merge with stable

mercurial/revlog.py

@@ -1,2643 +1,2646
 # revlog.py - storage back-end 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.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullhex,
     nullid,
     nullrev,
     short,
     wdirfilenodeids,
     wdirhex,
     wdirid,
     wdirrev,
 )
 from .i18n import _
 from .revlogutils.constants import (
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_ISCENSORED,
     REVIDX_KNOWN_FLAGS,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
 )
 from .thirdparty import (
     attr,
 )
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     repository,
     templatefilters,
     util,
 )
 from .revlogutils import (
     deltas as deltautil,
 )
 from .utils import (
     interfaceutil,
     storageutil,
     stringutil,
 )
 
 # blanked usage of all the name to prevent pyflakes constraints
 # We need these name available in the module for extensions.
 REVLOGV0
 REVLOGV1
 REVLOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_KNOWN_FLAGS
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod(r'parsers')
 try:
     from . import rustext
     rustext.__name__  # force actual import (see hgdemandimport)
 except ImportError:
     rustext = None
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 # Store flag processors (cf. 'addflagprocessor()' to register)
 _flagprocessors = {
     REVIDX_ISCENSORED: None,
 }
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 def addflagprocessor(flag, processor):
     """Register a flag processor on a revision data flag.
 
     Invariant:
     - Flags need to be defined in REVIDX_KNOWN_FLAGS and REVIDX_FLAGS_ORDER,
       and REVIDX_RAWTEXT_CHANGING_FLAGS if they can alter rawtext.
     - Only one flag processor can be registered on a specific flag.
     - flagprocessors must be 3-tuples of functions (read, write, raw) with the
       following signatures:
           - (read)  f(self, rawtext) -> text, bool
           - (write) f(self, text) -> rawtext, bool
           - (raw)   f(self, rawtext) -> bool
       "text" is presented to the user. "rawtext" is stored in revlog data, not
       directly visible to the user.
       The boolean returned by these transforms is used to determine whether
       the returned text can be used for hash integrity checking. For example,
       if "write" returns False, then "text" is used to generate hash. If
       "write" returns True, that basically means "rawtext" returned by "write"
       should be used to generate hash. Usually, "write" and "read" return
       different booleans. And "raw" returns a same boolean as "write".
 
       Note: The 'raw' transform is used for changegroup generation and in some
       debug commands. In this case the transform only indicates whether the
       contents can be used for hash integrity checks.
     """
     _insertflagprocessor(flag, processor, _flagprocessors)
 
 def _insertflagprocessor(flag, processor, flagprocessors):
     if not flag & REVIDX_KNOWN_FLAGS:
         msg = _("cannot register processor on unknown flag '%#x'.") % (flag)
         raise error.ProgrammingError(msg)
     if flag not in REVIDX_FLAGS_ORDER:
         msg = _("flag '%#x' undefined in REVIDX_FLAGS_ORDER.") % (flag)
         raise error.ProgrammingError(msg)
     if flag in flagprocessors:
         msg = _("cannot register multiple processors on flag '%#x'.") % (flag)
         raise error.Abort(msg)
     flagprocessors[flag] = processor
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     if (type & ~REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError('unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
     node:       expected hash of the revision
     p1, p2:     parent revs of the revision
     btext:      built text cache consisting of a one-element list
     cachedelta: (baserev, uncompressed_delta) or None
     flags:      flags associated to the revision storage
 
     One of btext[0] or cachedelta must be set.
     """
     node = attr.ib()
     p1 = attr.ib()
     p2 = attr.ib()
     btext = attr.ib()
     textlen = attr.ib()
     cachedelta = attr.ib()
     flags = attr.ib()
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     linknode = attr.ib(default=None)
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class revlogproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 # index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 indexformatv0 = struct.Struct(">4l20s20s20s")
 indexformatv0_pack = indexformatv0.pack
 indexformatv0_unpack = indexformatv0.unpack
 
 class revlogoldindex(list):
     def __getitem__(self, i):
         if i == -1:
             return (0, 0, 0, -1, -1, -1, -1, nullid)
         return list.__getitem__(self, i)
 
 class revlogoldio(object):
     def __init__(self):
         self.size = indexformatv0.size
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap = {nullid: nullrev}
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = indexformatv0_unpack(cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         return revlogoldindex(index), nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise error.RevlogError(_('index entry flags need revlog '
                                       'version 1'))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return indexformatv0_pack(*e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = struct.Struct(">Qiiiiii20s12x")
 indexformatng_pack = indexformatng.pack
 versionformat = struct.Struct(">I")
 versionformat_pack = versionformat.pack
 versionformat_unpack = versionformat.unpack
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7fffffff
 
 class revlogio(object):
     def __init__(self):
         self.size = indexformatng.size
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
         p = indexformatng_pack(*entry)
         if rev == 0:
             p = versionformat_pack(version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
     """
     def __init__(self, opener, indexfile, datafile=None, checkambig=False,
                  mmaplargeindex=False, censorable=False):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + ".d")
         self.opener = opener
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._mmaplargeindex = mmaplargeindex
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, '')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = []
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._nodecache = {nullid: nullrev}
         self._nodepos = None
         self._compengine = 'zlib'
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(_flagprocessors)
 
         # 2-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._loadindex()
 
     def _loadindex(self):
         mmapindexthreshold = None
         opts = getattr(self.opener, 'options', {}) or {}
 
         if 'revlogv2' in opts:
             newversionflags = REVLOGV2 | FLAG_INLINE_DATA
         elif 'revlogv1' in opts:
             newversionflags = REVLOGV1 | FLAG_INLINE_DATA
             if 'generaldelta' in opts:
                 newversionflags |= FLAG_GENERALDELTA
+        elif getattr(self.opener, 'options', None) is not None:
+            # If options provided but no 'revlog*' found, the repository
+            # would have no 'requires' file in it, which means we have to
+            # stick to the old format.
+            newversionflags = REVLOGV0
         else:
             newversionflags = REVLOG_DEFAULT_VERSION
 
         if 'chunkcachesize' in opts:
             self._chunkcachesize = opts['chunkcachesize']
         if 'maxchainlen' in opts:
             self._maxchainlen = opts['maxchainlen']
         if 'deltabothparents' in opts:
             self._deltabothparents = opts['deltabothparents']
         self._lazydeltabase = bool(opts.get('lazydeltabase', False))
         if 'compengine' in opts:
             self._compengine = opts['compengine']
         if 'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts['maxdeltachainspan']
         if self._mmaplargeindex and 'mmapindexthreshold' in opts:
             mmapindexthreshold = opts['mmapindexthreshold']
         self._sparserevlog = bool(opts.get('sparse-revlog', False))
         withsparseread = bool(opts.get('with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if 'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts['sparse-read-density-threshold']
         if 'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts['sparse-read-min-gap-size']
         if opts.get('enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in opts.get(b'flagprocessors', {}).iteritems():
             _insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(_('revlog chunk cache size %r is not '
                                       'greater than 0') % self._chunkcachesize)
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(_('revlog chunk cache size %r is not a '
                                       'power of 2') % self._chunkcachesize)
 
         indexdata = ''
         self._initempty = True
         try:
             with self._indexfp() as f:
                 if (mmapindexthreshold is not None and
                     self.opener.fstat(f).st_size >= mmapindexthreshold):
                     # TODO: should .close() to release resources without
                     # relying on Python GC
                     indexdata = util.buffer(util.mmapread(f))
                 else:
                     indexdata = f.read()
             if len(indexdata) > 0:
                 versionflags = versionformat_unpack(indexdata[:4])[0]
                 self._initempty = False
             else:
                 versionflags = newversionflags
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
             versionflags = newversionflags
 
         self.version = versionflags
 
         flags = versionflags & ~0xFFFF
         fmt = versionflags & 0xFFFF
 
         if fmt == REVLOGV0:
             if flags:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = False
             self._generaldelta = False
 
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = versionflags & FLAG_INLINE_DATA
             self._generaldelta = versionflags & FLAG_GENERALDELTA
 
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise error.RevlogError(_('unknown flags (%#04x) in version %d '
                                           'revlog %s') %
                                         (flags >> 16, fmt, self.indexfile))
 
             self._inline = versionflags & FLAG_INLINE_DATA
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(_('unknown version (%d) in revlog %s') %
                                     (fmt, self.indexfile))
 
         self._storedeltachains = True
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(indexdata, self._inline)
         except (ValueError, IndexError):
             raise error.RevlogError(_("index %s is corrupted") %
                                     self.indexfile)
         self.index, nodemap, self._chunkcache = d
         if nodemap is not None:
             self.nodemap = self._nodecache = nodemap
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = {}
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def _compressor(self):
         return util.compengines[self._compengine].revlogcompressor()
 
     def _indexfp(self, mode='r'):
         """file object for the revlog's index file"""
         args = {r'mode': mode}
         if mode != 'r':
             args[r'checkambig'] = self._checkambig
         if mode == 'w':
             args[r'atomictemp'] = True
         return self.opener(self.indexfile, **args)
 
     def _datafp(self, mode='r'):
         """file object for the revlog's data file"""
         return self.opener(self.datafile, mode=mode)
 
     @contextlib.contextmanager
     def _datareadfp(self, existingfp=None):
         """file object suitable to read data"""
         # Use explicit file handle, if given.
         if existingfp is not None:
             yield existingfp
 
         # Use a file handle being actively used for writes, if available.
         # There is some danger to doing this because reads will seek the
         # file. However, _writeentry() performs a SEEK_END before all writes,
         # so we should be safe.
         elif self._writinghandles:
             if self._inline:
                 yield self._writinghandles[0]
             else:
                 yield self._writinghandles[1]
 
         # Otherwise open a new file handle.
         else:
             if self._inline:
                 func = self._indexfp
             else:
                 func = self._datafp
             with func() as fp:
                 yield fp
 
     def tip(self):
         return self.node(len(self.index) - 1)
     def __contains__(self, rev):
         return 0 <= rev < len(self)
     def __len__(self):
         return len(self.index)
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         return storageutil.iterrevs(len(self), start=start, stop=stop)
 
     @util.propertycache
     def nodemap(self):
         if self.index:
             # populate mapping down to the initial node
             node0 = self.index[0][7]  # get around changelog filtering
             self.rev(node0)
         return self._nodecache
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if ((self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS)
             or (self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS)):
             return False
         return True
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, '')
         self._pcache = {}
 
         try:
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _('no node'))
         except KeyError:
             # pure python cache lookup failed
             n = self._nodecache
             i = self.index
             p = self._nodepos
             if p is None:
                 p = len(i) - 1
             else:
                 assert p < len(i)
             for r in pycompat.xrange(p, -1, -1):
                 v = i[r][7]
                 n[v] = r
                 if v == node:
                     self._nodepos = r - 1
                     return r
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _('no node'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(rev, raw=True)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev, raw=False))
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
         return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse revision order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         # first, make sure start revisions aren't filtered
         revs = list(revs)
         checkrev = self.node
         for r in revs:
             checkrev(r)
         # and we're sure ancestors aren't filtered as well
 
         if rustext is not None:
             lazyancestors = rustext.ancestor.LazyAncestors
             arg = self.index
         elif util.safehasattr(parsers, 'rustlazyancestors'):
             lazyancestors = ancestor.rustlazyancestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         if rustext is not None:
-            # TODO: WdirUnsupported should be raised instead of GraphError
-            # if common includes wdirrev
             return rustext.ancestor.MissingAncestors(self.index, common)
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in heads.iteritems() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevs()
             except AttributeError:
                 return self._headrevs()
         return dagop.headrevs(revs, self.parentrevs)
 
     def computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = set(self.rev(n) for n in stop or [])
 
         revs = dagop.headrevssubset(self.revs, self.parentrevs, startrev=start,
                                     stoprevs=stoprevs)
 
         return [self.node(rev) for rev in revs]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError): # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         commonancestorsheads is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return a in self._commonancestorsheads(a, b)
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except error.LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if "%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = wdirhex.startswith(id)
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     raise error.RevlogError
                 return partial
             if maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             return None
         except error.RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise error.AmbiguousPrefixLookupError(
                     id, self.indexfile, _('ambiguous identifier'))
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[:l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [n for n in nl if hex(n).startswith(id) and
                       self.hasnode(n)]
                 if nullhex.startswith(id):
                     nl.append(nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.indexfile, _('ambiguous identifier'))
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise error.LookupError(id, self.indexfile, _('no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
         def isvalid(prefix):
             try:
                 node = self._partialmatch(prefix)
             except error.AmbiguousPrefixLookupError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if node is None:
                 raise error.LookupError(node, self.indexfile, _('no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == 'f' for c in prefix)
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != wdirid:
                     raise error.LookupError(node, self.indexfile, _('no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == wdirid:
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, 41):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def _cachesegment(self, offset, data):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _readsegment(self, offset, length, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
 
         Raises if the requested number of bytes could not be read.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (((offset + length + cachesize) & ~(cachesize - 1))
                       - realoffset)
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
 
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
             startoffset = offset - realoffset
             if len(d) - startoffset < length:
                 raise error.RevlogError(
                     _('partial read of revlog %s; expected %d bytes from '
                       'offset %d, got %d') %
                     (self.indexfile if self._inline else self.datafile,
                      length, realoffset, len(d) - startoffset))
 
             return util.buffer(d, startoffset, length)
 
         if len(d) < length:
             raise error.RevlogError(
                 _('partial read of revlog %s; expected %d bytes from offset '
                   '%d, got %d') %
                 (self.indexfile if self._inline else self.datafile,
                  length, offset, len(d)))
 
         return d
 
     def _getsegment(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._readsegment(offset, length, df=df)
 
     def _getsegmentforrevs(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self._io.size
             end += (endrev + 1) * self._io.size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self._io.size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = deltautil.slicechunk(self, revs,
                                                 targetsize=targetsize)
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, df=df)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev, df=df) for rev in revschunk]
 
             decomp = self.decompress
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(decomp(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot
         """
         if not self._sparserevlog:
             return self.deltaparent(rev) == nullrev
         elif util.safehasattr(self.index, 'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         p2 = entry[6]
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     def snapshotdepth(self, rev):
         """number of snapshot in the chain before this one"""
         if not self.issnapshot(rev):
             raise error.ProgrammingError('revision %d not a snapshot')
         return len(self._deltachain(rev)[0]) - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.revision(rev1, raw=True),
                               self.revision(rev2, raw=True))
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         raw - an optional argument specifying if the revision data is to be
         treated as raw data when applying flag transforms. 'raw' should be set
         to True when generating changegroups or in debug commands.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         cachedrev = None
         flags = None
         rawtext = None
         if node == nullid:
             return ""
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 # _cache only stores rawtext
                 if raw:
                     return self._revisioncache[2]
                 # duplicated, but good for perf
                 if rev is None:
                     rev = self.rev(node)
                 if flags is None:
                     flags = self.flags(rev)
                 # no extra flags set, no flag processor runs, text = rawtext
                 if flags == REVIDX_DEFAULT_FLAGS:
                     return self._revisioncache[2]
                 # rawtext is reusable. need to run flag processor
                 rawtext = self._revisioncache[2]
 
             cachedrev = self._revisioncache[1]
 
         # look up what we need to read
         if rawtext is None:
             if rev is None:
                 rev = self.rev(node)
 
             chain, stopped = self._deltachain(rev, stoprev=cachedrev)
             if stopped:
                 rawtext = self._revisioncache[2]
 
             # drop cache to save memory
             self._revisioncache = None
 
             targetsize = None
             rawsize = self.index[rev][2]
             if 0 <= rawsize:
                 targetsize = 4 * rawsize
 
             bins = self._chunks(chain, df=_df, targetsize=targetsize)
             if rawtext is None:
                 rawtext = bytes(bins[0])
                 bins = bins[1:]
 
             rawtext = mdiff.patches(rawtext, bins)
             self._revisioncache = (node, rev, rawtext)
 
         if flags is None:
             if rev is None:
                 rev = self.rev(node)
             flags = self.flags(rev)
 
         text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
 
         return text
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return storageutil.hashrevisionsha1(text, p1, p2)
 
     def _processflags(self, text, flags, operation, raw=False):
         """Inspect revision data flags and applies transforms defined by
         registered flag processors.
 
         ``text`` - the revision data to process
         ``flags`` - the revision flags
         ``operation`` - the operation being performed (read or write)
         ``raw`` - an optional argument describing if the raw transform should be
         applied.
 
         This method processes the flags in the order (or reverse order if
         ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
         flag processors registered for present flags. The order of flags defined
         in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.
 
         Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
         processed text and ``validatehash`` is a bool indicating whether the
         returned text should be checked for hash integrity.
 
