transaction: remember original len(repo) instead of tracking added revs (API)

It's silly to keep updating xrange(len(changelog), len(changelog) + 1) for
each added revision. Instead, let's simply remember the first revision to
be added.

The test output slightly changed as the branch cache is also warmed up by
stream clone, which seems more consistent.

.. api::

   ``tr.changes['revs']`` is replaced by ``tr.changes['origrepolen']`` which
   is the first revision number to be added.

mercurial/changelog.py

@@ -1,563 +1,547
 # changelog.py - changelog 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
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
 )
 from .thirdparty import (
     attr,
 )
 
 from . import (
     encoding,
     error,
     pycompat,
     revlog,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
 
 _defaultextra = {'branch': 'default'}
 
 def _string_escape(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
     >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
     >>> s
     'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n'
     >>> res = _string_escape(s)
     >>> s == stringutil.unescapestr(res)
     True
     """
     # subset of the string_escape codec
     text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
     return text.replace('\0', '\\0')
 
 def decodeextra(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar',
     ...                                 b'baz': chr(92) + chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
     """
     extra = _defaultextra.copy()
     for l in text.split('\0'):
         if l:
             if '\\0' in l:
                 # fix up \0 without getting into trouble with \\0
                 l = l.replace('\\\\', '\\\\\n')
                 l = l.replace('\\0', '\0')
                 l = l.replace('\n', '')
             k, v = stringutil.unescapestr(l).split(':', 1)
             extra[k] = v
     return extra
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [_string_escape('%s:%s' % (k, d[k])) for k in sorted(d)]
     return "\0".join(items)
 
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')
 
 class appender(object):
     '''the changelog index must be updated last on disk, so we use this class
     to delay writes to it'''
     def __init__(self, vfs, name, mode, buf):
         self.data = buf
         fp = vfs(name, mode)
         self.fp = fp
         self.offset = fp.tell()
         self.size = vfs.fstat(fp).st_size
         self._end = self.size
 
     def end(self):
         return self._end
     def tell(self):
         return self.offset
     def flush(self):
         pass
 
     @property
     def closed(self):
         return self.fp.closed
 
     def close(self):
         self.fp.close()
 
     def seek(self, offset, whence=0):
         '''virtual file offset spans real file and data'''
         if whence == 0:
             self.offset = offset
         elif whence == 1:
             self.offset += offset
         elif whence == 2:
             self.offset = self.end() + offset
         if self.offset < self.size:
             self.fp.seek(self.offset)
 
     def read(self, count=-1):
         '''only trick here is reads that span real file and data'''
         ret = ""
         if self.offset < self.size:
             s = self.fp.read(count)
             ret = s
             self.offset += len(s)
             if count > 0:
                 count -= len(s)
         if count != 0:
             doff = self.offset - self.size
             self.data.insert(0, "".join(self.data))
             del self.data[1:]
             s = self.data[0][doff:doff + count]
             self.offset += len(s)
             ret += s
         return ret
 
     def write(self, s):
         self.data.append(bytes(s))
         self.offset += len(s)
         self._end += len(s)
 
     def __enter__(self):
         self.fp.__enter__()
         return self
 
     def __exit__(self, *args):
         return self.fp.__exit__(*args)
 
 def _divertopener(opener, target):
     """build an opener that writes in 'target.a' instead of 'target'"""
     def _divert(name, mode='r', checkambig=False):
         if name != target:
             return opener(name, mode)
         return opener(name + ".a", mode)
     return _divert
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
     def _delay(name, mode='r', checkambig=False):
         if name != target:
             return opener(name, mode)
         return appender(opener, name, mode, buf)
     return _delay
 
 @attr.s
 class _changelogrevision(object):
     # Extensions might modify _defaultextra, so let the constructor below pass
     # it in
     extra = attr.ib()
     manifest = attr.ib(default=nullid)
     user = attr.ib(default='')
     date = attr.ib(default=(0, 0))
     files = attr.ib(default=attr.Factory(list))
     description = attr.ib(default='')
 
 class changelogrevision(object):
     """Holds results of a parsed changelog revision.
 
     Changelog revisions consist of multiple pieces of data, including
     the manifest node, user, and date. This object exposes a view into
     the parsed object.
     """
 
     __slots__ = (
         u'_offsets',
         u'_text',
     )
 
     def __new__(cls, text):
         if not text:
             return _changelogrevision(extra=_defaultextra)
 
         self = super(changelogrevision, cls).__new__(cls)
         # We could return here and implement the following as an __init__.
         # But doing it here is equivalent and saves an extra function call.
 
         # format used:
         # nodeid\n        : manifest node in ascii
         # user\n          : user, no \n or \r allowed
         # time tz extra\n : date (time is int or float, timezone is int)
         #                 : extra is metadata, encoded and separated by '\0'
         #                 : older versions ignore it
         # files\n\n       : files modified by the cset, no \n or \r allowed
         # (.*)            : comment (free text, ideally utf-8)
         #
         # changelog v0 doesn't use extra
 
         nl1 = text.index('\n')
         nl2 = text.index('\n', nl1 + 1)
         nl3 = text.index('\n', nl2 + 1)
 
         # The list of files may be empty. Which means nl3 is the first of the
         # double newline that precedes the description.
         if text[nl3 + 1:nl3 + 2] == '\n':
             doublenl = nl3
         else:
             doublenl = text.index('\n\n', nl3 + 1)
 
         self._offsets = (nl1, nl2, nl3, doublenl)
         self._text = text
 
         return self
 
     @property
     def manifest(self):
         return bin(self._text[0:self._offsets[0]])
 
     @property
     def user(self):
         off = self._offsets
         return encoding.tolocal(self._text[off[0] + 1:off[1]])
 
     @property
     def _rawdate(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1:off[2]]
         return dateextra.split(' ', 2)[0:2]
 
     @property
     def _rawextra(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1:off[2]]
         fields = dateextra.split(' ', 2)
         if len(fields) != 3:
             return None
 
         return fields[2]
 
     @property
     def date(self):
         raw = self._rawdate
         time = float(raw[0])
         # Various tools did silly things with the timezone.
         try:
             timezone = int(raw[1])
         except ValueError:
             timezone = 0
 
         return time, timezone
 
     @property
     def extra(self):
         raw = self._rawextra
         if raw is None:
             return _defaultextra
 
         return decodeextra(raw)
 
     @property
     def files(self):
         off = self._offsets
         if off[2] == off[3]:
             return []
 
         return self._text[off[2] + 1:off[3]].split('\n')
 
     @property
     def description(self):
         return encoding.tolocal(self._text[self._offsets[3] + 2:])
 
 class changelog(revlog.revlog):
     def __init__(self, opener, trypending=False):
         """Load a changelog revlog using an opener.
 
         If ``trypending`` is true, we attempt to load the index from a
         ``00changelog.i.a`` file instead of the default ``00changelog.i``.
         The ``00changelog.i.a`` file contains index (and possibly inline
         revision) data for a transaction that hasn't been finalized yet.
         It exists in a separate file to facilitate readers (such as
         hooks processes) accessing data before a transaction is finalized.
         """
         if trypending and opener.exists('00changelog.i.a'):
             indexfile = '00changelog.i.a'
         else:
             indexfile = '00changelog.i'
 
         datafile = '00changelog.d'
         revlog.revlog.__init__(self, opener, indexfile, datafile=datafile,
                                checkambig=True, mmaplargeindex=True)
 
         if self._initempty:
             # changelogs don't benefit from generaldelta
             self.version &= ~revlog.FLAG_GENERALDELTA
             self._generaldelta = False
 
         # Delta chains for changelogs tend to be very small because entries
         # tend to be small and don't delta well with each. So disable delta
         # chains.
         self._storedeltachains = False
 
         self._realopener = opener
         self._delayed = False
         self._delaybuf = None
         self._divert = False
         self.filteredrevs = frozenset()
 
     def tiprev(self):
         for i in pycompat.xrange(len(self) -1, -2, -1):
             if i not in self.filteredrevs:
                 return i
 
     def tip(self):
         """filtered version of revlog.tip"""
         return self.node(self.tiprev())
 
     def __contains__(self, rev):
         """filtered version of revlog.__contains__"""
         return (0 <= rev < len(self)
                 and rev not in self.filteredrevs)
 
     def __iter__(self):
         """filtered version of revlog.__iter__"""
         if len(self.filteredrevs) == 0:
             return revlog.revlog.__iter__(self)
 
         def filterediter():
             for i in pycompat.xrange(len(self)):
                 if i not in self.filteredrevs:
                     yield i
 
         return filterediter()
 
     def revs(self, start=0, stop=None):
         """filtered version of revlog.revs"""
         for i in super(changelog, self).revs(start, stop):
             if i not in self.filteredrevs:
                 yield i
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         return self.index.reachableroots2(minroot, heads, roots, includepath)
 
     def headrevs(self):
         if self.filteredrevs:
             try:
                 return self.index.headrevsfiltered(self.filteredrevs)
             # AttributeError covers non-c-extension environments and
             # old c extensions without filter handling.
             except AttributeError:
                 return self._headrevs()
 
         return super(changelog, self).headrevs()
 
     def strip(self, *args, **kwargs):
         # XXX make something better than assert
         # We can't expect proper strip behavior if we are filtered.
         assert not self.filteredrevs
         super(changelog, self).strip(*args, **kwargs)
 
     def rev(self, node):
         """filtered version of revlog.rev"""
         r = super(changelog, self).rev(node)
         if r in self.filteredrevs:
             raise error.FilteredLookupError(hex(node), self.indexfile,
                                             _('filtered node'))
         return r
 
     def node(self, rev):
         """filtered version of revlog.node"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).node(rev)
 
     def linkrev(self, rev):
         """filtered version of revlog.linkrev"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).linkrev(rev)
 
     def parentrevs(self, rev):
         """filtered version of revlog.parentrevs"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).parentrevs(rev)
 
     def flags(self, rev):
         """filtered version of revlog.flags"""
         if rev in self.filteredrevs:
             raise error.FilteredIndexError(rev)
         return super(changelog, self).flags(rev)
 
     def delayupdate(self, tr):
         "delay visibility of index updates to other readers"
 
         if not self._delayed:
             if len(self) == 0:
                 self._divert = True
                 if self._realopener.exists(self.indexfile + '.a'):
                     self._realopener.unlink(self.indexfile + '.a')
                 self.opener = _divertopener(self._realopener, self.indexfile)
             else:
                 self._delaybuf = []
                 self.opener = _delayopener(self._realopener, self.indexfile,
                                            self._delaybuf)
         self._delayed = True
         tr.addpending('cl-%i' % id(self), self._writepending)
         tr.addfinalize('cl-%i' % id(self), self._finalize)
 
     def _finalize(self, tr):
         "finalize index updates"
         self._delayed = False
         self.opener = self._realopener
         # move redirected index data back into place
         if self._divert:
             assert not self._delaybuf
             tmpname = self.indexfile + ".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile, checkambig=True)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, 'a', checkambig=True)
             fp.write("".join(self._delaybuf))
             fp.close()
             self._delaybuf = None
         self._divert = False
         # split when we're done
         self._enforceinlinesize(tr)
 
     def _writepending(self, tr):
         "create a file containing the unfinalized state for pretxnchangegroup"
         if self._delaybuf:
             # make a temporary copy of the index
             fp1 = self._realopener(self.indexfile)
             pendingfilename = self.indexfile + ".a"
             # register as a temp file to ensure cleanup on failure
             tr.registertmp(pendingfilename)
             # write existing data
             fp2 = self._realopener(pendingfilename, "w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write("".join(self._delaybuf))
             fp2.close()
             # switch modes so finalize can simply rename
             self._delaybuf = None
             self._divert = True
             self.opener = _divertopener(self._realopener, self.indexfile)
 
         if self._divert:
             return True
 
         return False
 
     def _enforceinlinesize(self, tr, fp=None):
         if not self._delayed:
             revlog.revlog._enforceinlinesize(self, tr, fp)
 
     def read(self, node):
         """Obtain data from a parsed changelog revision.
 
         Returns a 6-tuple of:
 
            - manifest node in binary
            - author/user as a localstr
            - date as a 2-tuple of (time, timezone)
            - list of files
            - commit message as a localstr
            - dict of extra metadata
 
         Unless you need to access all fields, consider calling
         ``changelogrevision`` instead, as it is faster for partial object
         access.
         """
         c = changelogrevision(self.revision(node))
         return (
             c.manifest,
             c.user,
             c.date,
             c.files,
             c.description,
             c.extra
         )
 
     def changelogrevision(self, nodeorrev):
         """Obtain a ``changelogrevision`` for a node or revision."""
         return changelogrevision(self.revision(nodeorrev))
 
     def readfiles(self, node):
         """
         short version of read that only returns the files modified by the cset
         """
         text = self.revision(node)
         if not text:
             return []
         last = text.index("\n\n")
         l = text[:last].split('\n')
         return l[3:]
 
     def add(self, manifest, files, desc, transaction, p1, p2,
                   user, date=None, extra=None):
         # Convert to UTF-8 encoded bytestrings as the very first
         # thing: calling any method on a localstr object will turn it
         # into a str object and the cached UTF-8 string is thus lost.
         user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
 
         user = user.strip()
         # An empty username or a username with a "\n" will make the
         # revision text contain two "\n\n" sequences -> corrupt
         # repository since read cannot unpack the revision.
         if not user:
             raise error.RevlogError(_("empty username"))
         if "\n" in user:
             raise error.RevlogError(_("username %r contains a newline")
                                     % pycompat.bytestr(user))
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = "%d %d" % dateutil.parsedate(date)
         else:
             parseddate = "%d %d" % dateutil.makedate()
         if extra:
             branch = extra.get("branch")
             if branch in ("default", ""):
                 del extra["branch"]
             elif branch in (".", "null", "tip"):
                 raise error.RevlogError(_('the name \'%s\' is reserved')
                                         % branch)
         if extra:
             extra = encodeextra(extra)
             parseddate = "%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sorted(files) + ["", desc]
         text = "\n".join(l)
         return self.addrevision(text, transaction, len(self), p1, p2)
 
     def branchinfo(self, rev):
         """return the branch name and open/close state of a revision
 
         This function exists because creating a changectx object
         just to access this is costly."""
         extra = self.read(rev)[5]
         return encoding.tolocal(extra.get("branch")), 'close' in extra
-
-    def _addrevision(self, node, rawtext, transaction, *args, **kwargs):
-        # overlay over the standard revlog._addrevision to track the new
-        # revision on the transaction.
-        rev = len(self)
-        node = super(changelog, self)._addrevision(node, rawtext, transaction,
-                                                   *args, **kwargs)
-        revs = transaction.changes.get('revs')
-        if revs is not None:
-            if revs:
-                assert revs[-1] + 1 == rev
-                revs = pycompat.membershiprange(revs[0], rev + 1)
-            else:
-                revs = pycompat.membershiprange(rev, rev + 1)
-            transaction.changes['revs'] = revs
-        return node

mercurial/localrepo.py

@@ -1,2435 +1,2435
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import random
 import sys
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     short,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     changegroup,
     changelog,
     color,
     context,
     dirstate,
     dirstateguard,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     manifest,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     namespaces,
     narrowspec,
     obsolete,
     pathutil,
     phases,
     pushkey,
     pycompat,
     repository,
     repoview,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     interfaceutil,
     procutil,
     stringutil,
 )
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # set of (path, vfs-location) tuples. vfs-location is:
 # - 'plain for vfs relative paths
 # - '' for svfs relative paths
 _cachedfiles = set()
 
 class _basefilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         return super(_basefilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(_basefilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(_basefilecache, self).__delete__(repo.unfiltered())
 
 class repofilecache(_basefilecache):
     """filecache for files in .hg but outside of .hg/store"""
     def __init__(self, *paths):
         super(repofilecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, 'plain'))
 
     def join(self, obj, fname):
         return obj.vfs.join(fname)
 
 class storecache(_basefilecache):
     """filecache for files in the store"""
     def __init__(self, *paths):
         super(storecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, ''))
 
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 def isfilecached(repo, name):
     """check if a repo has already cached "name" filecache-ed property
 
     This returns (cachedobj-or-None, iscached) tuple.
     """
     cacheentry = repo.unfiltered()._filecache.get(name, None)
     if not cacheentry:
         return None, False
     return cacheentry.obj, True
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 moderncaps = {'lookup', 'branchmap', 'pushkey', 'known', 'getbundle',
               'unbundle'}
 legacycaps = moderncaps.union({'changegroupsubset'})
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class localcommandexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'sendcommands()')
 
         if self._closed:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'close()')
 
         # We don't need to support anything fancy. Just call the named
         # method on the peer and return a resolved future.
         fn = getattr(self._peer, pycompat.sysstr(command))
 
         f = pycompat.futures.Future()
 
         try:
             result = fn(**pycompat.strkwargs(args))
         except Exception:
             pycompat.future_set_exception_info(f, sys.exc_info()[1:])
         else:
             f.set_result(result)
 
         return f
 
     def sendcommands(self):
         self._sent = True
 
     def close(self):
         self._closed = True
 
 @interfaceutil.implementer(repository.ipeercommands)
 class localpeer(repository.peer):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=None):
         super(localpeer, self).__init__()
 
         if caps is None:
             caps = moderncaps.copy()
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
 
     # Begin of _basepeer interface.
 
     def url(self):
         return self._repo.url()
 
     def local(self):
         return self._repo
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         self._repo.close()
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def capabilities(self):
         return self._caps
 
     def clonebundles(self):
         return self._repo.tryread('clonebundles.manifest')
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         """Used to test argument passing over the wire"""
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None,
                   **kwargs):
         chunks = exchange.getbundlechunks(self._repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps,
                                           **kwargs)[1]
         cb = util.chunkbuffer(chunks)
 
         if exchange.bundle2requested(bundlecaps):
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler('01', cb, None)
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def stream_out(self):
         raise error.Abort(_('cannot perform stream clone against local '
                             'peer'))
 
     def unbundle(self, bundle, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 bundle = exchange.readbundle(self.ui, bundle, None)
                 ret = exchange.unbundle(self._repo, bundle, heads, 'push', url)
                 if util.safehasattr(ret, 'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(_('push failed:'),
                                       stringutil.forcebytestr(exc))
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def commandexecutor(self):
         return localcommandexecutor(self)
 
     # End of peer interface.
 
 @interfaceutil.implementer(repository.ipeerlegacycommands)
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         super(locallegacypeer, self).__init__(repo, caps=legacycaps)
 
     # Begin of baselegacywirecommands interface.
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def changegroup(self, nodes, source):
         outgoing = discovery.outgoing(self._repo, missingroots=nodes,
                                       missingheads=self._repo.heads())
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     def changegroupsubset(self, bases, heads, source):
         outgoing = discovery.outgoing(self._repo, missingroots=bases,
                                       missingheads=heads)
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     # End of baselegacywirecommands interface.
 
