filelog.
 
     For performance reasons, visits only revisions mentioned in the file-level
     filelog, rather than filtering through all changesets (much faster, but
     doesn't include deletes or duplicate changes). For a slower, more accurate
     result, use ``file()``.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
 
     If some linkrev points to revisions filtered by the current repoview, we'll
     work around it to return a non-filtered value.
     """
 
     # i18n: "filelog" is a keyword
     pat = getstring(x, _("filelog requires a pattern"))
     s = set()
     cl = repo.changelog
 
     if not matchmod.patkind(pat):
         f = pathutil.canonpath(repo.root, repo.getcwd(), pat)
         files = [f]
     else:
         m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=repo[None])
         files = (f for f in repo[None] if m(f))
 
     for f in files:
         fl = repo.file(f)
         known = {}
         scanpos = 0
         for fr in list(fl):
             fn = fl.node(fr)
             if fn in known:
                 s.add(known[fn])
                 continue
 
             lr = fl.linkrev(fr)
             if lr in cl:
                 s.add(lr)
             elif scanpos is not None:
                 # lowest matching changeset is filtered, scan further
                 # ahead in changelog
                 start = max(lr, scanpos) + 1
                 scanpos = None
                 for r in cl.revs(start):
                     # minimize parsing of non-matching entries
                     if f in cl.revision(r) and f in cl.readfiles(r):
                         try:
                             # try to use manifest delta fastpath
                             n = repo[r].filenode(f)
                             if n not in known:
                                 if n == fn:
                                     s.add(r)
                                     scanpos = r
                                     break
                                 else:
                                     known[n] = r
                         except error.ManifestLookupError:
                             # deletion in changelog
                             continue
 
     return subset & s
 
 @predicate('first(set, [n])', safe=True)
 def first(repo, subset, x):
     """An alias for limit().
     """
     return limit(repo, subset, x)
 
 def _follow(repo, subset, x, name, followfirst=False):
     l = getargs(x, 0, 1, _("%s takes no arguments or a pattern") % name)
     c = repo['.']
     if l:
         x = getstring(l[0], _("%s expected a pattern") % name)
         matcher = matchmod.match(repo.root, repo.getcwd(), [x],
                                  ctx=repo[None], default='path')
 
         files = c.manifest().walk(matcher)
 
         s = set()
         for fname in files:
             fctx = c[fname]
             s = s.union(set(c.rev() for c in fctx.ancestors(followfirst)))
             # include the revision responsible for the most recent version
             s.add(fctx.introrev())
     else:
         s = _revancestors(repo, baseset([c.rev()]), followfirst)
 
     return subset & s
 
 @predicate('follow([pattern])', safe=True)
 def follow(repo, subset, x):
     """
     An alias for ``::.`` (ancestors of the working directory's first parent).
     If pattern is specified, the histories of files matching given
     pattern is followed, including copies.
     """
     return _follow(repo, subset, x, 'follow')
 
 @predicate('_followfirst', safe=True)
 def _followfirst(repo, subset, x):
     # ``followfirst([pattern])``
     # Like ``follow([pattern])`` but follows only the first parent of
     # every revisions or files revisions.
     return _follow(repo, subset, x, '_followfirst', followfirst=True)
 
 @predicate('all()', safe=True)
 def getall(repo, subset, x):
     """All changesets, the same as ``0:tip``.
     """
     # i18n: "all" is a keyword
     getargs(x, 0, 0, _("all takes no arguments"))
     return subset & spanset(repo)  # drop "null" if any
 
 @predicate('grep(regex)')
 def grep(repo, subset, x):
     """Like ``keyword(string)`` but accepts a regex. Use ``grep(r'...')``
     to ensure special escape characters are handled correctly. Unlike
     ``keyword(string)``, the match is case-sensitive.
     """
     try:
         # i18n: "grep" is a keyword
         gr = re.compile(getstring(x, _("grep requires a string")))
     except re.error as e:
         raise error.ParseError(_('invalid match pattern: %s') % e)
 
     def matches(x):
         c = repo[x]
         for e in c.files() + [c.user(), c.description()]:
             if gr.search(e):
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<grep %r>', gr.pattern))
 
 @predicate('_matchfiles', safe=True)
 def _matchfiles(repo, subset, x):
     # _matchfiles takes a revset list of prefixed arguments:
     #
     #   [p:foo, i:bar, x:baz]
     #
     # builds a match object from them and filters subset. Allowed
     # prefixes are 'p:' for regular patterns, 'i:' for include
     # patterns and 'x:' for exclude patterns. Use 'r:' prefix to pass
     # a revision identifier, or the empty string to reference the
     # working directory, from which the match object is
     # initialized. Use 'd:' to set the default matching mode, default
     # to 'glob'. At most one 'r:' and 'd:' argument can be passed.
 
     l = getargs(x, 1, -1, "_matchfiles requires at least one argument")
     pats, inc, exc = [], [], []
     rev, default = None, None
     for arg in l:
         s = getstring(arg, "_matchfiles requires string arguments")
         prefix, value = s[:2], s[2:]
         if prefix == 'p:':
             pats.append(value)
         elif prefix == 'i:':
             inc.append(value)
         elif prefix == 'x:':
             exc.append(value)
         elif prefix == 'r:':
             if rev is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'revision')
             if value != '': # empty means working directory; leave rev as None
                 rev = value
         elif prefix == 'd:':
             if default is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'default mode')
             default = value
         else:
             raise error.ParseError('invalid _matchfiles prefix: %s' % prefix)
     if not default:
         default = 'glob'
 
     m = matchmod.match(repo.root, repo.getcwd(), pats, include=inc,
                        exclude=exc, ctx=repo[rev], default=default)
 
     # This directly read the changelog data as creating changectx for all
     # revisions is quite expensive.
     getfiles = repo.changelog.readfiles
     wdirrev = node.wdirrev
     def matches(x):
         if x == wdirrev:
             files = repo[x].files()
         else:
             files = getfiles(x)
         for f in files:
             if m(f):
                 return True
         return False
 
     return subset.filter(matches,
                          condrepr=('<matchfiles patterns=%r, include=%r '
                                    'exclude=%r, default=%r, rev=%r>',
                                    pats, inc, exc, default, rev))
 
 @predicate('file(pattern)', safe=True)
 def hasfile(repo, subset, x):
     """Changesets affecting files matched by pattern.
 
     For a faster but less accurate result, consider using ``filelog()``
     instead.
 
     This predicate uses ``glob:`` as the default kind of pattern.
     """
     # i18n: "file" is a keyword
     pat = getstring(x, _("file requires a pattern"))
     return _matchfiles(repo, subset, ('string', 'p:' + pat))
 
 @predicate('head()', safe=True)
 def head(repo, subset, x):
     """Changeset is a named branch head.
     """
     # i18n: "head" is a keyword
     getargs(x, 0, 0, _("head takes no arguments"))
     hs = set()
     cl = repo.changelog
     for b, ls in repo.branchmap().iteritems():
         hs.update(cl.rev(h) for h in ls)
     # XXX using a set to feed the baseset is wrong. Sets are not ordered.
     # This does not break because of other fullreposet misbehavior.
     # XXX We should combine with subset first: 'subset & baseset(...)'. This is
     # necessary to ensure we preserve the order in subset.
     return baseset(hs) & subset
 
 @predicate('heads(set)', safe=True)
 def heads(repo, subset, x):
     """Members of set with no children in set.
     """
     s = getset(repo, subset, x)
     ps = parents(repo, subset, x)
     return s - ps
 
 @predicate('hidden()', safe=True)
 def hidden(repo, subset, x):
     """Hidden changesets.
     """
     # i18n: "hidden" is a keyword
     getargs(x, 0, 0, _("hidden takes no arguments"))
     hiddenrevs = repoview.filterrevs(repo, 'visible')
     return subset & hiddenrevs
 
 @predicate('keyword(string)', safe=True)
 def keyword(repo, subset, x):
     """Search commit message, user name, and names of changed files for
     string. The match is case-insensitive.
     """
     # i18n: "keyword" is a keyword
     kw = encoding.lower(getstring(x, _("keyword requires a string")))
 
     def matches(r):
         c = repo[r]
         return any(kw in encoding.lower(t)
                    for t in c.files() + [c.user(), c.description()])
 
     return subset.filter(matches, condrepr=('<keyword %r>', kw))
 
 @predicate('limit(set[, n[, offset]])', safe=True)
 def limit(repo, subset, x):
     """First n members of set, defaulting to 1, starting from offset.
     """
     args = getargsdict(x, 'limit', 'set n offset')
     if 'set' not in args:
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit requires one to three arguments"))
     try:
         lim, ofs = 1, 0
         if 'n' in args:
             # i18n: "limit" is a keyword
             lim = int(getstring(args['n'], _("limit requires a number")))
         if 'offset' in args:
             # i18n: "limit" is a keyword
             ofs = int(getstring(args['offset'], _("limit requires a number")))
         if ofs < 0:
             raise error.ParseError(_("negative offset"))
     except (TypeError, ValueError):
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit expects a number"))
     os = getset(repo, fullreposet(repo), args['set'])
     result = []
     it = iter(os)
     for x in xrange(ofs):
         y = next(it, None)
         if y is None:
             break
     for x in xrange(lim):
         y = next(it, None)
         if y is None:
             break
         elif y in subset:
             result.append(y)
     return baseset(result, datarepr=('<limit n=%d, offset=%d, %r, %r>',
                                      lim, ofs, subset, os))
 
 @predicate('last(set, [n])', safe=True)
 def last(repo, subset, x):
     """Last n members of set, defaulting to 1.
     """
     # i18n: "last" is a keyword
     l = getargs(x, 1, 2, _("last requires one or two arguments"))
     try:
         lim = 1
         if len(l) == 2:
             # i18n: "last" is a keyword
             lim = int(getstring(l[1], _("last requires a number")))
     except (TypeError, ValueError):
         # i18n: "last" is a keyword
         raise error.ParseError(_("last expects a number"))
     os = getset(repo, fullreposet(repo), l[0])
     os.reverse()
     result = []
     it = iter(os)
     for x in xrange(lim):
         y = next(it, None)
         if y is None:
             break
         elif y in subset:
             result.append(y)
     return baseset(result, datarepr=('<last n=%d, %r, %r>', lim, subset, os))
 
 @predicate('max(set)', safe=True)
 def maxrev(repo, subset, x):
     """Changeset with highest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.max()
         if m in subset:
             return baseset([m], datarepr=('<max %r, %r>', subset, os))
     except ValueError:
         # os.max() throws a ValueError when the collection is empty.
         # Same as python's max().
         pass
     return baseset(datarepr=('<max %r, %r>', subset, os))
 
 @predicate('merge()', safe=True)
 def merge(repo, subset, x):
     """Changeset is a merge changeset.
     """
     # i18n: "merge" is a keyword
     getargs(x, 0, 0, _("merge takes no arguments"))
     cl = repo.changelog
     return subset.filter(lambda r: cl.parentrevs(r)[1] != -1,
                          condrepr='<merge>')
 
 @predicate('branchpoint()', safe=True)
 def branchpoint(repo, subset, x):
     """Changesets with more than one child.
     """
     # i18n: "branchpoint" is a keyword
     getargs(x, 0, 0, _("branchpoint takes no arguments"))
     cl = repo.changelog
     if not subset:
         return baseset()
     # XXX this should be 'parentset.min()' assuming 'parentset' is a smartset
     # (and if it is not, it should.)
     baserev = min(subset)
     parentscount = [0]*(len(repo) - baserev)
     for r in cl.revs(start=baserev + 1):
         for p in cl.parentrevs(r):
             if p >= baserev:
                 parentscount[p - baserev] += 1
     return subset.filter(lambda r: parentscount[r - baserev] > 1,
                          condrepr='<branchpoint>')
 
 @predicate('min(set)', safe=True)
 def minrev(repo, subset, x):
     """Changeset with lowest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.min()
         if m in subset:
             return baseset([m], datarepr=('<min %r, %r>', subset, os))
     except ValueError:
         # os.min() throws a ValueError when the collection is empty.
         # Same as python's min().
         pass
     return baseset(datarepr=('<min %r, %r>', subset, os))
 
 @predicate('modifies(pattern)', safe=True)
 def modifies(repo, subset, x):
     """Changesets modifying files matched by pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "modifies" is a keyword
     pat = getstring(x, _("modifies requires a pattern"))
     return checkstatus(repo, subset, pat, 0)
 
 @predicate('named(namespace)')
 def named(repo, subset, x):
     """The changesets in a given namespace.
 
     If `namespace` starts with `re:`, the remainder of the string is treated as
     a regular expression. To match a namespace that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "named" is a keyword
     args = getargs(x, 1, 1, _('named requires a namespace argument'))
 
     ns = getstring(args[0],
                    # i18n: "named" is a keyword
                    _('the argument to named must be a string'))
     kind, pattern, matcher = util.stringmatcher(ns)
     namespaces = set()
     if kind == 'literal':
         if pattern not in repo.names:
             raise error.RepoLookupError(_("namespace '%s' does not exist")
                                         % ns)
         namespaces.add(repo.names[pattern])
     else:
         for name, ns in repo.names.iteritems():
             if matcher(name):
                 namespaces.add(ns)
         if not namespaces:
             raise error.RepoLookupError(_("no namespace exists"
                                           " that match '%s'") % pattern)
 
     names = set()
     for ns in namespaces:
         for name in ns.listnames(repo):
             if name not in ns.deprecated:
                 names.update(repo[n].rev() for n in ns.nodes(repo, name))
 
     names -= set([node.nullrev])
     return subset & names
 
 @predicate('id(string)', safe=True)
 def node_(repo, subset, x):
     """Revision non-ambiguously specified by the given hex string prefix.
     """
     # i18n: "id" is a keyword
     l = getargs(x, 1, 1, _("id requires one argument"))
     # i18n: "id" is a keyword
     n = getstring(l[0], _("id requires a string"))
     if len(n) == 40:
         try:
             rn = repo.changelog.rev(node.bin(n))
         except (LookupError, TypeError):
             rn = None
     else:
         rn = None
         pm = repo.changelog._partialmatch(n)
         if pm is not None:
             rn = repo.changelog.rev(pm)
 
     if rn is None:
         return baseset()
     result = baseset([rn])
     return result & subset
 
 @predicate('obsolete()', safe=True)
 def obsolete(repo, subset, x):
     """Mutable changeset with a newer version."""
     # i18n: "obsolete" is a keyword
     getargs(x, 0, 0, _("obsolete takes no arguments"))
     obsoletes = obsmod.getrevs(repo, 'obsolete')
     return subset & obsoletes
 
 @predicate('only(set, [set])', safe=True)
 def only(repo, subset, x):
     """Changesets that are ancestors of the first set that are not ancestors
     of any other head in the repo. If a second set is specified, the result
     is ancestors of the first set that are not ancestors of the second set
     (i.e. ::<set1> - ::<set2>).
     """
     cl = repo.changelog
     # i18n: "only" is a keyword
     args = getargs(x, 1, 2, _('only takes one or two arguments'))
     include = getset(repo, fullreposet(repo), args[0])
     if len(args) == 1:
         if not include:
             return baseset()
 
         descendants = set(_revdescendants(repo, include, False))
         exclude = [rev for rev in cl.headrevs()
             if not rev in descendants and not rev in include]
     else:
         exclude = getset(repo, fullreposet(repo), args[1])
 
     results = set(cl.findmissingrevs(common=exclude, heads=include))
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & results
 
 @predicate('origin([set])', safe=True)
 def origin(repo, subset, x):
     """
     Changesets that were specified as a source for the grafts, transplants or
     rebases that created the given revisions.  Omitting the optional set is the
     same as passing all().  If a changeset created by these operations is itself
     specified as a source for one of these operations, only the source changeset
     for the first operation is selected.
     """
     if x is not None:
         dests = getset(repo, fullreposet(repo), x)
     else:
         dests = fullreposet(repo)
 
     def _firstsrc(rev):
         src = _getrevsource(repo, rev)
         if src is None:
             return None
 
         while True:
             prev = _getrevsource(repo, src)
 
             if prev is None:
                 return src
             src = prev
 
     o = set([_firstsrc(r) for r in dests])
     o -= set([None])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & o
 