         Note: If the ``raw`` argument is set, it has precedence over the
         operation and will only update the value of ``validatehash``.
         """
         # fast path: no flag processors will run
         if flags == 0:
             return text, True
         if not operation in ('read', 'write'):
             raise error.ProgrammingError(_("invalid '%s' operation") %
                                          operation)
         # Check all flags are known.
         if flags & ~REVIDX_KNOWN_FLAGS:
             raise error.RevlogError(_("incompatible revision flag '%#x'") %
                                     (flags & ~REVIDX_KNOWN_FLAGS))
         validatehash = True
         # Depending on the operation (read or write), the order might be
         # reversed due to non-commutative transforms.
         orderedflags = REVIDX_FLAGS_ORDER
         if operation == 'write':
             orderedflags = reversed(orderedflags)
 
         for flag in orderedflags:
             # If a flagprocessor has been registered for a known flag, apply the
             # related operation transform and update result tuple.
             if flag & flags:
                 vhash = True
 
                 if flag not in self._flagprocessors:
                     message = _("missing processor for flag '%#x'") % (flag)
                     raise error.RevlogError(message)
 
                 processor = self._flagprocessors[flag]
                 if processor is not None:
                     readtransform, writetransform, rawtransform = processor
 
                     if raw:
                         vhash = rawtransform(self, text)
                     elif operation == 'read':
                         text, vhash = readtransform(self, text)
                     else: # write operation
                         text, vhash = writetransform(self, text)
                 validatehash = validatehash and vhash
 
         return text, validatehash
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 # Clear the revision cache on hash failure. The revision cache
                 # only stores the raw revision and clearing the cache does have
                 # the side-effect that we won't have a cache hit when the raw
                 # revision data is accessed. But this case should be rare and
                 # it is extra work to teach the cache about the hash
                 # verification state.
                 if self._revisioncache and self._revisioncache[0] == node:
                     self._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(_("integrity check failed on %s:%s")
                     % (self.indexfile, pycompat.bytestr(revornode)))
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.indexfile, node, text)
             raise
 
     def _enforceinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         tiprev = len(self) - 1
         if (not self._inline or
             (self.start(tiprev) + self.length(tiprev)) < _maxinline):
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise error.RevlogError(_("%s not found in the transaction")
                                     % self.indexfile)
 
         trindex = trinfo[2]
         if trindex is not None:
             dataoff = self.start(trindex)
         else:
             # revlog was stripped at start of transaction, use all leftover data
             trindex = len(self) - 1
             dataoff = self.end(tiprev)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
 
         with self._indexfp('r') as ifh, self._datafp('w') as dfh:
             for r in self:
                 dfh.write(self._getsegmentforrevs(r, r, df=ifh)[1])
 
         with self._indexfp('w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             io = self._io
             for i in self:
                 e = io.packentry(self.index[i], self.node, self.version, i)
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored.
         """
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None,
                     node=None, flags=REVIDX_DEFAULT_FLAGS, deltacomputer=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         node - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         flags - the known flags to set on the revision
         deltacomputer - an optional deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise error.RevlogError(_("attempted to add linkrev -1 to %s")
                                     % self.indexfile)
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = self._processflags(text, flags, 'write')
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _("%s: size of %d bytes exceeds maximum revlog storage of 2GiB")
                 % (self.indexfile, len(rawtext)))
 
         node = node or self.hash(rawtext, p1, p2)
         if node in self.nodemap:
             return node
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(rawtext, transaction, link, p1, p2, node,
                                    flags, cachedelta=cachedelta,
                                    deltacomputer=deltacomputer)
 
     def addrawrevision(self, rawtext, transaction, link, p1, p2, node, flags,
                        cachedelta=None, deltacomputer=None):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp("a+")
         ifh = self._indexfp("a+")
         try:
             return self._addrevision(node, rawtext, transaction, link, p1, p2,
                                      flags, cachedelta, ifh, dfh,
                                      deltacomputer=deltacomputer)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return '', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return '', compressed
 
         if data[0:1] == '\0':
             return '', data
         return 'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == 'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(_('revlog decompress error: %s') %
                                         stringutil.forcebytestr(e))
         # '\0' is more common than 'u' so it goes first.
         elif t == '\0':
             return data
         elif t == 'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor()
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(_('unknown compression type %r') % t)
 
         return compressor.decompress(data)
 
     def _addrevision(self, node, rawtext, transaction, link, p1, p2, flags,
                      cachedelta, ifh, dfh, alwayscache=False,
                      deltacomputer=None):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == nullid:
             raise error.RevlogError(_("%s: attempt to add null revision") %
                                     self.indexfile)
         if node == wdirid or node in wdirfilenodeids:
             raise error.RevlogError(_("%s: attempt to add wdir revision") %
                                     self.indexfile)
 
         if self._inline:
             fh = ifh
         else:
             fh = dfh
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
         offset = self.end(prev)
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(revlog.size(self, cachedelta[0]),
                                         cachedelta[1])
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         e = (offset_type(offset, flags), deltainfo.deltalen, textlen,
              deltainfo.base, link, p1r, p2r, node)
         self.index.append(e)
         self.nodemap[node] = curr
 
         # Reset the pure node cache start lookup offset to account for new
         # revision.
         if self._nodepos is not None:
             self._nodepos = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         self._writeentry(transaction, ifh, dfh, entry, deltainfo.data,
                          link, offset)
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo, fh)
 
         if type(rawtext) == bytes: # only accept immutable objects
             self._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return node
 
     def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self._enforceinlinesize(transaction, ifh)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         if self._writinghandles:
             raise error.ProgrammingError('cannot nest addgroup() calls')
 
         nodes = []
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp("a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self._datafp("a+")
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 nodes.append(node)
 
                 if node in self.nodemap:
                     self._nodeduplicatecallback(transaction, node)
                     # this can happen if two branches make the same change
                     continue
 
                 for p in (p1, p2):
                     if p not in self.nodemap:
                         raise error.LookupError(p, self.indexfile,
                                                 _('unknown parent'))
 
                 if deltabase not in self.nodemap:
                     raise error.LookupError(deltabase, self.indexfile,
                                             _('unknown delta base'))
 
                 baserev = self.rev(deltabase)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(self.indexfile,
                                                       self.node(baserev))
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
                 # We're only using addgroup() in the context of changegroup
                 # generation so the revision data can always be handled as raw
                 # by the flagprocessor.
                 self._addrevision(node, None, transaction, link,
                                   p1, p2, flags, (baserev, delta),
                                   ifh, dfh,
                                   alwayscache=bool(addrevisioncb),
                                   deltacomputer=deltacomputer)
 
                 if addrevisioncb:
                     addrevisioncb(self, node)
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp("a+")
                     ifh = self._indexfp("a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
 
         return nodes
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         return storageutil.deltaiscensored(delta, baserev, self.rawsize)
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         return storageutil.resolvestripinfo(minlink, len(self) - 1,
                                             self.headrevs(),
                                             self.linkrev, self.parentrevs)
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = {}
         self._chunkclear()
         for x in pycompat.xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
         self._nodepos = None
 
     def checksize(self):
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, 2)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     def emitrevisions(self, nodes, nodesorder=None, revisiondata=False,
                       assumehaveparentrevisions=False,
                       deltamode=repository.CG_DELTAMODE_STD):
         if nodesorder not in ('nodes', 'storage', 'linear', None):
             raise error.ProgrammingError('unhandled value for nodesorder: %s' %
                                          nodesorder)
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = 'storage'
 
         if (not self._storedeltachains and
                 deltamode != repository.CG_DELTAMODE_PREV):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self, nodes, nodesorder, revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self.candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions)
 
     DELTAREUSEALWAYS = 'always'
     DELTAREUSESAMEREVS = 'samerevs'
     DELTAREUSENEVER = 'never'
 
     DELTAREUSEFULLADD = 'fulladd'
 
     DELTAREUSEALL = {'always', 'samerevs', 'never', 'fulladd'}
 
     def clone(self, tr, destrevlog, addrevisioncb=None,
               deltareuse=DELTAREUSESAMEREVS, forcedeltabothparents=None):
         """Copy this revlog to another, possibly with format changes.
 
         The destination revlog will contain the same revisions and nodes.
         However, it may not be bit-for-bit identical due to e.g. delta encoding
         differences.
 
         The ``deltareuse`` argument control how deltas from the existing revlog
         are preserved in the destination revlog. The argument can have the
         following values:
 
         DELTAREUSEALWAYS
            Deltas will always be reused (if possible), even if the destination
            revlog would not select the same revisions for the delta. This is the
            fastest mode of operation.
         DELTAREUSESAMEREVS
            Deltas will be reused if the destination revlog would pick the same
            revisions for the delta. This mode strikes a balance between speed
            and optimization.
         DELTAREUSENEVER
            Deltas will never be reused. This is the slowest mode of execution.
            This mode can be used to recompute deltas (e.g. if the diff/delta
            algorithm changes).
 
         Delta computation can be slow, so the choice of delta reuse policy can
         significantly affect run time.
 
         The default policy (``DELTAREUSESAMEREVS``) strikes a balance between
         two extremes. Deltas will be reused if they are appropriate. But if the
         delta could choose a better revision, it will do so. This means if you
         are converting a non-generaldelta revlog to a generaldelta revlog,
         deltas will be recomputed if the delta's parent isn't a parent of the
         revision.
 
         In addition to the delta policy, the ``forcedeltabothparents``
         argument controls whether to force compute deltas against both parents
         for merges. By default, the current default is used.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(_('value for deltareuse invalid: %s') % deltareuse)
 
         if len(destrevlog):
             raise ValueError(_('destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_('source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_('destination revlog has filtered revisions'))
 
         # lazydeltabase controls whether to reuse a cached delta, if possible.
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             populatecachedelta = deltareuse in (self.DELTAREUSEALWAYS,
                                                 self.DELTAREUSESAMEREVS)
 
             deltacomputer = deltautil.deltacomputer(destrevlog)
             index = self.index
             for rev in self:
                 entry = index[rev]
 
                 # Some classes override linkrev to take filtered revs into
                 # account. Use raw entry from index.
                 flags = entry[0] & 0xffff
                 linkrev = entry[4]
                 p1 = index[entry[5]][7]
                 p2 = index[entry[6]][7]
                 node = entry[7]
 
                 # (Possibly) reuse the delta from the revlog if allowed and
                 # the revlog chunk is a delta.
                 cachedelta = None
                 rawtext = None
                 if populatecachedelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 if not cachedelta:
                     rawtext = self.revision(rev, raw=True)
 
 
                 if deltareuse == self.DELTAREUSEFULLADD:
                     destrevlog.addrevision(rawtext, tr, linkrev, p1, p2,
                                            cachedelta=cachedelta,
                                            node=node, flags=flags,
                                            deltacomputer=deltacomputer)
                 else:
                     ifh = destrevlog.opener(destrevlog.indexfile, 'a+',
                                             checkambig=False)
                     dfh = None
                     if not destrevlog._inline:
                         dfh = destrevlog.opener(destrevlog.datafile, 'a+')
                     try:
                         destrevlog._addrevision(node, rawtext, tr, linkrev, p1,
                                                 p2, flags, cachedelta, ifh, dfh,
                                                 deltacomputer=deltacomputer)
                     finally:
                         if dfh:
                             dfh.close()
                         ifh.close()
 
                 if addrevisioncb:
                     addrevisioncb(self, rev, node)
         finally:
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if (self.version & 0xFFFF) == REVLOGV0:
             raise error.RevlogError(_('cannot censor with version %d revlogs') %
                                     self.version)
 
         censorrev = self.rev(censornode)
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(censorrev):
             raise error.Abort(_('censor tombstone must be no longer than '
                                 'censored data'))
 
         # Rewriting the revlog in place is hard. Our strategy for censoring is
         # to create a new revlog, copy all revisions to it, then replace the
         # revlogs on transaction close.
 
         newindexfile = self.indexfile + b'.tmpcensored'
         newdatafile = self.datafile + b'.tmpcensored'
 
         # This is a bit dangerous. We could easily have a mismatch of state.
         newrl = revlog(self.opener, newindexfile, newdatafile,
                        censorable=True)
         newrl.version = self.version
         newrl._generaldelta = self._generaldelta
         newrl._io = self._io
 
         for rev in self.revs():
             node = self.node(rev)
             p1, p2 = self.parents(node)
 
             if rev == censorrev:
                 newrl.addrawrevision(tombstone, tr, self.linkrev(censorrev),
                                      p1, p2, censornode, REVIDX_ISCENSORED)
 
                 if newrl.deltaparent(rev) != nullrev:
                     raise error.Abort(_('censored revision stored as delta; '
                                         'cannot censor'),
                                       hint=_('censoring of revlogs is not '
                                              'fully implemented; please report '
                                              'this bug'))
                 continue
 
             if self.iscensored(rev):
                 if self.deltaparent(rev) != nullrev:
                     raise error.Abort(_('cannot censor due to censored '
                                         'revision having delta stored'))
                 rawtext = self._chunk(rev)
             else:
                 rawtext = self.revision(rev, raw=True)
 
             newrl.addrawrevision(rawtext, tr, self.linkrev(rev), p1, p2, node,
                                  self.flags(rev))
 
         tr.addbackup(self.indexfile, location='store')
         if not self._inline:
             tr.addbackup(self.datafile, location='store')
 
         self.opener.rename(newrl.indexfile, self.indexfile)
         if not self._inline:
             self.opener.rename(newrl.datafile, self.datafile)
 
         self.clearcaches()
         self._loadindex()
 
     def verifyintegrity(self, state):
         """Verifies the integrity of the revlog.
 
         Yields ``revlogproblem`` instances describing problems that are
         found.
         """
         dd, di = self.checksize()
         if dd:
             yield revlogproblem(error=_('data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_('index contains %d extra bytes') % di)
 
         version = self.version & 0xFFFF
 
         # The verifier tells us what version revlog we should be.
         if version != state['expectedversion']:
             yield revlogproblem(
                 warning=_("warning: '%s' uses revlog format %d; expected %d") %
                         (self.indexfile, version, state['expectedversion']))
 
         state['skipread'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "revision(rev, raw=True)". "text"
             # mentioned below is "revision(rev, raw=False)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see revlog.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get('skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 if skipflags:
                     state['skipread'].add(node)
                 else:
                     # Side-effect: read content and verify hash.
                     self.revision(node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.revision(node, raw=True))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_('unpacked size is %d, %d expected') % (l2, l1),
                         node=node)
 
             except error.CensoredNodeError:
                 if state['erroroncensored']:
                     yield revlogproblem(error=_('censored file data'),
                                         node=node)
                     state['skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_('unpacking %s: %s') % (short(node),
                                                    stringutil.forcebytestr(e)),
                     node=node)
                 state['skipread'].add(node)
 
     def storageinfo(self, exclusivefiles=False, sharedfiles=False,
                     revisionscount=False, trackedsize=False,
                     storedsize=False):
         d = {}
 
         if exclusivefiles:
             d['exclusivefiles'] = [(self.opener, self.indexfile)]
             if not self._inline:
                 d['exclusivefiles'].append((self.opener, self.datafile))
 
         if sharedfiles:
             d['sharedfiles'] = []
 
         if revisionscount:
             d['revisionscount'] = len(self)
 
         if trackedsize:
             d['trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d['storedsize'] = sum(self.opener.stat(path).st_size
                                   for path in self.files())
 
         return d

mercurial/setdiscovery.py

@@ -1,355 +1,356
 # setdiscovery.py - improved discovery of common nodeset for mercurial
 #
 # Copyright 2010 Benoit Boissinot <[e-mail]>
 # and Peter Arrenbrecht <[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.
 """
 Algorithm works in the following way. You have two repository: local and
 remote. They both contains a DAG of changelists.
 
 The goal of the discovery protocol is to find one set of node *common*,
 the set of nodes shared by local and remote.
 
 One of the issue with the original protocol was latency, it could
 potentially require lots of roundtrips to discover that the local repo was a
 subset of remote (which is a very common case, you usually have few changes
 compared to upstream, while upstream probably had lots of development).
 
 The new protocol only requires one interface for the remote repo: `known()`,
 which given a set of changelists tells you if they are present in the DAG.
 
 The algorithm then works as follow:
 
  - We will be using three sets, `common`, `missing`, `unknown`. Originally
  all nodes are in `unknown`.
  - Take a sample from `unknown`, call `remote.known(sample)`
    - For each node that remote knows, move it and all its ancestors to `common`
    - For each node that remote doesn't know, move it and all its descendants
    to `missing`
  - Iterate until `unknown` is empty
 
 There are a couple optimizations, first is instead of starting with a random
 sample of missing, start by sending all heads, in the case where the local
 repo is a subset, you computed the answer in one round trip.
 
 Then you can do something similar to the bisecting strategy used when
 finding faulty changesets. Instead of random samples, you can try picking
 nodes that will maximize the number of nodes that will be
 classified with it (since all ancestors or descendants will be marked as well).
 """
 
 from __future__ import absolute_import
 
 import collections
 import random
 
 from .i18n import _
 from .node import (
     nullid,
     nullrev,
 )
 from . import (
     error,
     util,
 )
 
 def _updatesample(revs, heads, sample, parentfn, quicksamplesize=0):
     """update an existing sample to match the expected size
 
     The sample is updated with revs exponentially distant from each head of the
     <revs> set. (H~1, H~2, H~4, H~8, etc).
 
     If a target size is specified, the sampling will stop once this size is
     reached. Otherwise sampling will happen until roots of the <revs> set are
     reached.
 
     :revs:  set of revs we want to discover (if None, assume the whole dag)
     :heads: set of DAG head revs
     :sample: a sample to update
     :parentfn: a callable to resolve parents for a revision
     :quicksamplesize: optional target size of the sample"""
     dist = {}
     visit = collections.deque(heads)
     seen = set()
     factor = 1
     while visit:
         curr = visit.popleft()
         if curr in seen:
             continue
         d = dist.setdefault(curr, 1)
         if d > factor:
             factor *= 2
         if d == factor:
             sample.add(curr)
             if quicksamplesize and (len(sample) >= quicksamplesize):
                 return
         seen.add(curr)
 
         for p in parentfn(curr):
             if p != nullrev and (not revs or p in revs):
                 dist.setdefault(p, d + 1)
                 visit.append(p)
 
 def _takequicksample(repo, headrevs, revs, size):
     """takes a quick sample of size <size>
 
     It is meant for initial sampling and focuses on querying heads and close
     ancestors of heads.
 
     :dag: a dag object
     :headrevs: set of head revisions in local DAG to consider
     :revs: set of revs to discover
     :size: the maximum size of the sample"""
     if len(revs) <= size:
         return list(revs)
     sample = set(repo.revs('heads(%ld)', revs))
 
     if len(sample) >= size:
         return _limitsample(sample, size)
 
     _updatesample(None, headrevs, sample, repo.changelog.parentrevs,
                   quicksamplesize=size)
     return sample
 
 def _takefullsample(repo, headrevs, revs, size):
     if len(revs) <= size:
         return list(revs)
     sample = set(repo.revs('heads(%ld)', revs))
 
     # update from heads
     revsheads = set(repo.revs('heads(%ld)', revs))
     _updatesample(revs, revsheads, sample, repo.changelog.parentrevs)
 
     # update from roots
     revsroots = set(repo.revs('roots(%ld)', revs))
 
     # _updatesample() essentially does interaction over revisions to look up
     # their children. This lookup is expensive and doing it in a loop is
     # quadratic. We precompute the children for all relevant revisions and
     # make the lookup in _updatesample() a simple dict lookup.
     #
     # Because this function can be called multiple times during discovery, we
     # may still perform redundant work and there is room to optimize this by
     # keeping a persistent cache of children across invocations.
     children = {}
 
     parentrevs = repo.changelog.parentrevs
     for rev in repo.changelog.revs(start=min(revsroots)):
         # Always ensure revision has an entry so we don't need to worry about
         # missing keys.
         children.setdefault(rev, [])
 
         for prev in parentrevs(rev):
             if prev == nullrev:
                 continue
 
             children.setdefault(prev, []).append(rev)
 
     _updatesample(revs, revsroots, sample, children.__getitem__)
     assert sample
     sample = _limitsample(sample, size)
     if len(sample) < size:
         more = size - len(sample)
         sample.update(random.sample(list(revs - sample), more))
     return sample
 
 def _limitsample(sample, desiredlen):
     """return a random subset of sample of at most desiredlen item"""
     if len(sample) > desiredlen:
         sample = set(random.sample(sample, desiredlen))
     return sample
 
 class partialdiscovery(object):
     """an object representing ongoing discovery
 
     Feed with data from the remote repository, this object keep track of the
     current set of changeset in various states:
 
     - common:    revs also known remotely
     - undecided: revs we don't have information on yet
     - missing:   revs missing remotely
     (all tracked revisions are known locally)
     """
 
     def __init__(self, repo, targetheads):
         self._repo = repo
         self._targetheads = targetheads
         self._common = repo.changelog.incrementalmissingrevs()
         self._undecided = None
         self.missing = set()
 
     def addcommons(self, commons):
         """registrer nodes known as common"""
         self._common.addbases(commons)
-        self._common.removeancestorsfrom(self.undecided)
+        if self._undecided is not None:
+            self._common.removeancestorsfrom(self._undecided)
 
     def addmissings(self, missings):
         """registrer some nodes as missing"""
         newmissing = self._repo.revs('%ld::%ld', missings, self.undecided)
         if newmissing:
             self.missing.update(newmissing)
             self.undecided.difference_update(newmissing)
 
     def addinfo(self, sample):
         """consume an iterable of (rev, known) tuples"""
         common = set()
         missing = set()
         for rev, known in sample:
             if known:
                 common.add(rev)
             else:
                 missing.add(rev)
         if common:
             self.addcommons(common)
         if missing:
             self.addmissings(missing)
 
     def hasinfo(self):
         """return True is we have any clue about the remote state"""
         return self._common.hasbases()
 
     def iscomplete(self):
         """True if all the necessary data have been gathered"""
         return self._undecided is not None and not self._undecided
 