 # Increment the sub-version when the revlog v2 format changes to lock out old
 # clients.
 REVLOGV2_REQUIREMENT = 'exp-revlogv2.0'
 
 # A repository with the sparserevlog feature will have delta chains that
 # can spread over a larger span. Sparse reading cuts these large spans into
 # pieces, so that each piece isn't too big.
 # Without the sparserevlog capability, reading from the repository could use
 # huge amounts of memory, because the whole span would be read at once,
 # including all the intermediate revisions that aren't pertinent for the chain.
 # This is why once a repository has enabled sparse-read, it becomes required.
 SPARSEREVLOG_REQUIREMENT = 'sparserevlog'
 
 # Functions receiving (ui, features) that extensions can register to impact
 # the ability to load repositories with custom requirements. Only
 # functions defined in loaded extensions are called.
 #
 # The function receives a set of requirement strings that the repository
 # is capable of opening. Functions will typically add elements to the
 # set to reflect that the extension knows how to handle that requirements.
 featuresetupfuncs = set()
 
 @interfaceutil.implementer(repository.completelocalrepository)
 class localrepository(object):
 
     # obsolete experimental requirements:
     #  - manifestv2: An experimental new manifest format that allowed
     #    for stem compression of long paths. Experiment ended up not
     #    being successful (repository sizes went up due to worse delta
     #    chains), and the code was deleted in 4.6.
     supportedformats = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
         REVLOGV2_REQUIREMENT,
         SPARSEREVLOG_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         'store',
         'fncache',
         'shared',
         'relshared',
         'dotencode',
         'exp-sparse',
         'internal-phase'
     }
     openerreqs = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
     }
 
     # list of prefix for file which can be written without 'wlock'
     # Extensions should extend this list when needed
     _wlockfreeprefix = {
         # We migh consider requiring 'wlock' for the next
         # two, but pretty much all the existing code assume
         # wlock is not needed so we keep them excluded for
         # now.
         'hgrc',
         'requires',
         # XXX cache is a complicatged business someone
         # should investigate this in depth at some point
         'cache/',
         # XXX shouldn't be dirstate covered by the wlock?
         'dirstate',
         # XXX bisect was still a bit too messy at the time
         # this changeset was introduced. Someone should fix
         # the remainig bit and drop this line
         'bisect.state',
     }
 
     def __init__(self, baseui, path, create=False, intents=None):
         self.requirements = set()
         self.filtername = None
         # wvfs: rooted at the repository root, used to access the working copy
         self.wvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
         # vfs: rooted at .hg, used to access repo files outside of .hg/store
         self.vfs = None
         # svfs: usually rooted at .hg/store, used to access repository history
         # If this is a shared repository, this vfs may point to another
         # repository's .hg/store directory.
         self.svfs = None
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         self.auditor = pathutil.pathauditor(
             self.root, callback=self._checknested)
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         self.nofsauditor = pathutil.pathauditor(
             self.root, callback=self._checknested, realfs=False, cached=True)
         self.baseui = baseui
         self.ui = baseui.copy()
         self.ui.copy = baseui.copy # prevent copying repo configuration
         self.vfs = vfsmod.vfs(self.path, cacheaudited=True)
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             self.vfs.audit = self._getvfsward(self.vfs.audit)
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
         try:
             self.ui.readconfig(self.vfs.join("hgrc"), self.root)
             self._loadextensions()
         except IOError:
             pass
 
         if featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in featuresetupfuncs:
                 if setupfunc.__module__ in extmods:
                     setupfunc(self.ui, self.supported)
         else:
             self.supported = self._basesupported
         color.setup(self.ui)
 
         # Add compression engines.
         for name in util.compengines:
             engine = util.compengines[name]
             if engine.revlogheader():
                 self.supported.add('exp-compression-%s' % name)
 
         if not self.vfs.isdir():
             if create:
                 self.requirements = newreporequirements(self)
 
                 if not self.wvfs.exists():
                     self.wvfs.makedirs()
                 self.vfs.makedir(notindexed=True)
 
                 if 'store' in self.requirements:
                     self.vfs.mkdir("store")
 
                     # create an invalid changelog
                     self.vfs.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
             else:
                 try:
                     self.vfs.stat()
                 except OSError as inst:
                     if inst.errno != errno.ENOENT:
                         raise
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 self.requirements = scmutil.readrequires(
                         self.vfs, self.supported)
             except IOError as inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
         cachepath = self.vfs.join('cache')
         self.sharedpath = self.path
         try:
             sharedpath = self.vfs.read("sharedpath").rstrip('\n')
             if 'relshared' in self.requirements:
                 sharedpath = self.vfs.join(sharedpath)
             vfs = vfsmod.vfs(sharedpath, realpath=True)
             cachepath = vfs.join('cache')
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         if 'exp-sparse' in self.requirements and not sparse.enabled:
             raise error.RepoError(_('repository is using sparse feature but '
                                     'sparse is not enabled; enable the '
                                     '"sparse" extensions to access'))
 
         self.store = store.store(
             self.requirements, self.sharedpath,
             lambda base: vfsmod.vfs(base, cacheaudited=True))
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self.cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
         self.cachevfs.createmode = self.store.createmode
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             if util.safehasattr(self.svfs, 'vfs'): # this is filtervfs
                 self.svfs.vfs.audit = self._getsvfsward(self.svfs.vfs.audit)
             else: # standard vfs
                 self.svfs.audit = self._getsvfsward(self.svfs.audit)
         self._applyopenerreqs()
         if create:
             self._writerequirements()
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = {}
         self._revbranchcache = None
         self._filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # post-dirstate-status hooks
         self._postdsstatus = []
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
         # Key to signature value.
         self._sparsesignaturecache = {}
         # Signature to cached matcher instance.
         self._sparsematchercache = {}
 
     def _getvfsward(self, origfunc):
         """build a ward for self.vfs"""
         rref = weakref.ref(self)
         def checkvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if (repo is None
                 or not util.safehasattr(repo, '_wlockref')
                 or not util.safehasattr(repo, '_lockref')):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.path):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.path) + 1:]
             if path.startswith('cache/'):
                 msg = 'accessing cache with vfs instead of cachevfs: "%s"'
                 repo.ui.develwarn(msg % path, stacklevel=2, config="cache-vfs")
             if path.startswith('journal.'):
                 # journal is covered by 'lock'
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn('write with no lock: "%s"' % path,
                                       stacklevel=2, config='check-locks')
             elif repo._currentlock(repo._wlockref) is None:
                 # rest of vfs files are covered by 'wlock'
                 #
                 # exclude special files
                 for prefix in self._wlockfreeprefix:
                     if path.startswith(prefix):
                         return
                 repo.ui.develwarn('write with no wlock: "%s"' % path,
                                   stacklevel=2, config='check-locks')
             return ret
         return checkvfs
 
     def _getsvfsward(self, origfunc):
         """build a ward for self.svfs"""
         rref = weakref.ref(self)
         def checksvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if repo is None or not util.safehasattr(repo, '_lockref'):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.sharedpath):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.sharedpath) + 1:]
             if repo._currentlock(repo._lockref) is None:
                 repo.ui.develwarn('write with no lock: "%s"' % path,
                                   stacklevel=3)
             return ret
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _loadextensions(self):
         extensions.loadall(self.ui)
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool('experimental', 'bundle2-advertise'):
             caps = set(caps)
             capsblob = bundle2.encodecaps(bundle2.getrepocaps(self,
                                                               role='client'))
             caps.add('bundle2=' + urlreq.quote(capsblob))
         return caps
 
     def _applyopenerreqs(self):
         self.svfs.options = dict((r, 1) for r in self.requirements
                                            if r in self.openerreqs)
         # experimental config: format.chunkcachesize
         chunkcachesize = self.ui.configint('format', 'chunkcachesize')
         if chunkcachesize is not None:
             self.svfs.options['chunkcachesize'] = chunkcachesize
         # experimental config: format.maxchainlen
         maxchainlen = self.ui.configint('format', 'maxchainlen')
         if maxchainlen is not None:
             self.svfs.options['maxchainlen'] = maxchainlen
         # experimental config: format.manifestcachesize
         manifestcachesize = self.ui.configint('format', 'manifestcachesize')
         if manifestcachesize is not None:
             self.svfs.options['manifestcachesize'] = manifestcachesize
         deltabothparents = self.ui.configbool('storage',
             'revlog.optimize-delta-parent-choice')
         self.svfs.options['deltabothparents'] = deltabothparents
         self.svfs.options['lazydeltabase'] = not scmutil.gddeltaconfig(self.ui)
         chainspan = self.ui.configbytes('experimental', 'maxdeltachainspan')
         if 0 <= chainspan:
             self.svfs.options['maxdeltachainspan'] = chainspan
         mmapindexthreshold = self.ui.configbytes('experimental',
                                                  'mmapindexthreshold')
         if mmapindexthreshold is not None:
             self.svfs.options['mmapindexthreshold'] = mmapindexthreshold
         withsparseread = self.ui.configbool('experimental', 'sparse-read')
         srdensitythres = float(self.ui.config('experimental',
                                               'sparse-read.density-threshold'))
         srmingapsize = self.ui.configbytes('experimental',
                                            'sparse-read.min-gap-size')
         self.svfs.options['with-sparse-read'] = withsparseread
         self.svfs.options['sparse-read-density-threshold'] = srdensitythres
         self.svfs.options['sparse-read-min-gap-size'] = srmingapsize
         sparserevlog = SPARSEREVLOG_REQUIREMENT in self.requirements
         self.svfs.options['sparse-revlog'] = sparserevlog
         if sparserevlog:
             self.svfs.options['generaldelta'] = True
 
         for r in self.requirements:
             if r.startswith('exp-compression-'):
                 self.svfs.options['compengine'] = r[len('exp-compression-'):]
 
         # TODO move "revlogv2" to openerreqs once finalized.
         if REVLOGV2_REQUIREMENT in self.requirements:
             self.svfs.options['revlogv2'] = True
 
     def _writerequirements(self):
         scmutil.writerequires(self.vfs, self.requirements)
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository"""
         cls = repoview.newtype(self.unfiltered().__class__)
         return cls(self, name, visibilityexceptions)
 
     @repofilecache('bookmarks', 'bookmarks.current')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     # _phasesets depend on changelog. what we need is to call
     # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache('phaseroots', '00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         return obsolete.makestore(self.ui, self)
 
     @storecache('00changelog.i')
     def changelog(self):
         return changelog.changelog(self.svfs,
                                    trypending=txnutil.mayhavepending(self.root))
 
     def _constructmanifest(self):
         # This is a temporary function while we migrate from manifest to
         # manifestlog. It allows bundlerepo and unionrepo to intercept the
         # manifest creation.
         return manifest.manifestrevlog(self.svfs)
 
     @storecache('00manifest.i')
     def manifestlog(self):
         return manifest.manifestlog(self.svfs, self)
 
     @repofilecache('dirstate')
     def dirstate(self):
         return self._makedirstate()
 
     def _makedirstate(self):
         """Extension point for wrapping the dirstate per-repo."""
         sparsematchfn = lambda: sparse.matcher(self)
 
         return dirstate.dirstate(self.vfs, self.ui, self.root,
                                  self._dirstatevalidate, sparsematchfn)
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(_("warning: ignoring unknown"
                                " working parent %s!\n") % short(node))
             return nullid
 
     @storecache(narrowspec.FILENAME)
     def narrowpats(self):
         """matcher patterns for this repository's narrowspec
 
         A tuple of (includes, excludes).
         """
         source = self
         if self.shared():
             from . import hg
             source = hg.sharedreposource(self)
         return narrowspec.load(source)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always(self.root, '')
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     # TODO(martinvonz): make this property-like instead?
     def narrowmatch(self):
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         target = self
         if self.shared():
             from . import hg
             target = hg.sharedreposource(self)
         narrowspec.save(target, newincludes, newexcludes)
         self.invalidate(clearfilecache=True)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, context.basectx):
             return changeid
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [context.changectx(self, i)
                     for i in pycompat.xrange(*changeid.indices(len(self)))
                     if i not in self.changelog.filteredrevs]
         try:
             return context.changectx(self, changeid)
         except error.WdirUnsupported:
             return context.workingctx(self)
 
     def __contains__(self, changeid):
         """True if the given changeid exists
 
         error.AmbiguousPrefixLookupError is raised if an ambiguous node
         specified.
         """
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         # no need to pay the cost of repoview.changelog
         unfi = self.unfiltered()
         return len(unfi.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revsetlang.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()`` or
         ``repo.anyrevs([expr], user=True)``.
 
         Returns a revset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         '''
         expr = revsetlang.formatspec(expr, *args)
         m = revset.match(None, expr)
         return m(self)
 
     def set(self, expr, *args):
         '''Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def anyrevs(self, specs, user=False, localalias=None):
         '''Find revisions matching one of the given revsets.
 
