revlog: use revlog.display_id in integrity error

Differential Revision: https://phab.mercurial-scm.org/D10586

mercurial/revlog.py

@@ -1,3180 +1,3180 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Olivia 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 binascii
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
     wdirrev,
 )
 from .i18n import _
 from .pycompat import getattr
 from .revlogutils.constants import (
     ALL_KINDS,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_HASCOPIESINFO,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
 )
 from .thirdparty import attr
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     templatefilters,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     flagutil,
     nodemap as nodemaputil,
     revlogv0,
     sidedata as sidedatautil,
 )
 from .utils import (
     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_HASCOPIESINFO
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod('parsers')
 rustancestor = policy.importrust('ancestor')
 rustdagop = policy.importrust('dagop')
 rustrevlog = policy.importrust('revlog')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 # 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 offset_type(offset, type):
     if (type & ~flagutil.REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError(b'unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 
 def _verify_revision(rl, skipflags, state, node):
     """Verify the integrity of the given revlog ``node`` while providing a hook
     point for extensions to influence the operation."""
     if skipflags:
         state[b'skipread'].add(node)
     else:
         # Side-effect: read content and verify hash.
         rl.revision(node)
 
 
 # True if a fast implementation for persistent-nodemap is available
 #
 # We also consider we have a "fast" implementation in "pure" python because
 # people using pure don't really have performance consideration (and a
 # wheelbarrow of other slowness source)
 HAS_FAST_PERSISTENT_NODEMAP = rustrevlog is not None or util.safehasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @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()
     sidedata = attr.ib()
     protocol_flags = 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)
 
 
 def parse_index_v1(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline)
     return index, cache
 
 
 def parse_index_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, revlogv2=True)
     return index, cache
 
 
 if util.safehasattr(parsers, 'parse_index_devel_nodemap'):
 
     def parse_index_v1_nodemap(data, inline):
         index, cache = parsers.parse_index_devel_nodemap(data, inline)
         return index, cache
 
 
 else:
     parse_index_v1_nodemap = None
 
 
 def parse_index_v1_mixed(data, inline):
     index, cache = parse_index_v1(data, inline)
     return rustrevlog.MixedIndex(index), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 
 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.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
 
     `concurrencychecker` is an optional function that receives 3 arguments: a
     file handle, a filename, and an expected position. It should check whether
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
     """
 
     _flagserrorclass = error.RevlogError
 
     def __init__(
         self,
         opener,
         target,
         radix,
         postfix=None,
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
     ):
         """
         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.
 
         `target`: a (KIND, ID) tuple that identify the content stored in
         this revlog. It help the rest of the code to understand what the revlog
         is about without having to resort to heuristic and index filename
         analysis. Note: that this must be reliably be set by normal code, but
         that test, debug, or performance measurement code might not set this to
         accurate value.
         """
         self.upperboundcomp = upperboundcomp
 
         self.radix = radix
 
         if postfix is None:
             indexfile = b'%s.i' % self.radix
             datafile = b'%s.d' % self.radix
         elif postfix == b'a':
             indexfile = b'%s.i.a' % self.radix
             datafile = b'%s.d' % self.radix
         else:
             indexfile = b'%s.i.%s' % (self.radix, postfix)
             datafile = b'%s.d.%s' % (self.radix, postfix)
 
         self._indexfile = indexfile
         self._datafile = datafile
         self.nodemap_file = None
         self.postfix = postfix
         self.opener = opener
         if persistentnodemap:
             self.nodemap_file = nodemaputil.get_nodemap_file(self)
 
         assert target[0] in ALL_KINDS
         assert len(target) == 2
         self.target = target
         #  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, b'')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._compengine = b'zlib'
         self._compengineopts = {}
         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(flagutil.flagprocessors)
 
         # 2-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._loadindex()
 
         self._concurrencychecker = concurrencychecker
 
     def _init_opts(self):
         """process options (from above/config) to setup associated default revlog mode
 
         These values might be affected when actually reading on disk information.
 
         The relevant values are returned for use in _loadindex().
 
         * newversionflags:
             version header to use if we need to create a new revlog
 
         * mmapindexthreshold:
             minimal index size for start to use mmap
 
         * force_nodemap:
             force the usage of a "development" version of the nodemap code
         """
         mmapindexthreshold = None
         opts = self.opener.options
 
         if b'revlogv2' in opts:
             newversionflags = REVLOGV2 | FLAG_INLINE_DATA
         elif b'revlogv1' in opts:
             newversionflags = REVLOGV1 | FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 newversionflags |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             newversionflags = REVLOGV0
         else:
             newversionflags = REVLOG_DEFAULT_VERSION
 
         if b'chunkcachesize' in opts:
             self._chunkcachesize = opts[b'chunkcachesize']
         if b'maxchainlen' in opts:
             self._maxchainlen = opts[b'maxchainlen']
         if b'deltabothparents' in opts:
             self._deltabothparents = opts[b'deltabothparents']
         self._lazydelta = bool(opts.get(b'lazydelta', True))
         self._lazydeltabase = False
         if self._lazydelta:
             self._lazydeltabase = bool(opts.get(b'lazydeltabase', False))
         if b'compengine' in opts:
             self._compengine = opts[b'compengine']
         if b'zlib.level' in opts:
             self._compengineopts[b'zlib.level'] = opts[b'zlib.level']
         if b'zstd.level' in opts:
             self._compengineopts[b'zstd.level'] = opts[b'zstd.level']
         if b'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts[b'maxdeltachainspan']
         if self._mmaplargeindex and b'mmapindexthreshold' in opts:
             mmapindexthreshold = opts[b'mmapindexthreshold']
         self.hassidedata = bool(opts.get(b'side-data', False))
         self._sparserevlog = bool(opts.get(b'sparse-revlog', False))
         withsparseread = bool(opts.get(b'with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if b'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts[b'sparse-read-density-threshold']
         if b'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts[b'sparse-read-min-gap-size']
         if opts.get(b'enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in pycompat.iteritems(
             opts.get(b'flagprocessors', {})
         ):
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % self._chunkcachesize
             )
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % self._chunkcachesize
             )
         force_nodemap = opts.get(b'devel-force-nodemap', False)
         return newversionflags, mmapindexthreshold, force_nodemap
 