     @property
     def undecided(self):
         if self._undecided is not None:
             return self._undecided
         self._undecided = set(self._common.missingancestors(self._targetheads))
         return self._undecided
 
     def commonheads(self):
         """the heads of the known common set"""
         # heads(common) == heads(common.bases) since common represents
         # common.bases and all its ancestors
         return self._common.basesheads()
 
 def findcommonheads(ui, local, remote,
                     initialsamplesize=100,
                     fullsamplesize=200,
                     abortwhenunrelated=True,
                     ancestorsof=None):
     '''Return a tuple (common, anyincoming, remoteheads) used to identify
     missing nodes from or in remote.
     '''
     start = util.timer()
 
     roundtrips = 0
     cl = local.changelog
     clnode = cl.node
     clrev = cl.rev
 
     if ancestorsof is not None:
         ownheads = [clrev(n) for n in ancestorsof]
     else:
         ownheads = [rev for rev in cl.headrevs() if rev != nullrev]
 
     # early exit if we know all the specified remote heads already
     ui.debug("query 1; heads\n")
     roundtrips += 1
     sample = _limitsample(ownheads, initialsamplesize)
     # indices between sample and externalized version must match
     sample = list(sample)
 
     with remote.commandexecutor() as e:
         fheads = e.callcommand('heads', {})
         fknown = e.callcommand('known', {
             'nodes': [clnode(r) for r in sample],
         })
 
     srvheadhashes, yesno = fheads.result(), fknown.result()
 
     if cl.tip() == nullid:
         if srvheadhashes != [nullid]:
             return [nullid], True, srvheadhashes
         return [nullid], False, []
 
     # start actual discovery (we note this before the next "if" for
     # compatibility reasons)
     ui.status(_("searching for changes\n"))
 
     srvheads = []
     for node in srvheadhashes:
         if node == nullid:
             continue
 
         try:
             srvheads.append(clrev(node))
         # Catches unknown and filtered nodes.
         except error.LookupError:
             continue
 
     if len(srvheads) == len(srvheadhashes):
         ui.debug("all remote heads known locally\n")
         return srvheadhashes, False, srvheadhashes
 
     if len(sample) == len(ownheads) and all(yesno):
         ui.note(_("all local heads known remotely\n"))
         ownheadhashes = [clnode(r) for r in ownheads]
         return ownheadhashes, True, srvheadhashes
 
     # full blown discovery
 
     disco = partialdiscovery(local, ownheads)
     # treat remote heads (and maybe own heads) as a first implicit sample
     # response
     disco.addcommons(srvheads)
     disco.addinfo(zip(sample, yesno))
 
     full = False
     progress = ui.makeprogress(_('searching'), unit=_('queries'))
     while not disco.iscomplete():
 
         if full or disco.hasinfo():
             if full:
                 ui.note(_("sampling from both directions\n"))
             else:
                 ui.debug("taking initial sample\n")
             samplefunc = _takefullsample
             targetsize = fullsamplesize
         else:
             # use even cheaper initial sample
             ui.debug("taking quick initial sample\n")
             samplefunc = _takequicksample
             targetsize = initialsamplesize
         sample = samplefunc(local, ownheads, disco.undecided, targetsize)
 
         roundtrips += 1
         progress.update(roundtrips)
         ui.debug("query %i; still undecided: %i, sample size is: %i\n"
                  % (roundtrips, len(disco.undecided), len(sample)))
         # indices between sample and externalized version must match
         sample = list(sample)
 
         with remote.commandexecutor() as e:
             yesno = e.callcommand('known', {
                 'nodes': [clnode(r) for r in sample],
             }).result()
 
         full = True
 
         disco.addinfo(zip(sample, yesno))
 
     result = disco.commonheads()
     elapsed = util.timer() - start
     progress.complete()
     ui.debug("%d total queries in %.4fs\n" % (roundtrips, elapsed))
     msg = ('found %d common and %d unknown server heads,'
            ' %d roundtrips in %.4fs\n')
     missing = set(result) - set(srvheads)
     ui.log('discovery', msg, len(result), len(missing), roundtrips,
            elapsed)
 
     if not result and srvheadhashes != [nullid]:
         if abortwhenunrelated:
             raise error.Abort(_("repository is unrelated"))
         else:
             ui.warn(_("warning: repository is unrelated\n"))
         return ({nullid}, True, srvheadhashes,)
 
     anyincoming = (srvheadhashes != [nullid])
     result = {clnode(r) for r in result}
     return result, anyincoming, srvheadhashes

mercurial/ui.py

@@ -1,2077 +1,2110
 # ui.py - user interface bits 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 collections
 import contextlib
 import errno
 import getpass
 import inspect
 import os
 import re
 import signal
 import socket
 import subprocess
 import sys
 import traceback
 
 from .i18n import _
 from .node import hex
 
 from . import (
     color,
     config,
     configitems,
     encoding,
     error,
     formatter,
     loggingutil,
     progress,
     pycompat,
     rcutil,
     scmutil,
     util,
 )
 from .utils import (
     dateutil,
     procutil,
     stringutil,
 )
 
 urlreq = util.urlreq
 
 # for use with str.translate(None, _keepalnum), to keep just alphanumerics
 _keepalnum = ''.join(c for c in map(pycompat.bytechr, range(256))
                      if not c.isalnum())
 
 # The config knobs that will be altered (if unset) by ui.tweakdefaults.
 tweakrc = b"""
 [ui]
 # The rollback command is dangerous. As a rule, don't use it.
 rollback = False
 # Make `hg status` report copy information
 statuscopies = yes
 # Prefer curses UIs when available. Revert to plain-text with `text`.
 interface = curses
 
 [commands]
 # Grep working directory by default.
 grep.all-files = True
 # Make `hg status` emit cwd-relative paths by default.
 status.relative = yes
 # Refuse to perform an `hg update` that would cause a file content merge
 update.check = noconflict
 # Show conflicts information in `hg status`
 status.verbose = True
 
 [diff]
 git = 1
 showfunc = 1
 word-diff = 1
 """
 
 samplehgrcs = {
     'user':
 b"""# example user config (see 'hg help config' for more info)
 [ui]
 # name and email, e.g.
 # username = Jane Doe <[e-mail]>
 username =
 
 # We recommend enabling tweakdefaults to get slight improvements to
 # the UI over time. Make sure to set HGPLAIN in the environment when
 # writing scripts!
 # tweakdefaults = True
 
 # uncomment to disable color in command output
 # (see 'hg help color' for details)
 # color = never
 
 # uncomment to disable command output pagination
 # (see 'hg help pager' for details)
 # paginate = never
 
 [extensions]
 # uncomment these lines to enable some popular extensions
 # (see 'hg help extensions' for more info)
 #
 # churn =
 """,
 
     'cloned':
 b"""# example repository config (see 'hg help config' for more info)
 [paths]
 default = %s
 
 # path aliases to other clones of this repo in URLs or filesystem paths
 # (see 'hg help config.paths' for more info)
 #
 # default:pushurl = ssh://[e-mail]/hg/jdoes-fork
 # my-fork         = ssh://[e-mail]/hg/jdoes-fork
 # my-clone        = /home/jdoe/jdoes-clone
 
 [ui]
 # name and email (local to this repository, optional), e.g.
 # username = Jane Doe <[e-mail]>
 """,
 
     'local':
 b"""# example repository config (see 'hg help config' for more info)
 [paths]
 # path aliases to other clones of this repo in URLs or filesystem paths
 # (see 'hg help config.paths' for more info)
 #
 # default         = http://example.com/hg/example-repo
 # default:pushurl = ssh://[e-mail]/hg/jdoes-fork
 # my-fork         = ssh://[e-mail]/hg/jdoes-fork
 # my-clone        = /home/jdoe/jdoes-clone
 
 [ui]
 # name and email (local to this repository, optional), e.g.
 # username = Jane Doe <[e-mail]>
 """,
 
     'global':
 b"""# example system-wide hg config (see 'hg help config' for more info)
 
 [ui]
 # uncomment to disable color in command output
 # (see 'hg help color' for details)
 # color = never
 
 # uncomment to disable command output pagination
 # (see 'hg help pager' for details)
 # paginate = never
 
 [extensions]
 # uncomment these lines to enable some popular extensions
 # (see 'hg help extensions' for more info)
 #
 # blackbox =
 # churn =
 """,
 }
 
 def _maybestrurl(maybebytes):
     return pycompat.rapply(pycompat.strurl, maybebytes)
 
 def _maybebytesurl(maybestr):
     return pycompat.rapply(pycompat.bytesurl, maybestr)
 
 class httppasswordmgrdbproxy(object):
     """Delays loading urllib2 until it's needed."""
     def __init__(self):
         self._mgr = None
 
     def _get_mgr(self):
         if self._mgr is None:
             self._mgr = urlreq.httppasswordmgrwithdefaultrealm()
         return self._mgr
 
     def add_password(self, realm, uris, user, passwd):
         return self._get_mgr().add_password(
             _maybestrurl(realm), _maybestrurl(uris),
             _maybestrurl(user), _maybestrurl(passwd))
 
     def find_user_password(self, realm, uri):
         mgr = self._get_mgr()
         return _maybebytesurl(mgr.find_user_password(_maybestrurl(realm),
                                                      _maybestrurl(uri)))
 
 def _catchterm(*args):
     raise error.SignalInterrupt
 
 # unique object used to detect no default value has been provided when
 # retrieving configuration value.
 _unset = object()
 
 # _reqexithandlers: callbacks run at the end of a request
 _reqexithandlers = []
 
 class ui(object):
     def __init__(self, src=None):
         """Create a fresh new ui object if no src given
 
         Use uimod.ui.load() to create a ui which knows global and user configs.
         In most cases, you should use ui.copy() to create a copy of an existing
         ui object.
         """
         # _buffers: used for temporary capture of output
         self._buffers = []
         # 3-tuple describing how each buffer in the stack behaves.
         # Values are (capture stderr, capture subprocesses, apply labels).
         self._bufferstates = []
         # When a buffer is active, defines whether we are expanding labels.
         # This exists to prevent an extra list lookup.
         self._bufferapplylabels = None
         self.quiet = self.verbose = self.debugflag = self.tracebackflag = False
         self._reportuntrusted = True
         self._knownconfig = configitems.coreitems
         self._ocfg = config.config() # overlay
         self._tcfg = config.config() # trusted
         self._ucfg = config.config() # untrusted
         self._trustusers = set()
         self._trustgroups = set()
         self.callhooks = True
         # Insecure server connections requested.
         self.insecureconnections = False
         # Blocked time
         self.logblockedtimes = False
         # color mode: see mercurial/color.py for possible value
         self._colormode = None
         self._terminfoparams = {}
         self._styles = {}
         self._uninterruptible = False
 
         if src:
             self._fout = src._fout
             self._ferr = src._ferr
             self._fin = src._fin
             self._fmsg = src._fmsg
             self._fmsgout = src._fmsgout
             self._fmsgerr = src._fmsgerr
             self._finoutredirected = src._finoutredirected
             self._loggers = src._loggers.copy()
             self.pageractive = src.pageractive
             self._disablepager = src._disablepager
             self._tweaked = src._tweaked
 
             self._tcfg = src._tcfg.copy()
             self._ucfg = src._ucfg.copy()
             self._ocfg = src._ocfg.copy()
             self._trustusers = src._trustusers.copy()
             self._trustgroups = src._trustgroups.copy()
             self.environ = src.environ
             self.callhooks = src.callhooks
             self.insecureconnections = src.insecureconnections
             self._colormode = src._colormode
             self._terminfoparams = src._terminfoparams.copy()
             self._styles = src._styles.copy()
 
             self.fixconfig()
 
             self.httppasswordmgrdb = src.httppasswordmgrdb
             self._blockedtimes = src._blockedtimes
         else:
             self._fout = procutil.stdout
             self._ferr = procutil.stderr
             self._fin = procutil.stdin
             self._fmsg = None
             self._fmsgout = self.fout  # configurable
             self._fmsgerr = self.ferr  # configurable
             self._finoutredirected = False
             self._loggers = {}
             self.pageractive = False
             self._disablepager = False
             self._tweaked = False
 
             # shared read-only environment
             self.environ = encoding.environ
 
             self.httppasswordmgrdb = httppasswordmgrdbproxy()
             self._blockedtimes = collections.defaultdict(int)
 
         allowed = self.configlist('experimental', 'exportableenviron')
         if '*' in allowed:
             self._exportableenviron = self.environ
         else:
             self._exportableenviron = {}
             for k in allowed:
                 if k in self.environ:
                     self._exportableenviron[k] = self.environ[k]
 
     @classmethod
     def load(cls):
         """Create a ui and load global and user configs"""
         u = cls()
         # we always trust global config files and environment variables
         for t, f in rcutil.rccomponents():
             if t == 'path':
                 u.readconfig(f, trust=True)
             elif t == 'items':
                 sections = set()
                 for section, name, value, source in f:
                     # do not set u._ocfg
                     # XXX clean this up once immutable config object is a thing
                     u._tcfg.set(section, name, value, source)
                     u._ucfg.set(section, name, value, source)
                     sections.add(section)
                 for section in sections:
                     u.fixconfig(section=section)
             else:
                 raise error.ProgrammingError('unknown rctype: %s' % t)
         u._maybetweakdefaults()
         return u
 
     def _maybetweakdefaults(self):
         if not self.configbool('ui', 'tweakdefaults'):
             return
         if self._tweaked or self.plain('tweakdefaults'):
             return
 
         # Note: it is SUPER IMPORTANT that you set self._tweaked to
         # True *before* any calls to setconfig(), otherwise you'll get
         # infinite recursion between setconfig and this method.
         #
         # TODO: We should extract an inner method in setconfig() to
         # avoid this weirdness.
         self._tweaked = True
         tmpcfg = config.config()
         tmpcfg.parse('<tweakdefaults>', tweakrc)
         for section in tmpcfg:
             for name, value in tmpcfg.items(section):
                 if not self.hasconfig(section, name):
                     self.setconfig(section, name, value, "<tweakdefaults>")
 
     def copy(self):
         return self.__class__(self)
 
     def resetstate(self):
         """Clear internal state that shouldn't persist across commands"""
         if self._progbar:
             self._progbar.resetstate()  # reset last-print time of progress bar
         self.httppasswordmgrdb = httppasswordmgrdbproxy()
 
     @contextlib.contextmanager
     def timeblockedsection(self, key):
         # this is open-coded below - search for timeblockedsection to find them
         starttime = util.timer()
         try:
             yield
         finally:
             self._blockedtimes[key + '_blocked'] += \
                 (util.timer() - starttime) * 1000
 
     @contextlib.contextmanager
     def uninterruptible(self):
         """Mark an operation as unsafe.
 
         Most operations on a repository are safe to interrupt, but a
         few are risky (for example repair.strip). This context manager
         lets you advise Mercurial that something risky is happening so
         that control-C etc can be blocked if desired.
         """
         enabled = self.configbool('experimental', 'nointerrupt')
         if (enabled and
             self.configbool('experimental', 'nointerrupt-interactiveonly')):
             enabled = self.interactive()
         if self._uninterruptible or not enabled:
             # if nointerrupt support is turned off, the process isn't
             # interactive, or we're already in an uninterruptible
             # block, do nothing.
             yield
             return
         def warn():
             self.warn(_("shutting down cleanly\n"))
             self.warn(
                 _("press ^C again to terminate immediately (dangerous)\n"))
             return True
         with procutil.uninterruptible(warn):
             try:
                 self._uninterruptible = True
                 yield
             finally:
                 self._uninterruptible = False
 
     def formatter(self, topic, opts):
         return formatter.formatter(self, self, topic, opts)
 
     def _trusted(self, fp, f):
         st = util.fstat(fp)
         if util.isowner(st):
             return True
 
         tusers, tgroups = self._trustusers, self._trustgroups
         if '*' in tusers or '*' in tgroups:
             return True
 
         user = util.username(st.st_uid)
         group = util.groupname(st.st_gid)
         if user in tusers or group in tgroups or user == util.username():
             return True
 
         if self._reportuntrusted:
             self.warn(_('not trusting file %s from untrusted '
                         'user %s, group %s\n') % (f, user, group))
         return False
 
     def readconfig(self, filename, root=None, trust=False,
                    sections=None, remap=None):
         try:
             fp = open(filename, r'rb')
         except IOError:
             if not sections: # ignore unless we were looking for something
                 return
             raise
 
         cfg = config.config()
         trusted = sections or trust or self._trusted(fp, filename)
 
         try:
             cfg.read(filename, fp, sections=sections, remap=remap)
             fp.close()
         except error.ConfigError as inst:
             if trusted:
                 raise
             self.warn(_("ignored: %s\n") % stringutil.forcebytestr(inst))
 
         if self.plain():
             for k in ('debug', 'fallbackencoding', 'quiet', 'slash',
                       'logtemplate', 'message-output', 'statuscopies', 'style',
                       'traceback', 'verbose'):
                 if k in cfg['ui']:
                     del cfg['ui'][k]
             for k, v in cfg.items('defaults'):
                 del cfg['defaults'][k]
             for k, v in cfg.items('commands'):
                 del cfg['commands'][k]
         # Don't remove aliases from the configuration if in the exceptionlist
         if self.plain('alias'):
             for k, v in cfg.items('alias'):
                 del cfg['alias'][k]
         if self.plain('revsetalias'):
             for k, v in cfg.items('revsetalias'):
                 del cfg['revsetalias'][k]
         if self.plain('templatealias'):
             for k, v in cfg.items('templatealias'):
                 del cfg['templatealias'][k]
 
         if trusted:
             self._tcfg.update(cfg)
             self._tcfg.update(self._ocfg)
         self._ucfg.update(cfg)
         self._ucfg.update(self._ocfg)
 
         if root is None:
             root = os.path.expanduser('~')
         self.fixconfig(root=root)
 
     def fixconfig(self, root=None, section=None):
         if section in (None, 'paths'):
             # expand vars and ~
             # translate paths relative to root (or home) into absolute paths
             root = root or encoding.getcwd()
             for c in self._tcfg, self._ucfg, self._ocfg:
                 for n, p in c.items('paths'):
                     # Ignore sub-options.
                     if ':' in n:
                         continue
                     if not p:
                         continue
                     if '%%' in p:
                         s = self.configsource('paths', n) or 'none'
                         self.warn(_("(deprecated '%%' in path %s=%s from %s)\n")
                                   % (n, p, s))
                         p = p.replace('%%', '%')
                     p = util.expandpath(p)
                     if not util.hasscheme(p) and not os.path.isabs(p):
                         p = os.path.normpath(os.path.join(root, p))
                     c.set("paths", n, p)
 
         if section in (None, 'ui'):
             # update ui options
             self._fmsgout, self._fmsgerr = _selectmsgdests(self)
             self.debugflag = self.configbool('ui', 'debug')
             self.verbose = self.debugflag or self.configbool('ui', 'verbose')
             self.quiet = not self.debugflag and self.configbool('ui', 'quiet')
             if self.verbose and self.quiet:
                 self.quiet = self.verbose = False
             self._reportuntrusted = self.debugflag or self.configbool("ui",
                 "report_untrusted")
             self.tracebackflag = self.configbool('ui', 'traceback')
             self.logblockedtimes = self.configbool('ui', 'logblockedtimes')
 
         if section in (None, 'trusted'):
             # update trust information
             self._trustusers.update(self.configlist('trusted', 'users'))
             self._trustgroups.update(self.configlist('trusted', 'groups'))
 