         Revset aliases from the configuration are not expanded by default. To
         expand user aliases, specify ``user=True``. To provide some local
         definitions overriding user aliases, set ``localalias`` to
         ``{name: definitionstring}``.
         '''
         if user:
             m = revset.matchany(self.ui, specs,
                                 lookup=revset.lookupfn(self),
                                 localalias=localalias)
         else:
             m = revset.matchany(None, specs, localalias=localalias)
         return m(self)
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
 
         # map tag name to (node, hist)
         alltags = tagsmod.findglobaltags(self.ui, self)
         # map tag name to tag type
         tagtypes = dict((tag, 'global') for tag in alltags)
 
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         return self._bookmarks.names(node)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def branchtip(self, branch, ignoremissing=False):
         '''return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         '''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_("unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         return scmutil.revsymbol(self, key).node()
 
     def lookupbranch(self, key):
         if key in self.branchmap():
             return key
 
         return scmutil.revsymbol(self, key).branch()
 
     def known(self, nodes):
         cl = self.changelog
         nm = cl.nodemap
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool('phases', 'publish', untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered('visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return 'store'
         return None
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.svfs, f)
 
     def setparents(self, p1, p2=nullid):
         with self.dirstate.parentchange():
             copies = self.dirstate.setparents(p1, p2)
             pctx = self[p1]
             if copies:
                 # Adjust copy records, the dirstate cannot do it, it
                 # requires access to parents manifests. Preserve them
                 # only for entries added to first parent.
                 for f in copies:
                     if f not in pctx and copies[f] in pctx:
                         self.dirstate.copy(copies[f], f)
             if p2 == nullid:
                 for f, s in sorted(self.dirstate.copies().items()):
                     if f not in pctx and s not in pctx:
                         self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid,
                                changectx=changectx)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def _loadfilter(self, filter):
         if filter not in self._filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: procutil.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not pycompat.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self._filterpats[filter] = l
         return self._filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self.wvfs.islink(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False, **kwargs):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(filename, data, backgroundclose=backgroundclose,
                             **kwargs)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
             else:
                 self.wvfs.setflags(filename, False, False)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if (self.ui.configbool('devel', 'all-warnings')
                 or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError('transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest(name=desc)
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found"),
                 hint=_("run 'hg recover' to clean up transaction"))
 
         idbase = "%.40f#%f" % (random.random(), time.time())
         ha = hex(hashlib.sha1(idbase).digest())
         txnid = 'TXN:' + ha
         self.hook('pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {'plain': self.vfs} # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         # Code to track tag movement
         #
         # Since tags are all handled as file content, it is actually quite hard
         # to track these movement from a code perspective. So we fallback to a
         # tracking at the repository level. One could envision to track changes
         # to the '.hgtags' file through changegroup apply but that fails to
         # cope with case where transaction expose new heads without changegroup
         # being involved (eg: phase movement).
         #
         # For now, We gate the feature behind a flag since this likely comes
         # with performance impacts. The current code run more often than needed
         # and do not use caches as much as it could.  The current focus is on
         # the behavior of the feature so we disable it by default. The flag
         # will be removed when we are happy with the performance impact.
         #
         # Once this feature is no longer experimental move the following
         # documentation to the appropriate help section:
         #
         # The ``HG_TAG_MOVED`` variable will be set if the transaction touched
         # tags (new or changed or deleted tags). In addition the details of
         # these changes are made available in a file at:
         #     ``REPOROOT/.hg/changes/tags.changes``.
         # Make sure you check for HG_TAG_MOVED before reading that file as it
         # might exist from a previous transaction even if no tag were touched
         # in this one. Changes are recorded in a line base format::
         #
         #     <action> <hex-node> <tag-name>\n
         #
         # Actions are defined as follow:
         #   "-R": tag is removed,
         #   "+A": tag is added,
         #   "-M": tag is moved (old value),
         #   "+M": tag is moved (new value),
         tracktags = lambda x: None
         # experimental config: experimental.hook-track-tags
         shouldtracktags = self.ui.configbool('experimental', 'hook-track-tags')
         if desc != 'strip' and shouldtracktags:
             oldheads = self.changelog.headrevs()
             def tracktags(tr2):
                 repo = reporef()
                 oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads)
                 newheads = repo.changelog.headrevs()
                 newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads)
                 # notes: we compare lists here.
                 # As we do it only once buiding set would not be cheaper
                 changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes)
                 if changes:
                     tr2.hookargs['tag_moved'] = '1'
                     with repo.vfs('changes/tags.changes', 'w',
                                   atomictemp=True) as changesfile:
                         # note: we do not register the file to the transaction
                         # because we needs it to still exist on the transaction
                         # is close (for txnclose hooks)
                         tagsmod.writediff(changesfile, changes)
         def validate(tr2):
             """will run pre-closing hooks"""
             # XXX the transaction API is a bit lacking here so we take a hacky
             # path for now
             #
             # We cannot add this as a "pending" hooks since the 'tr.hookargs'
             # dict is copied before these run. In addition we needs the data
             # available to in memory hooks too.
             #
             # Moreover, we also need to make sure this runs before txnclose
             # hooks and there is no "pending" mechanism that would execute
             # logic only if hooks are about to run.
             #
             # Fixing this limitation of the transaction is also needed to track
             # other families of changes (bookmarks, phases, obsolescence).
             #
             # This will have to be fixed before we remove the experimental
             # gating.
             tracktags(tr2)
             repo = reporef()
             if repo.ui.configbool('experimental', 'single-head-per-branch'):
                 scmutil.enforcesinglehead(repo, tr2, desc)
             if hook.hashook(repo.ui, 'pretxnclose-bookmark'):
                 for name, (old, new) in sorted(tr.changes['bookmarks'].items()):
                     args = tr.hookargs.copy()
                     args.update(bookmarks.preparehookargs(name, old, new))
                     repo.hook('pretxnclose-bookmark', throw=True,
                               txnname=desc,
                               **pycompat.strkwargs(args))
             if hook.hashook(repo.ui, 'pretxnclose-phase'):
                 cl = repo.unfiltered().changelog
                 for rev, (old, new) in tr.changes['phases'].items():
                     args = tr.hookargs.copy()
                     node = hex(cl.node(rev))
                     args.update(phases.preparehookargs(node, old, new))
                     repo.hook('pretxnclose-phase', throw=True, txnname=desc,
                               **pycompat.strkwargs(args))
 
             repo.hook('pretxnclose', throw=True,
                       txnname=desc, **pycompat.strkwargs(tr.hookargs))
         def releasefn(tr, success):
             repo = reporef()
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 narrowspec.restorebackup(self, 'journal.narrowspec')
                 repo.dirstate.restorebackup(None, 'journal.dirstate')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(rp, self.svfs, vfsmap,
                                      "journal",
                                      "undo",
                                      aftertrans(renames),
                                      self.store.createmode,
                                      validator=validate,
                                      releasefn=releasefn,
                                      checkambigfiles=_cachedfiles,
                                      name=desc)
-        tr.changes['revs'] = pycompat.xrange(0, 0)
+        tr.changes['origrepolen'] = len(self)
         tr.changes['obsmarkers'] = set()
         tr.changes['phases'] = {}
         tr.changes['bookmarks'] = {}
 
         tr.hookargs['txnid'] = txnid
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize('flush-fncache', self.store.write)
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run
             """
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hookfunc():
                 repo = reporef()
                 if hook.hashook(repo.ui, 'txnclose-bookmark'):
                     bmchanges = sorted(tr.changes['bookmarks'].items())
                     for name, (old, new) in bmchanges:
                         args = tr.hookargs.copy()
                         args.update(bookmarks.preparehookargs(name, old, new))
                         repo.hook('txnclose-bookmark', throw=False,
                                   txnname=desc, **pycompat.strkwargs(args))
 
                 if hook.hashook(repo.ui, 'txnclose-phase'):
                     cl = repo.unfiltered().changelog
                     phasemv = sorted(tr.changes['phases'].items())
                     for rev, (old, new) in phasemv:
                         args = tr.hookargs.copy()
                         node = hex(cl.node(rev))
                         args.update(phases.preparehookargs(node, old, new))
                         repo.hook('txnclose-phase', throw=False, txnname=desc,
                                   **pycompat.strkwargs(args))
 
                 repo.hook('txnclose', throw=False, txnname=desc,
                           **pycompat.strkwargs(hookargs))
             reporef()._afterlock(hookfunc)
         tr.addfinalize('txnclose-hook', txnclosehook)
         # Include a leading "-" to make it happen before the transaction summary
         # reports registered via scmutil.registersummarycallback() whose names
         # are 00-txnreport etc. That way, the caches will be warm when the
         # callbacks run.
         tr.addpostclose('-warm-cache', self._buildcacheupdater(tr))
         def txnaborthook(tr2):
             """To be run if transaction is aborted
             """
             reporef().hook('txnabort', throw=False, txnname=desc,
                            **pycompat.strkwargs(tr2.hookargs))
         tr.addabort('txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose('refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         scmutil.registersummarycallback(self, tr, desc)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     @unfilteredmethod
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, 'journal.dirstate')
         narrowspec.savebackup(self, 'journal.narrowspec')
         self.vfs.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.vfs.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.vfs.write("journal.bookmarks",
                           self.vfs.tryread("bookmarks"))
         self.svfs.write("journal.phaseroots",
                            self.svfs.tryread("phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 vfsmap = {'': self.svfs,
                           'plain': self.vfs,}
                 transaction.rollback(self.svfs, vfsmap, "journal",
                                      self.ui.warn,
                                      checkambigfiles=_cachedfiles)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 dsguard = dirstateguard.dirstateguard(self, 'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise error.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {'plain': self.vfs, '': self.svfs}
         transaction.rollback(self.svfs, vfsmap, 'undo', ui.warn,
                              checkambigfiles=_cachedfiles)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks', checkambig=True)
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots', checkambig=True)
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, 'undo.narrowspec')
             self.dirstate.restorebackup(None, 'undo.dirstate')
             try:
                 branch = self.vfs.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
             mergemod.mergestate.clean(self, self['.'].node())
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def _buildcacheupdater(self, newtransaction):
         """called during transaction to build the callback updating cache
 
         Lives on the repository to help extension who might want to augment
         this logic. For this purpose, the created transaction is passed to the
         method.
         """
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         def updater(tr):
             repo = reporef()
             repo.updatecaches(tr)
         return updater
 
     @unfilteredmethod
     def updatecaches(self, tr=None, full=False):
         """warm appropriate caches
 
         If this function is called after a transaction closed. The transaction
         will be available in the 'tr' argument. This can be used to selectively
         update caches relevant to the changes in that transaction.
 
         If 'full' is set, make sure all caches the function knows about have
         up-to-date data. Even the ones usually loaded more lazily.
         """
         if tr is not None and tr.hookargs.get('source') == 'strip':
             # During strip, many caches are invalid but
             # later call to `destroyed` will refresh them.
             return
 
-        if tr is None or tr.changes['revs']:
+        if tr is None or tr.changes['origrepolen'] < len(self):
             # updating the unfiltered branchmap should refresh all the others,
             self.ui.debug('updating the branch cache\n')
             branchmap.updatecache(self.filtered('served'))
 
         if full:
             rbc = self.revbranchcache()
             for r in self.changelog:
                 rbc.branchinfo(r)
             rbc.write()
 
             # ensure the working copy parents are in the manifestfulltextcache
             for ctx in self['.'].parents():
                 ctx.manifest()  # accessing the manifest is enough
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._branchcaches.clear()
         self.invalidatevolatilesets()
         self._sparsesignaturecache.clear()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
             if (k == 'changelog' and
                 self.currenttransaction() and
                 self.changelog._delayed):
                 # The changelog object may store unwritten revisions. We don't
                 # want to lose them.
                 # TODO: Solve the problem instead of working around it.
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             k = pycompat.sysstr(k)
             if k == r'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(self, vfs, lockname, wait, releasefn, acquirefn, desc,
               inheritchecker=None, parentenvvar=None):
         parentlock = None
         # the contents of parentenvvar are used by the underlying lock to
         # determine whether it can be inherited
         if parentenvvar is not None:
             parentlock = encoding.environ.get(parentenvvar)
 
         timeout = 0
         warntimeout = 0
         if wait:
             timeout = self.ui.configint("ui", "timeout")
             warntimeout = self.ui.configint("ui", "timeout.warn")
         # internal config: ui.signal-safe-lock
         signalsafe = self.ui.configbool('ui', 'signal-safe-lock')
 
         l = lockmod.trylock(self.ui, vfs, lockname, timeout, warntimeout,
                             releasefn=releasefn,
                             acquirefn=acquirefn, desc=desc,
                             inheritchecker=inheritchecker,
                             parentlock=parentlock,
                             signalsafe=signalsafe)
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else: # no lock have been found.
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(self.svfs, "lock", wait, None,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def _wlockchecktransaction(self):
         if self.currenttransaction() is not None:
             raise error.LockInheritanceContractViolation(
                 'wlock cannot be inherited in the middle of a transaction')
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (self.ui.configbool('devel', 'all-warnings')
                      or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn('"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.vfs, "wlock", wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot,
                        inheritchecker=self._wlockchecktransaction,
                        parentenvvar='HG_WLOCK_LOCKER')
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = manifest2.get(fname, nullid)
         if isinstance(fctx, context.filectx):
             node = fctx.filenode()
             if node in [fparent1, fparent2]:
                 self.ui.debug('reusing %s filelog entry\n' % fname)
                 if manifest1.flags(fname) != fctx.flags():
                     changelist.append(fname)
                 return node
 
         flog = self.file(fname)
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # Here, we used to search backwards through history to try to find
             # where the file copy came from if the source of a copy was not in
             # the parent directory. However, this doesn't actually make sense to
             # do (what does a copy from something not in your working copy even
             # mean?) and it causes bugs (eg, issue4476). Instead, we will warn
             # the user that copy information was dropped, so if they didn't
             # expect this outcome it can be fixed, but this is the correct
             # behavior in this circumstance.
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         text = fctx.data()
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
         # are just the flags changed during merge?
         elif fname in manifest1 and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def checkcommitpatterns(self, wctx, vdirs, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == '.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _('file not found!'))
                 if f in vdirs: # visited directory
                     d = f + '/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _("no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _("file not tracked!"))
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra=None):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         wlock = lock = tr = None
         try:
             wlock = self.wlock()
             lock = self.lock() # for recent changelog (see issue4368)
 
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and not match.always():
                 raise error.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(status.clean) # mq may commit clean files
 
             # check subrepos
             subs, commitsubs, newstate = subrepoutil.precommit(
                 self.ui, wctx, status, match, force=force)
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, vdirs, match, status, fail)
 
             cctx = context.workingcommitctx(self, status,
                                             text, user, date, extra)
 
             # internal config: ui.allowemptycommit
             allowemptycommit = (wctx.branch() != wctx.p1().branch()
                                 or extra.get('close') or merge or cctx.files()
                                 or self.ui.configbool('ui', 'allowemptycommit'))
             if not allowemptycommit:
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                                    subrepoutil.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepoutil.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 tr = self.transaction('commit')
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
             tr.close()
 
         finally:
             lockmod.release(tr, lock, wlock)
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook("commit", node=node, parent1=parent1,
                           parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
 
         ctx.files() should list all files involved in this commit, i.e.
         modified/added/removed files. On merge, it may be wider than the
         ctx.files() to be committed, since any file nodes derived directly
         from p1 or p2 are excluded from the committed ctx.files().
         """
 
         tr = None
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.manifestnode():
                 # reuse an existing manifest revision
                 self.ui.debug('reusing known manifest\n')
                 mn = ctx.manifestnode()
                 files = ctx.files()
             elif ctx.files():
                 m1ctx = p1.manifestctx()
                 m2ctx = p2.manifestctx()
                 mctx = m1ctx.copy()
 
                 m = mctx.read()
                 m1 = m1ctx.read()
                 m2 = m2ctx.read()
 
                 # check in files
                 added = []
                 changed = []
                 removed = list(ctx.removed())
                 linkrev = len(self)
                 self.ui.note(_("committing files:\n"))
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         if fctx is None:
                             removed.append(f)
                         else:
                             added.append(f)
                             m[f] = self._filecommit(fctx, m1, m2, linkrev,
                                                     trp, changed)
                             m.setflag(f, fctx.flags())
                     except OSError as inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError as inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
 
                 # update manifest
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m]
                 for f in drop:
                     del m[f]
                 files = changed + removed
                 md = None
                 if not files:
                     # if no "files" actually changed in terms of the changelog,
                     # try hard to detect unmodified manifest entry so that the
                     # exact same commit can be reproduced later on convert.
                     md = m1.diff(m, scmutil.matchfiles(self, ctx.files()))
                 if not files and md:
                     self.ui.debug('not reusing manifest (no file change in '
                                   'changelog, but manifest differs)\n')
                 if files or md:
                     self.ui.note(_("committing manifest\n"))
                     mn = mctx.write(trp, linkrev,
                                     p1.manifestnode(), p2.manifestnode(),
                                     added, drop)
                 else:
                     self.ui.debug('reusing manifest form p1 (listed files '
                                   'actually unchanged)\n')
                     mn = p1.manifestnode()
             else:
                 self.ui.debug('reusing manifest from p1 (no file change)\n')
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.ui.note(_("committing changelog\n"))
             self.changelog.delayupdate(tr)
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             # set the new commit is proper phase
             targetphase = subrepoutil.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.registernew(self, tr, targetphase, [n])
             tr.close()
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # refresh all repository caches
         self.updatecaches()
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(node2, match, ignored, clean, unknown,
                                   listsubrepos)
 
     def addpostdsstatus(self, ps):
         """Add a callback to run within the wlock, at the point at which status
         fixups happen.
 
         On status completion, callback(wctx, status) will be called with the
         wlock held, unless the dirstate has changed from underneath or the wlock
         couldn't be grabbed.
 
         Callbacks should not capture and use a cached copy of the dirstate --
         it might change in the meanwhile. Instead, they should access the
         dirstate via wctx.repo().dirstate.
 