     def _loadindex(self):
 
         newversionflags, mmapindexthreshold, force_nodemap = self._init_opts()
         indexdata = b''
         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 = INDEX_HEADER.unpack(indexdata[:4])[0]
                 self._initempty = False
             else:
                 versionflags = newversionflags
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
             versionflags = newversionflags
 
         flags = self._format_flags = versionflags & ~0xFFFF
         fmt = self._format_version = versionflags & 0xFFFF
 
         if fmt == REVLOGV0:
             if flags:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.display_id)
                 )
 
             self._inline = False
             self._generaldelta = False
 
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.display_id)
                 )
 
             self._inline = versionflags & FLAG_INLINE_DATA
             self._generaldelta = versionflags & FLAG_GENERALDELTA
 
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.display_id)
                 )
 
             # There is a bug in the transaction handling when going from an
             # inline revlog to a separate index and data file. Turn it off until
             # it's fixed, since v2 revlogs sometimes get rewritten on exchange.
             # See issue6485
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(
                 _(b'unknown version (%d) in revlog %s') % (fmt, self.display_id)
             )
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self._generaldelta:
             self._sparserevlog = False
 
         self._storedeltachains = True
 
         devel_nodemap = (
             self.nodemap_file
             and force_nodemap
             and parse_index_v1_nodemap is not None
         )
 
         use_rust_index = False
         if rustrevlog is not None:
             if self.nodemap_file is not None:
                 use_rust_index = True
             else:
                 use_rust_index = self.opener.options.get(b'rust.index')
 
         self._parse_index = parse_index_v1
         if self._format_version == REVLOGV0:
             self._parse_index = revlogv0.parse_index_v0
         elif fmt == REVLOGV2:
             self._parse_index = parse_index_v2
         elif devel_nodemap:
             self._parse_index = parse_index_v1_nodemap
         elif use_rust_index:
             self._parse_index = parse_index_v1_mixed
         try:
             d = self._parse_index(indexdata, self._inline)
             index, _chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self.nodemap_file is not None
                 and util.safehasattr(index, 'update_nodemap_data')
             )
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
                     docket = nodemap_data[0]
                     if (
                         len(d[0]) > docket.tip_rev
                         and d[0][docket.tip_rev][7] == docket.tip_node
                     ):
                         # no changelog tampering
                         self._nodemap_docket = docket
                         index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
                 _(b"index %s is corrupted") % self.display_id
             )
         self.index, self._chunkcache = d
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def revlog_kind(self):
         return self.target[0]
 
     @util.propertycache
     def display_id(self):
         """The public facing "ID" of the revlog that we use in message"""
         # Maybe we should build a user facing representation of
         # revlog.target instead of using `self.radix`
         return self.radix
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     def _indexfp(self, mode=b'r'):
         """file object for the revlog's index file"""
         args = {'mode': mode}
         if mode != b'r':
             args['checkambig'] = self._checkambig
         if mode == b'w':
             args['atomictemp'] = True
         return self.opener(self._indexfile, **args)
 
     def _datafp(self, mode=b'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 tiprev(self):
         return len(self.index) - 1
 
     def tip(self):
         return self.node(self.tiprev())
 
     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)
 
     @property
     def nodemap(self):
         msg = (
             b"revlog.nodemap is deprecated, "
             b"use revlog.index.[has_node|rev|get_rev]"
         )
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     @property
     def _nodecache(self):
         msg = b"revlog._nodecache is deprecated, use revlog.index.nodemap"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     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 update_caches(self, transaction):
         if self.nodemap_file is not None:
             if transaction is None:
                 nodemaputil.update_persistent_nodemap(self)
             else:
                 nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, b'')
         self._pcache = {}
         self._nodemap_docket = None
         self.index.clearcaches()
         # The python code is the one responsible for validating the docket, we
         # end up having to refresh it here.
         use_nodemap = (
             not self._inline
             and self.nodemap_file is not None
             and util.safehasattr(self.index, 'update_nodemap_data')
         )
         if use_nodemap:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
                 self.index.update_nodemap_data(*nodemap_data)
 
     def rev(self, node):
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if (
                 node == self.nodeconstants.wdirid
                 or node in self.nodeconstants.wdirfilenodeids
             ):
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.display_id, _(b'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 sidedata_length(self, rev):
         if not self.hassidedata:
             return 0
         return self.index[rev][9]
 
     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.rawdata(rev)
         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 & (flagutil.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
         if entry[5] == nullrev:
             return entry[6], entry[5]
         else:
             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)]
         # inline node() to avoid function call overhead
         if d[5] == self.nullid:
             return i[d[6]][7], i[d[5]][7]
         else:
             return i[d[5]][7], i[d[6]][7]
 