         if section in (None, b'devel', b'ui') and self.debugflag:
             tracked = set()
             if self.configbool(b'devel', b'debug.extensions'):
                 tracked.add(b'extension')
             if tracked:
                 logger = loggingutil.fileobjectlogger(self._ferr, tracked)
                 self.setlogger(b'debug', logger)
 
     def backupconfig(self, section, item):
         return (self._ocfg.backup(section, item),
                 self._tcfg.backup(section, item),
                 self._ucfg.backup(section, item),)
     def restoreconfig(self, data):
         self._ocfg.restore(data[0])
         self._tcfg.restore(data[1])
         self._ucfg.restore(data[2])
 
     def setconfig(self, section, name, value, source=''):
         for cfg in (self._ocfg, self._tcfg, self._ucfg):
             cfg.set(section, name, value, source)
         self.fixconfig(section=section)
         self._maybetweakdefaults()
 
     def _data(self, untrusted):
         return untrusted and self._ucfg or self._tcfg
 
     def configsource(self, section, name, untrusted=False):
         return self._data(untrusted).source(section, name)
 
     def config(self, section, name, default=_unset, untrusted=False):
         """return the plain string version of a config"""
         value = self._config(section, name, default=default,
                              untrusted=untrusted)
         if value is _unset:
             return None
         return value
 
     def _config(self, section, name, default=_unset, untrusted=False):
         value = itemdefault = default
         item = self._knownconfig.get(section, {}).get(name)
         alternates = [(section, name)]
 
         if item is not None:
             alternates.extend(item.alias)
             if callable(item.default):
                 itemdefault = item.default()
             else:
                 itemdefault = item.default
         else:
             msg = ("accessing unregistered config item: '%s.%s'")
             msg %= (section, name)
             self.develwarn(msg, 2, 'warn-config-unknown')
 
         if default is _unset:
             if item is None:
                 value = default
             elif item.default is configitems.dynamicdefault:
                 value = None
                 msg = "config item requires an explicit default value: '%s.%s'"
                 msg %= (section, name)
                 self.develwarn(msg, 2, 'warn-config-default')
             else:
                 value = itemdefault
         elif (item is not None
               and item.default is not configitems.dynamicdefault
               and default != itemdefault):
             msg = ("specifying a mismatched default value for a registered "
                    "config item: '%s.%s' '%s'")
             msg %= (section, name, pycompat.bytestr(default))
             self.develwarn(msg, 2, 'warn-config-default')
 
         for s, n in alternates:
             candidate = self._data(untrusted).get(s, n, None)
             if candidate is not None:
                 value = candidate
                 section = s
                 name = n
                 break
 
         if self.debugflag and not untrusted and self._reportuntrusted:
             for s, n in alternates:
                 uvalue = self._ucfg.get(s, n)
                 if uvalue is not None and uvalue != value:
                     self.debug("ignoring untrusted configuration option "
                                "%s.%s = %s\n" % (s, n, uvalue))
         return value
 
     def configsuboptions(self, section, name, default=_unset, untrusted=False):
         """Get a config option and all sub-options.
 
         Some config options have sub-options that are declared with the
         format "key:opt = value". This method is used to return the main
         option and all its declared sub-options.
 
         Returns a 2-tuple of ``(option, sub-options)``, where `sub-options``
         is a dict of defined sub-options where keys and values are strings.
         """
         main = self.config(section, name, default, untrusted=untrusted)
         data = self._data(untrusted)
         sub = {}
         prefix = '%s:' % name
         for k, v in data.items(section):
             if k.startswith(prefix):
                 sub[k[len(prefix):]] = v
 
         if self.debugflag and not untrusted and self._reportuntrusted:
             for k, v in sub.items():
                 uvalue = self._ucfg.get(section, '%s:%s' % (name, k))
                 if uvalue is not None and uvalue != v:
                     self.debug('ignoring untrusted configuration option '
                                '%s:%s.%s = %s\n' % (section, name, k, uvalue))
 
         return main, sub
 
     def configpath(self, section, name, default=_unset, untrusted=False):
         'get a path config item, expanded relative to repo root or config file'
         v = self.config(section, name, default, untrusted)
         if v is None:
             return None
         if not os.path.isabs(v) or "://" not in v:
             src = self.configsource(section, name, untrusted)
             if ':' in src:
                 base = os.path.dirname(src.rsplit(':')[0])
                 v = os.path.join(base, os.path.expanduser(v))
         return v
 
     def configbool(self, section, name, default=_unset, untrusted=False):
         """parse a configuration element as a boolean
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'true', b'yes')
         >>> u.configbool(s, b'true')
         True
         >>> u.setconfig(s, b'false', b'no')
         >>> u.configbool(s, b'false')
         False
         >>> u.configbool(s, b'unknown')
         False
         >>> u.configbool(s, b'unknown', True)
         True
         >>> u.setconfig(s, b'invalid', b'somevalue')
         >>> u.configbool(s, b'invalid')
         Traceback (most recent call last):
             ...
         ConfigError: foo.invalid is not a boolean ('somevalue')
         """
 
         v = self._config(section, name, default, untrusted=untrusted)
         if v is None:
             return v
         if v is _unset:
             if default is _unset:
                 return False
             return default
         if isinstance(v, bool):
             return v
         b = stringutil.parsebool(v)
         if b is None:
             raise error.ConfigError(_("%s.%s is not a boolean ('%s')")
                                     % (section, name, v))
         return b
 
     def configwith(self, convert, section, name, default=_unset,
                    desc=None, untrusted=False):
         """parse a configuration element with a conversion function
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'float1', b'42')
         >>> u.configwith(float, s, b'float1')
         42.0
         >>> u.setconfig(s, b'float2', b'-4.25')
         >>> u.configwith(float, s, b'float2')
         -4.25
         >>> u.configwith(float, s, b'unknown', 7)
         7.0
         >>> u.setconfig(s, b'invalid', b'somevalue')
         >>> u.configwith(float, s, b'invalid')
         Traceback (most recent call last):
             ...
         ConfigError: foo.invalid is not a valid float ('somevalue')
         >>> u.configwith(float, s, b'invalid', desc=b'womble')
         Traceback (most recent call last):
             ...
         ConfigError: foo.invalid is not a valid womble ('somevalue')
         """
 
         v = self.config(section, name, default, untrusted)
         if v is None:
             return v # do not attempt to convert None
         try:
             return convert(v)
         except (ValueError, error.ParseError):
             if desc is None:
                 desc = pycompat.sysbytes(convert.__name__)
             raise error.ConfigError(_("%s.%s is not a valid %s ('%s')")
                                     % (section, name, desc, v))
 
     def configint(self, section, name, default=_unset, untrusted=False):
         """parse a configuration element as an integer
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'int1', b'42')
         >>> u.configint(s, b'int1')
         42
         >>> u.setconfig(s, b'int2', b'-42')
         >>> u.configint(s, b'int2')
         -42
         >>> u.configint(s, b'unknown', 7)
         7
         >>> u.setconfig(s, b'invalid', b'somevalue')
         >>> u.configint(s, b'invalid')
         Traceback (most recent call last):
             ...
         ConfigError: foo.invalid is not a valid integer ('somevalue')
         """
 
         return self.configwith(int, section, name, default, 'integer',
                                untrusted)
 
     def configbytes(self, section, name, default=_unset, untrusted=False):
         """parse a configuration element as a quantity in bytes
 
         Units can be specified as b (bytes), k or kb (kilobytes), m or
         mb (megabytes), g or gb (gigabytes).
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'val1', b'42')
         >>> u.configbytes(s, b'val1')
         42
         >>> u.setconfig(s, b'val2', b'42.5 kb')
         >>> u.configbytes(s, b'val2')
         43520
         >>> u.configbytes(s, b'unknown', b'7 MB')
         7340032
         >>> u.setconfig(s, b'invalid', b'somevalue')
         >>> u.configbytes(s, b'invalid')
         Traceback (most recent call last):
             ...
         ConfigError: foo.invalid is not a byte quantity ('somevalue')
         """
 
         value = self._config(section, name, default, untrusted)
         if value is _unset:
             if default is _unset:
                 default = 0
             value = default
         if not isinstance(value, bytes):
             return value
         try:
             return util.sizetoint(value)
         except error.ParseError:
             raise error.ConfigError(_("%s.%s is not a byte quantity ('%s')")
                                     % (section, name, value))
 
     def configlist(self, section, name, default=_unset, untrusted=False):
         """parse a configuration element as a list of comma/space separated
         strings
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'list1', b'this,is "a small" ,test')
         >>> u.configlist(s, b'list1')
         ['this', 'is', 'a small', 'test']
         >>> u.setconfig(s, b'list2', b'this, is "a small" , test ')
         >>> u.configlist(s, b'list2')
         ['this', 'is', 'a small', 'test']
         """
         # default is not always a list
         v = self.configwith(config.parselist, section, name, default,
                                'list', untrusted)
         if isinstance(v, bytes):
             return config.parselist(v)
         elif v is None:
             return []
         return v
 
     def configdate(self, section, name, default=_unset, untrusted=False):
         """parse a configuration element as a tuple of ints
 
         >>> u = ui(); s = b'foo'
         >>> u.setconfig(s, b'date', b'0 0')
         >>> u.configdate(s, b'date')
         (0, 0)
         """
         if self.config(section, name, default, untrusted):
             return self.configwith(dateutil.parsedate, section, name, default,
                                    'date', untrusted)
         if default is _unset:
             return None
         return default
 
     def hasconfig(self, section, name, untrusted=False):
         return self._data(untrusted).hasitem(section, name)
 
     def has_section(self, section, untrusted=False):
         '''tell whether section exists in config.'''
         return section in self._data(untrusted)
 
     def configitems(self, section, untrusted=False, ignoresub=False):
         items = self._data(untrusted).items(section)
         if ignoresub:
             items = [i for i in items if ':' not in i[0]]
         if self.debugflag and not untrusted and self._reportuntrusted:
             for k, v in self._ucfg.items(section):
                 if self._tcfg.get(section, k) != v:
                     self.debug("ignoring untrusted configuration option "
                                "%s.%s = %s\n" % (section, k, v))
         return items
 
     def walkconfig(self, untrusted=False):
         cfg = self._data(untrusted)
         for section in cfg.sections():
             for name, value in self.configitems(section, untrusted):
                 yield section, name, value
 
     def plain(self, feature=None):
         '''is plain mode active?
 
         Plain mode means that all configuration variables which affect
         the behavior and output of Mercurial should be
         ignored. Additionally, the output should be stable,
         reproducible and suitable for use in scripts or applications.
 
         The only way to trigger plain mode is by setting either the
         `HGPLAIN' or `HGPLAINEXCEPT' environment variables.
 
         The return value can either be
         - False if HGPLAIN is not set, or feature is in HGPLAINEXCEPT
         - False if feature is disabled by default and not included in HGPLAIN
         - True otherwise
         '''
         if ('HGPLAIN' not in encoding.environ and
                 'HGPLAINEXCEPT' not in encoding.environ):
             return False
         exceptions = encoding.environ.get('HGPLAINEXCEPT',
                 '').strip().split(',')
         # TODO: add support for HGPLAIN=+feature,-feature syntax
         if '+strictflags' not in encoding.environ.get('HGPLAIN', '').split(','):
             exceptions.append('strictflags')
         if feature and exceptions:
             return feature not in exceptions
         return True
 
     def username(self, acceptempty=False):
         """Return default username to be used in commits.
 
         Searched in this order: $HGUSER, [ui] section of hgrcs, $EMAIL
         and stop searching if one of these is set.
         If not found and acceptempty is True, returns None.
         If not found and ui.askusername is True, ask the user, else use
         ($LOGNAME or $USER or $LNAME or $USERNAME) + "@full.hostname".
         If no username could be found, raise an Abort error.
         """
         user = encoding.environ.get("HGUSER")
         if user is None:
             user = self.config("ui", "username")
             if user is not None:
                 user = os.path.expandvars(user)
         if user is None:
             user = encoding.environ.get("EMAIL")
         if user is None and acceptempty:
             return user
         if user is None and self.configbool("ui", "askusername"):
             user = self.prompt(_("enter a commit username:"), default=None)
         if user is None and not self.interactive():
             try:
                 user = '%s@%s' % (procutil.getuser(),
                                   encoding.strtolocal(socket.getfqdn()))
                 self.warn(_("no username found, using '%s' instead\n") % user)
             except KeyError:
                 pass
         if not user:
             raise error.Abort(_('no username supplied'),
                              hint=_("use 'hg config --edit' "
                                     'to set your username'))
         if "\n" in user:
             raise error.Abort(_("username %r contains a newline\n")
                               % pycompat.bytestr(user))
         return user
 
     def shortuser(self, user):
         """Return a short representation of a user name or email address."""
         if not self.verbose:
             user = stringutil.shortuser(user)
         return user
 
     def expandpath(self, loc, default=None):
         """Return repository location relative to cwd or from [paths]"""
         try:
             p = self.paths.getpath(loc)
             if p:
                 return p.rawloc
         except error.RepoError:
             pass
 
         if default:
             try:
                 p = self.paths.getpath(default)
                 if p:
                     return p.rawloc
             except error.RepoError:
                 pass
 
         return loc
 
     @util.propertycache
     def paths(self):
         return paths(self)
 
     @property
     def fout(self):
         return self._fout
 
     @fout.setter
     def fout(self, f):
         self._fout = f
         self._fmsgout, self._fmsgerr = _selectmsgdests(self)
 
     @property
     def ferr(self):
         return self._ferr
 
     @ferr.setter
     def ferr(self, f):
         self._ferr = f
         self._fmsgout, self._fmsgerr = _selectmsgdests(self)
 
     @property
     def fin(self):
         return self._fin
 
     @fin.setter
     def fin(self, f):
         self._fin = f
 
     @property
     def fmsg(self):
         """Stream dedicated for status/error messages; may be None if
         fout/ferr are used"""
         return self._fmsg
 
     @fmsg.setter
     def fmsg(self, f):
         self._fmsg = f
         self._fmsgout, self._fmsgerr = _selectmsgdests(self)
 
     def pushbuffer(self, error=False, subproc=False, labeled=False):
         """install a buffer to capture standard output of the ui object
 
         If error is True, the error output will be captured too.
 
         If subproc is True, output from subprocesses (typically hooks) will be
         captured too.
 
         If labeled is True, any labels associated with buffered
         output will be handled. By default, this has no effect
         on the output returned, but extensions and GUI tools may
         handle this argument and returned styled output. If output
         is being buffered so it can be captured and parsed or
         processed, labeled should not be set to True.
         """
         self._buffers.append([])
         self._bufferstates.append((error, subproc, labeled))
         self._bufferapplylabels = labeled
 
     def popbuffer(self):
         '''pop the last buffer and return the buffered output'''
         self._bufferstates.pop()
         if self._bufferstates:
             self._bufferapplylabels = self._bufferstates[-1][2]
         else:
             self._bufferapplylabels = None
 
         return "".join(self._buffers.pop())
 
     def _isbuffered(self, dest):
         if dest is self._fout:
             return bool(self._buffers)
         if dest is self._ferr:
             return bool(self._bufferstates and self._bufferstates[-1][0])
         return False
 
     def canwritewithoutlabels(self):
         '''check if write skips the label'''
         if self._buffers and not self._bufferapplylabels:
             return True
         return self._colormode is None
 
     def canbatchlabeledwrites(self):
         '''check if write calls with labels are batchable'''
         # Windows color printing is special, see ``write``.
         return self._colormode != 'win32'
 
     def write(self, *args, **opts):
         '''write args to output
 
         By default, this method simply writes to the buffer or stdout.
         Color mode can be set on the UI class to have the output decorated
         with color modifier before being written to stdout.
 
         The color used is controlled by an optional keyword argument, "label".
         This should be a string containing label names separated by space.
         Label names take the form of "topic.type". For example, ui.debug()
         issues a label of "ui.debug".
 
         When labeling output for a specific command, a label of
         "cmdname.type" is recommended. For example, status issues
         a label of "status.modified" for modified files.
         '''
-        self._write(self._fout, *args, **opts)
+        dest = self._fout
+
+        # inlined _write() for speed
+        if self._buffers:
+            label = opts.get(r'label', '')
+            if label and self._bufferapplylabels:
+                self._buffers[-1].extend(self.label(a, label) for a in args)
+            else:
+                self._buffers[-1].extend(args)
+            return
+
+        # inliend _writenobuf() for speed
+        self._progclear()
+        msg = b''.join(args)
+
+        # opencode timeblockedsection because this is a critical path
+        starttime = util.timer()
+        try:
+            if self._colormode == 'win32':
+                # windows color printing is its own can of crab, defer to
+                # the color module and that is it.
+                color.win32print(self, dest.write, msg, **opts)
+            else:
+                if self._colormode is not None:
+                    label = opts.get(r'label', '')
+                    msg = self.label(msg, label)
+                dest.write(msg)
+        except IOError as err:
+            raise error.StdioError(err)
+        finally:
+            self._blockedtimes['stdio_blocked'] += \
+                (util.timer() - starttime) * 1000
 
     def write_err(self, *args, **opts):
         self._write(self._ferr, *args, **opts)
 
     def _write(self, dest, *args, **opts):
+        # update write() as well if you touch this code
         if self._isbuffered(dest):
-            if self._bufferapplylabels:
-                label = opts.get(r'label', '')
+            label = opts.get(r'label', '')
+            if label and self._bufferapplylabels:
                 self._buffers[-1].extend(self.label(a, label) for a in args)
             else:
                 self._buffers[-1].extend(args)
         else:
             self._writenobuf(dest, *args, **opts)
 
     def _writenobuf(self, dest, *args, **opts):
+        # update write() as well if you touch this code
         self._progclear()
         msg = b''.join(args)
 
         # opencode timeblockedsection because this is a critical path
         starttime = util.timer()
         try:
             if dest is self._ferr and not getattr(self._fout, 'closed', False):
                 self._fout.flush()
             if getattr(dest, 'structured', False):
                 # channel for machine-readable output with metadata, where
                 # no extra colorization is necessary.
                 dest.write(msg, **opts)
             elif self._colormode == 'win32':
                 # windows color printing is its own can of crab, defer to
                 # the color module and that is it.
                 color.win32print(self, dest.write, msg, **opts)
             else:
                 if self._colormode is not None:
                     label = opts.get(r'label', '')
                     msg = self.label(msg, label)
                 dest.write(msg)
             # stderr may be buffered under win32 when redirected to files,
             # including stdout.
             if dest is self._ferr and not getattr(self._ferr, 'closed', False):
                 dest.flush()
         except IOError as err:
             if (dest is self._ferr
                 and err.errno in (errno.EPIPE, errno.EIO, errno.EBADF)):
                 # no way to report the error, so ignore it
                 return
             raise error.StdioError(err)
         finally:
             self._blockedtimes['stdio_blocked'] += \
                 (util.timer() - starttime) * 1000
 
     def _writemsg(self, dest, *args, **opts):
         _writemsgwith(self._write, dest, *args, **opts)
 
     def _writemsgnobuf(self, dest, *args, **opts):
         _writemsgwith(self._writenobuf, dest, *args, **opts)
 
     def flush(self):
         # opencode timeblockedsection because this is a critical path
         starttime = util.timer()
         try:
             try:
                 self._fout.flush()
             except IOError as err:
                 if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
                     raise error.StdioError(err)
             finally:
                 try:
                     self._ferr.flush()
                 except IOError as err:
                     if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
                         raise error.StdioError(err)
         finally:
             self._blockedtimes['stdio_blocked'] += \
                 (util.timer() - starttime) * 1000
 
     def _isatty(self, fh):
         if self.configbool('ui', 'nontty'):
             return False
         return procutil.isatty(fh)
 
     def protectfinout(self):
         """Duplicate ui streams and redirect original if they are stdio
 
         Returns (fin, fout) which point to the original ui fds, but may be
         copy of them. The returned streams can be considered "owned" in that
         print(), exec(), etc. never reach to them.
         """
         if self._finoutredirected:
             # if already redirected, protectstdio() would just create another
             # nullfd pair, which is equivalent to returning self._fin/_fout.
             return self._fin, self._fout
         fin, fout = procutil.protectstdio(self._fin, self._fout)
         self._finoutredirected = (fin, fout) != (self._fin, self._fout)
         return fin, fout
 
     def restorefinout(self, fin, fout):
         """Restore ui streams from possibly duplicated (fin, fout)"""
         if (fin, fout) == (self._fin, self._fout):
             return
         procutil.restorestdio(self._fin, self._fout, fin, fout)
         # protectfinout() won't create more than one duplicated streams,
         # so we can just turn the redirection flag off.
         self._finoutredirected = False
 
     @contextlib.contextmanager
     def protectedfinout(self):
         """Run code block with protected standard streams"""
         fin, fout = self.protectfinout()
         try:
             yield fin, fout
         finally:
             self.restorefinout(fin, fout)
 
     def disablepager(self):
         self._disablepager = True
 
     def pager(self, command):
         """Start a pager for subsequent command output.
 