 @predicate('outgoing([path])', safe=True)
 def outgoing(repo, subset, x):
     """Changesets not found in the specified destination repository, or the
     default push location.
     """
     # Avoid cycles.
     from . import (
         discovery,
         hg,
     )
     # i18n: "outgoing" is a keyword
     l = getargs(x, 0, 1, _("outgoing takes one or no arguments"))
     # i18n: "outgoing" is a keyword
     dest = l and getstring(l[0], _("outgoing requires a repository path")) or ''
     dest = repo.ui.expandpath(dest or 'default-push', dest or 'default')
     dest, branches = hg.parseurl(dest)
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     repo.ui.pushbuffer()
     outgoing = discovery.findcommonoutgoing(repo, other, onlyheads=revs)
     repo.ui.popbuffer()
     cl = repo.changelog
     o = set([cl.rev(r) for r in outgoing.missing])
     return subset & o
 
 @predicate('p1([set])', safe=True)
 def p1(repo, subset, x):
     """First parent of changesets in set, or the working directory.
     """
     if x is None:
         p = repo[x].p1().rev()
         if p >= 0:
             return subset & baseset([p])
         return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         ps.add(cl.parentrevs(r)[0])
     ps -= set([node.nullrev])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & ps
 
 @predicate('p2([set])', safe=True)
 def p2(repo, subset, x):
     """Second parent of changesets in set, or the working directory.
     """
     if x is None:
         ps = repo[x].parents()
         try:
             p = ps[1].rev()
             if p >= 0:
                 return subset & baseset([p])
             return baseset()
         except IndexError:
             return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         ps.add(cl.parentrevs(r)[1])
     ps -= set([node.nullrev])
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimisations from the fact this is a baseset.
     return subset & ps
 
 @predicate('parents([set])', safe=True)
 def parents(repo, subset, x):
     """
     The set of all parents for all changesets in set, or the working directory.
     """
     if x is None:
         ps = set(p.rev() for p in repo[x].parents())
     else:
         ps = set()
         cl = repo.changelog
         up = ps.update
         parentrevs = cl.parentrevs
         for r in getset(repo, fullreposet(repo), x):
             if r == node.wdirrev:
                 up(p.rev() for p in repo[r].parents())
             else:
                 up(parentrevs(r))
     ps -= set([node.nullrev])
     return subset & ps
 
 def _phase(repo, subset, target):
     """helper to select all rev in phase <target>"""
     repo._phasecache.loadphaserevs(repo) # ensure phase's sets are loaded
     if repo._phasecache._phasesets:
         s = repo._phasecache._phasesets[target] - repo.changelog.filteredrevs
         s = baseset(s)
         s.sort() # set are non ordered, so we enforce ascending
         return subset & s
     else:
         phase = repo._phasecache.phase
         condition = lambda r: phase(repo, r) == target
         return subset.filter(condition, condrepr=('<phase %r>', target),
                              cache=False)
 
 @predicate('draft()', safe=True)
 def draft(repo, subset, x):
     """Changeset in draft phase."""
     # i18n: "draft" is a keyword
     getargs(x, 0, 0, _("draft takes no arguments"))
     target = phases.draft
     return _phase(repo, subset, target)
 
 @predicate('secret()', safe=True)
 def secret(repo, subset, x):
     """Changeset in secret phase."""
     # i18n: "secret" is a keyword
     getargs(x, 0, 0, _("secret takes no arguments"))
     target = phases.secret
     return _phase(repo, subset, target)
 
 def parentspec(repo, subset, x, n):
     """``set^0``
     The set.
     ``set^1`` (or ``set^``), ``set^2``
     First or second parent, respectively, of all changesets in set.
     """
     try:
         n = int(n[1])
         if n not in (0, 1, 2):
             raise ValueError
     except (TypeError, ValueError):
         raise error.ParseError(_("^ expects a number 0, 1, or 2"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         if n == 0:
             ps.add(r)
         elif n == 1:
             ps.add(cl.parentrevs(r)[0])
         elif n == 2:
             parents = cl.parentrevs(r)
             if len(parents) > 1:
                 ps.add(parents[1])
     return subset & ps
 
 @predicate('present(set)', safe=True)
 def present(repo, subset, x):
     """An empty set, if any revision in set isn't found; otherwise,
     all revisions in set.
 
     If any of specified revisions is not present in the local repository,
     the query is normally aborted. But this predicate allows the query
     to continue even in such cases.
     """
     try:
         return getset(repo, subset, x)
     except error.RepoLookupError:
         return baseset()
 
 # for internal use
 @predicate('_notpublic', safe=True)
 def _notpublic(repo, subset, x):
     getargs(x, 0, 0, "_notpublic takes no arguments")
     repo._phasecache.loadphaserevs(repo) # ensure phase's sets are loaded
     if repo._phasecache._phasesets:
         s = set()
         for u in repo._phasecache._phasesets[1:]:
             s.update(u)
         s = baseset(s - repo.changelog.filteredrevs)
         s.sort()
         return subset & s
     else:
         phase = repo._phasecache.phase
         target = phases.public
         condition = lambda r: phase(repo, r) != target
         return subset.filter(condition, condrepr=('<phase %r>', target),
                              cache=False)
 
 @predicate('public()', safe=True)
 def public(repo, subset, x):
     """Changeset in public phase."""
     # i18n: "public" is a keyword
     getargs(x, 0, 0, _("public takes no arguments"))
     phase = repo._phasecache.phase
     target = phases.public
     condition = lambda r: phase(repo, r) == target
     return subset.filter(condition, condrepr=('<phase %r>', target),
                          cache=False)
 
 @predicate('remote([id [,path]])', safe=True)
 def remote(repo, subset, x):
     """Local revision that corresponds to the given identifier in a
     remote repository, if present. Here, the '.' identifier is a
     synonym for the current local branch.
     """
 
     from . import hg # avoid start-up nasties
     # i18n: "remote" is a keyword
     l = getargs(x, 0, 2, _("remote takes zero, one, or two arguments"))
 
     q = '.'
     if len(l) > 0:
     # i18n: "remote" is a keyword
         q = getstring(l[0], _("remote requires a string id"))
     if q == '.':
         q = repo['.'].branch()
 
     dest = ''
     if len(l) > 1:
         # i18n: "remote" is a keyword
         dest = getstring(l[1], _("remote requires a repository path"))
     dest = repo.ui.expandpath(dest or 'default')
     dest, branches = hg.parseurl(dest)
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     n = other.lookup(q)
     if n in repo:
         r = repo[n].rev()
         if r in subset:
             return baseset([r])
     return baseset()
 
 @predicate('removes(pattern)', safe=True)
 def removes(repo, subset, x):
     """Changesets which remove files matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "removes" is a keyword
     pat = getstring(x, _("removes requires a pattern"))
     return checkstatus(repo, subset, pat, 2)
 
 @predicate('rev(number)', safe=True)
 def rev(repo, subset, x):
     """Revision with the given numeric identifier.
     """
     # i18n: "rev" is a keyword
     l = getargs(x, 1, 1, _("rev requires one argument"))
     try:
         # i18n: "rev" is a keyword
         l = int(getstring(l[0], _("rev requires a number")))
     except (TypeError, ValueError):
         # i18n: "rev" is a keyword
         raise error.ParseError(_("rev expects a number"))
     if l not in repo.changelog and l != node.nullrev:
         return baseset()
     return subset & baseset([l])
 
 @predicate('matching(revision [, field])', safe=True)
 def matching(repo, subset, x):
     """Changesets in which a given set of fields match the set of fields in the
     selected revision or set.
 
     To match more than one field pass the list of fields to match separated
     by spaces (e.g. ``author description``).
 
     Valid fields are most regular revision fields and some special fields.
 
     Regular revision fields are ``description``, ``author``, ``branch``,
     ``date``, ``files``, ``phase``, ``parents``, ``substate``, ``user``
     and ``diff``.
     Note that ``author`` and ``user`` are synonyms. ``diff`` refers to the
     contents of the revision. Two revisions matching their ``diff`` will
     also match their ``files``.
 
     Special fields are ``summary`` and ``metadata``:
     ``summary`` matches the first line of the description.
     ``metadata`` is equivalent to matching ``description user date``
     (i.e. it matches the main metadata fields).
 
     ``metadata`` is the default field which is used when no fields are
     specified. You can match more than one field at a time.
     """
     # i18n: "matching" is a keyword
     l = getargs(x, 1, 2, _("matching takes 1 or 2 arguments"))
 
     revs = getset(repo, fullreposet(repo), l[0])
 
     fieldlist = ['metadata']
     if len(l) > 1:
             fieldlist = getstring(l[1],
                 # i18n: "matching" is a keyword
                 _("matching requires a string "
                 "as its second argument")).split()
 
     # Make sure that there are no repeated fields,
     # expand the 'special' 'metadata' field type
     # and check the 'files' whenever we check the 'diff'
     fields = []
     for field in fieldlist:
         if field == 'metadata':
             fields += ['user', 'description', 'date']
         elif field == 'diff':
             # a revision matching the diff must also match the files
             # since matching the diff is very costly, make sure to
             # also match the files first
             fields += ['files', 'diff']
         else:
             if field == 'author':
                 field = 'user'
             fields.append(field)
     fields = set(fields)
     if 'summary' in fields and 'description' in fields:
         # If a revision matches its description it also matches its summary
         fields.discard('summary')
 
     # We may want to match more than one field
     # Not all fields take the same amount of time to be matched
     # Sort the selected fields in order of increasing matching cost
     fieldorder = ['phase', 'parents', 'user', 'date', 'branch', 'summary',
         'files', 'description', 'substate', 'diff']
     def fieldkeyfunc(f):
         try:
             return fieldorder.index(f)
         except ValueError:
             # assume an unknown field is very costly
             return len(fieldorder)
     fields = list(fields)
     fields.sort(key=fieldkeyfunc)
 
     # Each field will be matched with its own "getfield" function
     # which will be added to the getfieldfuncs array of functions
     getfieldfuncs = []
     _funcs = {
         'user': lambda r: repo[r].user(),
         'branch': lambda r: repo[r].branch(),
         'date': lambda r: repo[r].date(),
         'description': lambda r: repo[r].description(),
         'files': lambda r: repo[r].files(),
         'parents': lambda r: repo[r].parents(),
         'phase': lambda r: repo[r].phase(),
         'substate': lambda r: repo[r].substate,
         'summary': lambda r: repo[r].description().splitlines()[0],
         'diff': lambda r: list(repo[r].diff(git=True),)
     }
     for info in fields:
         getfield = _funcs.get(info, None)
         if getfield is None:
             raise error.ParseError(
                 # i18n: "matching" is a keyword
                 _("unexpected field name passed to matching: %s") % info)
         getfieldfuncs.append(getfield)
     # convert the getfield array of functions into a "getinfo" function
     # which returns an array of field values (or a single value if there
     # is only one field to match)
     getinfo = lambda r: [f(r) for f in getfieldfuncs]
 
     def matches(x):
         for rev in revs:
             target = getinfo(rev)
             match = True
             for n, f in enumerate(getfieldfuncs):
                 if target[n] != f(x):
                     match = False
             if match:
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<matching%r %r>', fields, revs))
 
 @predicate('reverse(set)', safe=True)
 def reverse(repo, subset, x):
     """Reverse order of set.
     """
     l = getset(repo, subset, x)
     l.reverse()
     return l
 
 @predicate('roots(set)', safe=True)
 def roots(repo, subset, x):
     """Changesets in set with no parent changeset in set.
     """
     s = getset(repo, fullreposet(repo), x)
     parents = repo.changelog.parentrevs
     def filter(r):
         for p in parents(r):
             if 0 <= p and p in s:
                 return False
         return True
     return subset & s.filter(filter, condrepr='<roots>')
 
 _sortkeyfuncs = {
     'rev': lambda c: c.rev(),
     'branch': lambda c: c.branch(),
     'desc': lambda c: c.description(),
     'user': lambda c: c.user(),
     'author': lambda c: c.user(),
     'date': lambda c: c.date()[0],
 }
 
 def _getsortargs(x):
     """Parse sort options into (set, [(key, reverse)], opts)"""
     args = getargsdict(x, 'sort', 'set keys topo.firstbranch')
     if 'set' not in args:
         # i18n: "sort" is a keyword
         raise error.ParseError(_('sort requires one or two arguments'))
     keys = "rev"
     if 'keys' in args:
         # i18n: "sort" is a keyword
         keys = getstring(args['keys'], _("sort spec must be a string"))
 
     keyflags = []
     for k in keys.split():
         fk = k
         reverse = (k[0] == '-')
         if reverse:
             k = k[1:]
         if k not in _sortkeyfuncs and k != 'topo':
             raise error.ParseError(_("unknown sort key %r") % fk)
         keyflags.append((k, reverse))
 
     if len(keyflags) > 1 and any(k == 'topo' for k, reverse in keyflags):
         # i18n: "topo" is a keyword
         raise error.ParseError(_(
             'topo sort order cannot be combined with other sort keys'))
 
     opts = {}
     if 'topo.firstbranch' in args:
         if any(k == 'topo' for k, reverse in keyflags):
             opts['topo.firstbranch'] = args['topo.firstbranch']
         else:
             # i18n: "topo" and "topo.firstbranch" are keywords
             raise error.ParseError(_(
                 'topo.firstbranch can only be used when using the topo sort '
                 'key'))
 
     return args['set'], keyflags, opts
 
 @predicate('sort(set[, [-]key... [, ...]])', safe=True)
 def sort(repo, subset, x):
     """Sort set by keys. The default sort order is ascending, specify a key
     as ``-key`` to sort in descending order.
 
     The keys can be:
 
     - ``rev`` for the revision number,
     - ``branch`` for the branch name,
     - ``desc`` for the commit message (description),
     - ``user`` for user name (``author`` can be used as an alias),
     - ``date`` for the commit date
     - ``topo`` for a reverse topographical sort
 
     The ``topo`` sort order cannot be combined with other sort keys. This sort
     takes one optional argument, ``topo.firstbranch``, which takes a revset that
     specifies what topographical branches to prioritize in the sort.
 
     """
     s, keyflags, opts = _getsortargs(x)
     revs = getset(repo, subset, s)
 
     if not keyflags:
         return revs
     if len(keyflags) == 1 and keyflags[0][0] == "rev":
         revs.sort(reverse=keyflags[0][1])
         return revs
     elif keyflags[0][0] == "topo":
         firstbranch = ()
         if 'topo.firstbranch' in opts:
             firstbranch = getset(repo, subset, opts['topo.firstbranch'])
         revs = baseset(_toposort(revs, repo.changelog.parentrevs, firstbranch),
                        istopo=True)
         if keyflags[0][1]:
             revs.reverse()
         return revs
 
     # sort() is guaranteed to be stable
     ctxs = [repo[r] for r in revs]
     for k, reverse in reversed(keyflags):
         ctxs.sort(key=_sortkeyfuncs[k], reverse=reverse)
     return baseset([c.rev() for c in ctxs])
 
 def _toposort(revs, parentsfunc, firstbranch=()):
     """Yield revisions from heads to roots one (topo) branch at a time.
 
     This function aims to be used by a graph generator that wishes to minimize
     the number of parallel branches and their interleaving.
 