     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 rustancestor is not None:
             lazyancestors = rustancestor.LazyAncestors
             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 = [self.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 rustancestor is not None:
             return rustancestor.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 = [self.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 = [self.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],
                 [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 == self.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 != self.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 = [self.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 pycompat.iteritems(heads) 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()
         if rustdagop is not None:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     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 [self.nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = {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
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::(<roots> and <roots>::<heads>)))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(
                 minroot, heads, roots, includepath
             )
         except AttributeError:
             return dagop._reachablerootspure(
                 self.parentrevs, minroot, roots, heads, includepath
             )
 
     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 self.nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == self.nodeconstants.nodelen:
             # 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 b"%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) == 2 * self.nodeconstants.nodelen:
             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 = self.nodeconstants.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.display_id, _(b'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 self.nodeconstants.nullhex.startswith(id):
                     nl.append(self.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.display_id, _(b'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.display_id, _(b'no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
 
         def isvalid(prefix):
             try:
                 matchednode = self._partialmatch(prefix)
             except error.AmbiguousPrefixLookupError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if matchednode is None:
                 raise error.LookupError(node, self.display_id, _(b'no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == b'f' for c in pycompat.iterbytestr(prefix))
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, len(hexnode) + 1):
                 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 != self.nodeconstants.wdirid:
                     raise error.LookupError(
                         node, self.display_id, _(b'no node')
                     )
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == self.nodeconstants.wdirid:
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, len(hexnode) + 1):
             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(
                     _(
                         b'partial read of revlog %s; expected %d bytes from '
                         b'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(
                 _(
                     b'partial read of revlog %s; expected %d bytes from offset '
                     b'%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.index.entry_size
             end += (endrev + 1) * self.index.entry_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.index.entry_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, b'')
 
     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, b'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(b'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.rawdata(rev1), self.rawdata(rev2))
 
     def _processflags(self, text, flags, operation, raw=False):
         """deprecated entry point to access flag processors"""
         msg = b'_processflag(...) use the specialized variant'
         util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         if raw:
             return text, flagutil.processflagsraw(self, text, flags)
         elif operation == b'read':
             return flagutil.processflagsread(self, text, flags)
         else:  # write operation
             return flagutil.processflagswrite(self, text, flags)
 
     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 raw:
             msg = (
                 b'revlog.revision(..., raw=True) is deprecated, '
                 b'use revlog.rawdata(...)'
             )
             util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         return self._revisiondata(nodeorrev, _df, raw=raw)[0]
 
     def sidedata(self, nodeorrev, _df=None):
         """a map of extra data related to the changeset but not part of the hash
 
         This function currently return a dictionary. However, more advanced
         mapping object will likely be used in the future for a more
         efficient/lazy code.
         """
         return self._revisiondata(nodeorrev, _df)[1]
 
     def _revisiondata(self, nodeorrev, _df=None, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == self.nullid:
             return b"", {}
 
         # ``rawtext`` is the text as stored inside the revlog. Might be the
         # revision or might need to be processed to retrieve the revision.
         rev, rawtext, validated = self._rawtext(node, rev, _df=_df)
 
         if self.hassidedata:
             if rev is None:
                 rev = self.rev(node)
             sidedata = self._sidedata(rev)
         else:
             sidedata = {}
 
         if raw and validated:
             # if we don't want to process the raw text and that raw
             # text is cached, we can exit early.
             return rawtext, sidedata
         if rev is None:
             rev = self.rev(node)
         # the revlog's flag for this revision
         # (usually alter its state or content)
         flags = self.flags(rev)
 
         if validated and flags == REVIDX_DEFAULT_FLAGS:
             # no extra flags set, no flag processor runs, text = rawtext
             return rawtext, sidedata
 
         if raw:
             validatehash = flagutil.processflagsraw(self, rawtext, flags)
             text = rawtext
         else:
             r = flagutil.processflagsread(self, rawtext, flags)
             text, validatehash = r
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._revisioncache = (node, rev, rawtext)
 
         return text, sidedata
 
     def _rawtext(self, node, rev, _df=None):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
 
         # revision in the cache (could be useful to apply delta)
         cachedrev = None
         # An intermediate text to apply deltas to
         basetext = None
 
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 return (rev, self._revisioncache[2], True)
             cachedrev = self._revisioncache[1]
 
         if rev is None:
             rev = self.rev(node)
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             basetext = self._revisioncache[2]
 
         # drop cache to save memory, the caller is expected to
         # update self._revisioncache after validating the text
         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 basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext  # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         index_entry = self.index[rev]
         sidedata_offset = index_entry[8]
         sidedata_size = index_entry[9]
 
         if self._inline:
             sidedata_offset += self.index.entry_size * (1 + rev)
         if sidedata_size == 0:
             return {}
 
         segment = self._getsegment(sidedata_offset, sidedata_size)
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def rawdata(self, nodeorrev, _df=None):
         """return an uncompressed raw data of a given node or revision number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df, raw=True)[0]
 
     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 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(
                     _(b"integrity check failed on %s:%s")
-                    % (self._indexfile, pycompat.bytestr(revornode))
+                    % (self.display_id, 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
 
         troffset = tr.findoffset(self._indexfile)
         if troffset is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self._indexfile
             )
         trindex = 0
         tr.add(self._datafile, 0)
 