         Commands which produce a long stream of output should call
         this function to activate the user's preferred pagination
         mechanism (which may be no pager). Calling this function
         precludes any future use of interactive functionality, such as
         prompting the user or activating curses.
 
         Args:
           command: The full, non-aliased name of the command. That is, "log"
                    not "history, "summary" not "summ", etc.
         """
         if (self._disablepager
             or self.pageractive):
             # how pager should do is already determined
             return
 
         if not command.startswith('internal-always-') and (
             # explicit --pager=on (= 'internal-always-' prefix) should
             # take precedence over disabling factors below
             command in self.configlist('pager', 'ignore')
             or not self.configbool('ui', 'paginate')
             or not self.configbool('pager', 'attend-' + command, True)
             or encoding.environ.get('TERM') == 'dumb'
             # TODO: if we want to allow HGPLAINEXCEPT=pager,
             # formatted() will need some adjustment.
             or not self.formatted()
             or self.plain()
             or self._buffers
             # TODO: expose debugger-enabled on the UI object
             or '--debugger' in pycompat.sysargv):
             # We only want to paginate if the ui appears to be
             # interactive, the user didn't say HGPLAIN or
             # HGPLAINEXCEPT=pager, and the user didn't specify --debug.
             return
 
         pagercmd = self.config('pager', 'pager', rcutil.fallbackpager)
         if not pagercmd:
             return
 
         pagerenv = {}
         for name, value in rcutil.defaultpagerenv().items():
             if name not in encoding.environ:
                 pagerenv[name] = value
 
         self.debug('starting pager for command %s\n' %
                    stringutil.pprint(command))
         self.flush()
 
         wasformatted = self.formatted()
         if util.safehasattr(signal, "SIGPIPE"):
             signal.signal(signal.SIGPIPE, _catchterm)
         if self._runpager(pagercmd, pagerenv):
             self.pageractive = True
             # Preserve the formatted-ness of the UI. This is important
             # because we mess with stdout, which might confuse
             # auto-detection of things being formatted.
             self.setconfig('ui', 'formatted', wasformatted, 'pager')
             self.setconfig('ui', 'interactive', False, 'pager')
 
             # If pagermode differs from color.mode, reconfigure color now that
             # pageractive is set.
             cm = self._colormode
             if cm != self.config('color', 'pagermode', cm):
                 color.setup(self)
         else:
             # If the pager can't be spawned in dispatch when --pager=on is
             # given, don't try again when the command runs, to avoid a duplicate
             # warning about a missing pager command.
             self.disablepager()
 
     def _runpager(self, command, env=None):
         """Actually start the pager and set up file descriptors.
 
         This is separate in part so that extensions (like chg) can
         override how a pager is invoked.
         """
         if command == 'cat':
             # Save ourselves some work.
             return False
         # If the command doesn't contain any of these characters, we
         # assume it's a binary and exec it directly. This means for
         # simple pager command configurations, we can degrade
         # gracefully and tell the user about their broken pager.
         shell = any(c in command for c in "|&;<>()$`\\\"' \t\n*?[#~=%")
 
         if pycompat.iswindows and not shell:
             # Window's built-in `more` cannot be invoked with shell=False, but
             # its `more.com` can.  Hide this implementation detail from the
             # user so we can also get sane bad PAGER behavior.  MSYS has
             # `more.exe`, so do a cmd.exe style resolution of the executable to
             # determine which one to use.
             fullcmd = procutil.findexe(command)
             if not fullcmd:
                 self.warn(_("missing pager command '%s', skipping pager\n")
                           % command)
                 return False
 
             command = fullcmd
 
         try:
             pager = subprocess.Popen(
                 procutil.tonativestr(command), shell=shell, bufsize=-1,
                 close_fds=procutil.closefds, stdin=subprocess.PIPE,
                 stdout=procutil.stdout, stderr=procutil.stderr,
                 env=procutil.tonativeenv(procutil.shellenviron(env)))
         except OSError as e:
             if e.errno == errno.ENOENT and not shell:
                 self.warn(_("missing pager command '%s', skipping pager\n")
                           % command)
                 return False
             raise
 
         # back up original file descriptors
         stdoutfd = os.dup(procutil.stdout.fileno())
         stderrfd = os.dup(procutil.stderr.fileno())
 
         os.dup2(pager.stdin.fileno(), procutil.stdout.fileno())
         if self._isatty(procutil.stderr):
             os.dup2(pager.stdin.fileno(), procutil.stderr.fileno())
 
         @self.atexit
         def killpager():
             if util.safehasattr(signal, "SIGINT"):
                 signal.signal(signal.SIGINT, signal.SIG_IGN)
             # restore original fds, closing pager.stdin copies in the process
             os.dup2(stdoutfd, procutil.stdout.fileno())
             os.dup2(stderrfd, procutil.stderr.fileno())
             pager.stdin.close()
             pager.wait()
 
         return True
 
     @property
     def _exithandlers(self):
         return _reqexithandlers
 
     def atexit(self, func, *args, **kwargs):
         '''register a function to run after dispatching a request
 
         Handlers do not stay registered across request boundaries.'''
         self._exithandlers.append((func, args, kwargs))
         return func
 
     def interface(self, feature):
         """what interface to use for interactive console features?
 
         The interface is controlled by the value of `ui.interface` but also by
         the value of feature-specific configuration. For example:
 
         ui.interface.histedit = text
         ui.interface.chunkselector = curses
 
         Here the features are "histedit" and "chunkselector".
 
         The configuration above means that the default interfaces for commands
         is curses, the interface for histedit is text and the interface for
         selecting chunk is crecord (the best curses interface available).
 
         Consider the following example:
         ui.interface = curses
         ui.interface.histedit = text
 
         Then histedit will use the text interface and chunkselector will use
         the default curses interface (crecord at the moment).
         """
         alldefaults = frozenset(["text", "curses"])
 
         featureinterfaces = {
             "chunkselector": [
                 "text",
                 "curses",
             ],
             "histedit": [
                 "text",
                 "curses",
             ],
         }
 
         # Feature-specific interface
         if feature not in featureinterfaces.keys():
             # Programming error, not user error
             raise ValueError("Unknown feature requested %s" % feature)
 
         availableinterfaces = frozenset(featureinterfaces[feature])
         if alldefaults > availableinterfaces:
             # Programming error, not user error. We need a use case to
             # define the right thing to do here.
             raise ValueError(
                 "Feature %s does not handle all default interfaces" %
                 feature)
 
         if self.plain() or encoding.environ.get('TERM') == 'dumb':
             return "text"
 
         # Default interface for all the features
         defaultinterface = "text"
         i = self.config("ui", "interface")
         if i in alldefaults:
             defaultinterface = i
 
         choseninterface = defaultinterface
         f = self.config("ui", "interface.%s" % feature)
         if f in availableinterfaces:
             choseninterface = f
 
         if i is not None and defaultinterface != i:
             if f is not None:
                 self.warn(_("invalid value for ui.interface: %s\n") %
                           (i,))
             else:
                 self.warn(_("invalid value for ui.interface: %s (using %s)\n") %
                          (i, choseninterface))
         if f is not None and choseninterface != f:
             self.warn(_("invalid value for ui.interface.%s: %s (using %s)\n") %
                       (feature, f, choseninterface))
 
         return choseninterface
 
     def interactive(self):
         '''is interactive input allowed?
 
         An interactive session is a session where input can be reasonably read
         from `sys.stdin'. If this function returns false, any attempt to read
         from stdin should fail with an error, unless a sensible default has been
         specified.
 
         Interactiveness is triggered by the value of the `ui.interactive'
         configuration variable or - if it is unset - when `sys.stdin' points
         to a terminal device.
 
         This function refers to input only; for output, see `ui.formatted()'.
         '''
         i = self.configbool("ui", "interactive")
         if i is None:
             # some environments replace stdin without implementing isatty
             # usually those are non-interactive
             return self._isatty(self._fin)
 
         return i
 
     def termwidth(self):
         '''how wide is the terminal in columns?
         '''
         if 'COLUMNS' in encoding.environ:
             try:
                 return int(encoding.environ['COLUMNS'])
             except ValueError:
                 pass
         return scmutil.termsize(self)[0]
 
     def formatted(self):
         '''should formatted output be used?
 
         It is often desirable to format the output to suite the output medium.
         Examples of this are truncating long lines or colorizing messages.
         However, this is not often not desirable when piping output into other
         utilities, e.g. `grep'.
 
         Formatted output is triggered by the value of the `ui.formatted'
         configuration variable or - if it is unset - when `sys.stdout' points
         to a terminal device. Please note that `ui.formatted' should be
         considered an implementation detail; it is not intended for use outside
         Mercurial or its extensions.
 
         This function refers to output only; for input, see `ui.interactive()'.
         This function always returns false when in plain mode, see `ui.plain()'.
         '''
         if self.plain():
             return False
 
         i = self.configbool("ui", "formatted")
         if i is None:
             # some environments replace stdout without implementing isatty
             # usually those are non-interactive
             return self._isatty(self._fout)
 
         return i
 
     def _readline(self):
         # Replacing stdin/stdout temporarily is a hard problem on Python 3
         # because they have to be text streams with *no buffering*. Instead,
         # we use rawinput() only if call_readline() will be invoked by
         # PyOS_Readline(), so no I/O will be made at Python layer.
         usereadline = (self._isatty(self._fin) and self._isatty(self._fout)
                        and procutil.isstdin(self._fin)
                        and procutil.isstdout(self._fout))
         if usereadline:
             try:
                 # magically add command line editing support, where
                 # available
                 import readline
                 # force demandimport to really load the module
                 readline.read_history_file
                 # windows sometimes raises something other than ImportError
             except Exception:
                 usereadline = False
 
         # prompt ' ' must exist; otherwise readline may delete entire line
         # - http://bugs.python.org/issue12833
         with self.timeblockedsection('stdio'):
             if usereadline:
                 line = encoding.strtolocal(pycompat.rawinput(r' '))
                 # When stdin is in binary mode on Windows, it can cause
                 # raw_input() to emit an extra trailing carriage return
                 if pycompat.oslinesep == b'\r\n' and line.endswith(b'\r'):
                     line = line[:-1]
             else:
                 self._fout.write(b' ')
                 self._fout.flush()
                 line = self._fin.readline()
                 if not line:
                     raise EOFError
                 line = line.rstrip(pycompat.oslinesep)
 
         return line
 
     def prompt(self, msg, default="y"):
         """Prompt user with msg, read response.
         If ui is not interactive, the default is returned.
         """
         return self._prompt(msg, default=default)
 
     def _prompt(self, msg, **opts):
         default = opts[r'default']
         if not self.interactive():
             self._writemsg(self._fmsgout, msg, ' ', type='prompt', **opts)
             self._writemsg(self._fmsgout, default or '', "\n",
                            type='promptecho')
             return default
         self._writemsgnobuf(self._fmsgout, msg, type='prompt', **opts)
         self.flush()
         try:
             r = self._readline()
             if not r:
                 r = default
             if self.configbool('ui', 'promptecho'):
                 self._writemsg(self._fmsgout, r, "\n", type='promptecho')
             return r
         except EOFError:
             raise error.ResponseExpected()
 
     @staticmethod
     def extractchoices(prompt):
         """Extract prompt message and list of choices from specified prompt.
 
         This returns tuple "(message, choices)", and "choices" is the
         list of tuple "(response character, text without &)".
 
         >>> ui.extractchoices(b"awake? $$ &Yes $$ &No")
         ('awake? ', [('y', 'Yes'), ('n', 'No')])
         >>> ui.extractchoices(b"line\\nbreak? $$ &Yes $$ &No")
         ('line\\nbreak? ', [('y', 'Yes'), ('n', 'No')])
         >>> ui.extractchoices(b"want lots of $$money$$?$$Ye&s$$N&o")
         ('want lots of $$money$$?', [('s', 'Yes'), ('o', 'No')])
         """
 
         # Sadly, the prompt string may have been built with a filename
         # containing "$$" so let's try to find the first valid-looking
         # prompt to start parsing. Sadly, we also can't rely on
         # choices containing spaces, ASCII, or basically anything
         # except an ampersand followed by a character.
         m = re.match(br'(?s)(.+?)\$\$([^\$]*&[^ \$].*)', prompt)
         msg = m.group(1)
         choices = [p.strip(' ') for p in m.group(2).split('$$')]
         def choicetuple(s):
             ampidx = s.index('&')
             return s[ampidx + 1:ampidx + 2].lower(), s.replace('&', '', 1)
         return (msg, [choicetuple(s) for s in choices])
 
     def promptchoice(self, prompt, default=0):
         """Prompt user with a message, read response, and ensure it matches
         one of the provided choices. The prompt is formatted as follows:
 
            "would you like fries with that (Yn)? $$ &Yes $$ &No"
 
         The index of the choice is returned. Responses are case
         insensitive. If ui is not interactive, the default is
         returned.
         """
 
         msg, choices = self.extractchoices(prompt)
         resps = [r for r, t in choices]
         while True:
             r = self._prompt(msg, default=resps[default], choices=choices)
             if r.lower() in resps:
                 return resps.index(r.lower())
             # TODO: shouldn't it be a warning?
             self._writemsg(self._fmsgout, _("unrecognized response\n"))
 
     def getpass(self, prompt=None, default=None):
         if not self.interactive():
             return default
         try:
             self._writemsg(self._fmsgerr, prompt or _('password: '),
                            type='prompt', password=True)
             # disable getpass() only if explicitly specified. it's still valid
             # to interact with tty even if fin is not a tty.
             with self.timeblockedsection('stdio'):
                 if self.configbool('ui', 'nontty'):
                     l = self._fin.readline()
                     if not l:
                         raise EOFError
                     return l.rstrip('\n')
                 else:
                     return getpass.getpass('')
         except EOFError:
             raise error.ResponseExpected()
 
     def status(self, *msg, **opts):
         '''write status message to output (if ui.quiet is False)
 
         This adds an output label of "ui.status".
         '''
         if not self.quiet:
             self._writemsg(self._fmsgout, type='status', *msg, **opts)
 
     def warn(self, *msg, **opts):
         '''write warning message to output (stderr)
 
         This adds an output label of "ui.warning".
         '''
         self._writemsg(self._fmsgerr, type='warning', *msg, **opts)
 
     def error(self, *msg, **opts):
         '''write error message to output (stderr)
 
         This adds an output label of "ui.error".
         '''
         self._writemsg(self._fmsgerr, type='error', *msg, **opts)
 
     def note(self, *msg, **opts):
         '''write note to output (if ui.verbose is True)
 
         This adds an output label of "ui.note".
         '''
         if self.verbose:
             self._writemsg(self._fmsgout, type='note', *msg, **opts)
 
     def debug(self, *msg, **opts):
         '''write debug message to output (if ui.debugflag is True)
 
         This adds an output label of "ui.debug".
         '''
         if self.debugflag:
             self._writemsg(self._fmsgout, type='debug', *msg, **opts)
             self.log(b'debug', b'%s', b''.join(msg))
 
     def edit(self, text, user, extra=None, editform=None, pending=None,
              repopath=None, action=None):
         if action is None:
             self.develwarn('action is None but will soon be a required '
                            'parameter to ui.edit()')
         extra_defaults = {
             'prefix': 'editor',
             'suffix': '.txt',
         }
         if extra is not None:
             if extra.get('suffix') is not None:
                 self.develwarn('extra.suffix is not None but will soon be '
                                'ignored by ui.edit()')
             extra_defaults.update(extra)
         extra = extra_defaults
 
         if action == 'diff':
             suffix = '.diff'
         elif action:
             suffix = '.%s.hg.txt' % action
         else:
             suffix = extra['suffix']
 
         rdir = None
         if self.configbool('experimental', 'editortmpinhg'):
             rdir = repopath
         (fd, name) = pycompat.mkstemp(prefix='hg-' + extra['prefix'] + '-',
                                       suffix=suffix,
                                       dir=rdir)
         try:
             f = os.fdopen(fd, r'wb')
             f.write(util.tonativeeol(text))
             f.close()
 
             environ = {'HGUSER': user}
             if 'transplant_source' in extra:
                 environ.update({'HGREVISION': hex(extra['transplant_source'])})
             for label in ('intermediate-source', 'source', 'rebase_source'):
                 if label in extra:
                     environ.update({'HGREVISION': extra[label]})
                     break
             if editform:
                 environ.update({'HGEDITFORM': editform})
             if pending:
                 environ.update({'HG_PENDING': pending})
 
             editor = self.geteditor()
 
             self.system("%s \"%s\"" % (editor, name),
                         environ=environ,
                         onerr=error.Abort, errprefix=_("edit failed"),
                         blockedtag='editor')
 
             f = open(name, r'rb')
             t = util.fromnativeeol(f.read())
             f.close()
         finally:
             os.unlink(name)
 
         return t
 
     def system(self, cmd, environ=None, cwd=None, onerr=None, errprefix=None,
                blockedtag=None):
         '''execute shell command with appropriate output stream. command
         output will be redirected if fout is not stdout.
 
         if command fails and onerr is None, return status, else raise onerr
         object as exception.
         '''
         if blockedtag is None:
             # Long cmds tend to be because of an absolute path on cmd. Keep
             # the tail end instead
             cmdsuffix = cmd.translate(None, _keepalnum)[-85:]
             blockedtag = 'unknown_system_' + cmdsuffix
         out = self._fout
         if any(s[1] for s in self._bufferstates):
             out = self
         with self.timeblockedsection(blockedtag):
             rc = self._runsystem(cmd, environ=environ, cwd=cwd, out=out)
         if rc and onerr:
             errmsg = '%s %s' % (os.path.basename(cmd.split(None, 1)[0]),
                                 procutil.explainexit(rc))
             if errprefix:
                 errmsg = '%s: %s' % (errprefix, errmsg)
             raise onerr(errmsg)
         return rc
 
     def _runsystem(self, cmd, environ, cwd, out):
         """actually execute the given shell command (can be overridden by
         extensions like chg)"""
         return procutil.system(cmd, environ=environ, cwd=cwd, out=out)
 
     def traceback(self, exc=None, force=False):
         '''print exception traceback if traceback printing enabled or forced.
         only to call in exception handler. returns true if traceback
         printed.'''
         if self.tracebackflag or force:
             if exc is None:
                 exc = sys.exc_info()
             cause = getattr(exc[1], 'cause', None)
 
             if cause is not None:
                 causetb = traceback.format_tb(cause[2])
                 exctb = traceback.format_tb(exc[2])
                 exconly = traceback.format_exception_only(cause[0], cause[1])
 
                 # exclude frame where 'exc' was chained and rethrown from exctb
                 self.write_err('Traceback (most recent call last):\n',
                                ''.join(exctb[:-1]),
                                ''.join(causetb),
                                ''.join(exconly))
             else:
                 output = traceback.format_exception(exc[0], exc[1], exc[2])
                 self.write_err(encoding.strtolocal(r''.join(output)))
         return self.tracebackflag or force
 
     def geteditor(self):
         '''return editor to use'''
         if pycompat.sysplatform == 'plan9':
             # vi is the MIPS instruction simulator on Plan 9. We
             # instead default to E to plumb commit messages to
             # avoid confusion.
             editor = 'E'
         else:
             editor = 'vi'
         return (encoding.environ.get("HGEDITOR") or
                 self.config("ui", "editor", editor))
 
     @util.propertycache
     def _progbar(self):
         """setup the progbar singleton to the ui object"""
         if (self.quiet or self.debugflag
                 or self.configbool('progress', 'disable')
                 or not progress.shouldprint(self)):
             return None
         return getprogbar(self)
 
     def _progclear(self):
         """clear progress bar output if any. use it before any output"""
         if not haveprogbar(): # nothing loaded yet
             return
         if self._progbar is not None and self._progbar.printed:
             self._progbar.clear()
 
     def progress(self, topic, pos, item="", unit="", total=None):
         '''show a progress message
 
         By default a textual progress bar will be displayed if an operation
         takes too long. 'topic' is the current operation, 'item' is a
         non-numeric marker of the current position (i.e. the currently
         in-process file), 'pos' is the current numeric position (i.e.
         revision, bytes, etc.), unit is a corresponding unit label,
         and total is the highest expected pos.
 