         This list is emptied out after each status run -- extensions should
         make sure it adds to this list each time dirstate.status is called.
         Extensions should also make sure they don't call this for statuses
         that don't involve the dirstate.
         """
 
         # The list is located here for uniqueness reasons -- it is actually
         # managed by the workingctx, but that isn't unique per-repo.
         self._postdsstatus.append(ps)
 
     def postdsstatus(self):
         """Used by workingctx to get the list of post-dirstate-status hooks."""
         return self._postdsstatus
 
     def clearpostdsstatus(self):
         """Used by workingctx to clear post-dirstate-status hooks."""
         del self._postdsstatus[:]
 
     def heads(self, start=None):
         if start is None:
             cl = self.changelog
             headrevs = reversed(cl.headrevs())
             return [cl.node(rev) for rev in headrevs]
 
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs = pycompat.strkwargs(hookargs)
             hookargs[r'namespace'] = namespace
             hookargs[r'key'] = key
             hookargs[r'old'] = old
             hookargs[r'new'] = new
             self.hook('prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_("pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_("(%s)\n") % exc.hint)
             return False
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         def runhook():
             self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                       ret=ret)
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def savecommitmessage(self, text):
         fp = self.vfs('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             # if src and dest refer to a same file, vfs.rename is a no-op,
             # leaving both src and dest on disk. delete dest to make sure
             # the rename couldn't be such a no-op.
             vfs.tryunlink(dest)
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create, intents=None):
     return localrepository(ui, util.urllocalpath(path), create,
                            intents=intents)
 
 def islocal(path):
     return True
 
 def newreporequirements(repo):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     ui = repo.ui
     requirements = {'revlogv1'}
     if ui.configbool('format', 'usestore'):
         requirements.add('store')
         if ui.configbool('format', 'usefncache'):
             requirements.add('fncache')
             if ui.configbool('format', 'dotencode'):
                 requirements.add('dotencode')
 
     compengine = ui.config('experimental', 'format.compression')
     if compengine not in util.compengines:
         raise error.Abort(_('compression engine %s defined by '
                             'experimental.format.compression not available') %
                           compengine,
                           hint=_('run "hg debuginstall" to list available '
                                  'compression engines'))
 
     # zlib is the historical default and doesn't need an explicit requirement.
     if compengine != 'zlib':
         requirements.add('exp-compression-%s' % compengine)
 
     if scmutil.gdinitconfig(ui):
         requirements.add('generaldelta')
     if ui.configbool('experimental', 'treemanifest'):
         requirements.add('treemanifest')
     # experimental config: format.sparse-revlog
     if ui.configbool('format', 'sparse-revlog'):
         requirements.add(SPARSEREVLOG_REQUIREMENT)
 
     revlogv2 = ui.config('experimental', 'revlogv2')
     if revlogv2 == 'enable-unstable-format-and-corrupt-my-data':
         requirements.remove('revlogv1')
         # generaldelta is implied by revlogv2.
         requirements.discard('generaldelta')
         requirements.add(REVLOGV2_REQUIREMENT)
     # experimental config: format.internal-phase
     if repo.ui.configbool('format', 'internal-phase'):
         requirements.add('internal-phase')
 
     return requirements

mercurial/obsutil.py

@@ -1,982 +1,982
 # obsutil.py - utility functions for obsolescence
 #
 # Copyright 2017 Boris Feld <[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 (
     diffutil,
     encoding,
     node as nodemod,
     phases,
     util,
 )
 from .utils import (
     dateutil,
 )
 
 ### 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
 
 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 prednode(self):
         """Predecessor 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 predecessors (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]
 
 def getmarkers(repo, nodes=None, exclusive=False):
     """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
     elif exclusive:
         rawmarkers = exclusivemarkers(repo, nodes)
     else:
         rawmarkers = repo.obsstore.relevantmarkers(nodes)
 
     for markerdata in rawmarkers:
         yield marker(repo, markerdata)
 
 def closestpredecessors(repo, nodeid):
     """yield the list of next predecessors pointing on visible changectx nodes
 
     This function respect the repoview filtering, filtered revision will be
     considered missing.
     """
 
     precursors = repo.obsstore.predecessors
     stack = [nodeid]
     seen = set(stack)
 
     while stack:
         current = stack.pop()
         currentpreccs = precursors.get(current, ())
 
         for prec in currentpreccs:
             precnodeid = prec[0]
 
             # Basic cycle protection
             if precnodeid in seen:
                 continue
             seen.add(precnodeid)
 
             if precnodeid in repo:
                 yield precnodeid
             else:
                 stack.append(precnodeid)
 
 def allpredecessors(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.predecessors.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 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 _filterprunes(markers):
     """return a set with no prune markers"""
     return set(m for m in markers if m[1])
 
 def exclusivemarkers(repo, nodes):
     """set of markers relevant to "nodes" but no other locally-known nodes
 
     This function compute the set of markers "exclusive" to a locally-known
     node. This means we walk the markers starting from <nodes> until we reach a
     locally-known precursors outside of <nodes>. Element of <nodes> with
     locally-known successors outside of <nodes> are ignored (since their
     precursors markers are also relevant to these successors).
 
     For example:
 
         # (A0 rewritten as A1)
         #
         # A0 <-1- A1 # Marker "1" is exclusive to A1
 
         or
 
         # (A0 rewritten as AX; AX rewritten as A1; AX is unkown locally)
         #
         # <-1- A0 <-2- AX <-3- A1 # Marker "2,3" are exclusive to A1
 
         or
 
         # (A0 has unknown precursors, A0 rewritten as A1 and A2 (divergence))
         #
         #          <-2- A1 # Marker "2" is exclusive to A0,A1
         #        /
         # <-1- A0
         #        \
         #         <-3- A2 # Marker "3" is exclusive to A0,A2
         #
         # in addition:
         #
         #  Markers "2,3" are exclusive to A1,A2
         #  Markers "1,2,3" are exclusive to A0,A1,A2
 
         See test/test-obsolete-bundle-strip.t for more examples.
 
     An example usage is strip. When stripping a changeset, we also want to
     strip the markers exclusive to this changeset. Otherwise we would have
     "dangling"" obsolescence markers from its precursors: Obsolescence markers
     marking a node as obsolete without any successors available locally.
 
     As for relevant markers, the prune markers for children will be followed.
     Of course, they will only be followed if the pruned children is
     locally-known. Since the prune markers are relevant to the pruned node.
     However, while prune markers are considered relevant to the parent of the
     pruned changesets, prune markers for locally-known changeset (with no
     successors) are considered exclusive to the pruned nodes. This allows
     to strip the prune markers (with the rest of the exclusive chain) alongside
     the pruned changesets.
     """
     # running on a filtered repository would be dangerous as markers could be
     # reported as exclusive when they are relevant for other filtered nodes.
     unfi = repo.unfiltered()
 
     # shortcut to various useful item
     nm = unfi.changelog.nodemap
     precursorsmarkers = unfi.obsstore.predecessors
     successormarkers = unfi.obsstore.successors
     childrenmarkers = unfi.obsstore.children
 
     # exclusive markers (return of the function)
     exclmarkers = set()
     # we need fast membership testing
     nodes = set(nodes)
     # looking for head in the obshistory
     #
     # XXX we are ignoring all issues in regard with cycle for now.
     stack = [n for n in nodes if not _filterprunes(successormarkers.get(n, ()))]
     stack.sort()
     # nodes already stacked
     seennodes = set(stack)
     while stack:
         current = stack.pop()
         # fetch precursors markers
         markers = list(precursorsmarkers.get(current, ()))
         # extend the list with prune markers
         for mark in successormarkers.get(current, ()):
             if not mark[1]:
                 markers.append(mark)
         # and markers from children (looking for prune)
         for mark in childrenmarkers.get(current, ()):
             if not mark[1]:
                 markers.append(mark)
         # traverse the markers
         for mark in markers:
             if mark in exclmarkers:
                 # markers already selected
                 continue
 
             # If the markers is about the current node, select it
             #
             # (this delay the addition of markers from children)
             if mark[1] or mark[0] == current:
                 exclmarkers.add(mark)
 
             # should we keep traversing through the precursors?
             prec = mark[0]
 
             # nodes in the stack or already processed
             if prec in seennodes:
                 continue
 
             # is this a locally known node ?
             known = prec in nm
             # if locally-known and not in the <nodes> set the traversal
             # stop here.
             if known and prec not in nodes:
                 continue
 
             # do not keep going if there are unselected markers pointing to this
             # nodes. If we end up traversing these unselected markers later the
             # node will be taken care of at that point.
             precmarkers = _filterprunes(successormarkers.get(prec))
             if precmarkers.issubset(exclmarkers):
                 seennodes.add(prec)
                 stack.append(prec)
 
     return exclmarkers
 
 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)
 
 # effectflag field
 #
 # Effect-flag is a 1-byte bit field used to store what changed between a
 # changeset and its successor(s).
 #
 # The effect flag is stored in obs-markers metadata while we iterate on the
 # information design. That's why we have the EFFECTFLAGFIELD. If we come up
 # with an incompatible design for effect flag, we can store a new design under
 # another field name so we don't break readers. We plan to extend the existing
 # obsmarkers bit-field when the effect flag design will be stabilized.
 #
 # The effect-flag is placed behind an experimental flag
 # `effect-flags` set to off by default.
 #
 
 EFFECTFLAGFIELD = "ef1"
 
 DESCCHANGED = 1 << 0 # action changed the description
 METACHANGED = 1 << 1 # action change the meta
 DIFFCHANGED = 1 << 3 # action change diff introduced by the changeset
 PARENTCHANGED = 1 << 2 # action change the parent
 USERCHANGED = 1 << 4 # the user changed
 DATECHANGED = 1 << 5 # the date changed
 BRANCHCHANGED = 1 << 6 # the branch changed
 
 METABLACKLIST = [
     re.compile('^branch$'),
     re.compile('^.*-source$'),
     re.compile('^.*_source$'),
     re.compile('^source$'),
 ]
 
 def metanotblacklisted(metaitem):
     """ Check that the key of a meta item (extrakey, extravalue) does not
     match at least one of the blacklist pattern
     """
     metakey = metaitem[0]
 
     return not any(pattern.match(metakey) for pattern in METABLACKLIST)
 
 def _prepare_hunk(hunk):
     """Drop all information but the username and patch"""
     cleanhunk = []
     for line in hunk.splitlines():
         if line.startswith(b'# User') or not line.startswith(b'#'):
             if line.startswith(b'@@'):
                 line = b'@@\n'
             cleanhunk.append(line)
     return cleanhunk
 
 def _getdifflines(iterdiff):
     """return a cleaned up lines"""
     lines = next(iterdiff, None)
 
     if lines is None:
         return lines
 
     return _prepare_hunk(lines)
 
 def _cmpdiff(leftctx, rightctx):
     """return True if both ctx introduce the "same diff"
 
     This is a first and basic implementation, with many shortcoming.
     """
     diffopts = diffutil.diffallopts(leftctx.repo().ui, {'git': True})
     # Leftctx or right ctx might be filtered, so we need to use the contexts
     # with an unfiltered repository to safely compute the diff
     leftunfi = leftctx._repo.unfiltered()[leftctx.rev()]
     leftdiff = leftunfi.diff(opts=diffopts)
     rightunfi = rightctx._repo.unfiltered()[rightctx.rev()]
     rightdiff = rightunfi.diff(opts=diffopts)
 
     left, right = (0, 0)
     while None not in (left, right):
         left = _getdifflines(leftdiff)
         right = _getdifflines(rightdiff)
 
         if left != right:
             return False
     return True
 
 def geteffectflag(relation):
     """ From an obs-marker relation, compute what changed between the
     predecessor and the successor.
     """
     effects = 0
 
     source = relation[0]
 
     for changectx in relation[1]:
         # Check if description has changed
         if changectx.description() != source.description():
             effects |= DESCCHANGED
 
         # Check if user has changed
         if changectx.user() != source.user():
             effects |= USERCHANGED
 
         # Check if date has changed
         if changectx.date() != source.date():
             effects |= DATECHANGED
 
         # Check if branch has changed
         if changectx.branch() != source.branch():
             effects |= BRANCHCHANGED
 
         # Check if at least one of the parent has changed
         if changectx.parents() != source.parents():
             effects |= PARENTCHANGED
 
         # Check if other meta has changed
         changeextra = changectx.extra().items()
         ctxmeta = list(filter(metanotblacklisted, changeextra))
 
         sourceextra = source.extra().items()
         srcmeta = list(filter(metanotblacklisted, sourceextra))
 
         if ctxmeta != srcmeta:
             effects |= METACHANGED
 
         # Check if the diff has changed
         if not _cmpdiff(source, changectx):
             effects |= DIFFCHANGED
 
     return effects
 
 def getobsoleted(repo, tr):
     """return the set of pre-existing revisions obsoleted by a transaction"""
     torev = repo.unfiltered().changelog.nodemap.get
     phase = repo._phasecache.phase
     succsmarkers = repo.obsstore.successors.get
     public = phases.public
     addedmarkers = tr.changes.get('obsmarkers')
-    addedrevs = tr.changes['revs']
+    origrepolen = tr.changes['origrepolen']
     seenrevs = set()
     obsoleted = set()
     for mark in addedmarkers:
         node = mark[0]
         rev = torev(node)
-        if rev is None or rev in seenrevs or rev in addedrevs:
+        if rev is None or rev in seenrevs or rev >= origrepolen:
             continue
         seenrevs.add(rev)
         if phase(repo, rev) == public:
             continue
         if set(succsmarkers(node) or []).issubset(addedmarkers):
             obsoleted.add(rev)
     return obsoleted
 
 class _succs(list):
     """small class to represent a successors with some metadata about it"""
 
     def __init__(self, *args, **kwargs):
         super(_succs, self).__init__(*args, **kwargs)
         self.markers = set()
 
     def copy(self):
         new = _succs(self)
         new.markers = self.markers.copy()
         return new
 
     @util.propertycache
     def _set(self):
         # immutable
         return set(self)
 
     def canmerge(self, other):
         return self._set.issubset(other._set)
 
 def successorssets(repo, initialnode, closest=False, 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. By default, the successors set contains non-obsolete
     changesets only, walking the obsolescence graph until reaching a leaf. If
     'closest' is set to True, closest successors-sets are return (the
     obsolescence walk stops on known changesets).
 
     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, final successors unknown locally are considered to be pruned
     (pruned: obsoleted without any successors). (Final: successors not affected
     by markers).
 
     The 'closest' mode respect the repoview filtering. For example, without
     filter it will stop at the first locally known changeset, with 'visible'
     filter it will stop on visible changesets).
 
     The optional `cache` parameter is a dictionary that may contains
     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`
     *should* use this cache mechanism or risk a performance hit.
 
     Since results are different depending of the 'closest' most, the same cache
     cannot be reused for both mode.
     """
 
     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) Stop the walk:
         #    default case: Node is not obsolete
         #    closest case: Node is known at this repo filter level
         #      -> 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]
 
         # case 2 condition is a bit hairy because of closest,
         # we compute it on its own
         case2condition =  ((current not in succmarkers)
                            or (closest and current != initialnode
                                and current in repo))
 
         if current in cache:
             # case (1): We already know the successors sets
             stackedset.remove(toproceed.pop())
         elif case2condition:
             # case (2): end of walk.
             if current in repo:
                 # We have a valid successors.
                 cache[current] = [_succs((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
                     base = _succs()
                     base.markers.add(mark)
                     markss = [base]
                     for suc in mark[1]:
                         # cardinal product with previous successors
                         productresult = []
                         for prefix in markss:
                             for suffix in cache[suc]:
                                 newss = prefix.copy()
                                 newss.markers.update(suffix.markers)
                                 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 = []
                 candidates = sorted((s for s in succssets if s),
                                     key=len, reverse=True)
                 for cand in candidates:
                     for seensuccs in seen:
                         if cand.canmerge(seensuccs):
                             seensuccs.markers.update(cand.markers)
                             break
                     else:
                         final.append(cand)
                         seen.append(cand)
                 final.reverse() # put small successors set first
                 cache[current] = final
     return cache[initialnode]
 
 def successorsandmarkers(repo, ctx):
     """compute the raw data needed for computing obsfate
     Returns a list of dict, one dict per successors set
     """
     if not ctx.obsolete():
         return None
 
     ssets = successorssets(repo, ctx.node(), closest=True)
 
     # closestsuccessors returns an empty list for pruned revisions, remap it
     # into a list containing an empty list for future processing
     if ssets == []:
         ssets = [[]]
 
     # Try to recover pruned markers
     succsmap = repo.obsstore.successors
     fullsuccessorsets = [] # successor set + markers
     for sset in ssets:
         if sset:
             fullsuccessorsets.append(sset)
         else:
             # successorsset return an empty set() when ctx or one of its
             # successors is pruned.
             # In this case, walk the obs-markers tree again starting with ctx
             # and find the relevant pruning obs-makers, the ones without
             # successors.
             # Having these markers allow us to compute some information about
             # its fate, like who pruned this changeset and when.
 