         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(b'r') as ifh, self._datafp(b'w') as dfh:
             for r in self:
                 dfh.write(self._getsegmentforrevs(r, r, df=ifh)[1])
                 if troffset <= self.start(r):
                     trindex = r
 
         with self._indexfp(b'w') as fp:
             self._format_flags &= ~FLAG_INLINE_DATA
             self._inline = False
             for i in self:
                 e = self.index.entry_binary(i)
                 if i == 0:
                     header = self._format_flags | self._format_version
                     header = self.index.pack_header(header)
                     e = header + e
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self._indexfile, trindex * self.index.entry_size)
         nodemaputil.setup_persistent_nodemap(tr, self)
         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,
         sidedata=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(
                 _(b"attempted to add linkrev -1 to %s") % self._indexfile
             )
 
         if sidedata is None:
             sidedata = {}
         elif sidedata and not self.hassidedata:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _(
                     b"%s: size of %d bytes exceeds maximum revlog storage of 2GiB"
                 )
                 % (self._indexfile, len(rawtext))
             )
 
         node = node or self.hash(rawtext, p1, p2)
         rev = self.index.get_rev(node)
         if rev is not None:
             return rev
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
             sidedata=sidedata,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
         sidedata=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(b"a+")
         ifh = self._indexfp(b"a+")
         try:
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 ifh,
                 dfh,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return b'', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return b'', compressed
 
         if data[0:1] == b'\0':
             return b'', data
         return b'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 == b'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(
                     _(b'revlog decompress error: %s')
                     % stringutil.forcebytestr(e)
                 )
         # '\0' is more common than 'u' so it goes first.
         elif t == b'\0':
             return data
         elif t == b'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(self._compengineopts)
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         ifh,
         dfh,
         alwayscache=False,
         deltacomputer=None,
         sidedata=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 == self.nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self._indexfile
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%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._get_data_offset(prev)
 
         if self._concurrencychecker:
             if self._inline:
                 # offset is "as if" it were in the .d file, so we need to add on
                 # the size of the entry metadata.
                 self._concurrencychecker(
                     ifh, self._indexfile, offset + curr * self.index.entry_size
                 )
             else:
                 # Entries in the .i are a consistent size.
                 self._concurrencychecker(
                     ifh, self._indexfile, curr * self.index.entry_size
                 )
                 self._concurrencychecker(dfh, self._datafile, offset)
 
         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)
 
         if sidedata and self.hassidedata:
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = offset + deltainfo.deltalen
         else:
             serialized_sidedata = b""
             # Don't store the offset if the sidedata is empty, that way
             # we can easily detect empty sidedata and they will be no different
             # than ones we manually add.
             sidedata_offset = 0
 
         e = (
             offset_type(offset, flags),
             deltainfo.deltalen,
             textlen,
             deltainfo.base,
             link,
             p1r,
             p2r,
             node,
             sidedata_offset,
             len(serialized_sidedata),
         )
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0:
             header = self._format_flags | self._format_version
             header = self.index.pack_header(header)
             entry = header + entry
         self._writeentry(
             transaction,
             ifh,
             dfh,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
         )
 
         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 curr
 
     def _get_data_offset(self, prev):
         """Returns the current offset in the (in-transaction) data file.
         Versions < 2 of the revlog can get this 0(1), revlog v2 needs a docket
         file to store that information: since sidedata can be rewritten to the
         end of the data file within a transaction, you can have cases where, for
         example, rev `n` does not have sidedata while rev `n - 1` does, leading
         to `n - 1`'s sidedata being written after `n`'s data.
 
         TODO cache this in a docket file before getting out of experimental."""
         if self._format_version != REVLOGV2:
             return self.end(prev)
 
         offset = 0
         for rev, entry in enumerate(self.index):
             sidedata_end = entry[8] + entry[9]
             # Sidedata for a previous rev has potentially been written after
             # this rev's end, so take the max.
             offset = max(self.end(rev), offset, sidedata_end)
         return offset
 
     def _writeentry(
         self, transaction, ifh, dfh, entry, data, link, offset, sidedata
     ):
         # 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])
             if sidedata:
                 dfh.write(sidedata)
             ifh.write(entry)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self._indexfile, offset)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             if sidedata:
                 ifh.write(sidedata)
             self._enforceinlinesize(transaction, ifh)
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=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(b'cannot nest addgroup() calls')
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp(b"a+")
         isize = r * self.index.entry_size
         if self._inline:
             transaction.add(self._indexfile, end + isize)
             dfh = None
         else:
             transaction.add(self._indexfile, isize)
             transaction.add(self._datafile, end)
             dfh = self._datafp(b"a+")
 
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
         empty = True
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags, sidedata = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 rev = self.index.get_rev(node)
                 if rev is not None:
                     # this can happen if two branches make the same change
                     self._nodeduplicatecallback(transaction, rev)
                     if duplicaterevisioncb:
                         duplicaterevisioncb(self, rev)
                     empty = False
                     continue
 
                 for p in (p1, p2):
                     if not self.index.has_node(p):
                         raise error.LookupError(
                             p, self.radix, _(b'unknown parent')
                         )
 
                 if not self.index.has_node(deltabase):
                     raise error.LookupError(
                         deltabase, self.display_id, _(b'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(b">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.
                 rev = self._addrevision(
                     node,
                     None,
                     transaction,
                     link,
                     p1,
                     p2,
                     flags,
                     (baserev, delta),
                     ifh,
                     dfh,
                     alwayscache=alwayscache,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
 
                 if addrevisioncb:
                     addrevisioncb(self, rev)
                 empty = False
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp(b"a+")
                     ifh = self._indexfp(b"a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
         return not empty
 