         Multiple nested topics may be active at a time.
 
         All topics should be marked closed by setting pos to None at
         termination.
         '''
         self.deprecwarn("use ui.makeprogress() instead of ui.progress()",
                         "5.1")
         progress = self.makeprogress(topic, unit, total)
         if pos is not None:
             progress.update(pos, item=item)
         else:
             progress.complete()
 
     def makeprogress(self, topic, unit="", total=None):
         """Create a progress helper for the specified topic"""
         if getattr(self._fmsgerr, 'structured', False):
             # channel for machine-readable output with metadata, just send
             # raw information
             # TODO: consider porting some useful information (e.g. estimated
             # time) from progbar. we might want to support update delay to
             # reduce the cost of transferring progress messages.
             def updatebar(topic, pos, item, unit, total):
                 self._fmsgerr.write(None, type=b'progress', topic=topic,
                                     pos=pos, item=item, unit=unit, total=total)
         elif self._progbar is not None:
             updatebar = self._progbar.progress
         else:
             def updatebar(topic, pos, item, unit, total):
                 pass
         return scmutil.progress(self, updatebar, topic, unit, total)
 
     def getlogger(self, name):
         """Returns a logger of the given name; or None if not registered"""
         return self._loggers.get(name)
 
     def setlogger(self, name, logger):
         """Install logger which can be identified later by the given name
 
         More than one loggers can be registered. Use extension or module
         name to uniquely identify the logger instance.
         """
         self._loggers[name] = logger
 
     def log(self, event, msgfmt, *msgargs, **opts):
         '''hook for logging facility extensions
 
         event should be a readily-identifiable subsystem, which will
         allow filtering.
 
         msgfmt should be a newline-terminated format string to log, and
         *msgargs are %-formatted into it.
 
         **opts currently has no defined meanings.
         '''
         if not self._loggers:
             return
         activeloggers = [l for l in self._loggers.itervalues()
                          if l.tracked(event)]
         if not activeloggers:
             return
         msg = msgfmt % msgargs
         opts = pycompat.byteskwargs(opts)
         # guard against recursion from e.g. ui.debug()
         registeredloggers = self._loggers
         self._loggers = {}
         try:
             for logger in activeloggers:
                 logger.log(self, event, msg, opts)
         finally:
             self._loggers = registeredloggers
 
     def label(self, msg, label):
         '''style msg based on supplied label
 
         If some color mode is enabled, this will add the necessary control
         characters to apply such color. In addition, 'debug' color mode adds
         markup showing which label affects a piece of text.
 
         ui.write(s, 'label') is equivalent to
         ui.write(ui.label(s, 'label')).
         '''
         if self._colormode is not None:
             return color.colorlabel(self, msg, label)
         return msg
 
     def develwarn(self, msg, stacklevel=1, config=None):
         """issue a developer warning message
 
         Use 'stacklevel' to report the offender some layers further up in the
         stack.
         """
         if not self.configbool('devel', 'all-warnings'):
             if config is None or not self.configbool('devel', config):
                 return
         msg = 'devel-warn: ' + msg
         stacklevel += 1 # get in develwarn
         if self.tracebackflag:
             util.debugstacktrace(msg, stacklevel, self._ferr, self._fout)
             self.log('develwarn', '%s at:\n%s' %
                      (msg, ''.join(util.getstackframes(stacklevel))))
         else:
             curframe = inspect.currentframe()
             calframe = inspect.getouterframes(curframe, 2)
             fname, lineno, fmsg = calframe[stacklevel][1:4]
             fname, fmsg = pycompat.sysbytes(fname), pycompat.sysbytes(fmsg)
             self.write_err('%s at: %s:%d (%s)\n'
                            % (msg, fname, lineno, fmsg))
             self.log('develwarn', '%s at: %s:%d (%s)\n',
                      msg, fname, lineno, fmsg)
             curframe = calframe = None  # avoid cycles
 
     def deprecwarn(self, msg, version, stacklevel=2):
         """issue a deprecation warning
 
         - msg: message explaining what is deprecated and how to upgrade,
         - version: last version where the API will be supported,
         """
         if not (self.configbool('devel', 'all-warnings')
                 or self.configbool('devel', 'deprec-warn')):
             return
         msg += ("\n(compatibility will be dropped after Mercurial-%s,"
                 " update your code.)") % version
         self.develwarn(msg, stacklevel=stacklevel, config='deprec-warn')
 
     def exportableenviron(self):
         """The environment variables that are safe to export, e.g. through
         hgweb.
         """
         return self._exportableenviron
 
     @contextlib.contextmanager
     def configoverride(self, overrides, source=""):
         """Context manager for temporary config overrides
         `overrides` must be a dict of the following structure:
         {(section, name) : value}"""
         backups = {}
         try:
             for (section, name), value in overrides.items():
                 backups[(section, name)] = self.backupconfig(section, name)
                 self.setconfig(section, name, value, source)
             yield
         finally:
             for __, backup in backups.items():
                 self.restoreconfig(backup)
             # just restoring ui.quiet config to the previous value is not enough
             # as it does not update ui.quiet class member
             if ('ui', 'quiet') in overrides:
                 self.fixconfig(section='ui')
 
 class paths(dict):
     """Represents a collection of paths and their configs.
 
     Data is initially derived from ui instances and the config files they have
     loaded.
     """
     def __init__(self, ui):
         dict.__init__(self)
 
         for name, loc in ui.configitems('paths', ignoresub=True):
             # No location is the same as not existing.
             if not loc:
                 continue
             loc, sub = ui.configsuboptions('paths', name)
             self[name] = path(ui, name, rawloc=loc, suboptions=sub)
 
     def getpath(self, name, default=None):
         """Return a ``path`` from a string, falling back to default.
 
         ``name`` can be a named path or locations. Locations are filesystem
         paths or URIs.
 
         Returns None if ``name`` is not a registered path, a URI, or a local
         path to a repo.
         """
         # Only fall back to default if no path was requested.
         if name is None:
             if not default:
                 default = ()
             elif not isinstance(default, (tuple, list)):
                 default = (default,)
             for k in default:
                 try:
                     return self[k]
                 except KeyError:
                     continue
             return None
 
         # Most likely empty string.
         # This may need to raise in the future.
         if not name:
             return None
 
         try:
             return self[name]
         except KeyError:
             # Try to resolve as a local path or URI.
             try:
                 # We don't pass sub-options in, so no need to pass ui instance.
                 return path(None, None, rawloc=name)
             except ValueError:
                 raise error.RepoError(_('repository %s does not exist') %
                                         name)
 
 _pathsuboptions = {}
 
 def pathsuboption(option, attr):
     """Decorator used to declare a path sub-option.
 
     Arguments are the sub-option name and the attribute it should set on
     ``path`` instances.
 
     The decorated function will receive as arguments a ``ui`` instance,
     ``path`` instance, and the string value of this option from the config.
     The function should return the value that will be set on the ``path``
     instance.
 
     This decorator can be used to perform additional verification of
     sub-options and to change the type of sub-options.
     """
     def register(func):
         _pathsuboptions[option] = (attr, func)
         return func
     return register
 
 @pathsuboption('pushurl', 'pushloc')
 def pushurlpathoption(ui, path, value):
     u = util.url(value)
     # Actually require a URL.
     if not u.scheme:
         ui.warn(_('(paths.%s:pushurl not a URL; ignoring)\n') % path.name)
         return None
 
     # Don't support the #foo syntax in the push URL to declare branch to
     # push.
     if u.fragment:
         ui.warn(_('("#fragment" in paths.%s:pushurl not supported; '
                   'ignoring)\n') % path.name)
         u.fragment = None
 
     return bytes(u)
 
 @pathsuboption('pushrev', 'pushrev')
 def pushrevpathoption(ui, path, value):
     return value
 
 class path(object):
     """Represents an individual path and its configuration."""
 
     def __init__(self, ui, name, rawloc=None, suboptions=None):
         """Construct a path from its config options.
 
         ``ui`` is the ``ui`` instance the path is coming from.
         ``name`` is the symbolic name of the path.
         ``rawloc`` is the raw location, as defined in the config.
         ``pushloc`` is the raw locations pushes should be made to.
 
         If ``name`` is not defined, we require that the location be a) a local
         filesystem path with a .hg directory or b) a URL. If not,
         ``ValueError`` is raised.
         """
         if not rawloc:
             raise ValueError('rawloc must be defined')
 
         # Locations may define branches via syntax <base>#<branch>.
         u = util.url(rawloc)
         branch = None
         if u.fragment:
             branch = u.fragment
             u.fragment = None
 
         self.url = u
         self.branch = branch
 
         self.name = name
         self.rawloc = rawloc
         self.loc = '%s' % u
 
         # When given a raw location but not a symbolic name, validate the
         # location is valid.
         if not name and not u.scheme and not self._isvalidlocalpath(self.loc):
             raise ValueError('location is not a URL or path to a local '
                              'repo: %s' % rawloc)
 
         suboptions = suboptions or {}
 
         # Now process the sub-options. If a sub-option is registered, its
         # attribute will always be present. The value will be None if there
         # was no valid sub-option.
         for suboption, (attr, func) in _pathsuboptions.iteritems():
             if suboption not in suboptions:
                 setattr(self, attr, None)
                 continue
 
             value = func(ui, self, suboptions[suboption])
             setattr(self, attr, value)
 
     def _isvalidlocalpath(self, path):
         """Returns True if the given path is a potentially valid repository.
         This is its own function so that extensions can change the definition of
         'valid' in this case (like when pulling from a git repo into a hg
         one)."""
         return os.path.isdir(os.path.join(path, '.hg'))
 
     @property
     def suboptions(self):
         """Return sub-options and their values for this path.
 
         This is intended to be used for presentation purposes.
         """
         d = {}
         for subopt, (attr, _func) in _pathsuboptions.iteritems():
             value = getattr(self, attr)
             if value is not None:
                 d[subopt] = value
         return d
 
 # we instantiate one globally shared progress bar to avoid
 # competing progress bars when multiple UI objects get created
 _progresssingleton = None
 
 def getprogbar(ui):
     global _progresssingleton
     if _progresssingleton is None:
         # passing 'ui' object to the singleton is fishy,
         # this is how the extension used to work but feel free to rework it.
         _progresssingleton = progress.progbar(ui)
     return _progresssingleton
 
 def haveprogbar():
     return _progresssingleton is not None
 
 def _selectmsgdests(ui):
     name = ui.config(b'ui', b'message-output')
     if name == b'channel':
         if ui.fmsg:
             return ui.fmsg, ui.fmsg
         else:
             # fall back to ferr if channel isn't ready so that status/error
             # messages can be printed
             return ui.ferr, ui.ferr
     if name == b'stdio':
         return ui.fout, ui.ferr
     if name == b'stderr':
         return ui.ferr, ui.ferr
     raise error.Abort(b'invalid ui.message-output destination: %s' % name)
 
 def _writemsgwith(write, dest, *args, **opts):
     """Write ui message with the given ui._write*() function
 
     The specified message type is translated to 'ui.<type>' label if the dest
     isn't a structured channel, so that the message will be colorized.
     """
     # TODO: maybe change 'type' to a mandatory option
     if r'type' in opts and not getattr(dest, 'structured', False):
         opts[r'label'] = opts.get(r'label', '') + ' ui.%s' % opts.pop(r'type')
     write(dest, *args, **opts)

rust/hg-core/src/lib.rs

@@ -1,30 +1,37
 // Copyright 2018 Georges Racinet <[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.
 mod ancestors;
 pub mod dagops;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 #[cfg(test)]
 pub mod testing;
 
 /// Mercurial revision numbers
 ///
 /// As noted in revlog.c, revision numbers are actually encoded in
 /// 4 bytes, and are liberally converted to ints, whence the i32
 pub type Revision = i32;
 
 pub const NULL_REVISION: Revision = -1;
 
+/// Same as `mercurial.node.wdirrev`
+///
+/// This is also equal to `i32::max_value()`, but it's better to spell
+/// it out explicitely, same as in `mercurial.node`
+pub const WORKING_DIRECTORY_REVISION: Revision = 0x7fffffff;
+
 /// The simplest expression of what we need of Mercurial DAGs.
 pub trait Graph {
     /// Return the two parents of the given `Revision`.
     ///
     /// Each of the parents can be independently `NULL_REVISION`
     fn parents(&self, Revision) -> Result<[Revision; 2], GraphError>;
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
+    WorkingDirectoryUnsupported,
 }

rust/hg-cpython/src/cindex.rs

@@ -1,130 +1,133
 // cindex.rs
 //
 // Copyright 2018 Georges Racinet <[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.
 
 //! Bindings to use the Index defined by the parsers C extension
 //!
 //! Ideally, we should use an Index entirely implemented in Rust,
 //! but this will take some time to get there.
 #[cfg(feature = "python27")]
 extern crate python27_sys as python_sys;
 #[cfg(feature = "python3")]
 extern crate python3_sys as python_sys;
 
 use self::python_sys::PyCapsule_Import;
 use cpython::{PyClone, PyErr, PyObject, PyResult, Python};
-use hg::{Graph, GraphError, Revision};
+use hg::{Graph, GraphError, Revision, WORKING_DIRECTORY_REVISION};
 use libc::c_int;
 use std::ffi::CStr;
 use std::mem::transmute;
 
 type IndexParentsFn = unsafe extern "C" fn(
     index: *mut python_sys::PyObject,
     rev: c_int,
     ps: *mut [c_int; 2],
 ) -> c_int;
 
 /// A `Graph` backed up by objects and functions from revlog.c
 ///
 /// This implementation of the `Graph` trait, relies on (pointers to)
 /// - the C index object (`index` member)
 /// - the `index_get_parents()` function (`parents` member)
 ///
 /// # Safety
 ///
 /// The C index itself is mutable, and this Rust exposition is **not
 /// protected by the GIL**, meaning that this construct isn't safe with respect
 /// to Python threads.
 ///
 /// All callers of this `Index` must acquire the GIL and must not release it
 /// while working.
 ///
 /// # TODO find a solution to make it GIL safe again.
 ///
 /// This is non trivial, and can wait until we have a clearer picture with
 /// more Rust Mercurial constructs.
 ///
 /// One possibility would be to a `GILProtectedIndex` wrapper enclosing
 /// a `Python<'p>` marker and have it be the one implementing the
 /// `Graph` trait, but this would mean the `Graph` implementor would become
 /// likely to change between subsequent method invocations of the `hg-core`
 /// objects (a serious change of the `hg-core` API):
 /// either exposing ways to mutate the `Graph`, or making it a non persistent
 /// parameter in the relevant methods that need one.
 ///
 /// Another possibility would be to introduce an abstract lock handle into
 /// the core API, that would be tied to `GILGuard` / `Python<'p>`
 /// in the case of the `cpython` crate bindings yet could leave room for other
 /// mechanisms in other contexts.
 pub struct Index {
     index: PyObject,
     parents: IndexParentsFn,
 }
 
 impl Index {
     pub fn new(py: Python, index: PyObject) -> PyResult<Self> {
         Ok(Index {
             index: index,
             parents: decapsule_parents_fn(py)?,
         })
     }
 }
 
 impl Clone for Index {
     fn clone(&self) -> Self {
         let guard = Python::acquire_gil();
         Index {
             index: self.index.clone_ref(guard.python()),
             parents: self.parents.clone(),
         }
     }
 }
 
 impl Graph for Index {
     /// wrap a call to the C extern parents function
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
+        if rev == WORKING_DIRECTORY_REVISION {
+            return Err(GraphError::WorkingDirectoryUnsupported);
+        }
         let mut res: [c_int; 2] = [0; 2];
         let code = unsafe {
             (self.parents)(
                 self.index.as_ptr(),
                 rev as c_int,
                 &mut res as *mut [c_int; 2],
             )
         };
         match code {
             0 => Ok(res),
             _ => Err(GraphError::ParentOutOfRange(rev)),
         }
     }
 }
 
 /// Return the `index_get_parents` function of the parsers C Extension module.
 ///
 /// A pointer to the function is stored in the `parsers` module as a
 /// standard [Python capsule](https://docs.python.org/2/c-api/capsule.html).
 ///
 /// This function retrieves the capsule and casts the function pointer
 ///
 /// Casting function pointers is one of the rare cases of
 /// legitimate use cases of `mem::transmute()` (see
 /// https://doc.rust-lang.org/std/mem/fn.transmute.html of
 /// `mem::transmute()`.
 /// It is inappropriate for architectures where
 /// function and data pointer sizes differ (so-called "Harvard
 /// architectures"), but these are nowadays mostly DSPs
 /// and microcontrollers, hence out of our scope.
 fn decapsule_parents_fn(py: Python) -> PyResult<IndexParentsFn> {
     unsafe {
         let caps_name = CStr::from_bytes_with_nul_unchecked(
             b"mercurial.cext.parsers.index_get_parents_CAPI\0",
         );
         let from_caps = PyCapsule_Import(caps_name.as_ptr(), 0);
         if from_caps.is_null() {
             return Err(PyErr::fetch(py));
         }
         Ok(transmute(from_caps))
     }
 }

rust/hg-cpython/src/exceptions.rs

@@ -1,27 +1,38
 // ancestors.rs
 //
 // Copyright 2018 Georges Racinet <[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.
 