             # XXX we do not catch all prune markers (eg rewritten then pruned)
             # (fix me later)
             foundany = False
             for mark in succsmap.get(ctx.node(), ()):
                 if not mark[1]:
                     foundany = True
                     sset = _succs()
                     sset.markers.add(mark)
                     fullsuccessorsets.append(sset)
             if not foundany:
                 fullsuccessorsets.append(_succs())
 
     values = []
     for sset in fullsuccessorsets:
         values.append({'successors': sset, 'markers': sset.markers})
 
     return values
 
 def _getobsfate(successorssets):
     """ Compute a changeset obsolescence fate based on its successorssets.
     Successors can be the tipmost ones or the immediate ones. This function
     return values are not meant to be shown directly to users, it is meant to
     be used by internal functions only.
     Returns one fate from the following values:
     - pruned
     - diverged
     - superseded
     - superseded_split
     """
 
     if len(successorssets) == 0:
         # The commit has been pruned
         return 'pruned'
     elif len(successorssets) > 1:
         return 'diverged'
     else:
         # No divergence, only one set of successors
         successors = successorssets[0]
 
         if len(successors) == 1:
             return 'superseded'
         else:
             return 'superseded_split'
 
 def obsfateverb(successorset, markers):
     """ Return the verb summarizing the successorset and potentially using
     information from the markers
     """
     if not successorset:
         verb = 'pruned'
     elif len(successorset) == 1:
         verb = 'rewritten'
     else:
         verb = 'split'
     return verb
 
 def markersdates(markers):
     """returns the list of dates for a list of markers
     """
     return [m[4] for m in markers]
 
 def markersusers(markers):
     """ Returns a sorted list of markers users without duplicates
     """
     markersmeta = [dict(m[3]) for m in markers]
     users = set(encoding.tolocal(meta['user']) for meta in markersmeta
                 if meta.get('user'))
 
     return sorted(users)
 
 def markersoperations(markers):
     """ Returns a sorted list of markers operations without duplicates
     """
     markersmeta = [dict(m[3]) for m in markers]
     operations = set(meta.get('operation') for meta in markersmeta
                      if meta.get('operation'))
 
     return sorted(operations)
 
 def obsfateprinter(ui, repo, successors, markers, formatctx):
     """ Build a obsfate string for a single successorset using all obsfate
     related function defined in obsutil
     """
     quiet = ui.quiet
     verbose = ui.verbose
     normal = not verbose and not quiet
 
     line = []
 
     # Verb
     line.append(obsfateverb(successors, markers))
 
     # Operations
     operations = markersoperations(markers)
     if operations:
         line.append(" using %s" % ", ".join(operations))
 
     # Successors
     if successors:
         fmtsuccessors = [formatctx(repo[succ]) for succ in successors]
         line.append(" as %s" % ", ".join(fmtsuccessors))
 
     # Users
     users = markersusers(markers)
     # Filter out current user in not verbose mode to reduce amount of
     # information
     if not verbose:
         currentuser = ui.username(acceptempty=True)
         if len(users) == 1 and currentuser in users:
             users = None
 
     if (verbose or normal) and users:
         line.append(" by %s" % ", ".join(users))
 
     # Date
     dates = markersdates(markers)
 
     if dates and verbose:
         min_date = min(dates)
         max_date = max(dates)
 
         if min_date == max_date:
             fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
             line.append(" (at %s)" % fmtmin_date)
         else:
             fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
             fmtmax_date = dateutil.datestr(max_date, '%Y-%m-%d %H:%M %1%2')
             line.append(" (between %s and %s)" % (fmtmin_date, fmtmax_date))
 
     return "".join(line)
 
 
 filteredmsgtable = {
     "pruned": _("hidden revision '%s' is pruned"),
     "diverged": _("hidden revision '%s' has diverged"),
     "superseded": _("hidden revision '%s' was rewritten as: %s"),
     "superseded_split": _("hidden revision '%s' was split as: %s"),
     "superseded_split_several": _("hidden revision '%s' was split as: %s and "
                                   "%d more"),
 }
 
 def _getfilteredreason(repo, changeid, ctx):
     """return a human-friendly string on why a obsolete changeset is hidden
     """
     successors = successorssets(repo, ctx.node())
     fate = _getobsfate(successors)
 
     # Be more precise in case the revision is superseded
     if fate == 'pruned':
         return filteredmsgtable['pruned'] % changeid
     elif fate == 'diverged':
         return filteredmsgtable['diverged'] % changeid
     elif fate == 'superseded':
         single_successor = nodemod.short(successors[0][0])
         return filteredmsgtable['superseded'] % (changeid, single_successor)
     elif fate == 'superseded_split':
 
         succs = []
         for node_id in successors[0]:
             succs.append(nodemod.short(node_id))
 
         if len(succs) <= 2:
             fmtsuccs = ', '.join(succs)
             return filteredmsgtable['superseded_split'] % (changeid, fmtsuccs)
         else:
             firstsuccessors = ', '.join(succs[:2])
             remainingnumber = len(succs) - 2
 
             args = (changeid, firstsuccessors, remainingnumber)
             return filteredmsgtable['superseded_split_several'] % args
 
 def divergentsets(repo, ctx):
     """Compute sets of commits divergent with a given one"""
     cache = {}
     base = {}
     for n in allpredecessors(repo.obsstore, [ctx.node()]):
         if n == ctx.node():
             # a node can't be a base for divergence with itself
             continue
         nsuccsets = successorssets(repo, n, cache)
         for nsuccset in nsuccsets:
             if ctx.node() in nsuccset:
                 # we are only interested in *other* successor sets
                 continue
             if tuple(nsuccset) in base:
                 # we already know the latest base for this divergency
                 continue
             base[tuple(nsuccset)] = n
     return [{'divergentnodes': divset, 'commonpredecessor': b}
             for divset, b in base.iteritems()]
 
 def whyunstable(repo, ctx):
     result = []
     if ctx.orphan():
         for parent in ctx.parents():
             kind = None
             if parent.orphan():
                 kind = 'orphan'
             elif parent.obsolete():
                 kind = 'obsolete'
             if kind is not None:
                 result.append({'instability': 'orphan',
                                'reason': '%s parent' % kind,
                                'node': parent.hex()})
     if ctx.phasedivergent():
         predecessors = allpredecessors(repo.obsstore, [ctx.node()],
                                        ignoreflags=bumpedfix)
         immutable = [repo[p] for p in predecessors
                      if p in repo and not repo[p].mutable()]
         for predecessor in immutable:
             result.append({'instability': 'phase-divergent',
                            'reason': 'immutable predecessor',
                            'node': predecessor.hex()})
     if ctx.contentdivergent():
         dsets = divergentsets(repo, ctx)
         for dset in dsets:
             divnodes = [repo[n] for n in dset['divergentnodes']]
             result.append({'instability': 'content-divergent',
                            'divergentnodes': divnodes,
                            'reason': 'predecessor',
                            'node': nodemod.hex(dset['commonpredecessor'])})
     return result

mercurial/scmutil.py

@@ -1,1776 +1,1776
 # 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 errno
 import glob
 import hashlib
 import os
 import re
 import socket
 import subprocess
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     short,
     wdirid,
     wdirrev,
 )
 
 from . import (
     encoding,
     error,
     match as matchmod,
     obsolete,
     obsutil,
     pathutil,
     phases,
     policy,
     pycompat,
     revsetlang,
     similar,
     url,
     util,
     vfs,
 )
 
 from .utils import (
     procutil,
     stringutil,
 )
 
 if pycompat.iswindows:
     from . import scmwindows as scmplatform
 else:
     from . import scmposix as scmplatform
 
 parsers = policy.importmod(r'parsers')
 
 termsize = scmplatform.termsize
 
 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 ((r'<status modified=%s, added=%s, removed=%s, deleted=%s, '
                  r'unknown=%s, ignored=%s, clean=%s>') %
                 tuple(pycompat.sysstr(stringutil.pprint(v)) for v in 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:
             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 callcatch(ui, func):
     """call func() with global exception handling
 
     return func() if no exception happens. otherwise do some error handling
     and return an exit code accordingly. does not handle all exceptions.
     """
     try:
         try:
             return func()
         except: # re-raises
             ui.traceback()
             raise
     # Global exception handling, alphabetically
     # Mercurial-specific first, followed by built-in and library exceptions
     except error.LockHeld as inst:
         if inst.errno == errno.ETIMEDOUT:
             reason = _('timed out waiting for lock held by %r') % inst.locker
         else:
             reason = _('lock held by %r') % inst.locker
         ui.error(_("abort: %s: %s\n") % (
             inst.desc or stringutil.forcebytestr(inst.filename), reason))
         if not inst.locker:
             ui.error(_("(lock might be very busy)\n"))
     except error.LockUnavailable as inst:
         ui.error(_("abort: could not lock %s: %s\n") %
                  (inst.desc or stringutil.forcebytestr(inst.filename),
                   encoding.strtolocal(inst.strerror)))
     except error.OutOfBandError as inst:
         if inst.args:
             msg = _("abort: remote error:\n")
         else:
             msg = _("abort: remote error\n")
         ui.error(msg)
         if inst.args:
             ui.error(''.join(inst.args))
         if inst.hint:
             ui.error('(%s)\n' % inst.hint)
     except error.RepoError as inst:
         ui.error(_("abort: %s!\n") % inst)
         if inst.hint:
             ui.error(_("(%s)\n") % inst.hint)
     except error.ResponseError as inst:
         ui.error(_("abort: %s") % inst.args[0])
         msg = inst.args[1]
         if isinstance(msg, type(u'')):
             msg = pycompat.sysbytes(msg)
         if not isinstance(msg, bytes):
             ui.error(" %r\n" % (msg,))
         elif not msg:
             ui.error(_(" empty string\n"))
         else:
             ui.error("\n%r\n" % pycompat.bytestr(stringutil.ellipsis(msg)))
     except error.CensoredNodeError as inst:
         ui.error(_("abort: file censored %s!\n") % inst)
     except error.RevlogError as inst:
         ui.error(_("abort: %s!\n") % inst)
     except error.InterventionRequired as inst:
         ui.error("%s\n" % inst)
         if inst.hint:
             ui.error(_("(%s)\n") % inst.hint)
         return 1
     except error.WdirUnsupported:
         ui.error(_("abort: working directory revision cannot be specified\n"))
     except error.Abort as inst:
         ui.error(_("abort: %s\n") % inst)
         if inst.hint:
             ui.error(_("(%s)\n") % inst.hint)
     except ImportError as inst:
         ui.error(_("abort: %s!\n") % stringutil.forcebytestr(inst))
         m = stringutil.forcebytestr(inst).split()[-1]
         if m in "mpatch bdiff".split():
             ui.error(_("(did you forget to compile extensions?)\n"))
         elif m in "zlib".split():
             ui.error(_("(is your Python install correct?)\n"))
     except IOError as inst:
         if util.safehasattr(inst, "code"):
             ui.error(_("abort: %s\n") % stringutil.forcebytestr(inst))
         elif util.safehasattr(inst, "reason"):
             try: # usually it is in the form (errno, strerror)
                 reason = inst.reason.args[1]
             except (AttributeError, IndexError):
                 # it might be anything, for example a string
                 reason = inst.reason
             if isinstance(reason, pycompat.unicode):
                 # SSLError of Python 2.7.9 contains a unicode
                 reason = encoding.unitolocal(reason)
             ui.error(_("abort: error: %s\n") % reason)
         elif (util.safehasattr(inst, "args")
               and inst.args and inst.args[0] == errno.EPIPE):
             pass
         elif getattr(inst, "strerror", None):
             if getattr(inst, "filename", None):
                 ui.error(_("abort: %s: %s\n") % (
                     encoding.strtolocal(inst.strerror),
                     stringutil.forcebytestr(inst.filename)))
             else:
                 ui.error(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
         else:
             raise
     except OSError as inst:
         if getattr(inst, "filename", None) is not None:
             ui.error(_("abort: %s: '%s'\n") % (
                 encoding.strtolocal(inst.strerror),
                 stringutil.forcebytestr(inst.filename)))
         else:
             ui.error(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
     except MemoryError:
         ui.error(_("abort: out of memory\n"))
     except SystemExit as inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         return inst.code
     except socket.error as inst:
         ui.error(_("abort: %s\n") % stringutil.forcebytestr(inst.args[-1]))
 
     return -1
 
 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") % pycompat.bytestr(c))
     try:
         int(lbl)
         raise error.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
     if lbl.strip() != lbl:
         raise error.Abort(_("leading or trailing whitespace in name %r") % lbl)
 
 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")
                           % pycompat.bytestr(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: %s" % (msg, procutil.shellquote(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')
     lval = val.lower()
     bval = stringutil.parsebool(val)
     abort = pycompat.iswindows 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('%d;' % rev)
         key = s.digest()
     return key
 
 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):
             dirstat = os.stat(dirname)
             match = any(samestat(dirstat, lstdirstat) for lstdirstat in dirlst)
             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 binnode(ctx):
     """Return binary node id for a given basectx"""
     node = ctx.node()
     if node is None:
         return wdirid
     return node
 
 def intrev(ctx):
     """Return integer for a given basectx that can be used in comparison or
     arithmetic operation"""
     rev = ctx.rev()
     if rev is None:
         return wdirrev
     return rev
 
 def formatchangeid(ctx):
     """Format changectx as '{rev}:{node|formatnode}', which is the default
     template provided by logcmdutil.changesettemplater"""
     repo = ctx.repo()
     return formatrevnode(repo.ui, intrev(ctx), binnode(ctx))
 
 def formatrevnode(ui, rev, node):
     """Format given revision and node depending on the current verbosity"""
     if ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     return '%d:%s' % (rev, hexfunc(node))
 
 def resolvehexnodeidprefix(repo, prefix):
     if (prefix.startswith('x') and
         repo.ui.configbool('experimental', 'revisions.prefixhexnode')):
         prefix = prefix[1:]
     try:
         # Uses unfiltered repo because it's faster when prefix is ambiguous/
         # This matches the shortesthexnodeidprefix() function below.
         node = repo.unfiltered().changelog._partialmatch(prefix)
     except error.AmbiguousPrefixLookupError:
         revset = repo.ui.config('experimental', 'revisions.disambiguatewithin')
         if revset:
             # Clear config to avoid infinite recursion
             configoverrides = {('experimental',
                                 'revisions.disambiguatewithin'): None}
             with repo.ui.configoverride(configoverrides):
                 revs = repo.anyrevs([revset], user=True)
                 matches = []
                 for rev in revs:
                     node = repo.changelog.node(rev)
                     if hex(node).startswith(prefix):
                         matches.append(node)
                 if len(matches) == 1:
                     return matches[0]
         raise
     if node is None:
         return
     repo.changelog.rev(node)  # make sure node isn't filtered
     return node
 
 def mayberevnum(repo, prefix):
     """Checks if the given prefix may be mistaken for a revision number"""
     try:
         i = int(prefix)
         # if we are a pure int, then starting with zero will not be
         # confused as a rev; or, obviously, if the int is larger
         # than the value of the tip rev
         if prefix[0:1] == b'0' or i > len(repo):
             return False
         return True
     except ValueError:
         return False
 
 def shortesthexnodeidprefix(repo, node, minlength=1, cache=None):
     """Find the shortest unambiguous prefix that matches hexnode.
 