     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.index.entry_size
         else:
             end += rev * self.index.entry_size
 
         transaction.add(self._indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = util.lrucachedict(500)
         self._chunkclear()
 
         del self.index[rev:-1]
 
     def checksize(self):
         """Check size of index and data files
 
         return a (dd, di) tuple.
         - dd: extra bytes for the "data" file
         - di: extra bytes for the "index" file
 
         A healthy revlog will return (0, 0).
         """
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, io.SEEK_END)
                 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, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self.index.entry_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,
         sidedata_helpers=None,
     ):
         if nodesorder not in (b'nodes', b'storage', b'linear', None):
             raise error.ProgrammingError(
                 b'unhandled value for nodesorder: %s' % nodesorder
             )
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = b'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,
             sidedata_helpers=sidedata_helpers,
         )
 
     DELTAREUSEALWAYS = b'always'
     DELTAREUSESAMEREVS = b'samerevs'
     DELTAREUSENEVER = b'never'
 
     DELTAREUSEFULLADD = b'fulladd'
 
     DELTAREUSEALL = {b'always', b'samerevs', b'never', b'fulladd'}
 
     def clone(
         self,
         tr,
         destrevlog,
         addrevisioncb=None,
         deltareuse=DELTAREUSESAMEREVS,
         forcedeltabothparents=None,
         sidedata_helpers=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).
         DELTAREUSEFULLADD
            Revision will be re-added as if their were new content. This is
            slower than DELTAREUSEALWAYS but allow more mechanism to kicks in.
            eg: large file detection and handling.
 
         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.
 
         See `revlogutil.sidedata.get_sidedata_helpers` for the doc on
         `sidedata_helpers`.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(
                 _(b'value for deltareuse invalid: %s') % deltareuse
             )
 
         if len(destrevlog):
             raise ValueError(_(b'destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_(b'source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_(b'destination revlog has filtered revisions'))
 
         # lazydelta and lazydeltabase controls whether to reuse a cached delta,
         # if possible.
         oldlazydelta = destrevlog._lazydelta
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             self._clone(
                 tr,
                 destrevlog,
                 addrevisioncb,
                 deltareuse,
                 forcedeltabothparents,
                 sidedata_helpers,
             )
 
         finally:
             destrevlog._lazydelta = oldlazydelta
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
         sidedata_helpers,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         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 deltareuse == self.DELTAREUSEFULLADD:
                 text, sidedata = self._revisiondata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 destrevlog.addrevision(
                     text,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     cachedelta=cachedelta,
                     node=node,
                     flags=flags,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
             else:
                 if destrevlog._lazydelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 sidedata = None
                 if not cachedelta:
                     rawtext, sidedata = self._revisiondata(rev)
                 if sidedata is None:
                     sidedata = self.sidedata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 ifh = destrevlog.opener(
                     destrevlog._indexfile, b'a+', checkambig=False
                 )
                 dfh = None
                 if not destrevlog._inline:
                     dfh = destrevlog.opener(destrevlog._datafile, b'a+')
                 try:
                     destrevlog._addrevision(
                         node,
                         rawtext,
                         tr,
                         linkrev,
                         p1,
                         p2,
                         flags,
                         cachedelta,
                         ifh,
                         dfh,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
                 finally:
                     if dfh:
                         dfh.close()
                     ifh.close()
 
             if addrevisioncb:
                 addrevisioncb(self, rev, node)
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if self._format_version == REVLOGV0:
             raise error.RevlogError(
                 _(b'cannot censor with version %d revlogs')
                 % self._format_version
             )
 
         censorrev = self.rev(censornode)
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(censorrev):
             raise error.Abort(
                 _(b'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.
         #
         # This is a bit dangerous. We could easily have a mismatch of state.
         newrl = revlog(
             self.opener,
             target=self.target,
             radix=self.radix,
             postfix=b'tmpcensored',
             censorable=True,
         )
         newrl._format_version = self._format_version
         newrl._format_flags = self._format_flags
         newrl._generaldelta = self._generaldelta
         newrl._parse_index = self._parse_index
 
         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(
                         _(
                             b'censored revision stored as delta; '
                             b'cannot censor'
                         ),
                         hint=_(
                             b'censoring of revlogs is not '
                             b'fully implemented; please report '
                             b'this bug'
                         ),
                     )
                 continue
 
             if self.iscensored(rev):
                 if self.deltaparent(rev) != nullrev:
                     raise error.Abort(
                         _(
                             b'cannot censor due to censored '
                             b'revision having delta stored'
                         )
                     )
                 rawtext = self._chunk(rev)
             else:
                 rawtext = self.rawdata(rev)
 
             newrl.addrawrevision(
                 rawtext, tr, self.linkrev(rev), p1, p2, node, self.flags(rev)
             )
 
         tr.addbackup(self._indexfile, location=b'store')
         if not self._inline:
             tr.addbackup(self._datafile, location=b'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=_(b'data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_(b'index contains %d extra bytes') % di)
 
         version = self._format_version
 
         # The verifier tells us what version revlog we should be.
         if version != state[b'expectedversion']:
             yield revlogproblem(
                 warning=_(b"warning: '%s' uses revlog format %d; expected %d")
                 % (self.display_id, version, state[b'expectedversion'])
             )
 
         state[b'skipread'] = set()
         state[b'safe_renamed'] = 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 "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # 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 flagutil.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(b'skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_(b'unpacked size is %d, %d expected') % (l2, l1),
                         node=node,
                     )
 