     Example iteration order (numbers show the "true" order in a changelog):
 
       o  4
       |
       o  1
       |
       | o  3
       | |
       | o  2
       |/
       o  0
 
     Note that the ancestors of merges are understood by the current
     algorithm to be on the same branch. This means no reordering will
     occur behind a merge.
     """
 
     ### Quick summary of the algorithm
     #
     # This function is based around a "retention" principle. We keep revisions
     # in memory until we are ready to emit a whole branch that immediately
     # "merges" into an existing one. This reduces the number of parallel
     # branches with interleaved revisions.
     #
     # During iteration revs are split into two groups:
     # A) revision already emitted
     # B) revision in "retention". They are stored as different subgroups.
     #
     # for each REV, we do the following logic:
     #
     #   1) if REV is a parent of (A), we will emit it. If there is a
     #   retention group ((B) above) that is blocked on REV being
     #   available, we emit all the revisions out of that retention
     #   group first.
     #
     #   2) else, we'll search for a subgroup in (B) awaiting for REV to be
     #   available, if such subgroup exist, we add REV to it and the subgroup is
     #   now awaiting for REV.parents() to be available.
     #
     #   3) finally if no such group existed in (B), we create a new subgroup.
     #
     #
     # To bootstrap the algorithm, we emit the tipmost revision (which
     # puts it in group (A) from above).
 
     revs.sort(reverse=True)
 
     # Set of parents of revision that have been emitted. They can be considered
     # unblocked as the graph generator is already aware of them so there is no
     # need to delay the revisions that reference them.
     #
     # If someone wants to prioritize a branch over the others, pre-filling this
     # set will force all other branches to wait until this branch is ready to be
     # emitted.
     unblocked = set(firstbranch)
 
     # list of groups waiting to be displayed, each group is defined by:
     #
     #   (revs:    lists of revs waiting to be displayed,
     #    blocked: set of that cannot be displayed before those in 'revs')
     #
     # The second value ('blocked') correspond to parents of any revision in the
     # group ('revs') that is not itself contained in the group. The main idea
     # of this algorithm is to delay as much as possible the emission of any
     # revision.  This means waiting for the moment we are about to display
     # these parents to display the revs in a group.
     #
     # This first implementation is smart until it encounters a merge: it will
     # emit revs as soon as any parent is about to be emitted and can grow an
     # arbitrary number of revs in 'blocked'. In practice this mean we properly
     # retains new branches but gives up on any special ordering for ancestors
     # of merges. The implementation can be improved to handle this better.
     #
     # The first subgroup is special. It corresponds to all the revision that
     # were already emitted. The 'revs' lists is expected to be empty and the
     # 'blocked' set contains the parents revisions of already emitted revision.
     #
     # You could pre-seed the <parents> set of groups[0] to a specific
     # changesets to select what the first emitted branch should be.
     groups = [([], unblocked)]
     pendingheap = []
     pendingset = set()
 
     heapq.heapify(pendingheap)
     heappop = heapq.heappop
     heappush = heapq.heappush
     for currentrev in revs:
         # Heap works with smallest element, we want highest so we invert
         if currentrev not in pendingset:
             heappush(pendingheap, -currentrev)
             pendingset.add(currentrev)
         # iterates on pending rev until after the current rev have been
         # processed.
         rev = None
         while rev != currentrev:
             rev = -heappop(pendingheap)
             pendingset.remove(rev)
 
             # Seek for a subgroup blocked, waiting for the current revision.
             matching = [i for i, g in enumerate(groups) if rev in g[1]]
 
             if matching:
                 # The main idea is to gather together all sets that are blocked
                 # on the same revision.
                 #
                 # Groups are merged when a common blocking ancestor is
                 # observed. For example, given two groups:
                 #
                 # revs [5, 4] waiting for 1
                 # revs [3, 2] waiting for 1
                 #
                 # These two groups will be merged when we process
                 # 1. In theory, we could have merged the groups when
                 # we added 2 to the group it is now in (we could have
                 # noticed the groups were both blocked on 1 then), but
                 # the way it works now makes the algorithm simpler.
                 #
                 # We also always keep the oldest subgroup first. We can
                 # probably improve the behavior by having the longest set
                 # first. That way, graph algorithms could minimise the length
                 # of parallel lines their drawing. This is currently not done.
                 targetidx = matching.pop(0)
                 trevs, tparents = groups[targetidx]
                 for i in matching:
                     gr = groups[i]
                     trevs.extend(gr[0])
                     tparents |= gr[1]
                 # delete all merged subgroups (except the one we kept)
                 # (starting from the last subgroup for performance and
                 # sanity reasons)
                 for i in reversed(matching):
                     del groups[i]
             else:
                 # This is a new head. We create a new subgroup for it.
                 targetidx = len(groups)
                 groups.append(([], set([rev])))
 
             gr = groups[targetidx]
 
             # We now add the current nodes to this subgroups. This is done
             # after the subgroup merging because all elements from a subgroup
             # that relied on this rev must precede it.
             #
             # we also update the <parents> set to include the parents of the
             # new nodes.
             if rev == currentrev: # only display stuff in rev
                 gr[0].append(rev)
             gr[1].remove(rev)
             parents = [p for p in parentsfunc(rev) if p > node.nullrev]
             gr[1].update(parents)
             for p in parents:
                 if p not in pendingset:
                     pendingset.add(p)
                     heappush(pendingheap, -p)
 
             # Look for a subgroup to display
             #
             # When unblocked is empty (if clause), we were not waiting for any
             # revisions during the first iteration (if no priority was given) or
             # if we emitted a whole disconnected set of the graph (reached a
             # root).  In that case we arbitrarily take the oldest known
             # subgroup. The heuristic could probably be better.
             #
             # Otherwise (elif clause) if the subgroup is blocked on
             # a revision we just emitted, we can safely emit it as
             # well.
             if not unblocked:
                 if len(groups) > 1:  # display other subset
                     targetidx = 1
                     gr = groups[1]
             elif not gr[1] & unblocked:
                 gr = None
 
             if gr is not None:
                 # update the set of awaited revisions with the one from the
                 # subgroup
                 unblocked |= gr[1]
                 # output all revisions in the subgroup
                 for r in gr[0]:
                     yield r
                 # delete the subgroup that you just output
                 # unless it is groups[0] in which case you just empty it.
                 if targetidx:
                     del groups[targetidx]
                 else:
                     gr[0][:] = []
     # Check if we have some subgroup waiting for revisions we are not going to
     # iterate over
     for g in groups:
         for r in g[0]:
             yield r
 
 @predicate('subrepo([pattern])')
 def subrepo(repo, subset, x):
     """Changesets that add, modify or remove the given subrepo.  If no subrepo
     pattern is named, any subrepo changes are returned.
     """
     # i18n: "subrepo" is a keyword
     args = getargs(x, 0, 1, _('subrepo takes at most one argument'))
     pat = None
     if len(args) != 0:
         pat = getstring(args[0], _("subrepo requires a pattern"))
 
     m = matchmod.exact(repo.root, repo.root, ['.hgsubstate'])
 
     def submatches(names):
         k, p, m = util.stringmatcher(pat)
         for name in names:
             if m(name):
                 yield name
 
     def matches(x):
         c = repo[x]
         s = repo.status(c.p1().node(), c.node(), match=m)
 
         if pat is None:
             return s.added or s.modified or s.removed
 
         if s.added:
             return any(submatches(c.substate.keys()))
 
         if s.modified:
             subs = set(c.p1().substate.keys())
             subs.update(c.substate.keys())
 
             for path in submatches(subs):
                 if c.p1().substate.get(path) != c.substate.get(path):
                     return True
 
         if s.removed:
             return any(submatches(c.p1().substate.keys()))
 
         return False
 
     return subset.filter(matches, condrepr=('<subrepo %r>', pat))
 
 def _substringmatcher(pattern):
     kind, pattern, matcher = util.stringmatcher(pattern)
     if kind == 'literal':
         matcher = lambda s: pattern in s
     return kind, pattern, matcher
 
 @predicate('tag([name])', safe=True)
 def tag(repo, subset, x):
     """The specified tag by name, or all tagged revisions if no name is given.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a tag that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # i18n: "tag" is a keyword
     args = getargs(x, 0, 1, _("tag takes one or no arguments"))
     cl = repo.changelog
     if args:
         pattern = getstring(args[0],
                             # i18n: "tag" is a keyword
                             _('the argument to tag must be a string'))
         kind, pattern, matcher = util.stringmatcher(pattern)
         if kind == 'literal':
             # avoid resolving all tags
             tn = repo._tagscache.tags.get(pattern, None)
             if tn is None:
                 raise error.RepoLookupError(_("tag '%s' does not exist")
                                             % pattern)
             s = set([repo[tn].rev()])
         else:
             s = set([cl.rev(n) for t, n in repo.tagslist() if matcher(t)])
     else:
         s = set([cl.rev(n) for t, n in repo.tagslist() if t != 'tip'])
     return subset & s
 
 @predicate('tagged', safe=True)
 def tagged(repo, subset, x):
     return tag(repo, subset, x)
 
 @predicate('unstable()', safe=True)
 def unstable(repo, subset, x):
     """Non-obsolete changesets with obsolete ancestors.
     """
     # i18n: "unstable" is a keyword
     getargs(x, 0, 0, _("unstable takes no arguments"))
     unstables = obsmod.getrevs(repo, 'unstable')
     return subset & unstables
 
 
 @predicate('user(string)', safe=True)
 def user(repo, subset, x):
     """User name contains string. The match is case-insensitive.
 
     If `string` starts with `re:`, the remainder of the string is treated as
     a regular expression. To match a user that actually contains `re:`, use
     the prefix `literal:`.
     """
     return author(repo, subset, x)
 
 # experimental
 @predicate('wdir', safe=True)
 def wdir(repo, subset, x):
     # i18n: "wdir" is a keyword
     getargs(x, 0, 0, _("wdir takes no arguments"))
     if node.wdirrev in subset or isinstance(subset, fullreposet):
         return baseset([node.wdirrev])
     return baseset()
 
 # for internal use
 @predicate('_list', safe=True)
 def _list(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     # remove duplicates here. it's difficult for caller to deduplicate sets
     # because different symbols can point to the same rev.
     cl = repo.changelog
     ls = []
     seen = set()
     for t in s.split('\0'):
         try:
             # fast path for integer revision
             r = int(t)
             if str(r) != t or r not in cl:
                 raise ValueError
             revs = [r]
         except ValueError:
             revs = stringset(repo, subset, t)
 
         for r in revs:
             if r in seen:
                 continue
             if (r in subset
                 or r == node.nullrev and isinstance(subset, fullreposet)):
                 ls.append(r)
             seen.add(r)
     return baseset(ls)
 
 # for internal use
 @predicate('_intlist', safe=True)
 def _intlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     ls = [int(r) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 # for internal use
 @predicate('_hexlist', safe=True)
 def _hexlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     cl = repo.changelog
     ls = [cl.rev(node.bin(r)) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 methods = {
     "range": rangeset,
     "dagrange": dagrange,
     "string": stringset,
     "symbol": stringset,
     "and": andset,
     "or": orset,
     "not": notset,
     "difference": differenceset,
     "list": listset,
     "keyvalue": keyvaluepair,
     "func": func,
     "ancestor": ancestorspec,
     "parent": parentspec,
     "parentpost": p1,
 }
 
 def _matchonly(revs, bases):
     """
     >>> f = lambda *args: _matchonly(*map(parse, args))
     >>> f('ancestors(A)', 'not ancestors(B)')
     ('list', ('symbol', 'A'), ('symbol', 'B'))
     """
     if (revs is not None
         and revs[0] == 'func'
         and getstring(revs[1], _('not a symbol')) == 'ancestors'
         and bases is not None
         and bases[0] == 'not'
         and bases[1][0] == 'func'
         and getstring(bases[1][1], _('not a symbol')) == 'ancestors'):
         return ('list', revs[2], bases[1][2])
 
 def _optimize(x, small):
     if x is None:
         return 0, x
 
     smallbonus = 1
     if small:
         smallbonus = .5
 
     op = x[0]
     if op == 'minus':
         return _optimize(('and', x[1], ('not', x[2])), small)
     elif op == 'only':
         t = ('func', ('symbol', 'only'), ('list', x[1], x[2]))
         return _optimize(t, small)
     elif op == 'onlypost':
         return _optimize(('func', ('symbol', 'only'), x[1]), small)
     elif op == 'dagrangepre':
         return _optimize(('func', ('symbol', 'ancestors'), x[1]), small)
     elif op == 'dagrangepost':
         return _optimize(('func', ('symbol', 'descendants'), x[1]), small)
     elif op == 'rangeall':
         return _optimize(('range', ('string', '0'), ('string', 'tip')), small)
     elif op == 'rangepre':
         return _optimize(('range', ('string', '0'), x[1]), small)
     elif op == 'rangepost':
         return _optimize(('range', x[1], ('string', 'tip')), small)
     elif op == 'negate':
         s = getstring(x[1], _("can't negate that"))
         return _optimize(('string', '-' + s), small)
     elif op in 'string symbol negate':
         return smallbonus, x # single revisions are small
     elif op == 'and':
         wa, ta = _optimize(x[1], True)
         wb, tb = _optimize(x[2], True)
         w = min(wa, wb)
 
         # (::x and not ::y)/(not ::y and ::x) have a fast path
         tm = _matchonly(ta, tb) or _matchonly(tb, ta)
         if tm:
             return w, ('func', ('symbol', 'only'), tm)
 
         if tb is not None and tb[0] == 'not':
             return wa, ('difference', ta, tb[1])
 
         if wa > wb:
             return w, (op, tb, ta)
         return w, (op, ta, tb)
     elif op == 'or':
         # fast path for machine-generated expression, that is likely to have
         # lots of trivial revisions: 'a + b + c()' to '_list(a b) + c()'
         ws, ts, ss = [], [], []
         def flushss():
             if not ss:
                 return
             if len(ss) == 1:
                 w, t = ss[0]
             else:
                 s = '\0'.join(t[1] for w, t in ss)
                 y = ('func', ('symbol', '_list'), ('string', s))
                 w, t = _optimize(y, False)
             ws.append(w)
             ts.append(t)
             del ss[:]
         for y in x[1:]:
             w, t = _optimize(y, False)
             if t is not None and (t[0] == 'string' or t[0] == 'symbol'):
                 ss.append((w, t))
                 continue
             flushss()
             ws.append(w)
             ts.append(t)
         flushss()
         if len(ts) == 1:
             return ws[0], ts[0] # 'or' operation is fully optimized out
         # we can't reorder trees by weight because it would change the order.
         # ("sort(a + b)" == "sort(b + a)", but "a + b" != "b + a")
         #   ts = tuple(t for w, t in sorted(zip(ws, ts), key=lambda wt: wt[0]))
         return max(ws), (op,) + tuple(ts)
     elif op == 'not':
         # Optimize not public() to _notpublic() because we have a fast version
         if x[1] == ('func', ('symbol', 'public'), None):
             newsym = ('func', ('symbol', '_notpublic'), None)
             o = _optimize(newsym, not small)
             return o[0], o[1]
         else:
             o = _optimize(x[1], not small)
             return o[0], (op, o[1])
     elif op == 'parentpost':
         o = _optimize(x[1], small)
         return o[0], (op, o[1])
     elif op == 'group':
         return _optimize(x[1], small)
     elif op in 'dagrange range parent ancestorspec':
         if op == 'parent':
             # x^:y means (x^) : y, not x ^ (:y)
             post = ('parentpost', x[1])
             if x[2][0] == 'dagrangepre':
                 return _optimize(('dagrange', post, x[2][1]), small)
             elif x[2][0] == 'rangepre':
                 return _optimize(('range', post, x[2][1]), small)
 
         wa, ta = _optimize(x[1], small)
         wb, tb = _optimize(x[2], small)
         return wa + wb, (op, ta, tb)
     elif op == 'list':
         ws, ts = zip(*(_optimize(y, small) for y in x[1:]))
         return sum(ws), (op,) + ts
     elif op == 'func':
         f = getstring(x[1], _("not a symbol"))
         wa, ta = _optimize(x[2], small)
         if f in ("author branch closed date desc file grep keyword "
                  "outgoing user"):
             w = 10 # slow
         elif f in "modifies adds removes":
             w = 30 # slower
         elif f == "contains":
             w = 100 # very slow
         elif f == "ancestor":
             w = 1 * smallbonus
         elif f in "reverse limit first _intlist":
             w = 0
         elif f in "sort":
             w = 10 # assume most sorts look at changelog
         else:
             w = 1
         return w + wa, (op, x[1], ta)
     return 1, x
 
 def optimize(tree):
     _weight, newtree = _optimize(tree, small=True)
     return newtree
 
 # the set of valid characters for the initial letter of symbols in
 # alias declarations and definitions
 _aliassyminitletters = set(c for c in [chr(i) for i in xrange(256)]
                            if c.isalnum() or c in '._@$' or ord(c) > 127)
 
 def _parsewith(spec, lookup=None, syminitletters=None):
     """Generate a parse tree of given spec with given tokenizing options
 
     >>> _parsewith('foo($1)', syminitletters=_aliassyminitletters)
     ('func', ('symbol', 'foo'), ('symbol', '$1'))
     >>> _parsewith('$1')
     Traceback (most recent call last):
       ...
     ParseError: ("syntax error in revset '$1'", 0)
     >>> _parsewith('foo bar')
     Traceback (most recent call last):
       ...
     ParseError: ('invalid token', 4)
     """
     p = parser.parser(elements)
     tree, pos = p.parse(tokenize(spec, lookup=lookup,
                                  syminitletters=syminitletters))
     if pos != len(spec):
         raise error.ParseError(_('invalid token'), pos)
     return parser.simplifyinfixops(tree, ('list', 'or'))
 
 class _aliasrules(parser.basealiasrules):
     """Parsing and expansion rule set of revset aliases"""
     _section = _('revset alias')
 
     @staticmethod
     def _parse(spec):
         """Parse alias declaration/definition ``spec``
 
         This allows symbol names to use also ``$`` as an initial letter
         (for backward compatibility), and callers of this function should
         examine whether ``$`` is used also for unexpected symbols or not.
         """
         return _parsewith(spec, syminitletters=_aliassyminitletters)
 