     If "cache" is not None, it must be a dictionary that can be used for
     caching between calls to this method.
     """
     # _partialmatch() of filtered changelog could take O(len(repo)) time,
     # which would be unacceptably slow. so we look for hash collision in
     # unfiltered space, which means some hashes may be slightly longer.
 
     def disambiguate(prefix):
         """Disambiguate against revnums."""
         if repo.ui.configbool('experimental', 'revisions.prefixhexnode'):
             if mayberevnum(repo, prefix):
                 return 'x' + prefix
             else:
                 return prefix
 
         hexnode = hex(node)
         for length in range(len(prefix), len(hexnode) + 1):
             prefix = hexnode[:length]
             if not mayberevnum(repo, prefix):
                 return prefix
 
     cl = repo.unfiltered().changelog
     revset = repo.ui.config('experimental', 'revisions.disambiguatewithin')
     if revset:
         revs = None
         if cache is not None:
             revs = cache.get('disambiguationrevset')
         if revs is None:
             revs = repo.anyrevs([revset], user=True)
             if cache is not None:
                 cache['disambiguationrevset'] = revs
         if cl.rev(node) in revs:
             hexnode = hex(node)
             nodetree = None
             if cache is not None:
                 nodetree = cache.get('disambiguationnodetree')
             if not nodetree:
                 try:
                     nodetree = parsers.nodetree(cl.index, len(revs))
                 except AttributeError:
                     # no native nodetree
                     pass
                 else:
                     for r in revs:
                         nodetree.insert(r)
                     if cache is not None:
                         cache['disambiguationnodetree'] = nodetree
             if nodetree is not None:
                 length = max(nodetree.shortest(node), minlength)
                 prefix = hexnode[:length]
                 return disambiguate(prefix)
             for length in range(minlength, len(hexnode) + 1):
                 matches = []
                 prefix = hexnode[:length]
                 for rev in revs:
                     otherhexnode = repo[rev].hex()
                     if prefix == otherhexnode[:length]:
                         matches.append(otherhexnode)
                 if len(matches) == 1:
                     return disambiguate(prefix)
 
     try:
         return disambiguate(cl.shortest(node, minlength))
     except error.LookupError:
         raise error.RepoLookupError()
 
 def isrevsymbol(repo, symbol):
     """Checks if a symbol exists in the repo.
 
     See revsymbol() for details. Raises error.AmbiguousPrefixLookupError if the
     symbol is an ambiguous nodeid prefix.
     """
     try:
         revsymbol(repo, symbol)
         return True
     except error.RepoLookupError:
         return False
 
 def revsymbol(repo, symbol):
     """Returns a context given a single revision symbol (as string).
 
     This is similar to revsingle(), but accepts only a single revision symbol,
     i.e. things like ".", "tip", "1234", "deadbeef", "my-bookmark" work, but
     not "max(public())".
     """
     if not isinstance(symbol, bytes):
         msg = ("symbol (%s of type %s) was not a string, did you mean "
                "repo[symbol]?" % (symbol, type(symbol)))
         raise error.ProgrammingError(msg)
     try:
         if symbol in ('.', 'tip', 'null'):
             return repo[symbol]
 
         try:
             r = int(symbol)
             if '%d' % r != symbol:
                 raise ValueError
             l = len(repo.changelog)
             if r < 0:
                 r += l
             if r < 0 or r >= l and r != wdirrev:
                 raise ValueError
             return repo[r]
         except error.FilteredIndexError:
             raise
         except (ValueError, OverflowError, IndexError):
             pass
 
         if len(symbol) == 40:
             try:
                 node = bin(symbol)
                 rev = repo.changelog.rev(node)
                 return repo[rev]
             except error.FilteredLookupError:
                 raise
             except (TypeError, LookupError):
                 pass
 
         # look up bookmarks through the name interface
         try:
             node = repo.names.singlenode(repo, symbol)
             rev = repo.changelog.rev(node)
             return repo[rev]
         except KeyError:
             pass
 
         node = resolvehexnodeidprefix(repo, symbol)
         if node is not None:
             rev = repo.changelog.rev(node)
             return repo[rev]
 
         raise error.RepoLookupError(_("unknown revision '%s'") % symbol)
 
     except error.WdirUnsupported:
         return repo[None]
     except (error.FilteredIndexError, error.FilteredLookupError,
             error.FilteredRepoLookupError):
         raise _filterederror(repo, symbol)
 
 def _filterederror(repo, changeid):
     """build an exception to be raised about a filtered changeid
 
     This is extracted in a function to help extensions (eg: evolve) to
     experiment with various message variants."""
     if repo.filtername.startswith('visible'):
 
         # Check if the changeset is obsolete
         unfilteredrepo = repo.unfiltered()
         ctx = revsymbol(unfilteredrepo, changeid)
 
         # If the changeset is obsolete, enrich the message with the reason
         # that made this changeset not visible
         if ctx.obsolete():
             msg = obsutil._getfilteredreason(repo, changeid, ctx)
         else:
             msg = _("hidden revision '%s'") % changeid
 
         hint = _('use --hidden to access hidden revisions')
 
         return error.FilteredRepoLookupError(msg, hint=hint)
     msg = _("filtered revision '%s' (not in '%s' subset)")
     msg %= (changeid, repo.filtername)
     return error.FilteredRepoLookupError(msg)
 
 def revsingle(repo, revspec, default='.', localalias=None):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec], localalias=localalias)
     if not l:
         raise error.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def _pairspec(revspec):
     tree = revsetlang.parse(revspec)
     return tree and tree[0] in ('range', 'rangepre', 'rangepost', 'rangeall')
 
 def revpair(repo, revs):
     if not revs:
         return repo['.'], repo[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[first], repo[None]
 
     return repo[first], repo[second]
 
 def revrange(repo, specs, localalias=None):
     """Execute 1 to many revsets and return the union.
 
     This is the preferred mechanism for executing revsets using user-specified
     config options, such as revset aliases.
 
     The revsets specified by ``specs`` will be executed via a chained ``OR``
     expression. If ``specs`` is empty, an empty result is returned.
 
     ``specs`` can contain integers, in which case they are assumed to be
     revision numbers.
 
     It is assumed the revsets are already formatted. If you have arguments
     that need to be expanded in the revset, call ``revsetlang.formatspec()``
     and pass the result as an element of ``specs``.
 
     Specifying a single revset is allowed.
 
     Returns a ``revset.abstractsmartset`` which is a list-like interface over
     integer revisions.
     """
     allspecs = []
     for spec in specs:
         if isinstance(spec, int):
             spec = revsetlang.formatspec('rev(%d)', spec)
         allspecs.append(spec)
     return repo.anyrevs(allspecs, user=True, localalias=localalias)
 
 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) - 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 parsefollowlinespattern(repo, rev, pat, msg):
     """Return a file name from `pat` pattern suitable for usage in followlines
     logic.
     """
     if not matchmod.patkind(pat):
         return pathutil.canonpath(repo.root, repo.getcwd(), pat)
     else:
         ctx = repo[rev]
         m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=ctx)
         files = [f for f in ctx if m(f)]
         if len(files) != 1:
             raise error.ParseError(msg)
         return files[0]
 
 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 with .orig suffix) if not specified
     '''
     origbackuppath = ui.config('ui', 'origbackuppath')
     if not origbackuppath:
         return filepath + ".orig"
 
     # Convert filepath from an absolute path into a path inside the repo.
     filepathfromroot = util.normpath(os.path.relpath(filepath,
                                                      start=repo.root))
 
     origvfs = vfs.vfs(repo.wjoin(origbackuppath))
     origbackupdir = origvfs.dirname(filepathfromroot)
     if not origvfs.isdir(origbackupdir) or origvfs.islink(origbackupdir):
         ui.note(_('creating directory: %s\n') % origvfs.join(origbackupdir))
 
         # Remove any files that conflict with the backup file's path
         for f in reversed(list(util.finddirs(filepathfromroot))):
             if origvfs.isfileorlink(f):
                 ui.note(_('removing conflicting file: %s\n')
                         % origvfs.join(f))
                 origvfs.unlink(f)
                 break
 
         origvfs.makedirs(origbackupdir)
 
     if origvfs.isdir(filepathfromroot) and not origvfs.islink(filepathfromroot):
         ui.note(_('removing conflicting directory: %s\n')
                 % origvfs.join(filepathfromroot))
         origvfs.rmtree(filepathfromroot, forcibly=True)
 
     return origvfs.join(filepathfromroot)
 
 class _containsnode(object):
     """proxy __contains__(node) to container.__contains__ which accepts revs"""
 
     def __init__(self, repo, revcontainer):
         self._torev = repo.changelog.rev
         self._revcontains = revcontainer.__contains__
 
     def __contains__(self, node):
         return self._revcontains(self._torev(node))
 
 def cleanupnodes(repo, replacements, operation, moves=None, metadata=None,
                  fixphase=False, targetphase=None, backup=True):
     """do common cleanups when old nodes are replaced by new nodes
 
     That includes writing obsmarkers or stripping nodes, and moving bookmarks.
     (we might also want to move working directory parent in the future)
 
     By default, bookmark moves are calculated automatically from 'replacements',
     but 'moves' can be used to override that. Also, 'moves' may include
     additional bookmark moves that should not have associated obsmarkers.
 
     replacements is {oldnode: [newnode]} or a iterable of nodes if they do not
     have replacements. operation is a string, like "rebase".
 
     metadata is dictionary containing metadata to be stored in obsmarker if
     obsolescence is enabled.
     """
     assert fixphase or targetphase is None
     if not replacements and not moves:
         return
 
     # translate mapping's other forms
     if not util.safehasattr(replacements, 'items'):
         replacements = {n: () for n in replacements}
 
     # Calculate bookmark movements
     if moves is None:
         moves = {}
     # Unfiltered repo is needed since nodes in replacements might be hidden.
     unfi = repo.unfiltered()
     for oldnode, newnodes in replacements.items():
         if oldnode in moves:
             continue
         if len(newnodes) > 1:
             # usually a split, take the one with biggest rev number
             newnode = next(unfi.set('max(%ln)', newnodes)).node()
         elif len(newnodes) == 0:
             # move bookmark backwards
             roots = list(unfi.set('max((::%n) - %ln)', oldnode,
                                   list(replacements)))
             if roots:
                 newnode = roots[0].node()
             else:
                 newnode = nullid
         else:
             newnode = newnodes[0]
         moves[oldnode] = newnode
 
     allnewnodes = [n for ns in replacements.values() for n in ns]
     toretract = {}
     toadvance = {}
     if fixphase:
         precursors = {}
         for oldnode, newnodes in replacements.items():
             for newnode in newnodes:
                 precursors.setdefault(newnode, []).append(oldnode)
 
         allnewnodes.sort(key=lambda n: unfi[n].rev())
         newphases = {}
         def phase(ctx):
             return newphases.get(ctx.node(), ctx.phase())
         for newnode in allnewnodes:
             ctx = unfi[newnode]
             parentphase = max(phase(p) for p in ctx.parents())
             if targetphase is None:
                 oldphase = max(unfi[oldnode].phase()
                                for oldnode in precursors[newnode])
                 newphase = max(oldphase, parentphase)
             else:
                 newphase = max(targetphase, parentphase)
             newphases[newnode] = newphase
             if newphase > ctx.phase():
                 toretract.setdefault(newphase, []).append(newnode)
             elif newphase < ctx.phase():
                 toadvance.setdefault(newphase, []).append(newnode)
 
     with repo.transaction('cleanup') as tr:
         # Move bookmarks
         bmarks = repo._bookmarks
         bmarkchanges = []
         for oldnode, newnode in moves.items():
             oldbmarks = repo.nodebookmarks(oldnode)
             if not oldbmarks:
                 continue
             from . import bookmarks # avoid import cycle
             repo.ui.debug('moving bookmarks %r from %s to %s\n' %
                           (pycompat.rapply(pycompat.maybebytestr, oldbmarks),
                            hex(oldnode), hex(newnode)))
             # Delete divergent bookmarks being parents of related newnodes
             deleterevs = repo.revs('parents(roots(%ln & (::%n))) - parents(%n)',
                                    allnewnodes, newnode, oldnode)
             deletenodes = _containsnode(repo, deleterevs)
             for name in oldbmarks:
                 bmarkchanges.append((name, newnode))
                 for b in bookmarks.divergent2delete(repo, deletenodes, name):
                     bmarkchanges.append((b, None))
 
         if bmarkchanges:
             bmarks.applychanges(repo, tr, bmarkchanges)
 
         for phase, nodes in toretract.items():
             phases.retractboundary(repo, tr, phase, nodes)
         for phase, nodes in toadvance.items():
             phases.advanceboundary(repo, tr, phase, nodes)
 
         # Obsolete or strip nodes
         if obsolete.isenabled(repo, obsolete.createmarkersopt):
             # If a node is already obsoleted, and we want to obsolete it
             # without a successor, skip that obssolete request since it's
             # unnecessary. That's the "if s or not isobs(n)" check below.
             # Also sort the node in topology order, that might be useful for
             # some obsstore logic.
             # NOTE: the filtering and sorting might belong to createmarkers.
             isobs = unfi.obsstore.successors.__contains__
             torev = unfi.changelog.rev
             sortfunc = lambda ns: torev(ns[0])
             rels = [(unfi[n], tuple(unfi[m] for m in s))
                     for n, s in sorted(replacements.items(), key=sortfunc)
                     if s or not isobs(n)]
             if rels:
                 obsolete.createmarkers(repo, rels, operation=operation,
                                        metadata=metadata)
         else:
             from . import repair # avoid import cycle
             tostrip = list(replacements)
             if tostrip:
                 repair.delayedstrip(repo.ui, repo, tostrip, operation,
                                     backup=backup)
 
 def addremove(repo, matcher, prefix, opts=None):
     if opts is None:
         opts = {}
     m = matcher
     dry_run = opts.get('dry_run')
     try:
         similarity = float(opts.get('similarity') or 0)
     except ValueError:
         raise error.Abort(_('similarity must be a number'))
     if similarity < 0 or similarity > 100:
         raise error.Abort(_('similarity must be between 0 and 100'))
     similarity /= 100.0
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         if opts.get('subrepos') or m.exact(subpath) or any(submatch.files()):
             sub = wctx.sub(subpath)
             try:
                 if sub.addremove(submatch, prefix, opts):
                     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)
                 label = 'addremove.added'
             else:
                 status = _('removing %s\n') % m.uipath(abs)
                 label = 'addremove.removed'
             repo.ui.status(status, label=label)
 
     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, cached=True)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, subrepos=sorted(ctx.substate),
                                 unknown=True, ignored=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[0:1].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.
 
     On first access, the files defined as arguments are stat()ed and the
     results cached. The decorated function is called. The results are stashed
     away in a ``_filecache`` dict on the object whose method is decorated.
 
     On subsequent access, the cached result is returned.
 
     On external property set operations, stat() calls are performed and the new
     value is cached.
 
     On property delete operations, cached data is removed.
 
     When using the property API, cached data is always returned, if available:
     no stat() is performed to check if the file has changed and if the function
     needs to be called to reflect file changes.
 
     Others can muck about with the state of the ``_filecache`` dict. e.g. they
     can populate an entry before the property's getter is called. In this case,
     entries in ``_filecache`` will be used during property operations,
     if available. If the underlying file changes, it is up to external callers
     to reflect this by e.g. calling ``delattr(obj, attr)`` to remove the cached
     method result as well as possibly calling ``del obj._filecache[attr]`` to
     remove the ``filecacheentry``.
     """
 
     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).
         """
         raise NotImplementedError
 
     def __call__(self, func):
         self.func = func
         self.sname = func.__name__
         self.name = pycompat.sysbytes(self.sname)
         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.sname in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.sname]
 
         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.sname] = 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.sname] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.sname]
         except KeyError:
             raise AttributeError(self.sname)
 
 def extdatasource(repo, source):
     """Gather a map of rev -> value dict from the specified source
 
     A source spec is treated as a URL, with a special case shell: type
     for parsing the output from a shell command.
 
     The data is parsed as a series of newline-separated records where
     each record is a revision specifier optionally followed by a space
     and a freeform string value. If the revision is known locally, it
     is converted to a rev, otherwise the record is skipped.
 