             except error.CensoredNodeError:
                 if state[b'erroroncensored']:
                     yield revlogproblem(
                         error=_(b'censored file data'), node=node
                     )
                     state[b'skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_(b'unpacking %s: %s')
                     % (short(node), stringutil.forcebytestr(e)),
                     node=node,
                 )
                 state[b'skipread'].add(node)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         d = {}
 
         if exclusivefiles:
             d[b'exclusivefiles'] = [(self.opener, self._indexfile)]
             if not self._inline:
                 d[b'exclusivefiles'].append((self.opener, self._datafile))
 
         if sharedfiles:
             d[b'sharedfiles'] = []
 
         if revisionscount:
             d[b'revisionscount'] = len(self)
 
         if trackedsize:
             d[b'trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d[b'storedsize'] = sum(
                 self.opener.stat(path).st_size for path in self.files()
             )
 
         return d
 
     def rewrite_sidedata(self, helpers, startrev, endrev):
         if not self.hassidedata:
             return
         # inline are not yet supported because they suffer from an issue when
         # rewriting them (since it's not an append-only operation).
         # See issue6485.
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         # changelog implement some "delayed" writing mechanism that assume that
         # all index data is writen in append mode and is therefor incompatible
         # with the seeked write done in this method. The use of such "delayed"
         # writing will soon be removed for revlog version that support side
         # data, so for now, we only keep this simple assert to highlight the
         # situation.
         delayed = getattr(self, '_delayed', False)
         diverted = getattr(self, '_divert', False)
         if delayed and not diverted:
             msg = "cannot rewrite_sidedata of a delayed revlog"
             raise error.ProgrammingError(msg)
 
         new_entries = []
         # append the new sidedata
         with self._datafp(b'a+') as fp:
             # Maybe this bug still exists, see revlog._writeentry
             fp.seek(0, os.SEEK_END)
             current_offset = fp.tell()
             for rev in range(startrev, endrev + 1):
                 entry = self.index[rev]
                 new_sidedata, flags = sidedatautil.run_sidedata_helpers(
                     store=self,
                     sidedata_helpers=helpers,
                     sidedata={},
                     rev=rev,
                 )
 
                 serialized_sidedata = sidedatautil.serialize_sidedata(
                     new_sidedata
                 )
                 if entry[8] != 0 or entry[9] != 0:
                     # rewriting entries that already have sidedata is not
                     # supported yet, because it introduces garbage data in the
                     # revlog.
                     msg = b"Rewriting existing sidedata is not supported yet"
                     raise error.Abort(msg)
 
                 # Apply (potential) flags to add and to remove after running
                 # the sidedata helpers
                 new_offset_flags = entry[0] | flags[0] & ~flags[1]
                 entry = (new_offset_flags,) + entry[1:8]
                 entry += (current_offset, len(serialized_sidedata))
 
                 fp.write(serialized_sidedata)
                 new_entries.append(entry)
                 current_offset += len(serialized_sidedata)
 
         # rewrite the new index entries
         with self._indexfp(b'r+') as fp:
             fp.seek(startrev * self.index.entry_size)
             for i, e in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, e[8], e[9], e[0])
                 packed = self.index.entry_binary(rev)
                 if rev == 0:
                     header = self._format_flags | self._format_version
                     header = self.index.pack_header(header)
                     packed = header + packed
                 fp.write(packed)

tests/test-lfs.t

@@ -1,1238 +1,1238 b''
 #require no-reposimplestore no-chg
 
   $ hg init requirements
   $ cd requirements
 
 # LFS not loaded by default.
 
   $ hg config extensions
   [1]
 
 # Adding lfs to requires file will auto-load lfs extension.
 
   $ echo lfs >> .hg/requires
   $ hg config extensions
   extensions.lfs=
 
 # But only if there is no config entry for the extension already.
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs=!
   > EOF
 
   $ hg config extensions
   abort: repository requires features unknown to this Mercurial: lfs
   (see https://mercurial-scm.org/wiki/MissingRequirement for more information)
   [255]
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs=
   > EOF
 
   $ hg config extensions
   extensions.lfs=
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs = missing.py
   > EOF
 
   $ hg config extensions
   \*\*\* failed to import extension lfs from missing.py: [Errno *] $ENOENT$: 'missing.py' (glob)
   abort: repository requires features unknown to this Mercurial: lfs
   (see https://mercurial-scm.org/wiki/MissingRequirement for more information)
   [255]
 
   $ cd ..
 
 # Initial setup
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > lfs=
   > [lfs]
   > # Test deprecated config
   > threshold=1000B
   > EOF
 
   $ LONG=AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Prepare server and enable extension
   $ hg init server
   $ hg clone -q server client
   $ cd client
 
 # Commit small file
   $ echo s > smallfile
   $ echo '**.py = LF' > .hgeol
   $ hg --config lfs.track='"size(\">1000B\")"' commit -Aqm "add small file"
   hg: parse error: unsupported file pattern: size(">1000B")
   (paths must be prefixed with "path:")
   [10]
   $ hg --config lfs.track='size(">1000B")' commit -Aqm "add small file"
 
 # Commit large file
   $ echo $LONG > largefile
   $ grep lfs .hg/requires
   [1]
   $ hg commit --traceback -Aqm "add large file"
   $ grep lfs .hg/requires
   lfs
 