 //! Bindings for Rust errors
 //!
 //! [`GraphError`] exposes `hg::GraphError` as a subclass of `ValueError`
+//! but some variants of `hg::GraphError` can be converted directly to other
+//! existing Python exceptions if appropriate.
 //!
 //! [`GraphError`]: struct.GraphError.html
 use cpython::exc::ValueError;
 use cpython::{PyErr, Python};
 use hg;
 
 py_exception!(rustext, GraphError, ValueError);
 
 impl GraphError {
     pub fn pynew(py: Python, inner: hg::GraphError) -> PyErr {
         match inner {
             hg::GraphError::ParentOutOfRange(r) => {
                 GraphError::new(py, ("ParentOutOfRange", r))
             }
+            hg::GraphError::WorkingDirectoryUnsupported => {
+                match py
+                    .import("mercurial.error")
+                    .and_then(|m| m.get(py, "WdirUnsupported"))
+                {
+                    Err(e) => e,
+                    Ok(cls) => PyErr::from_instance(py, cls),
+                }
+            }
         }
     }
 }

tests/test-clone.t

@@ -1,1290 +1,1293
 #testcases sshv1 sshv2
 
 #if sshv2
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > sshpeer.advertise-v2 = true
   > sshserver.support-v2 = true
   > EOF
 #endif
 
 Prepare repo a:
 
   $ hg init a
   $ cd a
   $ echo a > a
   $ hg add a
   $ hg commit -m test
   $ echo first line > b
   $ hg add b
 
 Create a non-inlined filelog:
 
   $ "$PYTHON" -c 'open("data1", "wb").write(b"".join(b"%d\n" % x for x in range(10000)))'
   $ for j in 0 1 2 3 4 5 6 7 8 9; do
   >   cat data1 >> b
   >   hg commit -m test
   > done
 
 List files in store/data (should show a 'b.d'):
 
 #if reporevlogstore
   $ for i in .hg/store/data/*; do
   >   echo $i
   > done
   .hg/store/data/a.i
   .hg/store/data/b.d
   .hg/store/data/b.i
 #endif
 
 Trigger branchcache creation:
 
   $ hg branches
   default                       10:a7949464abda
   $ ls .hg/cache
   branch2-served
   manifestfulltextcache (reporevlogstore !)
   rbc-names-v1
   rbc-revs-v1
 
 Default operation:
 
   $ hg clone . ../b
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd ../b
 
 Ensure branchcache got copied over:
 
   $ ls .hg/cache
   branch2-served
   rbc-names-v1
   rbc-revs-v1
 
   $ cat a
   a
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 11 changesets with 11 changes to 2 files
 
 Invalid dest '' must abort:
 
   $ hg clone . ''
   abort: empty destination path is not valid
   [255]
 
 No update, with debug option:
 
 #if hardlink
   $ hg --debug clone -U . ../c --config progress.debug=true
   linking: 1 files
   linking: 2 files
   linking: 3 files
   linking: 4 files
   linking: 5 files
   linking: 6 files
   linking: 7 files
   linking: 8 files
   linked 8 files (reporevlogstore !)
   linking: 9 files (reposimplestore !)
   linking: 10 files (reposimplestore !)
   linking: 11 files (reposimplestore !)
   linking: 12 files (reposimplestore !)
   linking: 13 files (reposimplestore !)
   linking: 14 files (reposimplestore !)
   linking: 15 files (reposimplestore !)
   linking: 16 files (reposimplestore !)
   linking: 17 files (reposimplestore !)
   linking: 18 files (reposimplestore !)
   linked 18 files (reposimplestore !)
 #else
   $ hg --debug clone -U . ../c --config progress.debug=true
   linking: 1 files
   copying: 2 files
   copying: 3 files
   copying: 4 files
   copying: 5 files
   copying: 6 files
   copying: 7 files
   copying: 8 files
   copied 8 files (reporevlogstore !)
   copying: 9 files (reposimplestore !)
   copying: 10 files (reposimplestore !)
   copying: 11 files (reposimplestore !)
   copying: 12 files (reposimplestore !)
   copying: 13 files (reposimplestore !)
   copying: 14 files (reposimplestore !)
   copying: 15 files (reposimplestore !)
   copying: 16 files (reposimplestore !)
   copying: 17 files (reposimplestore !)
   copying: 18 files (reposimplestore !)
   copied 18 files (reposimplestore !)
 #endif
   $ cd ../c
 
 Ensure branchcache got copied over:
 
   $ ls .hg/cache
   branch2-served
   rbc-names-v1
   rbc-revs-v1
 
   $ cat a 2>/dev/null || echo "a not present"
   a not present
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 11 changesets with 11 changes to 2 files
 
 Default destination:
 
   $ mkdir ../d
   $ cd ../d
   $ hg clone ../a
   destination directory: a
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd a
   $ hg cat a
   a
   $ cd ../..
 
 Check that we drop the 'file:' from the path before writing the .hgrc:
 
   $ hg clone file:a e
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ grep 'file:' e/.hg/hgrc
   [1]
 
 Check that path aliases are expanded:
 
   $ hg clone -q -U --config 'paths.foobar=a#0' foobar f
   $ hg -R f showconfig paths.default
   $TESTTMP/a#0
 
 Use --pull:
 
   $ hg clone --pull a g
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 11 changesets with 11 changes to 2 files
   new changesets acb14030fe0a:a7949464abda
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R g verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 11 changesets with 11 changes to 2 files
 
 Invalid dest '' with --pull must abort (issue2528):
 
   $ hg clone --pull a ''
   abort: empty destination path is not valid
   [255]
 
 Clone to '.':
 
   $ mkdir h
   $ cd h
   $ hg clone ../a .
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd ..
 
 
 *** Tests for option -u ***
 
 Adding some more history to repo a:
 
   $ cd a
   $ hg tag ref1
   $ echo the quick brown fox >a
   $ hg ci -m "hacked default"
   $ hg up ref1
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg branch stable
   marked working directory as branch stable
   (branches are permanent and global, did you want a bookmark?)
   $ echo some text >a
   $ hg ci -m "starting branch stable"
   $ hg tag ref2
   $ echo some more text >a
   $ hg ci -m "another change for branch stable"
   $ hg up ref2
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg parents
   changeset:   13:e8ece76546a6
   branch:      stable
   tag:         ref2
   parent:      10:a7949464abda
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     starting branch stable
   
 
 Repo a has two heads:
 
   $ hg heads
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
   $ cd ..
 
 
 Testing --noupdate with --updaterev (must abort):
 
   $ hg clone --noupdate --updaterev 1 a ua
   abort: cannot specify both --noupdate and --updaterev
   [255]
 
 
 Testing clone -u:
 
   $ hg clone -u . a ua
   updating to branch stable
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has both heads:
 
   $ hg -R ua heads
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
 Same revision checked out in repo a and ua:
 
   $ hg -R a parents --template "{node|short}\n"
   e8ece76546a6
   $ hg -R ua parents --template "{node|short}\n"
   e8ece76546a6
 
   $ rm -r ua
 
 
 Testing clone --pull -u:
 
   $ hg clone --pull -u . a ua
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 16 changesets with 16 changes to 3 files (+1 heads)
   new changesets acb14030fe0a:0aae7cf88f0d
   updating to branch stable
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has both heads:
 
   $ hg -R ua heads
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
 Same revision checked out in repo a and ua:
 
   $ hg -R a parents --template "{node|short}\n"
   e8ece76546a6
   $ hg -R ua parents --template "{node|short}\n"
   e8ece76546a6
 
   $ rm -r ua
 
 
 Testing clone -u <branch>:
 
   $ hg clone -u stable a ua
   updating to branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has both heads:
 
   $ hg -R ua heads
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
 Branch 'stable' is checked out:
 
   $ hg -R ua parents
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
 
   $ rm -r ua
 
 
 Testing default checkout:
 
   $ hg clone a ua
   updating to branch default
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has both heads:
 
   $ hg -R ua heads
   changeset:   15:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
 Branch 'default' is checked out:
 
   $ hg -R ua parents
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 Test clone with a branch named "@" (issue3677)
 
   $ hg -R ua branch @
   marked working directory as branch @
   $ hg -R ua commit -m 'created branch @'
   $ hg clone ua atbranch
   updating to branch default
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R atbranch heads
   changeset:   16:798b6d97153e
   branch:      @
   tag:         tip
   parent:      12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     created branch @
   
   changeset:   15:0aae7cf88f0d
   branch:      stable
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
   $ hg -R atbranch parents
   changeset:   12:f21241060d6a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     hacked default
   
 
   $ rm -r ua atbranch
 
 
 Testing #<branch>:
 
   $ hg clone -u . a#stable ua
   adding changesets
   adding manifests
   adding file changes
   added 14 changesets with 14 changes to 3 files
   new changesets acb14030fe0a:0aae7cf88f0d
   updating to branch stable
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has branch 'stable' and 'default' (was changed in fd511e9eeea6):
 
   $ hg -R ua heads
   changeset:   13:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   10:a7949464abda
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     test
   
 
 Same revision checked out in repo a and ua:
 
   $ hg -R a parents --template "{node|short}\n"
   e8ece76546a6
   $ hg -R ua parents --template "{node|short}\n"
   e8ece76546a6
 
   $ rm -r ua
 
 
 Testing -u -r <branch>:
 
   $ hg clone -u . -r stable a ua
   adding changesets
   adding manifests
   adding file changes
   added 14 changesets with 14 changes to 3 files
   new changesets acb14030fe0a:0aae7cf88f0d
   updating to branch stable
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has branch 'stable' and 'default' (was changed in fd511e9eeea6):
 
   $ hg -R ua heads
   changeset:   13:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   10:a7949464abda
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     test
   
 
 Same revision checked out in repo a and ua:
 
   $ hg -R a parents --template "{node|short}\n"
   e8ece76546a6
   $ hg -R ua parents --template "{node|short}\n"
   e8ece76546a6
 
   $ rm -r ua
 
 
 Testing -r <branch>:
 
   $ hg clone -r stable a ua
   adding changesets
   adding manifests
   adding file changes
   added 14 changesets with 14 changes to 3 files
   new changesets acb14030fe0a:0aae7cf88f0d
   updating to branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Repo ua has branch 'stable' and 'default' (was changed in fd511e9eeea6):
 
   $ hg -R ua heads
   changeset:   13:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
   changeset:   10:a7949464abda
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     test
   
 
 Branch 'stable' is checked out:
 
   $ hg -R ua parents
   changeset:   13:0aae7cf88f0d
   branch:      stable
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     another change for branch stable
   
 
   $ rm -r ua
 
 
 Issue2267: Error in 1.6 hg.py: TypeError: 'NoneType' object is not
 iterable in addbranchrevs()
 
   $ cat <<EOF > simpleclone.py
   > from mercurial import hg, ui as uimod
   > myui = uimod.ui.load()
   > repo = hg.repository(myui, b'a')
   > hg.clone(myui, {}, repo, dest=b"ua")
   > EOF
 
   $ "$PYTHON" simpleclone.py
   updating to branch default
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ rm -r ua
 
   $ cat <<EOF > branchclone.py
   > from mercurial import extensions, hg, ui as uimod
   > myui = uimod.ui.load()
   > extensions.loadall(myui)
   > extensions.populateui(myui)
   > repo = hg.repository(myui, b'a')
   > hg.clone(myui, {}, repo, dest=b"ua", branch=[b"stable",])
   > EOF
 
   $ "$PYTHON" branchclone.py
   adding changesets
   adding manifests
   adding file changes
   added 14 changesets with 14 changes to 3 files
   new changesets acb14030fe0a:0aae7cf88f0d
   updating to branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ rm -r ua
 
 
 Test clone with special '@' bookmark:
   $ cd a
   $ hg bookmark -r a7949464abda @  # branch point of stable from default
   $ hg clone . ../i
   updating to bookmark @
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg id -i ../i
   a7949464abda
   $ rm -r ../i
 
   $ hg bookmark -f -r stable @
   $ hg bookmarks
      @                         15:0aae7cf88f0d
   $ hg clone . ../i
   updating to bookmark @ on branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg id -i ../i
   0aae7cf88f0d
   $ cd "$TESTTMP"
 
 
 Testing failures:
 
   $ mkdir fail
   $ cd fail
 
 No local source
 
   $ hg clone a b
   abort: repository a not found!
   [255]
 
 No remote source
 
 #if windows
   $ hg clone http://$LOCALIP:3121/a b
   abort: error: * (glob)
   [255]
 #else
   $ hg clone http://$LOCALIP:3121/a b
   abort: error: *refused* (glob)
   [255]
 #endif
   $ rm -rf b # work around bug with http clone
 
 
 #if unix-permissions no-root
 
 Inaccessible source
 
   $ mkdir a
   $ chmod 000 a
   $ hg clone a b
   abort: Permission denied: *$TESTTMP/fail/a/.hg* (glob)
   [255]
 
 Inaccessible destination
 
   $ hg init b
   $ cd b
   $ hg clone . ../a
   abort: Permission denied: *../a* (glob)
   [255]
   $ cd ..
   $ chmod 700 a
   $ rm -r a b
 
 #endif
 
 
 #if fifo
 
 Source of wrong type
 
   $ mkfifo a
   $ hg clone a b
   abort: $ENOTDIR$: *$TESTTMP/fail/a/.hg* (glob)
   [255]
   $ rm a
 
 #endif
 
 Default destination, same directory
 
   $ hg init q
   $ hg clone q
   destination directory: q
   abort: destination 'q' is not empty
   [255]
 
 destination directory not empty
 
   $ mkdir a
   $ echo stuff > a/a
   $ hg clone q a
   abort: destination 'a' is not empty
   [255]
 
 
 #if unix-permissions no-root
 
 leave existing directory in place after clone failure
 
   $ hg init c
   $ cd c
   $ echo c > c
   $ hg commit -A -m test
   adding c
   $ chmod -rx .hg/store/data
   $ cd ..
   $ mkdir d
   $ hg clone c d 2> err
   [255]
   $ test -d d
   $ test -d d/.hg
   [1]
 
 re-enable perm to allow deletion
 
   $ chmod +rx c/.hg/store/data
 
 #endif
 
   $ cd ..
 
 Test clone from the repository in (emulated) revlog format 0 (issue4203):
 
   $ mkdir issue4203
   $ mkdir -p src/.hg
   $ echo foo > src/foo
   $ hg -R src add src/foo
   $ hg -R src commit -m '#0'
   $ hg -R src log -q
   0:e1bab28bca43
+  $ hg -R src debugrevlog -c | egrep 'format|flags'
+  format : 0
+  flags  : (none)
   $ hg clone -U -q src dst
   $ hg -R dst log -q
   0:e1bab28bca43
 
 Create repositories to test auto sharing functionality
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > share=
   > EOF
 
   $ hg init empty
   $ hg init source1a
   $ cd source1a
   $ echo initial1 > foo
   $ hg -q commit -A -m initial
   $ echo second > foo
   $ hg commit -m second
   $ cd ..
 
   $ hg init filteredrev0
   $ cd filteredrev0
   $ cat >> .hg/hgrc << EOF
   > [experimental]
   > evolution.createmarkers=True
   > EOF
   $ echo initial1 > foo
   $ hg -q commit -A -m initial0
   $ hg -q up -r null
   $ echo initial2 > foo
   $ hg -q commit -A -m initial1
   $ hg debugobsolete c05d5c47a5cf81401869999f3d05f7d699d2b29a e082c1832e09a7d1e78b7fd49a592d372de854c8
   obsoleted 1 changesets
   $ cd ..
 
   $ hg -q clone --pull source1a source1b
   $ cd source1a
   $ hg bookmark bookA
   $ echo 1a > foo
   $ hg commit -m 1a
   $ cd ../source1b
   $ hg -q up -r 0
   $ echo head1 > foo
   $ hg commit -m head1
   created new head
   $ hg bookmark head1
   $ hg -q up -r 0
   $ echo head2 > foo
   $ hg commit -m head2
   created new head
   $ hg bookmark head2
   $ hg -q up -r 0
   $ hg branch branch1
   marked working directory as branch branch1
   (branches are permanent and global, did you want a bookmark?)
   $ echo branch1 > foo
   $ hg commit -m branch1
   $ hg -q up -r 0
   $ hg branch branch2
   marked working directory as branch branch2
   $ echo branch2 > foo
   $ hg commit -m branch2
   $ cd ..
   $ hg init source2
   $ cd source2
   $ echo initial2 > foo
   $ hg -q commit -A -m initial2
   $ echo second > foo
   $ hg commit -m second
   $ cd ..
 
 Clone with auto share from an empty repo should not result in share
 
   $ mkdir share
   $ hg --config share.pool=share clone empty share-empty
   (not using pooled storage: remote appears to be empty)
   updating to branch default
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ ls share
   $ test -d share-empty/.hg/store
   $ test -f share-empty/.hg/sharedpath
   [1]
 
 Clone with auto share from a repo with filtered revision 0 should not result in share
 
   $ hg --config share.pool=share clone filteredrev0 share-filtered
   (not using pooled storage: unable to resolve identity of remote)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   new changesets e082c1832e09
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Clone from repo with content should result in shared store being created
 
   $ hg --config share.pool=share clone source1a share-dest1a
   (sharing from new pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 3 changes to 1 files
   new changesets b5f04eac9d8f:e5bfe23c0b47
   searching for changes
   no changes found
   adding remote bookmark bookA
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 The shared repo should have been created
 
   $ ls share
   b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1
 
 The destination should point to it
 
   $ cat share-dest1a/.hg/sharedpath; echo
   $TESTTMP/share/b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1/.hg
 
 The destination should have bookmarks
 
   $ hg -R share-dest1a bookmarks
      bookA                     2:e5bfe23c0b47
 
 The default path should be the remote, not the share
 
   $ hg -R share-dest1a config paths.default
   $TESTTMP/source1a
 
 Clone with existing share dir should result in pull + share
 
   $ hg --config share.pool=share clone source1b share-dest1b
   (sharing from existing pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 4 changesets with 4 changes to 1 files (+4 heads)
   adding remote bookmark head1
   adding remote bookmark head2
   new changesets 4a8dc1ab4c13:6bacf4683960
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ ls share
   b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1
 
   $ cat share-dest1b/.hg/sharedpath; echo
   $TESTTMP/share/b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1/.hg
 
 We only get bookmarks from the remote, not everything in the share
 
   $ hg -R share-dest1b bookmarks
      head1                     3:4a8dc1ab4c13
      head2                     4:99f71071f117
 
 Default path should be source, not share.
 