     Note that both key and value are treated as UTF-8 and converted to
     the local encoding. This allows uniformity between local and
     remote data sources.
     """
 
     spec = repo.ui.config("extdata", source)
     if not spec:
         raise error.Abort(_("unknown extdata source '%s'") % source)
 
     data = {}
     src = proc = None
     try:
         if spec.startswith("shell:"):
             # external commands should be run relative to the repo root
             cmd = spec[6:]
             proc = subprocess.Popen(cmd, shell=True, bufsize=-1,
                                     close_fds=procutil.closefds,
                                     stdout=subprocess.PIPE, cwd=repo.root)
             src = proc.stdout
         else:
             # treat as a URL or file
             src = url.open(repo.ui, spec)
         for l in src:
             if " " in l:
                 k, v = l.strip().split(" ", 1)
             else:
                 k, v = l.strip(), ""
 
             k = encoding.tolocal(k)
             try:
                 data[revsingle(repo, k).rev()] = encoding.tolocal(v)
             except (error.LookupError, error.RepoLookupError):
                 pass # we ignore data for nodes that don't exist locally
     finally:
         if proc:
             proc.communicate()
         if src:
             src.close()
     if proc and proc.returncode != 0:
         raise error.Abort(_("extdata command '%s' failed: %s")
                           % (cmd, procutil.explainexit(proc.returncode)))
 
     return data
 
 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)
 
 class progress(object):
     def __init__(self, ui, topic, unit="", total=None):
         self.ui = ui
         self.pos = 0
         self.topic = topic
         self.unit = unit
         self.total = total
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         self.complete()
 
     def update(self, pos, item="", total=None):
         assert pos is not None
         if total:
             self.total = total
         self.pos = pos
         self._print(item)
 
     def increment(self, step=1, item="", total=None):
         self.update(self.pos + step, item, total)
 
     def complete(self):
         self.ui.progress(self.topic, None)
 
     def _print(self, item):
         self.ui.progress(self.topic, self.pos, item, self.unit,
                          self.total)
 
 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')
             or ui.configbool('format', 'usegeneraldelta')
             or ui.configbool('format', 'sparse-revlog'))
 
 def gddeltaconfig(ui):
     """helper function to know if incoming delta should be optimised
     """
     # experimental config: format.generaldelta
     return ui.configbool('format', 'generaldelta')
 
 class simplekeyvaluefile(object):
     """A simple file with key=value lines
 
     Keys must be alphanumerics and start with a letter, values must not
     contain '\n' characters"""
     firstlinekey = '__firstline'
 
     def __init__(self, vfs, path, keys=None):
         self.vfs = vfs
         self.path = path
 
     def read(self, firstlinenonkeyval=False):
         """Read the contents of a simple key-value file
 
         'firstlinenonkeyval' indicates whether the first line of file should
         be treated as a key-value pair or reuturned fully under the
         __firstline key."""
         lines = self.vfs.readlines(self.path)
         d = {}
         if firstlinenonkeyval:
             if not lines:
                 e = _("empty simplekeyvalue file")
                 raise error.CorruptedState(e)
             # we don't want to include '\n' in the __firstline
             d[self.firstlinekey] = lines[0][:-1]
             del lines[0]
 
         try:
             # the 'if line.strip()' part prevents us from failing on empty
             # lines which only contain '\n' therefore are not skipped
             # by 'if line'
             updatedict = dict(line[:-1].split('=', 1) for line in lines
                                                       if line.strip())
             if self.firstlinekey in updatedict:
                 e = _("%r can't be used as a key")
                 raise error.CorruptedState(e % self.firstlinekey)
             d.update(updatedict)
         except ValueError as e:
             raise error.CorruptedState(str(e))
         return d
 
     def write(self, data, firstline=None):
         """Write key=>value mapping to a file
         data is a dict. Keys must be alphanumerical and start with a letter.
         Values must not contain newline characters.
 
         If 'firstline' is not None, it is written to file before
         everything else, as it is, not in a key=value form"""
         lines = []
         if firstline is not None:
             lines.append('%s\n' % firstline)
 
         for k, v in data.items():
             if k == self.firstlinekey:
                 e = "key name '%s' is reserved" % self.firstlinekey
                 raise error.ProgrammingError(e)
             if not k[0:1].isalpha():
                 e = "keys must start with a letter in a key-value file"
                 raise error.ProgrammingError(e)
             if not k.isalnum():
                 e = "invalid key name in a simple key-value file"
                 raise error.ProgrammingError(e)
             if '\n' in v:
                 e = "invalid value in a simple key-value file"
                 raise error.ProgrammingError(e)
             lines.append("%s=%s\n" % (k, v))
         with self.vfs(self.path, mode='wb', atomictemp=True) as fp:
             fp.write(''.join(lines))
 
 _reportobsoletedsource = [
     'debugobsolete',
     'pull',
     'push',
     'serve',
     'unbundle',
 ]
 
 _reportnewcssource = [
     'pull',
     'unbundle',
 ]
 
 def prefetchfiles(repo, revs, match):
     """Invokes the registered file prefetch functions, allowing extensions to
     ensure the corresponding files are available locally, before the command
     uses them."""
     if match:
         # The command itself will complain about files that don't exist, so
         # don't duplicate the message.
         match = matchmod.badmatch(match, lambda fn, msg: None)
     else:
         match = matchall(repo)
 
     fileprefetchhooks(repo, revs, match)
 
 # a list of (repo, revs, match) prefetch functions
 fileprefetchhooks = util.hooks()
 
 # A marker that tells the evolve extension to suppress its own reporting
 _reportstroubledchangesets = True
 
 def registersummarycallback(repo, otr, txnname=''):
     """register a callback to issue a summary after the transaction is closed
     """
     def txmatch(sources):
         return any(txnname.startswith(source) for source in sources)
 
     categories = []
 
     def reportsummary(func):
         """decorator for report callbacks."""
         # The repoview life cycle is shorter than the one of the actual
         # underlying repository. So the filtered object can die before the
         # weakref is used leading to troubles. We keep a reference to the
         # unfiltered object and restore the filtering when retrieving the
         # repository through the weakref.
         filtername = repo.filtername
         reporef = weakref.ref(repo.unfiltered())
         def wrapped(tr):
             repo = reporef()
             if filtername:
                 repo = repo.filtered(filtername)
             func(repo, tr)
         newcat = '%02i-txnreport' % len(categories)
         otr.addpostclose(newcat, wrapped)
         categories.append(newcat)
         return wrapped
 
     if txmatch(_reportobsoletedsource):
         @reportsummary
         def reportobsoleted(repo, tr):
             obsoleted = obsutil.getobsoleted(repo, tr)
             if obsoleted:
                 repo.ui.status(_('obsoleted %i changesets\n')
                                % len(obsoleted))
 
     if (obsolete.isenabled(repo, obsolete.createmarkersopt) and
         repo.ui.configbool('experimental', 'evolution.report-instabilities')):
         instabilitytypes = [
             ('orphan', 'orphan'),
             ('phase-divergent', 'phasedivergent'),
             ('content-divergent', 'contentdivergent'),
         ]
 
         def getinstabilitycounts(repo):
             filtered = repo.changelog.filteredrevs
             counts = {}
             for instability, revset in instabilitytypes:
                 counts[instability] = len(set(obsolete.getrevs(repo, revset)) -
                                           filtered)
             return counts
 
         oldinstabilitycounts = getinstabilitycounts(repo)
         @reportsummary
         def reportnewinstabilities(repo, tr):
             newinstabilitycounts = getinstabilitycounts(repo)
             for instability, revset in instabilitytypes:
                 delta = (newinstabilitycounts[instability] -
                          oldinstabilitycounts[instability])
                 msg = getinstabilitymessage(delta, instability)
                 if msg:
                     repo.ui.warn(msg)
 
     if txmatch(_reportnewcssource):
         @reportsummary
         def reportnewcs(repo, tr):
             """Report the range of new revisions pulled/unbundled."""
-            newrevs = tr.changes.get('revs', pycompat.xrange(0, 0))
-            if not newrevs:
+            origrepolen = tr.changes.get('origrepolen', len(repo))
+            if origrepolen >= len(repo):
                 return
 
             # Compute the bounds of new revisions' range, excluding obsoletes.
             unfi = repo.unfiltered()
-            revs = unfi.revs('%ld and not obsolete()', newrevs)
+            revs = unfi.revs('%d: and not obsolete()', origrepolen)
             if not revs:
                 # Got only obsoletes.
                 return
             minrev, maxrev = repo[revs.min()], repo[revs.max()]
 
             if minrev == maxrev:
                 revrange = minrev
             else:
                 revrange = '%s:%s' % (minrev, maxrev)
             repo.ui.status(_('new changesets %s\n') % revrange)
 
         @reportsummary
         def reportphasechanges(repo, tr):
             """Report statistics of phase changes for changesets pre-existing
             pull/unbundle.
             """
-            newrevs = tr.changes.get('revs', pycompat.xrange(0, 0))
+            origrepolen = tr.changes.get('origrepolen', len(repo))
             phasetracking = tr.changes.get('phases', {})
             if not phasetracking:
                 return
             published = [
                 rev for rev, (old, new) in phasetracking.iteritems()
-                if new == phases.public and rev not in newrevs
+                if new == phases.public and rev < origrepolen
             ]
             if not published:
                 return
             repo.ui.status(_('%d local changesets published\n')
                            % len(published))
 
 def getinstabilitymessage(delta, instability):
     """function to return the message to show warning about new instabilities
 
     exists as a separate function so that extension can wrap to show more
     information like how to fix instabilities"""
     if delta > 0:
         return _('%i new %s changesets\n') % (delta, instability)
 
 def nodesummaries(repo, nodes, maxnumnodes=4):
     if len(nodes) <= maxnumnodes or repo.ui.verbose:
         return ' '.join(short(h) for h in nodes)
     first = ' '.join(short(h) for h in nodes[:maxnumnodes])
     return _("%s and %d others") % (first, len(nodes) - maxnumnodes)
 
 def enforcesinglehead(repo, tr, desc):
     """check that no named branch has multiple heads"""
     if desc in ('strip', 'repair'):
         # skip the logic during strip
         return
     visible = repo.filtered('visible')
     # possible improvement: we could restrict the check to affected branch
     for name, heads in visible.branchmap().iteritems():
         if len(heads) > 1:
             msg = _('rejecting multiple heads on branch "%s"')
             msg %= name
             hint = _('%d heads: %s')
             hint %= (len(heads), nodesummaries(repo, heads))
             raise error.Abort(msg, hint=hint)
 
 def wrapconvertsink(sink):
     """Allow extensions to wrap the sink returned by convcmd.convertsink()
     before it is used, whether or not the convert extension was formally loaded.
     """
     return sink
 
 def unhidehashlikerevs(repo, specs, hiddentype):
     """parse the user specs and unhide changesets whose hash or revision number
     is passed.
 
     hiddentype can be: 1) 'warn': warn while unhiding changesets
                        2) 'nowarn': don't warn while unhiding changesets
 
     returns a repo object with the required changesets unhidden
     """
     if not repo.filtername or not repo.ui.configbool('experimental',
                                                      'directaccess'):
         return repo
 
     if repo.filtername not in ('visible', 'visible-hidden'):
         return repo
 
     symbols = set()
     for spec in specs:
         try:
             tree = revsetlang.parse(spec)
         except error.ParseError: # will be reported by scmutil.revrange()
             continue
 
         symbols.update(revsetlang.gethashlikesymbols(tree))
 
     if not symbols:
         return repo
 
     revs = _getrevsfromsymbols(repo, symbols)
 
     if not revs:
         return repo
 
     if hiddentype == 'warn':
         unfi = repo.unfiltered()
         revstr = ", ".join([pycompat.bytestr(unfi[l]) for l in revs])
         repo.ui.warn(_("warning: accessing hidden changesets for write "
                        "operation: %s\n") % revstr)
 
     # we have to use new filtername to separate branch/tags cache until we can
     # disbale these cache when revisions are dynamically pinned.
     return repo.filtered('visible-hidden', revs)
 
 def _getrevsfromsymbols(repo, symbols):
     """parse the list of symbols and returns a set of revision numbers of hidden
     changesets present in symbols"""
     revs = set()
     unfi = repo.unfiltered()
     unficl = unfi.changelog
     cl = repo.changelog
     tiprev = len(unficl)
     allowrevnums = repo.ui.configbool('experimental', 'directaccess.revnums')
     for s in symbols:
         try:
             n = int(s)
             if n <= tiprev:
                 if not allowrevnums:
                     continue
                 else:
                     if n not in cl:
                         revs.add(n)
                     continue
         except ValueError:
             pass
 
         try:
             s = resolvehexnodeidprefix(unfi, s)
         except (error.LookupError, error.WdirUnsupported):
             s = None
 
         if s is not None:
             rev = unficl.rev(s)
             if rev not in cl:
                 revs.add(rev)
 
     return revs
 
 def bookmarkrevs(repo, mark):
     """
     Select revisions reachable by a given bookmark
     """
     return repo.revs("ancestors(bookmark(%s)) - "
                      "ancestors(head() and not bookmark(%s)) - "
                      "ancestors(bookmark() and not bookmark(%s))",
                      mark, mark, mark)

tests/test-clone-uncompressed.t

@@ -1,512 +1,514
 #require serve no-reposimplestore no-chg
 
 #testcases stream-legacy stream-bundle2
 
 #if stream-bundle2
   $ cat << EOF >> $HGRCPATH
   > [experimental]
   > bundle2.stream = yes
   > EOF
 #endif
 
 Initialize repository
 the status call is to check for issue5130
 
   $ hg init server
   $ cd server
   $ touch foo
   $ hg -q commit -A -m initial
   >>> for i in range(1024):
   ...     with open(str(i), 'wb') as fh:
   ...         fh.write(b"%d" % i) and None
   $ hg -q commit -A -m 'add a lot of files'
   $ hg st
   $ hg --config server.uncompressed=false serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 Cannot stream clone when server.uncompressed is set
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=stream_out'
   200 Script output follows
   
   1
 
 #if stream-legacy
   $ hg debugcapabilities http://localhost:$HGPORT
   Main capabilities:
     batch
     branchmap
     $USUAL_BUNDLE2_CAPS_SERVER$
     changegroupsubset
     compression=$BUNDLE2_COMPRESSIONS$
     getbundle
     httpheader=1024
     httpmediatype=0.1rx,0.1tx,0.2tx
     known
     lookup
     pushkey
     unbundle=HG10GZ,HG10BZ,HG10UN
     unbundlehash
   Bundle2 capabilities:
     HG20
     bookmarks
     changegroup
       01
       02
     digests
       md5
       sha1
       sha512
     error
       abort
       unsupportedcontent
       pushraced
       pushkey
     hgtagsfnodes
     listkeys
     phases
       heads
     pushkey
     remote-changegroup
       http
       https
     rev-branch-cache
 
   $ hg clone --stream -U http://localhost:$HGPORT server-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 1025 changes to 1025 files
   new changesets 96ee1d7354c4:c17445101a72
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto 0.2 --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
   $ f --size body --hexdump --bytes 100
   body: size=232
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: cf 0b 45 52 52 4f 52 3a 41 42 4f 52 54 00 00 00 |..ERROR:ABORT...|
   0020: 00 01 01 07 3c 04 72 6d 65 73 73 61 67 65 73 74 |....<.rmessagest|
   0030: 72 65 61 6d 20 64 61 74 61 20 72 65 71 75 65 73 |ream data reques|
   0040: 74 65 64 20 62 75 74 20 73 65 72 76 65 72 20 64 |ted but server d|
   0050: 6f 65 73 20 6e 6f 74 20 61 6c 6c 6f 77 20 74 68 |oes not allow th|
   0060: 69 73 20 66                                     |is f|
 
 #endif
 #if stream-bundle2
   $ hg debugcapabilities http://localhost:$HGPORT
   Main capabilities:
     batch
     branchmap
     $USUAL_BUNDLE2_CAPS_SERVER$
     changegroupsubset
     compression=$BUNDLE2_COMPRESSIONS$
     getbundle
     httpheader=1024
     httpmediatype=0.1rx,0.1tx,0.2tx
     known
     lookup
     pushkey
     unbundle=HG10GZ,HG10BZ,HG10UN
     unbundlehash
   Bundle2 capabilities:
     HG20
     bookmarks
     changegroup
       01
       02
     digests
       md5
       sha1
       sha512
     error
       abort
       unsupportedcontent
       pushraced
       pushkey
     hgtagsfnodes
     listkeys
     phases
       heads
     pushkey
     remote-changegroup
       http
       https
     rev-branch-cache
 
   $ hg clone --stream -U http://localhost:$HGPORT server-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 1025 changes to 1025 files
   new changesets 96ee1d7354c4:c17445101a72
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto 0.2 --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
   $ f --size body --hexdump --bytes 100
   body: size=232
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: cf 0b 45 52 52 4f 52 3a 41 42 4f 52 54 00 00 00 |..ERROR:ABORT...|
   0020: 00 01 01 07 3c 04 72 6d 65 73 73 61 67 65 73 74 |....<.rmessagest|
   0030: 72 65 61 6d 20 64 61 74 61 20 72 65 71 75 65 73 |ream data reques|
   0040: 74 65 64 20 62 75 74 20 73 65 72 76 65 72 20 64 |ted but server d|
   0050: 6f 65 73 20 6e 6f 74 20 61 6c 6c 6f 77 20 74 68 |oes not allow th|
   0060: 69 73 20 66                                     |is f|
 
 #endif
 
   $ killdaemons.py
   $ cd server
   $ hg serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 Basic clone
 
 #if stream-legacy
   $ hg clone --stream -U http://localhost:$HGPORT clone1
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*/sec) (glob)
   searching for changes
   no changes found
 #endif
 #if stream-bundle2
   $ hg clone --stream -U http://localhost:$HGPORT clone1
   streaming all changes
   1030 files to transfer, 96.4 KB of data
   transferred 96.4 KB in * seconds (* */sec) (glob)
 