 # Ensure metadata is stored
   $ hg debugdata largefile 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:f11e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
   size 1501
   x-is-binary 0
 
 # Check the blobstore is populated
   $ find .hg/store/lfs/objects | sort
   .hg/store/lfs/objects
   .hg/store/lfs/objects/f1
   .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
 
 # Check the blob stored contains the actual contents of the file
   $ cat .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Push changes to the server
 
   $ hg push
   pushing to $TESTTMP/server
   searching for changes
   abort: lfs.url needs to be configured
   [255]
 
   $ cat >> $HGRCPATH << EOF
   > [lfs]
   > url=file:$TESTTMP/dummy-remote/
   > EOF
 
 Push to a local non-lfs repo with the extension enabled will add the
 lfs requirement
 
   $ grep lfs $TESTTMP/server/.hg/requires
   [1]
   $ hg push -v | egrep -v '^(uncompressed| )'
   pushing to $TESTTMP/server
   searching for changes
   lfs: found f11e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b in the local lfs store
   2 changesets found
   adding changesets
   adding manifests
   adding file changes
   calling hook pretxnchangegroup.lfs: hgext.lfs.checkrequireslfs
   added 2 changesets with 3 changes to 3 files
   $ grep lfs $TESTTMP/server/.hg/requires
   lfs
 
 # Unknown URL scheme
 
   $ hg push --config lfs.url=ftp://foobar
   abort: lfs: unknown url scheme: ftp
   [255]
 
   $ cd ../
 
 # Initialize new client (not cloning) and setup extension
   $ hg init client2
   $ cd client2
   $ cat >> .hg/hgrc <<EOF
   > [paths]
   > default = $TESTTMP/server
   > EOF
 
 # Pull from server
 
 Pulling a local lfs repo into a local non-lfs repo with the extension
 enabled adds the lfs requirement
 
   $ grep lfs .hg/requires $TESTTMP/server/.hg/requires
   $TESTTMP/server/.hg/requires:lfs
   $ hg pull default
   pulling from $TESTTMP/server
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 3 changes to 3 files
   new changesets 0ead593177f7:b88141481348
   (run 'hg update' to get a working copy)
   $ grep lfs .hg/requires $TESTTMP/server/.hg/requires
   .hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
 # Check the blobstore is not yet populated
   $ [ -d .hg/store/lfs/objects ]
   [1]
 
 # Update to the last revision containing the large file
   $ hg update
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 # Check the blobstore has been populated on update
   $ find .hg/store/lfs/objects | sort
   .hg/store/lfs/objects
   .hg/store/lfs/objects/f1
   .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
 
 # Check the contents of the file are fetched from blobstore when requested
   $ hg cat -r . largefile
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Check the file has been copied in the working copy
   $ cat largefile
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
   $ cd ..
 
 # Check rename, and switch between large and small files
 
   $ hg init repo3
   $ cd repo3
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > EOF
 
   $ echo LONGER-THAN-TEN-BYTES-WILL-TRIGGER-LFS > large
   $ echo SHORTER > small
   $ hg add . -q
   $ hg commit -m 'commit with lfs content'
 
   $ hg files -r . 'set:added()'
   large
   small
   $ hg files -r . 'set:added() & lfs()'
   large
 
   $ hg mv large l
   $ hg mv small s
   $ hg status 'set:removed()'
   R large
   R small
   $ hg status 'set:removed() & lfs()'
   R large
   $ hg commit -m 'renames'
 
   $ hg cat -r . l -T '{rawdata}\n'
   version https://git-lfs.github.com/spec/v1
   oid sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   size 39
   x-hg-copy large
   x-hg-copyrev 2c531e0992ff3107c511b53cb82a91b6436de8b2
   x-is-binary 0
   
 
   $ hg files -r . 'set:copied()'
   l
   s
   $ hg files -r . 'set:copied() & lfs()'
   l
   $ hg status --change . 'set:removed()'
   R large
   R small
   $ hg status --change . 'set:removed() & lfs()'
   R large
 
   $ echo SHORT > l
   $ echo BECOME-LARGER-FROM-SHORTER > s
   $ hg commit -m 'large to small, small to large'
 
   $ echo 1 >> l
   $ echo 2 >> s
   $ hg commit -m 'random modifications'
 
   $ echo RESTORE-TO-BE-LARGE > l
   $ echo SHORTER > s
   $ hg commit -m 'switch large and small again'
 
 # Test lfs_files template
 
   $ hg log -r 'all()' -T '{rev} {join(lfs_files, ", ")}\n'
   0 large
   1 l, large
   2 s
   3 s
   4 l
 
 # Push and pull the above repo
 
   $ hg --cwd .. init repo4
   $ hg push ../repo4
   pushing to ../repo4
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 10 changes to 4 files
 
   $ hg --cwd .. init repo5
   $ hg --cwd ../repo5 pull ../repo3
   pulling from ../repo3
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 10 changes to 4 files
   new changesets fd47a419c4f7:5adf850972b9
   (run 'hg update' to get a working copy)
 
   $ cd ..
 
 # Test clone
 
   $ hg init repo6
   $ cd repo6
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">30B")
   > EOF
 
   $ echo LARGE-BECAUSE-IT-IS-MORE-THAN-30-BYTES > large
   $ echo SMALL > small
   $ hg commit -Aqm 'create a lfs file' large small
   $ hg debuglfsupload -r 'all()' -v
   lfs: found 8e92251415339ae9b148c8da89ed5ec665905166a1ab11b09dca8fad83344738 in the local lfs store
 
   $ cd ..
 