     @staticmethod
     def _trygetfunc(tree):
         if tree[0] == 'func' and tree[1][0] == 'symbol':
             return tree[1][1], getlist(tree[2])
 
 def expandaliases(ui, tree, showwarning=None):
     aliases = _aliasrules.buildmap(ui.configitems('revsetalias'))
     tree = _aliasrules.expand(aliases, tree)
     if showwarning:
         # warn about problematic (but not referred) aliases
         for name, alias in sorted(aliases.iteritems()):
             if alias.error and not alias.warned:
                 showwarning(_('warning: %s\n') % (alias.error))
                 alias.warned = True
     return tree
 
 def foldconcat(tree):
     """Fold elements to be concatenated by `##`
     """
     if not isinstance(tree, tuple) or tree[0] in ('string', 'symbol'):
         return tree
     if tree[0] == '_concat':
         pending = [tree]
         l = []
         while pending:
             e = pending.pop()
             if e[0] == '_concat':
                 pending.extend(reversed(e[1:]))
             elif e[0] in ('string', 'symbol'):
                 l.append(e[1])
             else:
                 msg = _("\"##\" can't concatenate \"%s\" element") % (e[0])
                 raise error.ParseError(msg)
         return ('string', ''.join(l))
     else:
         return tuple(foldconcat(t) for t in tree)
 
 def parse(spec, lookup=None):
     return _parsewith(spec, lookup=lookup)
 
 def posttreebuilthook(tree, repo):
     # hook for extensions to execute code on the optimized tree
     pass
 
 def match(ui, spec, repo=None):
     if not spec:
         raise error.ParseError(_("empty query"))
     lookup = None
     if repo:
         lookup = repo.__contains__
     tree = parse(spec, lookup)
     return _makematcher(ui, tree, repo)
 
 def matchany(ui, specs, repo=None):
     """Create a matcher that will include any revisions matching one of the
     given specs"""
     if not specs:
         def mfunc(repo, subset=None):
             return baseset()
         return mfunc
     if not all(specs):
         raise error.ParseError(_("empty query"))
     lookup = None
     if repo:
         lookup = repo.__contains__
     if len(specs) == 1:
         tree = parse(specs[0], lookup)
     else:
         tree = ('or',) + tuple(parse(s, lookup) for s in specs)
     return _makematcher(ui, tree, repo)
 
 def _makematcher(ui, tree, repo):
     if ui:
         tree = expandaliases(ui, tree, showwarning=ui.warn)
     tree = foldconcat(tree)
     tree = optimize(tree)
     posttreebuilthook(tree, repo)
     def mfunc(repo, subset=None):
         if subset is None:
             subset = fullreposet(repo)
         if util.safehasattr(subset, 'isascending'):
             result = getset(repo, subset, tree)
         else:
             result = getset(repo, baseset(subset), tree)
         return result
     return mfunc
 
 def formatspec(expr, *args):
     '''
     This is a convenience function for using revsets internally, and
     escapes arguments appropriately. Aliases are intentionally ignored
     so that intended expression behavior isn't accidentally subverted.
 
     Supported arguments:
 
     %r = revset expression, parenthesized
     %d = int(arg), no quoting
     %s = string(arg), escaped and single-quoted
     %b = arg.branch(), escaped and single-quoted
     %n = hex(arg), single-quoted
     %% = a literal '%'
 
     Prefixing the type with 'l' specifies a parenthesized list of that type.
 
     >>> formatspec('%r:: and %lr', '10 or 11', ("this()", "that()"))
     '(10 or 11):: and ((this()) or (that()))'
     >>> formatspec('%d:: and not %d::', 10, 20)
     '10:: and not 20::'
     >>> formatspec('%ld or %ld', [], [1])
     "_list('') or 1"
     >>> formatspec('keyword(%s)', 'foo\\xe9')
     "keyword('foo\\\\xe9')"
     >>> b = lambda: 'default'
     >>> b.branch = b
     >>> formatspec('branch(%b)', b)
     "branch('default')"
     >>> formatspec('root(%ls)', ['a', 'b', 'c', 'd'])
     "root(_list('a\\x00b\\x00c\\x00d'))"
     '''
 
     def quote(s):
         return repr(str(s))
 
     def argtype(c, arg):
         if c == 'd':
             return str(int(arg))
         elif c == 's':
             return quote(arg)
         elif c == 'r':
             parse(arg) # make sure syntax errors are confined
             return '(%s)' % arg
         elif c == 'n':
             return quote(node.hex(arg))
         elif c == 'b':
             return quote(arg.branch())
 
     def listexp(s, t):
         l = len(s)
         if l == 0:
             return "_list('')"
         elif l == 1:
             return argtype(t, s[0])
         elif t == 'd':
             return "_intlist('%s')" % "\0".join(str(int(a)) for a in s)
         elif t == 's':
             return "_list('%s')" % "\0".join(s)
         elif t == 'n':
             return "_hexlist('%s')" % "\0".join(node.hex(a) for a in s)
         elif t == 'b':
             return "_list('%s')" % "\0".join(a.branch() for a in s)
 
         m = l // 2
         return '(%s or %s)' % (listexp(s[:m], t), listexp(s[m:], t))
 
     ret = ''
     pos = 0
     arg = 0
     while pos < len(expr):
         c = expr[pos]
         if c == '%':
             pos += 1
             d = expr[pos]
             if d == '%':
                 ret += d
             elif d in 'dsnbr':
                 ret += argtype(d, args[arg])
                 arg += 1
             elif d == 'l':
                 # a list of some type
                 pos += 1
                 d = expr[pos]
                 ret += listexp(list(args[arg]), d)
                 arg += 1
             else:
-                raise error.Abort('unexpected revspec format character %s' % d)
+                raise error.Abort(_('unexpected revspec format character %s')
+                                  % d)
         else:
             ret += c
         pos += 1
 
     return ret
 
 def prettyformat(tree):
     return parser.prettyformat(tree, ('string', 'symbol'))
 
 def depth(tree):
     if isinstance(tree, tuple):
         return max(map(depth, tree)) + 1
     else:
         return 0
 
 def funcsused(tree):
     if not isinstance(tree, tuple) or tree[0] in ('string', 'symbol'):
         return set()
     else:
         funcs = set()
         for s in tree[1:]:
             funcs |= funcsused(s)
         if tree[0] == 'func':
             funcs.add(tree[1][1])
         return funcs
 
 def _formatsetrepr(r):
     """Format an optional printable representation of a set
 
     ========  =================================
     type(r)   example
     ========  =================================
     tuple     ('<not %r>', other)
     str       '<branch closed>'
     callable  lambda: '<branch %r>' % sorted(b)
     object    other
     ========  =================================
     """
     if r is None:
         return ''
     elif isinstance(r, tuple):
         return r[0] % r[1:]
     elif isinstance(r, str):
         return r
     elif callable(r):
         return r()
     else:
         return repr(r)
 
 class abstractsmartset(object):
 
     def __nonzero__(self):
         """True if the smartset is not empty"""
         raise NotImplementedError()
 
     def __contains__(self, rev):
         """provide fast membership testing"""
         raise NotImplementedError()
 
     def __iter__(self):
         """iterate the set in the order it is supposed to be iterated"""
         raise NotImplementedError()
 
     # Attributes containing a function to perform a fast iteration in a given
     # direction. A smartset can have none, one, or both defined.
     #
     # Default value is None instead of a function returning None to avoid
     # initializing an iterator just for testing if a fast method exists.
     fastasc = None
     fastdesc = None
 
     def isascending(self):
         """True if the set will iterate in ascending order"""
         raise NotImplementedError()
 
     def isdescending(self):
         """True if the set will iterate in descending order"""
         raise NotImplementedError()
 
     def istopo(self):
         """True if the set will iterate in topographical order"""
         raise NotImplementedError()
 
     @util.cachefunc
     def min(self):
         """return the minimum element in the set"""
         if self.fastasc is not None:
             for r in self.fastasc():
                 return r
             raise ValueError('arg is an empty sequence')
         return min(self)
 
     @util.cachefunc
     def max(self):
         """return the maximum element in the set"""
         if self.fastdesc is not None:
             for r in self.fastdesc():
                 return r
             raise ValueError('arg is an empty sequence')
         return max(self)
 
     def first(self):
         """return the first element in the set (user iteration perspective)
 
         Return None if the set is empty"""
         raise NotImplementedError()
 
     def last(self):
         """return the last element in the set (user iteration perspective)
 
         Return None if the set is empty"""
         raise NotImplementedError()
 
     def __len__(self):
         """return the length of the smartsets
 
         This can be expensive on smartset that could be lazy otherwise."""
         raise NotImplementedError()
 
     def reverse(self):
         """reverse the expected iteration order"""
         raise NotImplementedError()
 
     def sort(self, reverse=True):
         """get the set to iterate in an ascending or descending order"""
         raise NotImplementedError()
 
     def __and__(self, other):
         """Returns a new object with the intersection of the two collections.
 
         This is part of the mandatory API for smartset."""
         if isinstance(other, fullreposet):
             return self
         return self.filter(other.__contains__, condrepr=other, cache=False)
 
     def __add__(self, other):
         """Returns a new object with the union of the two collections.
 
         This is part of the mandatory API for smartset."""
         return addset(self, other)
 
     def __sub__(self, other):
         """Returns a new object with the substraction of the two collections.
 
         This is part of the mandatory API for smartset."""
         c = other.__contains__
         return self.filter(lambda r: not c(r), condrepr=('<not %r>', other),
                            cache=False)
 
     def filter(self, condition, condrepr=None, cache=True):
         """Returns this smartset filtered by condition as a new smartset.
 
         `condition` is a callable which takes a revision number and returns a
         boolean. Optional `condrepr` provides a printable representation of
         the given `condition`.
 
         This is part of the mandatory API for smartset."""
         # builtin cannot be cached. but do not needs to
         if cache and util.safehasattr(condition, 'func_code'):
             condition = util.cachefunc(condition)
         return filteredset(self, condition, condrepr)
 
 class baseset(abstractsmartset):
     """Basic data structure that represents a revset and contains the basic
     operation that it should be able to perform.
 
     Every method in this class should be implemented by any smartset class.
     """
     def __init__(self, data=(), datarepr=None, istopo=False):
         """
         datarepr: a tuple of (format, obj, ...), a function or an object that
                   provides a printable representation of the given data.
         """
         self._ascending = None
         self._istopo = istopo
         if not isinstance(data, list):
             if isinstance(data, set):
                 self._set = data
                 # set has no order we pick one for stability purpose
                 self._ascending = True
             data = list(data)
         self._list = data
         self._datarepr = datarepr
 
     @util.propertycache
     def _set(self):
         return set(self._list)
 
     @util.propertycache
     def _asclist(self):
         asclist = self._list[:]
         asclist.sort()
         return asclist
 
     def __iter__(self):
         if self._ascending is None:
             return iter(self._list)
         elif self._ascending:
             return iter(self._asclist)
         else:
             return reversed(self._asclist)
 
     def fastasc(self):
         return iter(self._asclist)
 
     def fastdesc(self):
         return reversed(self._asclist)
 
     @util.propertycache
     def __contains__(self):
         return self._set.__contains__
 
     def __nonzero__(self):
         return bool(self._list)
 
     def sort(self, reverse=False):
         self._ascending = not bool(reverse)
         self._istopo = False
 
     def reverse(self):
         if self._ascending is None:
             self._list.reverse()
         else:
             self._ascending = not self._ascending
         self._istopo = False
 
     def __len__(self):
         return len(self._list)
 
     def isascending(self):
         """Returns True if the collection is ascending order, False if not.
 
         This is part of the mandatory API for smartset."""
         if len(self) <= 1:
             return True
         return self._ascending is not None and self._ascending
 
     def isdescending(self):
         """Returns True if the collection is descending order, False if not.
 
         This is part of the mandatory API for smartset."""
         if len(self) <= 1:
             return True
         return self._ascending is not None and not self._ascending
 
     def istopo(self):
         """Is the collection is in topographical order or not.
 
         This is part of the mandatory API for smartset."""
         if len(self) <= 1:
             return True
         return self._istopo
 
     def first(self):
         if self:
             if self._ascending is None:
                 return self._list[0]
             elif self._ascending:
                 return self._asclist[0]
             else:
                 return self._asclist[-1]
         return None
 
     def last(self):
         if self:
             if self._ascending is None:
                 return self._list[-1]
             elif self._ascending:
                 return self._asclist[-1]
             else:
                 return self._asclist[0]
         return None
 
     def __repr__(self):
         d = {None: '', False: '-', True: '+'}[self._ascending]
         s = _formatsetrepr(self._datarepr)
         if not s:
             l = self._list
             # if _list has been built from a set, it might have a different
             # order from one python implementation to another.
             # We fallback to the sorted version for a stable output.
             if self._ascending is not None:
                 l = self._asclist
             s = repr(l)
         return '<%s%s %s>' % (type(self).__name__, d, s)
 
 class filteredset(abstractsmartset):
     """Duck type for baseset class which iterates lazily over the revisions in
     the subset and contains a function which tests for membership in the
     revset
     """
     def __init__(self, subset, condition=lambda x: True, condrepr=None):
         """
         condition: a function that decide whether a revision in the subset
                    belongs to the revset or not.
         condrepr: a tuple of (format, obj, ...), a function or an object that
                   provides a printable representation of the given condition.
         """
         self._subset = subset
         self._condition = condition
         self._condrepr = condrepr
 
     def __contains__(self, x):
         return x in self._subset and self._condition(x)
 
     def __iter__(self):
         return self._iterfilter(self._subset)
 
     def _iterfilter(self, it):
         cond = self._condition
         for x in it:
             if cond(x):
                 yield x
 
     @property
     def fastasc(self):
         it = self._subset.fastasc
         if it is None:
             return None
         return lambda: self._iterfilter(it())
 
     @property
     def fastdesc(self):
         it = self._subset.fastdesc
         if it is None:
             return None
         return lambda: self._iterfilter(it())
 
     def __nonzero__(self):
         fast = None
         candidates = [self.fastasc if self.isascending() else None,
                       self.fastdesc if self.isdescending() else None,
                       self.fastasc,
                       self.fastdesc]
         for candidate in candidates:
             if candidate is not None:
                 fast = candidate
                 break
 
         if fast is not None:
             it = fast()
         else:
             it = self
 
         for r in it:
             return True
         return False
 
     def __len__(self):
         # Basic implementation to be changed in future patches.
         # until this gets improved, we use generator expression
         # here, since list compr is free to call __len__ again
         # causing infinite recursion
         l = baseset(r for r in self)
         return len(l)
 
     def sort(self, reverse=False):
         self._subset.sort(reverse=reverse)
 
     def reverse(self):
         self._subset.reverse()
 
     def isascending(self):
         return self._subset.isascending()
 
     def isdescending(self):
         return self._subset.isdescending()
 
     def istopo(self):
         return self._subset.istopo()
 
     def first(self):
         for x in self:
             return x
         return None
 
     def last(self):
         it = None
         if self.isascending():
             it = self.fastdesc
         elif self.isdescending():
             it = self.fastasc
         if it is not None:
             for x in it():
                 return x
             return None #empty case
         else:
             x = None
             for x in self:
                 pass
             return x
 
     def __repr__(self):
         xs = [repr(self._subset)]
         s = _formatsetrepr(self._condrepr)
         if s:
             xs.append(s)
         return '<%s %s>' % (type(self).__name__, ', '.join(xs))
 
 def _iterordered(ascending, iter1, iter2):
     """produce an ordered iteration from two iterators with the same order
 
     The ascending is used to indicated the iteration direction.
     """
     choice = max
     if ascending:
         choice = min
 
     val1 = None
     val2 = None
     try:
         # Consume both iterators in an ordered way until one is empty
         while True:
             if val1 is None:
                 val1 = next(iter1)
             if val2 is None:
                 val2 = next(iter2)
             n = choice(val1, val2)
             yield n
             if val1 == n:
                 val1 = None
             if val2 == n:
                 val2 = None
     except StopIteration:
         # Flush any remaining values and consume the other one
         it = iter2
         if val1 is not None:
             yield val1
             it = iter1
         elif val2 is not None:
             # might have been equality and both are empty
             yield val2
         for val in it:
             yield val
 
 class addset(abstractsmartset):
     """Represent the addition of two sets
 
     Wrapper structure for lazily adding two structures without losing much
     performance on the __contains__ method
 
     If the ascending attribute is set, that means the two structures are
     ordered in either an ascending or descending way. Therefore, we can add
     them maintaining the order by iterating over both at the same time
 
     >>> xs = baseset([0, 3, 2])
     >>> ys = baseset([5, 2, 4])
 