   $ ls -1 clone1/.hg/cache
   branch2-served
   rbc-names-v1
   rbc-revs-v1
 #endif
 
 getbundle requests with stream=1 are uncompressed
 
   $ get-with-headers.py $LOCALIP:$HGPORT '?cmd=getbundle' content-type --bodyfile body --hgproto '0.1 0.2 comp=zlib,none' --requestheader "x-hgarg-1=bundlecaps=HG20%2Cbundle2%3DHG20%250Abookmarks%250Achangegroup%253D01%252C02%250Adigests%253Dmd5%252Csha1%252Csha512%250Aerror%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250Ahgtagsfnodes%250Alistkeys%250Aphases%253Dheads%250Apushkey%250Aremote-changegroup%253Dhttp%252Chttps&cg=0&common=0000000000000000000000000000000000000000&heads=c17445101a72edac06facd130d14808dfbd5c7c2&stream=1"
   200 Script output follows
   content-type: application/mercurial-0.2
   
 
   $ f --size --hex --bytes 256 body
   body: size=112230
   0000: 04 6e 6f 6e 65 48 47 32 30 00 00 00 00 00 00 00 |.noneHG20.......|
   0010: 70 07 53 54 52 45 41 4d 32 00 00 00 00 03 00 09 |p.STREAM2.......|
   0020: 05 09 04 0c 35 62 79 74 65 63 6f 75 6e 74 39 38 |....5bytecount98|
   0030: 37 35 38 66 69 6c 65 63 6f 75 6e 74 31 30 33 30 |758filecount1030|
   0040: 72 65 71 75 69 72 65 6d 65 6e 74 73 64 6f 74 65 |requirementsdote|
   0050: 6e 63 6f 64 65 25 32 43 66 6e 63 61 63 68 65 25 |ncode%2Cfncache%|
   0060: 32 43 67 65 6e 65 72 61 6c 64 65 6c 74 61 25 32 |2Cgeneraldelta%2|
   0070: 43 72 65 76 6c 6f 67 76 31 25 32 43 73 74 6f 72 |Crevlogv1%2Cstor|
   0080: 65 00 00 80 00 73 08 42 64 61 74 61 2f 30 2e 69 |e....s.Bdata/0.i|
   0090: 00 03 00 01 00 00 00 00 00 00 00 02 00 00 00 01 |................|
   00a0: 00 00 00 00 00 00 00 01 ff ff ff ff ff ff ff ff |................|
   00b0: 80 29 63 a0 49 d3 23 87 bf ce fe 56 67 92 67 2c |.)c.I.#....Vg.g,|
   00c0: 69 d1 ec 39 00 00 00 00 00 00 00 00 00 00 00 00 |i..9............|
   00d0: 75 30 73 08 42 64 61 74 61 2f 31 2e 69 00 03 00 |u0s.Bdata/1.i...|
   00e0: 01 00 00 00 00 00 00 00 02 00 00 00 01 00 00 00 |................|
   00f0: 00 00 00 00 01 ff ff ff ff ff ff ff ff f9 76 da |..............v.|
 
 --uncompressed is an alias to --stream
 
 #if stream-legacy
   $ hg clone --uncompressed -U http://localhost:$HGPORT clone1-uncompressed
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*/sec) (glob)
   searching for changes
   no changes found
 #endif
 #if stream-bundle2
   $ hg clone --uncompressed -U http://localhost:$HGPORT clone1-uncompressed
   streaming all changes
   1030 files to transfer, 96.4 KB of data
   transferred 96.4 KB in * seconds (* */sec) (glob)
 #endif
 
 Clone with background file closing enabled
 
 #if stream-legacy
   $ hg --debug --config worker.backgroundclose=true --config worker.backgroundcloseminfilecount=1 clone --stream -U http://localhost:$HGPORT clone-background | grep -v adding
   using http://localhost:$HGPORT/
   sending capabilities command
   sending branchmap command
   streaming all changes
   sending stream_out command
   1027 files to transfer, 96.3 KB of data
   starting 4 threads for background file closing
+  updating the branch cache
   transferred 96.3 KB in * seconds (*/sec) (glob)
   query 1; heads
   sending batch command
   searching for changes
   all remote heads known locally
   no changes found
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-part: "phase-heads" supported
   bundle2-input-part: total payload size 24
   bundle2-input-bundle: 1 parts total
   checking for updated bookmarks
 #endif
 #if stream-bundle2
   $ hg --debug --config worker.backgroundclose=true --config worker.backgroundcloseminfilecount=1 clone --stream -U http://localhost:$HGPORT clone-background | grep -v adding
   using http://localhost:$HGPORT/
   sending capabilities command
   query 1; heads
   sending batch command
   streaming all changes
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "stream2" (params: 3 mandatory) supported
   applying stream bundle
   1030 files to transfer, 96.4 KB of data
   starting 4 threads for background file closing
   starting 4 threads for background file closing
+  updating the branch cache
   transferred 96.4 KB in * seconds (* */sec) (glob)
   bundle2-input-part: total payload size 112077
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-bundle: 1 parts total
   checking for updated bookmarks
 #endif
 
 Cannot stream clone when there are secret changesets
 
   $ hg -R server phase --force --secret -r tip
   $ hg clone --stream -U http://localhost:$HGPORT secret-denied
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   new changesets 96ee1d7354c4
 
   $ killdaemons.py
 
 Streaming of secrets can be overridden by server config
 
   $ cd server
   $ hg serve --config server.uncompressedallowsecret=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
 #if stream-legacy
   $ hg clone --stream -U http://localhost:$HGPORT secret-allowed
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*/sec) (glob)
   searching for changes
   no changes found
 #endif
 #if stream-bundle2
   $ hg clone --stream -U http://localhost:$HGPORT secret-allowed
   streaming all changes
   1030 files to transfer, 96.4 KB of data
   transferred 96.4 KB in * seconds (* */sec) (glob)
 #endif
 
   $ killdaemons.py
 
 Verify interaction between preferuncompressed and secret presence
 
   $ cd server
   $ hg serve --config server.preferuncompressed=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
   $ hg clone -U http://localhost:$HGPORT preferuncompressed-secret
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   new changesets 96ee1d7354c4
 
   $ killdaemons.py
 
 Clone not allowed when full bundles disabled and can't serve secrets
 
   $ cd server
   $ hg serve --config server.disablefullbundle=true -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
   $ cd ..
 
   $ hg clone --stream http://localhost:$HGPORT secret-full-disabled
   warning: stream clone requested but server has them disabled
   requesting all changes
   remote: abort: server has pull-based clones disabled
   abort: pull failed on remote
   (remove --pull if specified or upgrade Mercurial)
   [255]
 
 Local stream clone with secrets involved
 (This is just a test over behavior: if you have access to the repo's files,
 there is no security so it isn't important to prevent a clone here.)
 
   $ hg clone -U --stream server local-secret
   warning: stream clone requested but server has them disabled
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   new changesets 96ee1d7354c4
 
 Stream clone while repo is changing:
 
   $ mkdir changing
   $ cd changing
 
 extension for delaying the server process so we reliably can modify the repo
 while cloning
 
   $ cat > delayer.py <<EOF
   > import time
   > from mercurial import extensions, vfs
   > def __call__(orig, self, path, *args, **kwargs):
   >     if path == 'data/f1.i':
   >         time.sleep(2)
   >     return orig(self, path, *args, **kwargs)
   > extensions.wrapfunction(vfs.vfs, '__call__', __call__)
   > EOF
 
 prepare repo with small and big file to cover both code paths in emitrevlogdata
 
   $ hg init repo
   $ touch repo/f1
   $ $TESTDIR/seq.py 50000 > repo/f2
   $ hg -R repo ci -Aqm "0"
   $ hg serve -R repo -p $HGPORT1 -d --pid-file=hg.pid --config extensions.delayer=delayer.py
   $ cat hg.pid >> $DAEMON_PIDS
 
 clone while modifying the repo between stating file with write lock and
 actually serving file content
 
   $ hg clone -q --stream -U http://localhost:$HGPORT1 clone &
   $ sleep 1
   $ echo >> repo/f1
   $ echo >> repo/f2
   $ hg -R repo ci -m "1"
   $ wait
   $ hg -R clone id
   000000000000
   $ cd ..
 
 Stream repository with bookmarks
 --------------------------------
 
 (revert introduction of secret changeset)
 
   $ hg -R server phase --draft 'secret()'
 
 add a bookmark
 
   $ hg -R server bookmark -r tip some-bookmark
 
 clone it
 
 #if stream-legacy
   $ hg clone --stream http://localhost:$HGPORT with-bookmarks
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*) (glob)
   searching for changes
   no changes found
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT with-bookmarks
   streaming all changes
   1033 files to transfer, 96.6 KB of data
   transferred 96.6 KB in * seconds (* */sec) (glob)
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
   $ hg -R with-bookmarks bookmarks
      some-bookmark             1:c17445101a72
 
 Stream repository with phases
 -----------------------------
 
 Clone as publishing
 
   $ hg -R server phase -r 'all()'
   0: draft
   1: draft
 
 #if stream-legacy
   $ hg clone --stream http://localhost:$HGPORT phase-publish
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*) (glob)
   searching for changes
   no changes found
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT phase-publish
   streaming all changes
   1033 files to transfer, 96.6 KB of data
   transferred 96.6 KB in * seconds (* */sec) (glob)
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
   $ hg -R phase-publish phase -r 'all()'
   0: public
   1: public
 
 Clone as non publishing
 
   $ cat << EOF >> server/.hg/hgrc
   > [phases]
   > publish = False
   > EOF
   $ killdaemons.py
   $ hg -R server serve -p $HGPORT -d --pid-file=hg.pid
   $ cat hg.pid > $DAEMON_PIDS
 
 #if stream-legacy
 
 With v1 of the stream protocol, changeset are always cloned as public. It make
 stream v1 unsuitable for non-publishing repository.
 
   $ hg clone --stream http://localhost:$HGPORT phase-no-publish
   streaming all changes
   1027 files to transfer, 96.3 KB of data
   transferred 96.3 KB in * seconds (*) (glob)
   searching for changes
   no changes found
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R phase-no-publish phase -r 'all()'
   0: public
   1: public
 #endif
 #if stream-bundle2
   $ hg clone --stream http://localhost:$HGPORT phase-no-publish
   streaming all changes
   1034 files to transfer, 96.7 KB of data
   transferred 96.7 KB in * seconds (* */sec) (glob)
   updating to branch default
   1025 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R phase-no-publish phase -r 'all()'
   0: draft
   1: draft
 #endif
 
   $ killdaemons.py

tests/test-stream-bundle-v2.t

@@ -1,172 +1,174
 #require no-reposimplestore
 
 Test creating a consuming stream bundle v2
 
   $ getmainid() {
   >    hg -R main log --template '{node}\n' --rev "$1"
   > }
 
   $ cp $HGRCPATH $TESTTMP/hgrc.orig
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > evolution.createmarkers=True
   > evolution.exchange=True
   > bundle2-output-capture=True
   > [ui]
   > ssh="$PYTHON" "$TESTDIR/dummyssh"
   > logtemplate={rev}:{node|short} {phase} {author} {bookmarks} {desc|firstline}
   > [web]
   > push_ssl = false
   > allow_push = *
   > [phases]
   > publish=False
   > [extensions]
   > drawdag=$TESTDIR/drawdag.py
   > clonebundles=
   > EOF
 
 The extension requires a repo (currently unused)
 
   $ hg init main
   $ cd main
 
   $ hg debugdrawdag <<'EOF'
   > E
   > |
   > D
   > |
   > C
   > |
   > B
   > |
   > A
   > EOF
 
   $ hg bundle -a --type="none-v2;stream=v2" bundle.hg
   $ hg debugbundle bundle.hg
   Stream params: {}
   stream2 -- {bytecount: 1693, filecount: 11, requirements: dotencode%2Cfncache%2Cgeneraldelta%2Crevlogv1%2Cstore} (mandatory: True)
   $ hg debugbundle --spec bundle.hg
   none-v2;stream=v2;requirements%3Ddotencode%2Cfncache%2Cgeneraldelta%2Crevlogv1%2Cstore
 
 Test that we can apply the bundle as a stream clone bundle
 
   $ cat > .hg/clonebundles.manifest << EOF
   > http://localhost:$HGPORT1/bundle.hg BUNDLESPEC=`hg debugbundle --spec bundle.hg`
   > EOF
 
   $ hg serve -d -p $HGPORT --pid-file hg.pid --accesslog access.log
   $ cat hg.pid >> $DAEMON_PIDS
 
   $ "$PYTHON" $TESTDIR/dumbhttp.py -p $HGPORT1 --pid http.pid
   $ cat http.pid >> $DAEMON_PIDS
 
   $ cd ..
   $ hg clone http://localhost:$HGPORT streamv2-clone-implicit --debug
   using http://localhost:$HGPORT/
   sending capabilities command
   sending clonebundles command
   applying clone bundle from http://localhost:$HGPORT1/bundle.hg
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "stream2" (params: 3 mandatory) supported
   applying stream bundle
   11 files to transfer, 1.65 KB of data
   starting 4 threads for background file closing (?)
   starting 4 threads for background file closing (?)
   adding [s] data/A.i (66 bytes)
   adding [s] data/B.i (66 bytes)
   adding [s] data/C.i (66 bytes)
   adding [s] data/D.i (66 bytes)
   adding [s] data/E.i (66 bytes)
   adding [s] 00manifest.i (584 bytes)
   adding [s] 00changelog.i (595 bytes)
   adding [s] phaseroots (43 bytes)
   adding [c] branch2-served (94 bytes)
   adding [c] rbc-names-v1 (7 bytes)
   adding [c] rbc-revs-v1 (40 bytes)
   transferred 1.65 KB in \d\.\d seconds \(.*/sec\) (re)
   bundle2-input-part: total payload size 1840
   bundle2-input-bundle: 0 parts total
+  updating the branch cache
   finished applying clone bundle
   query 1; heads
   sending batch command
   searching for changes
   all remote heads known locally
   no changes found
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-part: "phase-heads" supported
   bundle2-input-part: total payload size 24
   bundle2-input-bundle: 1 parts total
   checking for updated bookmarks
   updating to branch default
   resolving manifests
    branchmerge: False, force: False, partial: False
    ancestor: 000000000000, local: 000000000000+, remote: 9bc730a19041
    A: remote created -> g
   getting A
    B: remote created -> g
   getting B
    C: remote created -> g
   getting C
    D: remote created -> g
   getting D
    E: remote created -> g
   getting E
   5 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg clone --stream http://localhost:$HGPORT streamv2-clone-explicit --debug
   using http://localhost:$HGPORT/
   sending capabilities command
   sending clonebundles command
   applying clone bundle from http://localhost:$HGPORT1/bundle.hg
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "stream2" (params: 3 mandatory) supported
   applying stream bundle
   11 files to transfer, 1.65 KB of data
   starting 4 threads for background file closing (?)
   starting 4 threads for background file closing (?)
   adding [s] data/A.i (66 bytes)
   adding [s] data/B.i (66 bytes)
   adding [s] data/C.i (66 bytes)
   adding [s] data/D.i (66 bytes)
   adding [s] data/E.i (66 bytes)
   adding [s] 00manifest.i (584 bytes)
   adding [s] 00changelog.i (595 bytes)
   adding [s] phaseroots (43 bytes)
   adding [c] branch2-served (94 bytes)
   adding [c] rbc-names-v1 (7 bytes)
   adding [c] rbc-revs-v1 (40 bytes)
   transferred 1.65 KB in *.* seconds (*/sec) (glob)
   bundle2-input-part: total payload size 1840
   bundle2-input-bundle: 0 parts total
+  updating the branch cache
   finished applying clone bundle
   query 1; heads
   sending batch command
   searching for changes
   all remote heads known locally
   no changes found
   sending getbundle command
   bundle2-input-bundle: with-transaction
   bundle2-input-part: "listkeys" (params: 1 mandatory) supported
   bundle2-input-part: "phase-heads" supported
   bundle2-input-part: total payload size 24
   bundle2-input-bundle: 1 parts total
   checking for updated bookmarks
   updating to branch default
   resolving manifests
    branchmerge: False, force: False, partial: False
    ancestor: 000000000000, local: 000000000000+, remote: 9bc730a19041
    A: remote created -> g
   getting A
    B: remote created -> g
   getting B
    C: remote created -> g
   getting C
    D: remote created -> g
   getting D
    E: remote created -> g
   getting E
   5 files updated, 0 files merged, 0 files removed, 0 files unresolved