   $ hg -R share-dest1b config paths.default
   $TESTTMP/source1b
 
 Checked out revision should be head of default branch
 
   $ hg -R share-dest1b log -r .
   changeset:   4:99f71071f117
   bookmark:    head2
   parent:      0:b5f04eac9d8f
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     head2
   
 
 Clone from unrelated repo should result in new share
 
   $ hg --config share.pool=share clone source2 share-dest2
   (sharing from new pooled repository 22aeff664783fd44c6d9b435618173c118c3448e)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 2 changes to 1 files
   new changesets 22aeff664783:63cf6c3dba4a
   searching for changes
   no changes found
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ ls share
   22aeff664783fd44c6d9b435618173c118c3448e
   b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1
 
 remote naming mode works as advertised
 
   $ hg --config share.pool=shareremote --config share.poolnaming=remote clone source1a share-remote1a
   (sharing from new pooled repository 195bb1fcdb595c14a6c13e0269129ed78f6debde)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 3 changes to 1 files
   new changesets b5f04eac9d8f:e5bfe23c0b47
   searching for changes
   no changes found
   adding remote bookmark bookA
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ ls shareremote
   195bb1fcdb595c14a6c13e0269129ed78f6debde
 
   $ hg --config share.pool=shareremote --config share.poolnaming=remote clone source1b share-remote1b
   (sharing from new pooled repository c0d4f83847ca2a873741feb7048a45085fd47c46)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 6 changesets with 6 changes to 1 files (+4 heads)
   new changesets b5f04eac9d8f:6bacf4683960
   searching for changes
   no changes found
   adding remote bookmark head1
   adding remote bookmark head2
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ ls shareremote
   195bb1fcdb595c14a6c13e0269129ed78f6debde
   c0d4f83847ca2a873741feb7048a45085fd47c46
 
 request to clone a single revision is respected in sharing mode
 
   $ hg --config share.pool=sharerevs clone -r 4a8dc1ab4c13 source1b share-1arev
   (sharing from new pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 2 changes to 1 files
   new changesets b5f04eac9d8f:4a8dc1ab4c13
   no changes found
   adding remote bookmark head1
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg -R share-1arev log -G
   @  changeset:   1:4a8dc1ab4c13
   |  bookmark:    head1
   |  tag:         tip
   |  user:        test
   |  date:        Thu Jan 01 00:00:00 1970 +0000
   |  summary:     head1
   |
   o  changeset:   0:b5f04eac9d8f
      user:        test
      date:        Thu Jan 01 00:00:00 1970 +0000
      summary:     initial
   
 
 making another clone should only pull down requested rev
 
   $ hg --config share.pool=sharerevs clone -r 99f71071f117 source1b share-1brev
   (sharing from existing pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files (+1 heads)
   adding remote bookmark head1
   adding remote bookmark head2
   new changesets 99f71071f117
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg -R share-1brev log -G
   @  changeset:   2:99f71071f117
   |  bookmark:    head2
   |  tag:         tip
   |  parent:      0:b5f04eac9d8f
   |  user:        test
   |  date:        Thu Jan 01 00:00:00 1970 +0000
   |  summary:     head2
   |
   | o  changeset:   1:4a8dc1ab4c13
   |/   bookmark:    head1
   |    user:        test
   |    date:        Thu Jan 01 00:00:00 1970 +0000
   |    summary:     head1
   |
   o  changeset:   0:b5f04eac9d8f
      user:        test
      date:        Thu Jan 01 00:00:00 1970 +0000
      summary:     initial
   
 
 Request to clone a single branch is respected in sharing mode
 
   $ hg --config share.pool=sharebranch clone -b branch1 source1b share-1bbranch1
   (sharing from new pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 2 changes to 1 files
   new changesets b5f04eac9d8f:5f92a6c1a1b1
   no changes found
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg -R share-1bbranch1 log -G
   o  changeset:   1:5f92a6c1a1b1
   |  branch:      branch1
   |  tag:         tip
   |  user:        test
   |  date:        Thu Jan 01 00:00:00 1970 +0000
   |  summary:     branch1
   |
   @  changeset:   0:b5f04eac9d8f
      user:        test
      date:        Thu Jan 01 00:00:00 1970 +0000
      summary:     initial
   
 
   $ hg --config share.pool=sharebranch clone -b branch2 source1b share-1bbranch2
   (sharing from existing pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files (+1 heads)
   new changesets 6bacf4683960
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg -R share-1bbranch2 log -G
   o  changeset:   2:6bacf4683960
   |  branch:      branch2
   |  tag:         tip
   |  parent:      0:b5f04eac9d8f
   |  user:        test
   |  date:        Thu Jan 01 00:00:00 1970 +0000
   |  summary:     branch2
   |
   | o  changeset:   1:5f92a6c1a1b1
   |/   branch:      branch1
   |    user:        test
   |    date:        Thu Jan 01 00:00:00 1970 +0000
   |    summary:     branch1
   |
   @  changeset:   0:b5f04eac9d8f
      user:        test
      date:        Thu Jan 01 00:00:00 1970 +0000
      summary:     initial
   
 
 -U is respected in share clone mode
 
   $ hg --config share.pool=share clone -U source1a share-1anowc
   (sharing from existing pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   searching for changes
   no changes found
   adding remote bookmark bookA
 
   $ ls share-1anowc
 
 Test that auto sharing doesn't cause failure of "hg clone local remote"
 
   $ cd $TESTTMP
   $ hg -R a id -r 0
   acb14030fe0a
   $ hg id -R remote -r 0
   abort: repository remote not found!
   [255]
   $ hg --config share.pool=share -q clone -e "\"$PYTHON\" \"$TESTDIR/dummyssh\"" a ssh://user@dummy/remote
   $ hg -R remote id -r 0
   acb14030fe0a
 
 Cloning into pooled storage doesn't race (issue5104)
 
   $ HGPOSTLOCKDELAY=2.0 hg --config share.pool=racepool --config extensions.lockdelay=$TESTDIR/lockdelay.py clone source1a share-destrace1 > race1.log 2>&1 &
   $ HGPRELOCKDELAY=1.0 hg --config share.pool=racepool --config extensions.lockdelay=$TESTDIR/lockdelay.py clone source1a share-destrace2  > race2.log 2>&1
   $ wait
 
   $ hg -R share-destrace1 log -r tip
   changeset:   2:e5bfe23c0b47
   bookmark:    bookA
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     1a
   
 
   $ hg -R share-destrace2 log -r tip
   changeset:   2:e5bfe23c0b47
   bookmark:    bookA
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     1a
   
 One repo should be new, the other should be shared from the pool. We
 don't care which is which, so we just make sure we always print the
 one containing "new pooled" first, then one one containing "existing
 pooled".
 
   $ (grep 'new pooled' race1.log > /dev/null && cat race1.log || cat race2.log) | grep -v lock
   (sharing from new pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 3 changes to 1 files
   new changesets b5f04eac9d8f:e5bfe23c0b47
   searching for changes
   no changes found
   adding remote bookmark bookA
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ (grep 'existing pooled' race1.log > /dev/null && cat race1.log || cat race2.log) | grep -v lock
   (sharing from existing pooled repository b5f04eac9d8f7a6a9fcb070243cccea7dc5ea0c1)
   searching for changes
   no changes found
   adding remote bookmark bookA
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 SEC: check for unsafe ssh url
 
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ssh = sh -c "read l; read l; read l"
   > EOF
 
   $ hg clone 'ssh://-oProxyCommand=touch${IFS}owned/path'
   abort: potentially unsafe url: 'ssh://-oProxyCommand=touch${IFS}owned/path'
   [255]
   $ hg clone 'ssh://%2DoProxyCommand=touch${IFS}owned/path'
   abort: potentially unsafe url: 'ssh://-oProxyCommand=touch${IFS}owned/path'
   [255]
   $ hg clone 'ssh://fakehost|touch%20owned/path'
   abort: no suitable response from remote hg!
   [255]
   $ hg clone 'ssh://fakehost%7Ctouch%20owned/path'
   abort: no suitable response from remote hg!
   [255]
 
   $ hg clone 'ssh://-oProxyCommand=touch [e-mail]/nonexistent/path'
   abort: potentially unsafe url: 'ssh://-oProxyCommand=touch owned [e-mail]/nonexistent/path'
   [255]
 
 #if windows
   $ hg clone "ssh://%26touch%20owned%20/" --debug
   running sh -c "read l; read l; read l" "&touch owned " "hg -R . serve --stdio"
   sending upgrade request: * proto=exp-ssh-v2-0003 (glob) (sshv2 !)
   sending hello command
   sending between command
   abort: no suitable response from remote hg!
   [255]
   $ hg clone "ssh://example.com:%26touch%20owned%20/" --debug
   running sh -c "read l; read l; read l" -p "&touch owned " example.com "hg -R . serve --stdio"
   sending upgrade request: * proto=exp-ssh-v2-0003 (glob) (sshv2 !)
   sending hello command
   sending between command
   abort: no suitable response from remote hg!
   [255]
 #else
   $ hg clone "ssh://%3btouch%20owned%20/" --debug
   running sh -c "read l; read l; read l" ';touch owned ' 'hg -R . serve --stdio'
   sending upgrade request: * proto=exp-ssh-v2-0003 (glob) (sshv2 !)
   sending hello command
   sending between command
   abort: no suitable response from remote hg!
   [255]
   $ hg clone "ssh://example.com:%3btouch%20owned%20/" --debug
   running sh -c "read l; read l; read l" -p ';touch owned ' example.com 'hg -R . serve --stdio'
   sending upgrade request: * proto=exp-ssh-v2-0003 (glob) (sshv2 !)
   sending hello command
   sending between command
   abort: no suitable response from remote hg!
   [255]
 #endif
 
   $ hg clone "ssh://v-alid.example.com/" --debug
   running sh -c "read l; read l; read l" v-alid\.example\.com ['"]hg -R \. serve --stdio['"] (re)
   sending upgrade request: * proto=exp-ssh-v2-0003 (glob) (sshv2 !)
   sending hello command
   sending between command
   abort: no suitable response from remote hg!
   [255]
 
 We should not have created a file named owned - if it exists, the
 attack succeeded.
   $ if test -f owned; then echo 'you got owned'; fi
 
 Cloning without fsmonitor enabled does not print a warning for small repos
 
   $ hg clone a fsmonitor-default
   updating to bookmark @ on branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Lower the warning threshold to simulate a large repo
 
   $ cat >> $HGRCPATH << EOF
   > [fsmonitor]
   > warn_update_file_count = 2
   > EOF
 
 We should see a warning about no fsmonitor on supported platforms
 
 #if linuxormacos no-fsmonitor
   $ hg clone a nofsmonitor
   updating to bookmark @ on branch stable
   (warning: large working directory being used without fsmonitor enabled; enable fsmonitor to improve performance; see "hg help -e fsmonitor")
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #else
   $ hg clone a nofsmonitor
   updating to bookmark @ on branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 
 We should not see warning about fsmonitor when it is enabled
 
 #if fsmonitor
   $ hg clone a fsmonitor-enabled
   updating to bookmark @ on branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 
 We can disable the fsmonitor warning
 
   $ hg --config fsmonitor.warn_when_unused=false clone a fsmonitor-disable-warning
   updating to bookmark @ on branch stable
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Loaded fsmonitor but disabled in config should still print warning
 
 #if linuxormacos fsmonitor
   $ hg --config fsmonitor.mode=off clone a fsmonitor-mode-off
   updating to bookmark @ on branch stable
   (warning: large working directory being used without fsmonitor enabled; enable fsmonitor to improve performance; see "hg help -e fsmonitor") (fsmonitor !)
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 
 Warning not printed if working directory isn't empty
 
   $ hg -q clone a fsmonitor-update
   (warning: large working directory being used without fsmonitor enabled; enable fsmonitor to improve performance; see "hg help -e fsmonitor") (?)
   $ cd fsmonitor-update
   $ hg up acb14030fe0a
   1 files updated, 0 files merged, 2 files removed, 0 files unresolved
   (leaving bookmark @)
   $ hg up cf0fe1914066
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 `hg update` from null revision also prints
 
   $ hg up null
   0 files updated, 0 files merged, 2 files removed, 0 files unresolved
 
 #if linuxormacos no-fsmonitor
   $ hg up cf0fe1914066
   (warning: large working directory being used without fsmonitor enabled; enable fsmonitor to improve performance; see "hg help -e fsmonitor")
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #else
   $ hg up cf0fe1914066
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 #endif
 
   $ cd ..
 

tests/test-rust-ancestor.py

@@ -1,159 +1,170
 from __future__ import absolute_import
 import sys
 import unittest
 
+from mercurial import (
+    error,
+    node,
+)
+
 try:
     from mercurial import rustext
     rustext.__name__  # trigger immediate actual import
 except ImportError:
     rustext = None
 else:
     # this would fail already without appropriate ancestor.__package__
     from mercurial.rustext.ancestor import (
         AncestorsIterator,
         LazyAncestors,
         MissingAncestors,
     )
 
 try:
     from mercurial.cext import parsers as cparsers
 except ImportError:
     cparsers = None
 
 # picked from test-parse-index2, copied rather than imported
 # so that it stays stable even if test-parse-index2 changes or disappears.
 data_non_inlined = (
     b'\x00\x00\x00\x01\x00\x00\x00\x00\x00\x01D\x19'
     b'\x00\x07e\x12\x00\x00\x00\x00\x00\x00\x00\x00\xff\xff\xff\xff'
     b'\xff\xff\xff\xff\xd1\xf4\xbb\xb0\xbe\xfc\x13\xbd\x8c\xd3\x9d'
     b'\x0f\xcd\xd9;\x8c\x07\x8cJ/\x00\x00\x00\x00\x00\x00\x00\x00\x00'
     b'\x00\x00\x00\x00\x00\x00\x01D\x19\x00\x00\x00\x00\x00\xdf\x00'
     b'\x00\x01q\x00\x00\x00\x01\x00\x00\x00\x01\x00\x00\x00\x00\xff'
     b'\xff\xff\xff\xc1\x12\xb9\x04\x96\xa4Z1t\x91\xdfsJ\x90\xf0\x9bh'
     b'\x07l&\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
     b'\x00\x01D\xf8\x00\x00\x00\x00\x01\x1b\x00\x00\x01\xb8\x00\x00'
     b'\x00\x01\x00\x00\x00\x02\x00\x00\x00\x01\xff\xff\xff\xff\x02\n'
     b'\x0e\xc6&\xa1\x92\xae6\x0b\x02i\xfe-\xe5\xbao\x05\xd1\xe7\x00'
     b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01F'
     b'\x13\x00\x00\x00\x00\x01\xec\x00\x00\x03\x06\x00\x00\x00\x01'
     b'\x00\x00\x00\x03\x00\x00\x00\x02\xff\xff\xff\xff\x12\xcb\xeby1'
     b'\xb6\r\x98B\xcb\x07\xbd`\x8f\x92\xd9\xc4\x84\xbdK\x00\x00\x00'
     b'\x00\x00\x00\x00\x00\x00\x00\x00\x00'
     )
 
 
 @unittest.skipIf(rustext is None or cparsers is None,
                  "rustext or the C Extension parsers module "
                  "ancestor relies on is not available")
 class rustancestorstest(unittest.TestCase):
     """Test the correctness of binding to Rust code.
 
     This test is merely for the binding to Rust itself: extraction of
     Python variable, giving back the results etc.
 
     It is not meant to test the algorithmic correctness of the operations
     on ancestors it provides. Hence the very simple embedded index data is
     good enough.
 
     Algorithmic correctness is asserted by the Rust unit tests.
     """
 
     def parseindex(self):
         return cparsers.parse_index2(data_non_inlined, False)[0]
 
     def testiteratorrevlist(self):
         idx = self.parseindex()
         # checking test assumption about the index binary data:
         self.assertEqual({i: (r[5], r[6]) for i, r in enumerate(idx)},
                          {0: (-1, -1),
                           1: (0, -1),
                           2: (1, -1),
                           3: (2, -1)})
         ait = AncestorsIterator(idx, [3], 0, True)
         self.assertEqual([r for r in ait], [3, 2, 1, 0])
 
         ait = AncestorsIterator(idx, [3], 0, False)
         self.assertEqual([r for r in ait], [2, 1, 0])
 
     def testlazyancestors(self):
         idx = self.parseindex()
         start_count = sys.getrefcount(idx)  # should be 2 (see Python doc)
         self.assertEqual({i: (r[5], r[6]) for i, r in enumerate(idx)},
                          {0: (-1, -1),
                           1: (0, -1),
                           2: (1, -1),
                           3: (2, -1)})
         lazy = LazyAncestors(idx, [3], 0, True)
         # we have two more references to the index:
         # - in its inner iterator for __contains__ and __bool__
         # - in the LazyAncestors instance itself (to spawn new iterators)
         self.assertEqual(sys.getrefcount(idx), start_count + 2)
 
         self.assertTrue(2 in lazy)
         self.assertTrue(bool(lazy))
         self.assertEqual(list(lazy), [3, 2, 1, 0])
         # a second time to validate that we spawn new iterators
         self.assertEqual(list(lazy), [3, 2, 1, 0])
 
         # now let's watch the refcounts closer
         ait = iter(lazy)
         self.assertEqual(sys.getrefcount(idx), start_count + 3)
         del ait
         self.assertEqual(sys.getrefcount(idx), start_count + 2)
         del lazy
         self.assertEqual(sys.getrefcount(idx), start_count)
 
         # let's check bool for an empty one
         self.assertFalse(LazyAncestors(idx, [0], 0, False))
 
     def testmissingancestors(self):
         idx = self.parseindex()
         missanc = MissingAncestors(idx, [1])
         self.assertTrue(missanc.hasbases())
         self.assertEqual(missanc.missingancestors([3]), [2, 3])
         missanc.addbases({2})
         self.assertEqual(missanc.bases(), {1, 2})
         self.assertEqual(missanc.missingancestors([3]), [3])
         self.assertEqual(missanc.basesheads(), {2})
 
     def testmissingancestorsremove(self):
         idx = self.parseindex()
         missanc = MissingAncestors(idx, [1])
         revs = {0, 1, 2, 3}
         missanc.removeancestorsfrom(revs)
         self.assertEqual(revs, {2, 3})
 
     def testrefcount(self):
         idx = self.parseindex()
         start_count = sys.getrefcount(idx)
 
         # refcount increases upon iterator init...
         ait = AncestorsIterator(idx, [3], 0, True)
         self.assertEqual(sys.getrefcount(idx), start_count + 1)
         self.assertEqual(next(ait), 3)
 
         # and decreases once the iterator is removed
         del ait
         self.assertEqual(sys.getrefcount(idx), start_count)
 
         # and removing ref to the index after iterator init is no issue
         ait = AncestorsIterator(idx, [3], 0, True)
         del idx
         self.assertEqual(list(ait), [3, 2, 1, 0])
 
     def testgrapherror(self):
         data = (data_non_inlined[:64 + 27] +
                 b'\xf2' +
                 data_non_inlined[64 + 28:])
         idx = cparsers.parse_index2(data, False)[0]
         with self.assertRaises(rustext.GraphError) as arc:
             AncestorsIterator(idx, [1], -1, False)
         exc = arc.exception
         self.assertIsInstance(exc, ValueError)
         # rust-cpython issues appropriate str instances for Python 2 and 3
         self.assertEqual(exc.args, ('ParentOutOfRange', 1))
 
+    def testwdirunsupported(self):
+        # trying to access ancestors of the working directory raises
+        # WdirUnsupported directly
+        idx = self.parseindex()
+        with self.assertRaises(error.WdirUnsupported):
+            list(AncestorsIterator(idx, [node.wdirrev], -1, False))
 
 if __name__ == '__main__':
     import silenttestrunner
     silenttestrunner.main(__name__)