     >>> rs = addset(xs, ys)
     >>> bool(rs), 0 in rs, 1 in rs, 5 in rs, rs.first(), rs.last()
     (True, True, False, True, 0, 4)
     >>> rs = addset(xs, baseset([]))
     >>> bool(rs), 0 in rs, 1 in rs, rs.first(), rs.last()
     (True, True, False, 0, 2)
     >>> rs = addset(baseset([]), baseset([]))
     >>> bool(rs), 0 in rs, rs.first(), rs.last()
     (False, False, None, None)
 
     iterate unsorted:
     >>> rs = addset(xs, ys)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs)  # without _genlist
     [0, 3, 2, 5, 4]
     >>> assert not rs._genlist
     >>> len(rs)
     5
     >>> [x for x in rs]  # with _genlist
     [0, 3, 2, 5, 4]
     >>> assert rs._genlist
 
     iterate ascending:
     >>> rs = addset(xs, ys, ascending=True)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs), list(x for x in rs.fastasc())  # without _asclist
     ([0, 2, 3, 4, 5], [0, 2, 3, 4, 5])
     >>> assert not rs._asclist
     >>> len(rs)
     5
     >>> [x for x in rs], [x for x in rs.fastasc()]
     ([0, 2, 3, 4, 5], [0, 2, 3, 4, 5])
     >>> assert rs._asclist
 
     iterate descending:
     >>> rs = addset(xs, ys, ascending=False)
     >>> # (use generator because pypy could call len())
     >>> list(x for x in rs), list(x for x in rs.fastdesc())  # without _asclist
     ([5, 4, 3, 2, 0], [5, 4, 3, 2, 0])
     >>> assert not rs._asclist
     >>> len(rs)
     5
     >>> [x for x in rs], [x for x in rs.fastdesc()]
     ([5, 4, 3, 2, 0], [5, 4, 3, 2, 0])
     >>> assert rs._asclist
 
     iterate ascending without fastasc:
     >>> rs = addset(xs, generatorset(ys), ascending=True)
     >>> assert rs.fastasc is None
     >>> [x for x in rs]
     [0, 2, 3, 4, 5]
 
     iterate descending without fastdesc:
     >>> rs = addset(generatorset(xs), ys, ascending=False)
     >>> assert rs.fastdesc is None
     >>> [x for x in rs]
     [5, 4, 3, 2, 0]
     """
     def __init__(self, revs1, revs2, ascending=None):
         self._r1 = revs1
         self._r2 = revs2
         self._iter = None
         self._ascending = ascending
         self._genlist = None
         self._asclist = None
 
     def __len__(self):
         return len(self._list)
 
     def __nonzero__(self):
         return bool(self._r1) or bool(self._r2)
 
     @util.propertycache
     def _list(self):
         if not self._genlist:
             self._genlist = baseset(iter(self))
         return self._genlist
 
     def __iter__(self):
         """Iterate over both collections without repeating elements
 
         If the ascending attribute is not set, iterate over the first one and
         then over the second one checking for membership on the first one so we
         dont yield any duplicates.
 
         If the ascending attribute is set, iterate over both collections at the
         same time, yielding only one value at a time in the given order.
         """
         if self._ascending is None:
             if self._genlist:
                 return iter(self._genlist)
             def arbitraryordergen():
                 for r in self._r1:
                     yield r
                 inr1 = self._r1.__contains__
                 for r in self._r2:
                     if not inr1(r):
                         yield r
             return arbitraryordergen()
         # try to use our own fast iterator if it exists
         self._trysetasclist()
         if self._ascending:
             attr = 'fastasc'
         else:
             attr = 'fastdesc'
         it = getattr(self, attr)
         if it is not None:
             return it()
         # maybe half of the component supports fast
         # get iterator for _r1
         iter1 = getattr(self._r1, attr)
         if iter1 is None:
             # let's avoid side effect (not sure it matters)
             iter1 = iter(sorted(self._r1, reverse=not self._ascending))
         else:
             iter1 = iter1()
         # get iterator for _r2
         iter2 = getattr(self._r2, attr)
         if iter2 is None:
             # let's avoid side effect (not sure it matters)
             iter2 = iter(sorted(self._r2, reverse=not self._ascending))
         else:
             iter2 = iter2()
         return _iterordered(self._ascending, iter1, iter2)
 
     def _trysetasclist(self):
         """populate the _asclist attribute if possible and necessary"""
         if self._genlist is not None and self._asclist is None:
             self._asclist = sorted(self._genlist)
 
     @property
     def fastasc(self):
         self._trysetasclist()
         if self._asclist is not None:
             return self._asclist.__iter__
         iter1 = self._r1.fastasc
         iter2 = self._r2.fastasc
         if None in (iter1, iter2):
             return None
         return lambda: _iterordered(True, iter1(), iter2())
 
     @property
     def fastdesc(self):
         self._trysetasclist()
         if self._asclist is not None:
             return self._asclist.__reversed__
         iter1 = self._r1.fastdesc
         iter2 = self._r2.fastdesc
         if None in (iter1, iter2):
             return None
         return lambda: _iterordered(False, iter1(), iter2())
 
     def __contains__(self, x):
         return x in self._r1 or x in self._r2
 
     def sort(self, reverse=False):
         """Sort the added set
 
         For this we use the cached list with all the generated values and if we
         know they are ascending or descending we can sort them in a smart way.
         """
         self._ascending = not reverse
 
     def isascending(self):
         return self._ascending is not None and self._ascending
 
     def isdescending(self):
         return self._ascending is not None and not self._ascending
 
     def istopo(self):
         # not worth the trouble asserting if the two sets combined are still
         # in topographical order. Use the sort() predicate to explicitly sort
         # again instead.
         return False
 
     def reverse(self):
         if self._ascending is None:
             self._list.reverse()
         else:
             self._ascending = not self._ascending
 
     def first(self):
         for x in self:
             return x
         return None
 
     def last(self):
         self.reverse()
         val = self.first()
         self.reverse()
         return val
 
     def __repr__(self):
         d = {None: '', False: '-', True: '+'}[self._ascending]
         return '<%s%s %r, %r>' % (type(self).__name__, d, self._r1, self._r2)
 
 class generatorset(abstractsmartset):
     """Wrap a generator for lazy iteration
 
     Wrapper structure for generators that provides lazy membership and can
     be iterated more than once.
     When asked for membership it generates values until either it finds the
     requested one or has gone through all the elements in the generator
     """
     def __init__(self, gen, iterasc=None):
         """
         gen: a generator producing the values for the generatorset.
         """
         self._gen = gen
         self._asclist = None
         self._cache = {}
         self._genlist = []
         self._finished = False
         self._ascending = True
         if iterasc is not None:
             if iterasc:
                 self.fastasc = self._iterator
                 self.__contains__ = self._asccontains
             else:
                 self.fastdesc = self._iterator
                 self.__contains__ = self._desccontains
 
     def __nonzero__(self):
         # Do not use 'for r in self' because it will enforce the iteration
         # order (default ascending), possibly unrolling a whole descending
         # iterator.
         if self._genlist:
             return True
         for r in self._consumegen():
             return True
         return False
 
     def __contains__(self, x):
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
 
         self._cache[x] = False
         return False
 
     def _asccontains(self, x):
         """version of contains optimised for ascending generator"""
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
             if l > x:
                 break
 
         self._cache[x] = False
         return False
 
     def _desccontains(self, x):
         """version of contains optimised for descending generator"""
         if x in self._cache:
             return self._cache[x]
 
         # Use new values only, as existing values would be cached.
         for l in self._consumegen():
             if l == x:
                 return True
             if l < x:
                 break
 
         self._cache[x] = False
         return False
 
     def __iter__(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         if it is not None:
             return it()
         # we need to consume the iterator
         for x in self._consumegen():
             pass
         # recall the same code
         return iter(self)
 
     def _iterator(self):
         if self._finished:
             return iter(self._genlist)
 
         # We have to use this complex iteration strategy to allow multiple
         # iterations at the same time. We need to be able to catch revision
         # removed from _consumegen and added to genlist in another instance.
         #
         # Getting rid of it would provide an about 15% speed up on this
         # iteration.
         genlist = self._genlist
         nextrev = self._consumegen().next
         _len = len # cache global lookup
         def gen():
             i = 0
             while True:
                 if i < _len(genlist):
                     yield genlist[i]
                 else:
                     yield nextrev()
                 i += 1
         return gen()
 
     def _consumegen(self):
         cache = self._cache
         genlist = self._genlist.append
         for item in self._gen:
             cache[item] = True
             genlist(item)
             yield item
         if not self._finished:
             self._finished = True
             asc = self._genlist[:]
             asc.sort()
             self._asclist = asc
             self.fastasc = asc.__iter__
             self.fastdesc = asc.__reversed__
 
     def __len__(self):
         for x in self._consumegen():
             pass
         return len(self._genlist)
 
     def sort(self, reverse=False):
         self._ascending = not reverse
 
     def reverse(self):
         self._ascending = not self._ascending
 
     def isascending(self):
         return self._ascending
 
     def isdescending(self):
         return not self._ascending
 
     def istopo(self):
         # not worth the trouble asserting if the two sets combined are still
         # in topographical order. Use the sort() predicate to explicitly sort
         # again instead.
         return False
 
     def first(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         if it is None:
             # we need to consume all and try again
             for x in self._consumegen():
                 pass
             return self.first()
         return next(it(), None)
 
     def last(self):
         if self._ascending:
             it = self.fastdesc
         else:
             it = self.fastasc
         if it is None:
             # we need to consume all and try again
             for x in self._consumegen():
                 pass
             return self.first()
         return next(it(), None)
 
     def __repr__(self):
         d = {False: '-', True: '+'}[self._ascending]
         return '<%s%s>' % (type(self).__name__, d)
 
 class spanset(abstractsmartset):
     """Duck type for baseset class which represents a range of revisions and
     can work lazily and without having all the range in memory
 
     Note that spanset(x, y) behave almost like xrange(x, y) except for two
     notable points:
     - when x < y it will be automatically descending,
     - revision filtered with this repoview will be skipped.
 
     """
     def __init__(self, repo, start=0, end=None):
         """
         start: first revision included the set
                (default to 0)
         end:   first revision excluded (last+1)
                (default to len(repo)
 
         Spanset will be descending if `end` < `start`.
         """
         if end is None:
             end = len(repo)
         self._ascending = start <= end
         if not self._ascending:
             start, end = end + 1, start +1
         self._start = start
         self._end = end
         self._hiddenrevs = repo.changelog.filteredrevs
 
     def sort(self, reverse=False):
         self._ascending = not reverse
 
     def reverse(self):
         self._ascending = not self._ascending
 
     def istopo(self):
         # not worth the trouble asserting if the two sets combined are still
         # in topographical order. Use the sort() predicate to explicitly sort
         # again instead.
         return False
 
     def _iterfilter(self, iterrange):
         s = self._hiddenrevs
         for r in iterrange:
             if r not in s:
                 yield r
 
     def __iter__(self):
         if self._ascending:
             return self.fastasc()
         else:
             return self.fastdesc()
 
     def fastasc(self):
         iterrange = xrange(self._start, self._end)
         if self._hiddenrevs:
             return self._iterfilter(iterrange)
         return iter(iterrange)
 
     def fastdesc(self):
         iterrange = xrange(self._end - 1, self._start - 1, -1)
         if self._hiddenrevs:
             return self._iterfilter(iterrange)
         return iter(iterrange)
 
     def __contains__(self, rev):
         hidden = self._hiddenrevs
         return ((self._start <= rev < self._end)
                 and not (hidden and rev in hidden))
 
     def __nonzero__(self):
         for r in self:
             return True
         return False
 
     def __len__(self):
         if not self._hiddenrevs:
             return abs(self._end - self._start)
         else:
             count = 0
             start = self._start
             end = self._end
             for rev in self._hiddenrevs:
                 if (end < rev <= start) or (start <= rev < end):
                     count += 1
             return abs(self._end - self._start) - count
 
     def isascending(self):
         return self._ascending
 
     def isdescending(self):
         return not self._ascending
 
     def first(self):
         if self._ascending:
             it = self.fastasc
         else:
             it = self.fastdesc
         for x in it():
             return x
         return None
 
     def last(self):
         if self._ascending:
             it = self.fastdesc
         else:
             it = self.fastasc
         for x in it():
             return x
         return None
 
     def __repr__(self):
         d = {False: '-', True: '+'}[self._ascending]
         return '<%s%s %d:%d>' % (type(self).__name__, d,
                                  self._start, self._end - 1)
 
 class fullreposet(spanset):
     """a set containing all revisions in the repo
 
     This class exists to host special optimization and magic to handle virtual
     revisions such as "null".
     """
 
     def __init__(self, repo):
         super(fullreposet, self).__init__(repo)
 
     def __and__(self, other):
         """As self contains the whole repo, all of the other set should also be
         in self. Therefore `self & other = other`.
 
         This boldly assumes the other contains valid revs only.
         """
         # other not a smartset, make is so
         if not util.safehasattr(other, 'isascending'):
             # filter out hidden revision
             # (this boldly assumes all smartset are pure)
             #
             # `other` was used with "&", let's assume this is a set like
             # object.
             other = baseset(other - self._hiddenrevs)
 
         # XXX As fullreposet is also used as bootstrap, this is wrong.
         #
         # With a giveme312() revset returning [3,1,2], this makes
         #   'hg log -r "giveme312()"' -> 1, 2, 3 (wrong)
         # We cannot just drop it because other usage still need to sort it:
         #   'hg log -r "all() and giveme312()"' -> 1, 2, 3 (right)
         #
         # There is also some faulty revset implementations that rely on it
         # (eg: children as of its state in e8075329c5fb)
         #
         # When we fix the two points above we can move this into the if clause
         other.sort(reverse=self.isdescending())
         return other
 
 def prettyformatset(revs):
     lines = []
     rs = repr(revs)
     p = 0
     while p < len(rs):
         q = rs.find('<', p + 1)
         if q < 0:
             q = len(rs)
         l = rs.count('<', 0, p) - rs.count('>', 0, p)
         assert l >= 0
         lines.append((l, rs[p:q].rstrip()))
         p = q
     return '\n'.join('  ' * l + s for l, s in lines)
 
 def loadpredicate(ui, extname, registrarobj):
     """Load revset predicates from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         symbols[name] = func
         if func._safe:
             safesymbols.add(name)
 
 # load built-in predicates explicitly to setup safesymbols
 loadpredicate(None, None, predicate)
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

mercurial/scmutil.py

@@ -1,1402 +1,1404 b''
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright 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 __future__ import absolute_import
 
 import contextlib
 import errno
 import glob
 import hashlib
 import os
 import re
 import shutil
 import stat
 import tempfile
 import threading
 
 from .i18n import _
 from .node import wdirrev
 from . import (
     encoding,
     error,
     match as matchmod,
     osutil,
     pathutil,
     phases,
     revset,
     similar,
     util,
 )
 
 if os.name == 'nt':
     from . import scmwindows as scmplatform
 else:
     from . import scmposix as scmplatform
 
 systemrcpath = scmplatform.systemrcpath
 userrcpath = scmplatform.userrcpath
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
 
     missing = set()
 
     for subpath in ctx2.substate:
         if subpath not in ctx1.substate:
             del subpaths[subpath]
             missing.add(subpath)
 
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
     # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,
     # status and diff will have an accurate result when it does
     # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared
     # against itself.
     for subpath in missing:
         yield subpath, ctx2.nullsub(subpath, ctx1)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             if n not in repo:
                 # discovery should not have included the filtered revision,
                 # we have to explicitly exclude it until discovery is cleanup.
                 continue
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise error.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise error.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise error.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise error.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise error.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise error.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 def filteredhash(repo, maxrev):
     """build hash of filtered revisions in the current repoview.
 
     Multiple caches perform up-to-date validation by checking that the
     tiprev and tipnode stored in the cache file match the current repository.
     However, this is not sufficient for validating repoviews because the set
     of revisions in the view may change without the repository tiprev and
     tipnode changing.
 
     This function hashes all the revs filtered from the view and returns
     that SHA-1 digest.
     """
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
     key = None
     revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
     if revs:
         s = hashlib.sha1()
         for rev in revs:
             s.update('%s;' % rev)
         key = s.digest()
     return key
 
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def tryread(self, path):
         '''gracefully return an empty string for missing files'''
         try:
             return self.read(path)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
         return ""
 
     def tryreadlines(self, path, mode='rb'):
         '''gracefully return an empty array for missing files'''
         try:
             return self.readlines(path, mode=mode)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
         return []
 
     def open(self, path, mode="r", text=False, atomictemp=False,
              notindexed=False, backgroundclose=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
         '''
         self.open = self.__call__
         return self.__call__(path, mode, text, atomictemp, notindexed,
                              backgroundclose=backgroundclose)
 
     def read(self, path):
         with self(path, 'rb') as fp:
             return fp.read()
 
     def readlines(self, path, mode='rb'):
         with self(path, mode=mode) as fp:
             return fp.readlines()
 
     def write(self, path, data, backgroundclose=False):
         with self(path, 'wb', backgroundclose=backgroundclose) as fp:
             return fp.write(data)
 
     def writelines(self, path, data, mode='wb', notindexed=False):
         with self(path, mode=mode, notindexed=notindexed) as fp:
             return fp.writelines(data)
 
     def append(self, path, data):
         with self(path, 'ab') as fp:
             return fp.write(data)
 
     def basename(self, path):
         """return base element of a path (as os.path.basename would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.basename(path)
 
     def chmod(self, path, mode):
         return os.chmod(self.join(path), mode)
 
     def dirname(self, path):
         """return dirname element of a path (as os.path.dirname would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.dirname(path)
 
     def exists(self, path=None):
         return os.path.exists(self.join(path))
 
     def fstat(self, fp):
         return util.fstat(fp)
 
     def isdir(self, path=None):
         return os.path.isdir(self.join(path))
 
     def isfile(self, path=None):
         return os.path.isfile(self.join(path))
 
     def islink(self, path=None):
         return os.path.islink(self.join(path))
 
     def isfileorlink(self, path=None):
         '''return whether path is a regular file or a symlink
 
         Unlike isfile, this doesn't follow symlinks.'''
         try:
             st = self.lstat(path)
         except OSError:
             return False
         mode = st.st_mode
         return stat.S_ISREG(mode) or stat.S_ISLNK(mode)
 
     def reljoin(self, *paths):
         """join various elements of a path together (as os.path.join would do)
 
         The vfs base is not injected so that path stay relative. This exists
         to allow handling of strange encoding if needed."""
         return os.path.join(*paths)
 
     def split(self, path):
         """split top-most element of a path (as os.path.split would do)
 
         This exists to allow handling of strange encoding if needed."""
         return os.path.split(path)
 
     def lexists(self, path=None):
         return os.path.lexists(self.join(path))
 
     def lstat(self, path=None):
         return os.lstat(self.join(path))
 
     def listdir(self, path=None):
         return os.listdir(self.join(path))
 
     def makedir(self, path=None, notindexed=True):
         return util.makedir(self.join(path), notindexed)
 
     def makedirs(self, path=None, mode=None):
         return util.makedirs(self.join(path), mode)
 
     def makelock(self, info, path):
         return util.makelock(info, self.join(path))
 
     def mkdir(self, path=None):
         return os.mkdir(self.join(path))
 
     def mkstemp(self, suffix='', prefix='tmp', dir=None, text=False):
         fd, name = tempfile.mkstemp(suffix=suffix, prefix=prefix,
                                     dir=self.join(dir), text=text)
         dname, fname = util.split(name)
         if dir:
             return fd, os.path.join(dir, fname)
         else:
             return fd, fname
 
     def readdir(self, path=None, stat=None, skip=None):
         return osutil.listdir(self.join(path), stat, skip)
 
     def readlock(self, path):
         return util.readlock(self.join(path))
 
     def rename(self, src, dst, checkambig=False):
         """Rename from src to dst
 
         checkambig argument is used with util.filestat, and is useful
         only if destination file is guarded by any lock
         (e.g. repo.lock or repo.wlock).
         """
         dstpath = self.join(dst)
         oldstat = checkambig and util.filestat(dstpath)
         if oldstat and oldstat.stat:
             ret = util.rename(self.join(src), dstpath)
             newstat = util.filestat(dstpath)
             if newstat.isambig(oldstat):
                 # stat of renamed file is ambiguous to original one
                 advanced = (oldstat.stat.st_mtime + 1) & 0x7fffffff
                 os.utime(dstpath, (advanced, advanced))
             return ret
         return util.rename(self.join(src), dstpath)
 
     def readlink(self, path):
         return os.readlink(self.join(path))
 
     def removedirs(self, path=None):
         """Remove a leaf directory and all empty intermediate ones
         """
         return util.removedirs(self.join(path))
 
     def rmtree(self, path=None, ignore_errors=False, forcibly=False):
         """Remove a directory tree recursively
 
         If ``forcibly``, this tries to remove READ-ONLY files, too.
         """
         if forcibly:
             def onerror(function, path, excinfo):
                 if function is not os.remove:
                     raise
                 # read-only files cannot be unlinked under Windows
                 s = os.stat(path)
                 if (s.st_mode & stat.S_IWRITE) != 0:
                     raise
                 os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
                 os.remove(path)
         else:
             onerror = None
         return shutil.rmtree(self.join(path),
                              ignore_errors=ignore_errors, onerror=onerror)
 
     def setflags(self, path, l, x):
         return util.setflags(self.join(path), l, x)
 
     def stat(self, path=None):
         return os.stat(self.join(path))
 
     def unlink(self, path=None):
         return util.unlink(self.join(path))
 
     def unlinkpath(self, path=None, ignoremissing=False):
         return util.unlinkpath(self.join(path), ignoremissing)
 
     def utime(self, path=None, t=None):
         return os.utime(self.join(path), t)
 
     def walk(self, path=None, onerror=None):
         """Yield (dirpath, dirs, files) tuple for each directories under path
 
         ``dirpath`` is relative one from the root of this vfs. This
         uses ``os.sep`` as path separator, even you specify POSIX
         style ``path``.
 
         "The root of this vfs" is represented as empty ``dirpath``.
         """
         root = os.path.normpath(self.join(None))
         # when dirpath == root, dirpath[prefixlen:] becomes empty
         # because len(dirpath) < prefixlen.
         prefixlen = len(pathutil.normasprefix(root))
         for dirpath, dirs, files in os.walk(self.join(path), onerror=onerror):
             yield (dirpath[prefixlen:], dirs, files)
 
     @contextlib.contextmanager
     def backgroundclosing(self, ui, expectedcount=-1):
         """Allow files to be closed asynchronously.
 
         When this context manager is active, ``backgroundclose`` can be passed
         to ``__call__``/``open`` to result in the file possibly being closed
         asynchronously, on a background thread.
         """
         # This is an arbitrary restriction and could be changed if we ever
         # have a use case.
         vfs = getattr(self, 'vfs', self)
         if getattr(vfs, '_backgroundfilecloser', None):
-            raise error.Abort('can only have 1 active background file closer')
+            raise error.Abort(
+                _('can only have 1 active background file closer'))
 
         with backgroundfilecloser(ui, expectedcount=expectedcount) as bfc:
             try:
                 vfs._backgroundfilecloser = bfc
                 yield bfc
             finally:
                 vfs._backgroundfilecloser = None
 
 class vfs(abstractvfs):
     '''Operate files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True, expandpath=False, realpath=False):
         if expandpath:
             base = util.expandpath(base)
         if realpath:
             base = os.path.realpath(base)
         self.base = base
         self.mustaudit = audit
         self.createmode = None
         self._trustnlink = None
 
     @property
     def mustaudit(self):
         return self._audit
 
     @mustaudit.setter
     def mustaudit(self, onoff):
         self._audit = onoff
         if onoff:
             self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     @util.propertycache
     def _chmod(self):
         return util.checkexec(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None or not self._chmod:
             return
         os.chmod(name, self.createmode & 0o666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False,
                  notindexed=False, backgroundclose=False, checkambig=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
 
         If ``backgroundclose`` is passed, the file may be closed asynchronously.
         It can only be used if the ``self.backgroundclosing()`` context manager
         is active. This should only be specified if the following criteria hold:
 
         1. There is a potential for writing thousands of files. Unless you
            are writing thousands of files, the performance benefits of
            asynchronously closing files is not realized.
         2. Files are opened exactly once for the ``backgroundclosing``
            active duration and are therefore free of race conditions between
            closing a file on a background thread and reopening it. (If the
            file were opened multiple times, there could be unflushed data
            because the original file handle hasn't been flushed/closed yet.)
 
         ``checkambig`` argument is passed to atomictemplfile (valid
         only for writing), and is useful only if target file is
         guarded by any lock (e.g. repo.lock or repo.wlock).
         '''
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise error.Abort("%s: %r" % (r, path))
         self.audit(path)
         f = self.join(path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ('r', 'rb'):
             dirname, basename = util.split(f)
             # If basename is empty, then the path is malformed because it points
             # to a directory. Let the posixfile() call below raise IOError.
             if basename:
                 if atomictemp:
                     util.makedirs(dirname, self.createmode, notindexed)
                     return util.atomictempfile(f, mode, self.createmode,
                                                checkambig=checkambig)
                 try:
                     if 'w' in mode:
                         util.unlink(f)
                         nlink = 0
                     else:
                         # nlinks() may behave differently for files on Windows
                         # shares if the file is open.
                         with util.posixfile(f):
                             nlink = util.nlinks(f)
                             if nlink < 1:
                                 nlink = 2 # force mktempcopy (issue1922)
                 except (OSError, IOError) as e:
                     if e.errno != errno.ENOENT:
                         raise
                     nlink = 0
                     util.makedirs(dirname, self.createmode, notindexed)
                 if nlink > 0:
                     if self._trustnlink is None:
                         self._trustnlink = nlink > 1 or util.checknlink(f)
                     if nlink > 1 or not self._trustnlink:
                         util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
 
         if backgroundclose:
             if not self._backgroundfilecloser:
-                raise error.Abort('backgroundclose can only be used when a '
+                raise error.Abort(_('backgroundclose can only be used when a '
                                   'backgroundclosing context manager is active')
+                                  )
 
             fp = delayclosedfile(fp, self._backgroundfilecloser)
 
         return fp
 
     def symlink(self, src, dst):
         self.audit(dst)
         linkname = self.join(dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         util.makedirs(os.path.dirname(linkname), self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError as err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             self.write(dst, src)
 
     def join(self, path, *insidef):
         if path:
             return os.path.join(self.base, path, *insidef)
         else:
             return self.base
 
 opener = vfs
 
 class auditvfs(object):
     def __init__(self, vfs):
         self.vfs = vfs
 
     @property
     def mustaudit(self):
         return self.vfs.mustaudit
 
     @mustaudit.setter
     def mustaudit(self, onoff):
         self.vfs.mustaudit = onoff
 
 class filtervfs(abstractvfs, auditvfs):
     '''Wrapper vfs for filtering filenames with a function.'''
 
     def __init__(self, vfs, filter):
         auditvfs.__init__(self, vfs)
         self._filter = filter
 
     def __call__(self, path, *args, **kwargs):
         return self.vfs(self._filter(path), *args, **kwargs)
 
     def join(self, path, *insidef):
         if path:
             return self.vfs.join(self._filter(self.vfs.reljoin(path, *insidef)))
         else:
             return self.vfs.join(path)
 
 filteropener = filtervfs
 
 class readonlyvfs(abstractvfs, auditvfs):
     '''Wrapper vfs preventing any writing.'''
 
     def __init__(self, vfs):
         auditvfs.__init__(self, vfs)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb'):
-            raise error.Abort('this vfs is read only')
+            raise error.Abort(_('this vfs is read only'))
         return self.vfs(path, mode, *args, **kw)
 
     def join(self, path, *insidef):
         return self.vfs.join(path, *insidef)
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = []
     defaultpath = os.path.join(util.datapath, 'default.d')
     if os.path.isdir(defaultpath):
         for f, kind in osutil.listdir(defaultpath):
             if f.endswith('.rc'):
                 path.append(os.path.join(defaultpath, f))
     path.extend(systemrcpath())
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 def intrev(rev):
     """Return integer for a given revision that can be used in comparison or
     arithmetic operation"""
     if rev is None:
         return wdirrev
     return rev
 
 def revsingle(repo, revspec, default='.'):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if not l:
         raise error.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def _pairspec(revspec):
     tree = revset.parse(revspec)
     tree = revset.optimize(tree)  # fix up "x^:y" -> "(x^):y"
     return tree and tree[0] in ('range', 'rangepre', 'rangepost', 'rangeall')
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise error.Abort(_('empty revision range'))
     if (first == second and len(revs) >= 2
         and not all(revrange(repo, [r]) for r in revs)):
         raise error.Abort(_('empty revision on one side of range'))
 
     # if top-level is range expression, the result must always be a pair
     if first == second and len(revs) == 1 and not _pairspec(revs[0]):
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
     allspecs = []
     for spec in revs:
         if isinstance(spec, int):
             spec = revset.formatspec('rev(%d)', spec)
         allspecs.append(spec)
     m = revset.matchany(repo.ui, allspecs, repo)
     return m(repo)
 
 def meaningfulparents(repo, ctx):
     """Return list of meaningful (or all if debug) parentrevs for rev.
 
     For merges (two non-nullrev revisions) both parents are meaningful.
     Otherwise the first parent revision is considered meaningful if it
     is not the preceding revision.
     """
     parents = ctx.parents()
     if len(parents) > 1:
         return parents
     if repo.ui.debugflag:
         return [parents[0], repo['null']]
     if parents[0].rev() >= intrev(ctx.rev()) - 1:
         return []
     return parents
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=(), opts=None, globbed=False, default='relpath',
                  badfn=None):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches, unless an alternate badfn callback
     is provided.'''
     if pats == ("",):
         pats = []
     if opts is None:
         opts = {}
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     def bad(f, msg):
         ctx.repo().ui.warn("%s: %s\n" % (m.rel(f), msg))
 
     if badfn is None:
         badfn = bad
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                   default, listsubrepos=opts.get('subrepos'), badfn=badfn)
 
     if m.always():
         pats = []
     return m, pats
 
 def match(ctx, pats=(), opts=None, globbed=False, default='relpath',
           badfn=None):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default, badfn=badfn)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files, badfn=None):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files, badfn=badfn)
 
 def origpath(ui, repo, filepath):
     '''customize where .orig files are created
 
     Fetch user defined path from config file: [ui] origbackuppath = <path>
     Fall back to default (filepath) if not specified
     '''
     origbackuppath = ui.config('ui', 'origbackuppath', None)
     if origbackuppath is None:
         return filepath + ".orig"
 
     filepathfromroot = os.path.relpath(filepath, start=repo.root)
     fullorigpath = repo.wjoin(origbackuppath, filepathfromroot)
 
     origbackupdir = repo.vfs.dirname(fullorigpath)
     if not repo.vfs.exists(origbackupdir):
         ui.note(_('creating directory: %s\n') % origbackupdir)
         util.makedirs(origbackupdir)
 
     return fullorigpath + ".orig"
 
 def addremove(repo, matcher, prefix, opts=None, dry_run=None, similarity=None):
     if opts is None:
         opts = {}
     m = matcher
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     def matchessubrepo(matcher, subpath):
         if matcher.exact(subpath):
             return True
         for f in matcher.files():
             if f.startswith(subpath):
                 return True
         return False
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         if opts.get('subrepos') or matchessubrepo(m, subpath):
             sub = wctx.sub(subpath)
             try:
                 submatch = matchmod.subdirmatcher(subpath, m)
                 if sub.addremove(submatch, prefix, opts, dry_run, similarity):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(_("skipping missing subrepository: %s\n")
                                  % join(subpath))
 
     rejected = []
     def badfn(f, msg):
         if f in m.files():
             m.bad(f, msg)
         rejected.append(f)
 
     badmatch = matchmod.badmatch(m, badfn)
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo,
                                                                     badmatch)
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _('adding %s\n') % m.uipath(abs)
             else:
                 status = _('removing %s\n') % m.uipath(abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files, badfn=lambda x, y: rejected.append(x))
     rejected = []
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
                                 full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     with repo.wlock():
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see https://mercurial-scm.org/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 def writerequires(opener, requirements):
     with opener('requires', 'w') as fp:
         for r in sorted(requirements):
             fp.write("%s\n" % r)
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behavior as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         return obj.join(fname)
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         # if accessed on the class, return the descriptor itself.
         if obj is None:
             return self
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 def _locksub(repo, lock, envvar, cmd, environ=None, *args, **kwargs):
     if lock is None:
         raise error.LockInheritanceContractViolation(
             'lock can only be inherited while held')
     if environ is None:
         environ = {}
     with lock.inherit() as locker:
         environ[envvar] = locker
         return repo.ui.system(cmd, environ=environ, *args, **kwargs)
 
 def wlocksub(repo, cmd, *args, **kwargs):
     """run cmd as a subprocess that allows inheriting repo's wlock
 
     This can only be called while the wlock is held. This takes all the
     arguments that ui.system does, and returns the exit code of the
     subprocess."""
     return _locksub(repo, repo.currentwlock(), 'HG_WLOCK_LOCKER', cmd, *args,
                     **kwargs)
 
 def gdinitconfig(ui):
     """helper function to know if a repo should be created as general delta
     """
     # experimental config: format.generaldelta
     return (ui.configbool('format', 'generaldelta', False)
             or ui.configbool('format', 'usegeneraldelta', True))
 
 def gddeltaconfig(ui):
     """helper function to know if incoming delta should be optimised
     """
     # experimental config: format.generaldelta
     return ui.configbool('format', 'generaldelta', False)
 
 class delayclosedfile(object):
     """Proxy for a file object whose close is delayed.
 
     Do not instantiate outside of the vfs layer.
     """
 
     def __init__(self, fh, closer):
         object.__setattr__(self, '_origfh', fh)
         object.__setattr__(self, '_closer', closer)
 
     def __getattr__(self, attr):
         return getattr(self._origfh, attr)
 
     def __setattr__(self, attr, value):
         return setattr(self._origfh, attr, value)
 
     def __delattr__(self, attr):
         return delattr(self._origfh, attr)
 
     def __enter__(self):
         return self._origfh.__enter__()
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         self._closer.close(self._origfh)
 
     def close(self):
         self._closer.close(self._origfh)
 
 class backgroundfilecloser(object):
     """Coordinates background closing of file handles on multiple threads."""
     def __init__(self, ui, expectedcount=-1):
         self._running = False
         self._entered = False
         self._threads = []
         self._threadexception = None
 
         # Only Windows/NTFS has slow file closing. So only enable by default
         # on that platform. But allow to be enabled elsewhere for testing.
         defaultenabled = os.name == 'nt'
         enabled = ui.configbool('worker', 'backgroundclose', defaultenabled)
 
         if not enabled:
             return
 
         # There is overhead to starting and stopping the background threads.
         # Don't do background processing unless the file count is large enough
         # to justify it.
         minfilecount = ui.configint('worker', 'backgroundcloseminfilecount',
                                     2048)
         # FUTURE dynamically start background threads after minfilecount closes.
         # (We don't currently have any callers that don't know their file count)
         if expectedcount > 0 and expectedcount < minfilecount:
             return
 
         # Windows defaults to a limit of 512 open files. A buffer of 128
         # should give us enough headway.
         maxqueue = ui.configint('worker', 'backgroundclosemaxqueue', 384)
         threadcount = ui.configint('worker', 'backgroundclosethreadcount', 4)
 
         ui.debug('starting %d threads for background file closing\n' %
                  threadcount)
 
         self._queue = util.queue(maxsize=maxqueue)
         self._running = True
 
         for i in range(threadcount):
             t = threading.Thread(target=self._worker, name='backgroundcloser')
             self._threads.append(t)
             t.start()
 
     def __enter__(self):
         self._entered = True
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         self._running = False
 
         # Wait for threads to finish closing so open files don't linger for
         # longer than lifetime of context manager.
         for t in self._threads:
             t.join()
 
     def _worker(self):
         """Main routine for worker thread."""
         while True:
             try:
                 fh = self._queue.get(block=True, timeout=0.100)
                 # Need to catch or the thread will terminate and
                 # we could orphan file descriptors.
                 try:
                     fh.close()
                 except Exception as e:
                     # Stash so can re-raise from main thread later.
                     self._threadexception = e
             except util.empty:
                 if not self._running:
                     break
 
     def close(self, fh):
         """Schedule a file for closing."""
         if not self._entered:
-            raise error.Abort('can only call close() when context manager '
-                              'active')
+            raise error.Abort(_('can only call close() when context manager '
+                              'active'))
 
         # If a background thread encountered an exception, raise now so we fail
         # fast. Otherwise we may potentially go on for minutes until the error
         # is acted on.
         if self._threadexception:
             e = self._threadexception
             self._threadexception = None
             raise e
 
         # If we're not actively running, close synchronously.
         if not self._running:
             fh.close()
             return
 
         self._queue.put(fh, block=True, timeout=None)

mercurial/sshpeer.py

@@ -1,374 +1,374 b''
 # sshpeer.py - ssh repository proxy class for mercurial
 #
 # Copyright 2005, 2006 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 __future__ import absolute_import
 
 import re
 
 from .i18n import _
 from . import (
     error,
     util,
     wireproto,
 )
 
 class remotelock(object):
     def __init__(self, repo):
         self.repo = repo
     def release(self):
         self.repo.unlock()
         self.repo = None
     def __enter__(self):
         return self
     def __exit__(self, exc_type, exc_val, exc_tb):
         if self.repo:
             self.release()
     def __del__(self):
         if self.repo:
             self.release()
 
 def _serverquote(s):
     if not s:
         return s
     '''quote a string for the remote shell ... which we assume is sh'''
     if re.match('[a-zA-Z0-9@%_+=:,./-]*$', s):
         return s
     return "'%s'" % s.replace("'", "'\\''")
 
 def _forwardoutput(ui, pipe):
     """display all data currently available on pipe as remote output.
 
     This is non blocking."""
     s = util.readpipe(pipe)
     if s:
         for l in s.splitlines():
             ui.status(_("remote: "), l, '\n')
 
 class doublepipe(object):
     """Operate a side-channel pipe in addition of a main one
 
     The side-channel pipe contains server output to be forwarded to the user
     input. The double pipe will behave as the "main" pipe, but will ensure the
     content of the "side" pipe is properly processed while we wait for blocking
     call on the "main" pipe.
 
     If large amounts of data are read from "main", the forward will cease after
     the first bytes start to appear. This simplifies the implementation
     without affecting actual output of sshpeer too much as we rarely issue
     large read for data not yet emitted by the server.
 
     The main pipe is expected to be a 'bufferedinputpipe' from the util module
     that handle all the os specific bites. This class lives in this module
     because it focus on behavior specific to the ssh protocol."""
 
     def __init__(self, ui, main, side):
         self._ui = ui
         self._main = main
         self._side = side
 
     def _wait(self):
         """wait until some data are available on main or side
 
         return a pair of boolean (ismainready, issideready)
 
         (This will only wait for data if the setup is supported by `util.poll`)
         """
         if getattr(self._main, 'hasbuffer', False): # getattr for classic pipe
             return (True, True) # main has data, assume side is worth poking at.
         fds = [self._main.fileno(), self._side.fileno()]
         try:
             act = util.poll(fds)
         except NotImplementedError:
             # non supported yet case, assume all have data.
             act = fds
         return (self._main.fileno() in act, self._side.fileno() in act)
 
     def write(self, data):
         return self._call('write', data)
 
     def read(self, size):
         return self._call('read', size)
 
     def readline(self):
         return self._call('readline')
 
     def _call(self, methname, data=None):
         """call <methname> on "main", forward output of "side" while blocking
         """
         # data can be '' or 0
         if (data is not None and not data) or self._main.closed:
             _forwardoutput(self._ui, self._side)
             return ''
         while True:
             mainready, sideready = self._wait()
             if sideready:
                 _forwardoutput(self._ui, self._side)
             if mainready:
                 meth = getattr(self._main, methname)
                 if data is None:
                     return meth()
                 else:
                     return meth(data)
 
     def close(self):
         return self._main.close()
 
     def flush(self):
         return self._main.flush()
 
 class sshpeer(wireproto.wirepeer):
     def __init__(self, ui, path, create=False):
         self._url = path
         self.ui = ui
         self.pipeo = self.pipei = self.pipee = None
 
         u = util.url(path, parsequery=False, parsefragment=False)
         if u.scheme != 'ssh' or not u.host or u.path is None:
             self._abort(error.RepoError(_("couldn't parse location %s") % path))
 
         self.user = u.user
         if u.passwd is not None:
             self._abort(error.RepoError(_("password in URL not supported")))
         self.host = u.host
         self.port = u.port
         self.path = u.path or "."
 
         sshcmd = self.ui.config("ui", "ssh", "ssh")
         remotecmd = self.ui.config("ui", "remotecmd", "hg")
 
         args = util.sshargs(sshcmd,
                             _serverquote(self.host),
                             _serverquote(self.user),
                             _serverquote(self.port))
 
         if create:
             cmd = '%s %s %s' % (sshcmd, args,
                 util.shellquote("%s init %s" %
                     (_serverquote(remotecmd), _serverquote(self.path))))
             ui.debug('running %s\n' % cmd)
             res = ui.system(cmd)
             if res != 0:
                 self._abort(error.RepoError(_("could not create remote repo")))
 
         self._validaterepo(sshcmd, args, remotecmd)
 
     def url(self):
         return self._url
 
     def _validaterepo(self, sshcmd, args, remotecmd):
         # cleanup up previous run
         self.cleanup()
 
         cmd = '%s %s %s' % (sshcmd, args,
             util.shellquote("%s -R %s serve --stdio" %
                 (_serverquote(remotecmd), _serverquote(self.path))))
         self.ui.debug('running %s\n' % cmd)
         cmd = util.quotecommand(cmd)
 
         # while self.subprocess isn't used, having it allows the subprocess to
         # to clean up correctly later
         #
         # no buffer allow the use of 'select'
         # feel free to remove buffering and select usage when we ultimately
         # move to threading.
         sub = util.popen4(cmd, bufsize=0)
         self.pipeo, self.pipei, self.pipee, self.subprocess = sub
 
         self.pipei = util.bufferedinputpipe(self.pipei)
         self.pipei = doublepipe(self.ui, self.pipei, self.pipee)
         self.pipeo = doublepipe(self.ui, self.pipeo, self.pipee)
 
         # skip any noise generated by remote shell
         self._callstream("hello")
         r = self._callstream("between", pairs=("%s-%s" % ("0"*40, "0"*40)))
         lines = ["", "dummy"]
         max_noise = 500
         while lines[-1] and max_noise:
             l = r.readline()
             self.readerr()
             if lines[-1] == "1\n" and l == "\n":
                 break
             if l:
                 self.ui.debug("remote: ", l)
             lines.append(l)
             max_noise -= 1
         else:
             self._abort(error.RepoError(_('no suitable response from '
                                           'remote hg')))
 
         self._caps = set()
         for l in reversed(lines):
             if l.startswith("capabilities:"):
                 self._caps.update(l[:-1].split(":")[1].split())
                 break
 
     def _capabilities(self):
         return self._caps
 
     def readerr(self):
         _forwardoutput(self.ui, self.pipee)
 
     def _abort(self, exception):
         self.cleanup()
         raise exception
 
     def cleanup(self):
         if self.pipeo is None:
             return
         self.pipeo.close()
         self.pipei.close()
         try:
             # read the error descriptor until EOF
             for l in self.pipee:
                 self.ui.status(_("remote: "), l)
         except (IOError, ValueError):
             pass
         self.pipee.close()
 
     __del__ = cleanup
 
     def _submitbatch(self, req):
         cmds = []
         for op, argsdict in req:
             args = ','.join('%s=%s' % (wireproto.escapearg(k),
                                        wireproto.escapearg(v))
                             for k, v in argsdict.iteritems())
             cmds.append('%s %s' % (op, args))
         rsp = self._callstream("batch", cmds=';'.join(cmds))
         available = self._getamount()
         # TODO this response parsing is probably suboptimal for large
         # batches with large responses.
         toread = min(available, 1024)
         work = rsp.read(toread)
         available -= toread
         chunk = work
         while chunk:
             while ';' in work:
                 one, work = work.split(';', 1)
                 yield wireproto.unescapearg(one)
             toread = min(available, 1024)
             chunk = rsp.read(toread)
             available -= toread
             work += chunk
         yield wireproto.unescapearg(work)
 
     def _callstream(self, cmd, **args):
         self.ui.debug("sending %s command\n" % cmd)
         self.pipeo.write("%s\n" % cmd)
         _func, names = wireproto.commands[cmd]
         keys = names.split()
         wireargs = {}
         for k in keys:
             if k == '*':
                 wireargs['*'] = args
                 break
             else:
                 wireargs[k] = args[k]
                 del args[k]
         for k, v in sorted(wireargs.iteritems()):
             self.pipeo.write("%s %d\n" % (k, len(v)))
             if isinstance(v, dict):
                 for dk, dv in v.iteritems():
                     self.pipeo.write("%s %d\n" % (dk, len(dv)))
                     self.pipeo.write(dv)
             else:
                 self.pipeo.write(v)
         self.pipeo.flush()
 
         return self.pipei
 
     def _callcompressable(self, cmd, **args):
         return self._callstream(cmd, **args)
 
     def _call(self, cmd, **args):
         self._callstream(cmd, **args)
         return self._recv()
 
     def _callpush(self, cmd, fp, **args):
         r = self._call(cmd, **args)
         if r:
             return '', r
         while True:
             d = fp.read(4096)
             if not d:
                 break
             self._send(d)
         self._send("", flush=True)
         r = self._recv()
         if r:
             return '', r
         return self._recv(), ''
 
     def _calltwowaystream(self, cmd, fp, **args):
         r = self._call(cmd, **args)
         if r:
             # XXX needs to be made better
-            raise error.Abort('unexpected remote reply: %s' % r)
+            raise error.Abort(_('unexpected remote reply: %s') % r)
         while True:
             d = fp.read(4096)
             if not d:
                 break
             self._send(d)
         self._send("", flush=True)
         return self.pipei
 
     def _getamount(self):
         l = self.pipei.readline()
         if l == '\n':
             self.readerr()
             msg = _('check previous remote output')
             self._abort(error.OutOfBandError(hint=msg))
         self.readerr()
         try:
             return int(l)
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), l))
 
     def _recv(self):
         return self.pipei.read(self._getamount())
 
     def _send(self, data, flush=False):
         self.pipeo.write("%d\n" % len(data))
         if data:
             self.pipeo.write(data)
         if flush:
             self.pipeo.flush()
         self.readerr()
 
     def lock(self):
         self._call("lock")
         return remotelock(self)
 
     def unlock(self):
         self._call("unlock")
 
     def addchangegroup(self, cg, source, url, lock=None):
         '''Send a changegroup to the remote server.  Return an integer
         similar to unbundle(). DEPRECATED, since it requires locking the
         remote.'''
         d = self._call("addchangegroup")
         if d:
             self._abort(error.RepoError(_("push refused: %s") % d))
         while True:
             d = cg.read(4096)
             if not d:
                 break
             self.pipeo.write(d)
             self.readerr()
 
         self.pipeo.flush()
 
         self.readerr()
         r = self._recv()
         if not r:
             return 1
         try:
             return int(r)
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), r))
 
 instance = sshpeer

mercurial/sshserver.py

@@ -1,134 +1,135 b''
 # sshserver.py - ssh protocol server support for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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 __future__ import absolute_import
 
 import os
 import sys
 
+from .i18n import _
 from . import (
     error,
     hook,
     util,
     wireproto,
 )
 
 class sshserver(wireproto.abstractserverproto):
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
         self.lock = None
         self.fin = ui.fin
         self.fout = ui.fout
 
         hook.redirect(True)
         ui.fout = repo.ui.fout = ui.ferr
 
         # Prevent insertion/deletion of CRs
         util.setbinary(self.fin)
         util.setbinary(self.fout)
 
     def getargs(self, args):
         data = {}
         keys = args.split()
         for n in xrange(len(keys)):
             argline = self.fin.readline()[:-1]
             arg, l = argline.split()
             if arg not in keys:
-                raise error.Abort("unexpected parameter %r" % arg)
+                raise error.Abort(_("unexpected parameter %r") % arg)
             if arg == '*':
                 star = {}
                 for k in xrange(int(l)):
                     argline = self.fin.readline()[:-1]
                     arg, l = argline.split()
                     val = self.fin.read(int(l))
                     star[arg] = val
                 data['*'] = star
             else:
                 val = self.fin.read(int(l))
                 data[arg] = val
         return [data[k] for k in keys]
 
     def getarg(self, name):
         return self.getargs(name)[0]
 
     def getfile(self, fpout):
         self.sendresponse('')
         count = int(self.fin.readline())
         while count:
             fpout.write(self.fin.read(count))
             count = int(self.fin.readline())
 
     def redirect(self):
         pass
 
     def groupchunks(self, changegroup):
         while True:
             d = changegroup.read(4096)
             if not d:
                 break
             yield d
 
     def sendresponse(self, v):
         self.fout.write("%d\n" % len(v))
         self.fout.write(v)
         self.fout.flush()
 
     def sendstream(self, source):
         write = self.fout.write
         for chunk in source.gen:
             write(chunk)
         self.fout.flush()
 
     def sendpushresponse(self, rsp):
         self.sendresponse('')
         self.sendresponse(str(rsp.res))
 
     def sendpusherror(self, rsp):
         self.sendresponse(rsp.res)
 
     def sendooberror(self, rsp):
         self.ui.ferr.write('%s\n-\n' % rsp.message)
         self.ui.ferr.flush()
         self.fout.write('\n')
         self.fout.flush()
 
     def serve_forever(self):
         try:
             while self.serve_one():
                 pass
         finally:
             if self.lock is not None:
                 self.lock.release()
         sys.exit(0)
 
     handlers = {
         str: sendresponse,
         wireproto.streamres: sendstream,
         wireproto.pushres: sendpushresponse,
         wireproto.pusherr: sendpusherror,
         wireproto.ooberror: sendooberror,
     }
 
     def serve_one(self):
         cmd = self.fin.readline()[:-1]
         if cmd and cmd in wireproto.commands:
             rsp = wireproto.dispatch(self.repo, self, cmd)
             self.handlers[rsp.__class__](self, rsp)
         elif cmd:
             impl = getattr(self, 'do_' + cmd, None)
             if impl:
                 r = impl()
                 if r is not None:
                     self.sendresponse(r)
             else: self.sendresponse("")
         return cmd != ''
 
     def _client(self):
         client = os.environ.get('SSH_CLIENT', '').split(' ', 1)[0]
         return 'remote:ssh:' + client

mercurial/sslutil.py

@@ -1,432 +1,432 b''
 # sslutil.py - SSL handling for mercurial
 #
 # Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
 # Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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 __future__ import absolute_import
 
 import hashlib
 import os
 import ssl
 import sys
 
 from .i18n import _
 from . import (
     error,
     util,
 )
 
 # Python 2.7.9+ overhauled the built-in SSL/TLS features of Python. It added
 # support for TLS 1.1, TLS 1.2, SNI, system CA stores, etc. These features are
 # all exposed via the "ssl" module.
 #
 # Depending on the version of Python being used, SSL/TLS support is either
 # modern/secure or legacy/insecure. Many operations in this module have
 # separate code paths depending on support in Python.
 
 hassni = getattr(ssl, 'HAS_SNI', False)
 
 try:
     OP_NO_SSLv2 = ssl.OP_NO_SSLv2
     OP_NO_SSLv3 = ssl.OP_NO_SSLv3
 except AttributeError:
     OP_NO_SSLv2 = 0x1000000
     OP_NO_SSLv3 = 0x2000000
 
 try:
     # ssl.SSLContext was added in 2.7.9 and presence indicates modern
     # SSL/TLS features are available.
     SSLContext = ssl.SSLContext
     modernssl = True
     _canloaddefaultcerts = util.safehasattr(SSLContext, 'load_default_certs')
 except AttributeError:
     modernssl = False
     _canloaddefaultcerts = False
 
     # We implement SSLContext using the interface from the standard library.
     class SSLContext(object):
         # ssl.wrap_socket gained the "ciphers" named argument in 2.7.
         _supportsciphers = sys.version_info >= (2, 7)
 
         def __init__(self, protocol):
             # From the public interface of SSLContext
             self.protocol = protocol
             self.check_hostname = False
             self.options = 0
             self.verify_mode = ssl.CERT_NONE
 
             # Used by our implementation.
             self._certfile = None
             self._keyfile = None
             self._certpassword = None
             self._cacerts = None
             self._ciphers = None
 
         def load_cert_chain(self, certfile, keyfile=None, password=None):
             self._certfile = certfile
             self._keyfile = keyfile
             self._certpassword = password
 
         def load_default_certs(self, purpose=None):
             pass
 
         def load_verify_locations(self, cafile=None, capath=None, cadata=None):
             if capath:
-                raise error.Abort('capath not supported')
+                raise error.Abort(_('capath not supported'))
             if cadata:
-                raise error.Abort('cadata not supported')
+                raise error.Abort(_('cadata not supported'))
 
             self._cacerts = cafile
 
         def set_ciphers(self, ciphers):
             if not self._supportsciphers:
-                raise error.Abort('setting ciphers not supported')
+                raise error.Abort(_('setting ciphers not supported'))
 
             self._ciphers = ciphers
 
         def wrap_socket(self, socket, server_hostname=None, server_side=False):
             # server_hostname is unique to SSLContext.wrap_socket and is used
             # for SNI in that context. So there's nothing for us to do with it
             # in this legacy code since we don't support SNI.
 
             args = {
                 'keyfile': self._keyfile,
                 'certfile': self._certfile,
                 'server_side': server_side,
                 'cert_reqs': self.verify_mode,
                 'ssl_version': self.protocol,
                 'ca_certs': self._cacerts,
             }
 
             if self._supportsciphers:
                 args['ciphers'] = self._ciphers
 
             return ssl.wrap_socket(socket, **args)
 
 def _hostsettings(ui, hostname):
     """Obtain security settings for a hostname.
 
     Returns a dict of settings relevant to that hostname.
     """
     s = {
         # Whether we should attempt to load default/available CA certs
         # if an explicit ``cafile`` is not defined.
         'allowloaddefaultcerts': True,
         # List of 2-tuple of (hash algorithm, hash).
         'certfingerprints': [],
         # Path to file containing concatenated CA certs. Used by
         # SSLContext.load_verify_locations().
         'cafile': None,
         # Whether certificate verification should be disabled.
         'disablecertverification': False,
         # Whether the legacy [hostfingerprints] section has data for this host.
         'legacyfingerprint': False,
         # ssl.CERT_* constant used by SSLContext.verify_mode.
         'verifymode': None,
     }
 
     # Look for fingerprints in [hostsecurity] section. Value is a list
     # of <alg>:<fingerprint> strings.
     fingerprints = ui.configlist('hostsecurity', '%s:fingerprints' % hostname,
                                  [])
     for fingerprint in fingerprints:
         if not (fingerprint.startswith(('sha1:', 'sha256:', 'sha512:'))):
             raise error.Abort(_('invalid fingerprint for %s: %s') % (
                                 hostname, fingerprint),
                               hint=_('must begin with "sha1:", "sha256:", '
                                      'or "sha512:"'))
 
         alg, fingerprint = fingerprint.split(':', 1)
         fingerprint = fingerprint.replace(':', '').lower()
         s['certfingerprints'].append((alg, fingerprint))
 
     # Fingerprints from [hostfingerprints] are always SHA-1.
     for fingerprint in ui.configlist('hostfingerprints', hostname, []):
         fingerprint = fingerprint.replace(':', '').lower()
         s['certfingerprints'].append(('sha1', fingerprint))
         s['legacyfingerprint'] = True
 
     # If a host cert fingerprint is defined, it is the only thing that
     # matters. No need to validate CA certs.
     if s['certfingerprints']:
         s['verifymode'] = ssl.CERT_NONE
 
     # If --insecure is used, don't take CAs into consideration.
     elif ui.insecureconnections:
         s['disablecertverification'] = True
         s['verifymode'] = ssl.CERT_NONE
 
     if ui.configbool('devel', 'disableloaddefaultcerts'):
         s['allowloaddefaultcerts'] = False
 
     # If both fingerprints and a per-host ca file are specified, issue a warning
     # because users should not be surprised about what security is or isn't
     # being performed.
     cafile = ui.config('hostsecurity', '%s:verifycertsfile' % hostname)
     if s['certfingerprints'] and cafile:
         ui.warn(_('(hostsecurity.%s:verifycertsfile ignored when host '
                   'fingerprints defined; using host fingerprints for '
                   'verification)\n') % hostname)
 
     # Try to hook up CA certificate validation unless something above
     # makes it not necessary.
     if s['verifymode'] is None:
         # Look at per-host ca file first.
         if cafile:
             cafile = util.expandpath(cafile)
             if not os.path.exists(cafile):
                 raise error.Abort(_('path specified by %s does not exist: %s') %
                                   ('hostsecurity.%s:verifycertsfile' % hostname,
                                    cafile))
             s['cafile'] = cafile
         else:
             # Find global certificates file in config.
             cafile = ui.config('web', 'cacerts')
 
             if cafile:
                 cafile = util.expandpath(cafile)
                 if not os.path.exists(cafile):
                     raise error.Abort(_('could not find web.cacerts: %s') %
                                       cafile)
             else:
                 # No global CA certs. See if we can load defaults.
                 cafile = _defaultcacerts()
                 if cafile:
                     ui.debug('using %s to enable OS X system CA\n' % cafile)
 
             s['cafile'] = cafile
 
         # Require certificate validation if CA certs are being loaded and
         # verification hasn't been disabled above.
         if cafile or (_canloaddefaultcerts and s['allowloaddefaultcerts']):
             s['verifymode'] = ssl.CERT_REQUIRED
         else:
             # At this point we don't have a fingerprint, aren't being
             # explicitly insecure, and can't load CA certs. Connecting
             # at this point is insecure. But we do it for BC reasons.
             # TODO abort here to make secure by default.
             s['verifymode'] = ssl.CERT_NONE
 
     assert s['verifymode'] is not None
 
     return s
 
 def wrapsocket(sock, keyfile, certfile, ui, serverhostname=None):
     """Add SSL/TLS to a socket.
 
     This is a glorified wrapper for ``ssl.wrap_socket()``. It makes sane
     choices based on what security options are available.
 
     In addition to the arguments supported by ``ssl.wrap_socket``, we allow
     the following additional arguments:
 
     * serverhostname - The expected hostname of the remote server. If the
       server (and client) support SNI, this tells the server which certificate
       to use.
     """
     if not serverhostname:
-        raise error.Abort('serverhostname argument is required')
+        raise error.Abort(_('serverhostname argument is required'))
 
     settings = _hostsettings(ui, serverhostname)
 
     # Despite its name, PROTOCOL_SSLv23 selects the highest protocol
     # that both ends support, including TLS protocols. On legacy stacks,
     # the highest it likely goes in TLS 1.0. On modern stacks, it can
     # support TLS 1.2.
     #
     # The PROTOCOL_TLSv* constants select a specific TLS version
     # only (as opposed to multiple versions). So the method for
     # supporting multiple TLS versions is to use PROTOCOL_SSLv23 and
     # disable protocols via SSLContext.options and OP_NO_* constants.
     # However, SSLContext.options doesn't work unless we have the
     # full/real SSLContext available to us.
     #
     # SSLv2 and SSLv3 are broken. We ban them outright.
     if modernssl:
         protocol = ssl.PROTOCOL_SSLv23
     else:
         protocol = ssl.PROTOCOL_TLSv1
 
     # TODO use ssl.create_default_context() on modernssl.
     sslcontext = SSLContext(protocol)
 
     # This is a no-op on old Python.
     sslcontext.options |= OP_NO_SSLv2 | OP_NO_SSLv3
 
     # This still works on our fake SSLContext.
     sslcontext.verify_mode = settings['verifymode']
 
     if certfile is not None:
         def password():
             f = keyfile or certfile
             return ui.getpass(_('passphrase for %s: ') % f, '')
         sslcontext.load_cert_chain(certfile, keyfile, password)
 
     if settings['cafile'] is not None:
         sslcontext.load_verify_locations(cafile=settings['cafile'])
         caloaded = True
     elif settings['allowloaddefaultcerts']:
         # This is a no-op on old Python.
         sslcontext.load_default_certs()
         caloaded = True
     else:
         caloaded = False
 
     sslsocket = sslcontext.wrap_socket(sock, server_hostname=serverhostname)
     # check if wrap_socket failed silently because socket had been
     # closed
     # - see http://bugs.python.org/issue13721
     if not sslsocket.cipher():
         raise error.Abort(_('ssl connection failed'))
 
     sslsocket._hgstate = {
         'caloaded': caloaded,
         'hostname': serverhostname,
         'settings': settings,
         'ui': ui,
     }
 
     return sslsocket
 
 def _verifycert(cert, hostname):
     '''Verify that cert (in socket.getpeercert() format) matches hostname.
     CRLs is not handled.
 
     Returns error message if any problems are found and None on success.
     '''
     if not cert:
         return _('no certificate received')
     dnsname = hostname.lower()
     def matchdnsname(certname):
         return (certname == dnsname or
                 '.' in dnsname and certname == '*.' + dnsname.split('.', 1)[1])
 
     san = cert.get('subjectAltName', [])
     if san:
         certnames = [value.lower() for key, value in san if key == 'DNS']
         for name in certnames:
             if matchdnsname(name):
                 return None
         if certnames:
             return _('certificate is for %s') % ', '.join(certnames)
 
     # subject is only checked when subjectAltName is empty
     for s in cert.get('subject', []):
         key, value = s[0]
         if key == 'commonName':
             try:
                 # 'subject' entries are unicode
                 certname = value.lower().encode('ascii')
             except UnicodeEncodeError:
                 return _('IDN in certificate not supported')
             if matchdnsname(certname):
                 return None
             return _('certificate is for %s') % certname
     return _('no commonName or subjectAltName found in certificate')
 
 
 # CERT_REQUIRED means fetch the cert from the server all the time AND
 # validate it against the CA store provided in web.cacerts.
 
 def _plainapplepython():
     """return true if this seems to be a pure Apple Python that
     * is unfrozen and presumably has the whole mercurial module in the file
       system
     * presumably is an Apple Python that uses Apple OpenSSL which has patches
       for using system certificate store CAs in addition to the provided
       cacerts file
     """
     if sys.platform != 'darwin' or util.mainfrozen() or not sys.executable:
         return False
     exe = os.path.realpath(sys.executable).lower()
     return (exe.startswith('/usr/bin/python') or
             exe.startswith('/system/library/frameworks/python.framework/'))
 
 def _defaultcacerts():
     """return path to default CA certificates or None."""
     if _plainapplepython():
         dummycert = os.path.join(os.path.dirname(__file__), 'dummycert.pem')
         if os.path.exists(dummycert):
             return dummycert
 
     return None
 
 def validatesocket(sock):
     """Validate a socket meets security requiremnets.
 
     The passed socket must have been created with ``wrapsocket()``.
     """
     host = sock._hgstate['hostname']
     ui = sock._hgstate['ui']
     settings = sock._hgstate['settings']
 
     try:
         peercert = sock.getpeercert(True)
         peercert2 = sock.getpeercert()
     except AttributeError:
         raise error.Abort(_('%s ssl connection error') % host)
 
     if not peercert:
         raise error.Abort(_('%s certificate error: '
                            'no certificate received') % host)
 
     if settings['disablecertverification']:
         # We don't print the certificate fingerprint because it shouldn't
         # be necessary: if the user requested certificate verification be
         # disabled, they presumably already saw a message about the inability
         # to verify the certificate and this message would have printed the
         # fingerprint. So printing the fingerprint here adds little to no
         # value.
         ui.warn(_('warning: connection security to %s is disabled per current '
                   'settings; communication is susceptible to eavesdropping '
                   'and tampering\n') % host)
         return
 
     # If a certificate fingerprint is pinned, use it and only it to
     # validate the remote cert.
     peerfingerprints = {
         'sha1': hashlib.sha1(peercert).hexdigest(),
         'sha256': hashlib.sha256(peercert).hexdigest(),
         'sha512': hashlib.sha512(peercert).hexdigest(),
     }
 
     def fmtfingerprint(s):
         return ':'.join([s[x:x + 2] for x in range(0, len(s), 2)])
 
     nicefingerprint = 'sha256:%s' % fmtfingerprint(peerfingerprints['sha256'])
 
     if settings['certfingerprints']:
         for hash, fingerprint in settings['certfingerprints']:
             if peerfingerprints[hash].lower() == fingerprint:
                 ui.debug('%s certificate matched fingerprint %s:%s\n' %
                          (host, hash, fmtfingerprint(fingerprint)))
                 return
 
         # Pinned fingerprint didn't match. This is a fatal error.
         if settings['legacyfingerprint']:
             section = 'hostfingerprint'
             nice = fmtfingerprint(peerfingerprints['sha1'])
         else:
             section = 'hostsecurity'
             nice = '%s:%s' % (hash, fmtfingerprint(peerfingerprints[hash]))
         raise error.Abort(_('certificate for %s has unexpected '
                             'fingerprint %s') % (host, nice),
                           hint=_('check %s configuration') % section)
 
     if not sock._hgstate['caloaded']:
         ui.warn(_('warning: certificate for %s not verified '
                   '(set hostsecurity.%s:certfingerprints=%s or web.cacerts '
                   'config settings)\n') % (host, host, nicefingerprint))
         return
 
     msg = _verifycert(peercert2, host)
     if msg:
         raise error.Abort(_('%s certificate error: %s') % (host, msg),
                          hint=_('set hostsecurity.%s:certfingerprints=%s '
                                 'config setting or use --insecure to connect '
                                 'insecurely') %
                               (host, nicefingerprint))