   $ hg clone repo6 repo7
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd repo7
   $ cat large
   LARGE-BECAUSE-IT-IS-MORE-THAN-30-BYTES
   $ cat small
   SMALL
 
   $ cd ..
 
   $ hg --config extensions.share= share repo7 sharedrepo
   updating working directory
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ grep lfs sharedrepo/.hg/requires
   lfs
 
 # Test rename and status
 
   $ hg init repo8
   $ cd repo8
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > EOF
 
   $ echo THIS-IS-LFS-BECAUSE-10-BYTES > a1
   $ echo SMALL > a2
   $ hg commit -m a -A a1 a2
   $ hg status
   $ hg mv a1 b1
   $ hg mv a2 a1
   $ hg mv b1 a2
   $ hg commit -m b
   $ hg status
   >>> with open('a2', 'wb') as f:
   ...     f.write(b'\1\nSTART-WITH-HG-FILELOG-METADATA') and None
   >>> with open('a1', 'wb') as f:
   ...     f.write(b'\1\nMETA\n') and None
   $ hg commit -m meta
   $ hg status
   $ hg log -T '{rev}: {file_copies} | {file_dels} | {file_adds}\n'
   2:  |  | 
   1: a1 (a2)a2 (a1) |  | 
   0:  |  | a1 a2
 
   $ for n in a1 a2; do
   >   for r in 0 1 2; do
   >     printf '\n%s @ %s\n' $n $r
   >     hg debugdata $n $r
   >   done
   > done
   
   a1 @ 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   
   a1 @ 1
   \x01 (esc)
   copy: a2
   copyrev: 50470ad23cf937b1f4b9f80bfe54df38e65b50d9
   \x01 (esc)
   SMALL
   
   a1 @ 2
   \x01 (esc)
   \x01 (esc)
   \x01 (esc)
   META
   
   a2 @ 0
   SMALL
   
   a2 @ 1
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-hg-copy a1
   x-hg-copyrev be23af27908a582af43e5cda209a5a9b319de8d4
   x-is-binary 0
   
   a2 @ 2
   version https://git-lfs.github.com/spec/v1
   oid sha256:876dadc86a8542f9798048f2c47f51dbf8e4359aed883e8ec80c5db825f0d943
   size 32
   x-is-binary 0
 
 # Verify commit hashes include rename metadata
 
   $ hg log -T '{rev}:{node|short} {desc}\n'
   2:0fae949de7fa meta
   1:9cd6bdffdac0 b
   0:7f96794915f7 a
 
   $ cd ..
 
 # Test bundle
 
   $ hg init repo9
   $ cd repo9
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > [diff]
   > git=1
   > EOF
 
   $ for i in 0 single two three 4; do
   >   echo 'THIS-IS-LFS-'$i > a
   >   hg commit -m a-$i -A a
   > done
 
   $ hg update 2 -q
   $ echo 'THIS-IS-LFS-2-CHILD' > a
   $ hg commit -m branching -q
 
   $ hg bundle --base 1 bundle.hg -v
   lfs: found 5ab7a3739a5feec94a562d070a14f36dba7cad17e5484a4a89eea8e5f3166888 in the local lfs store
   lfs: found a9c7d1cd6ce2b9bbdf46ed9a862845228717b921c089d0d42e3bcaed29eb612e in the local lfs store
   lfs: found f693890c49c409ec33673b71e53f297681f76c1166daf33b2ad7ebf8b1d3237e in the local lfs store
   lfs: found fda198fea753eb66a252e9856915e1f5cddbe41723bd4b695ece2604ad3c9f75 in the local lfs store
   4 changesets found
   uncompressed size of bundle content:
        * (changelog) (glob)
        * (manifests) (glob)
       * a (glob)
   $ hg --config extensions.strip= strip -r 2 --no-backup --force -q
   $ hg -R bundle.hg log -p -T '{rev} {desc}\n' a
   5 branching
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-2-CHILD
   
   4 a-4
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-three
   +THIS-IS-LFS-4
   
   3 a-three
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-three
   
   2 a-two
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-single
   +THIS-IS-LFS-two
   
   1 a-single
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-0
   +THIS-IS-LFS-single
   
   0 a-0
   diff --git a/a b/a
   new file mode 100644
   --- /dev/null
   +++ b/a
   @@ -0,0 +1,1 @@
   +THIS-IS-LFS-0
   
   $ hg bundle -R bundle.hg --base 1 bundle-again.hg -q
   $ hg -R bundle-again.hg log -p -T '{rev} {desc}\n' a
   5 branching
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-2-CHILD
   
   4 a-4
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-three
   +THIS-IS-LFS-4
   
   3 a-three
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-three
   
   2 a-two
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-single
   +THIS-IS-LFS-two
   
   1 a-single
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-0
   +THIS-IS-LFS-single
   
   0 a-0
   diff --git a/a b/a
   new file mode 100644
   --- /dev/null
   +++ b/a
   @@ -0,0 +1,1 @@
   +THIS-IS-LFS-0
   
   $ cd ..
 
 # Test isbinary
 
   $ hg init repo10
   $ cd repo10
   $ cat >> .hg/hgrc << EOF
   > [extensions]
   > lfs=
   > [lfs]
   > track=all()
   > EOF
   $ "$PYTHON" <<'EOF'
   > def write(path, content):
   >     with open(path, 'wb') as f:
   >         f.write(content)
   > write('a', b'\0\0')
   > write('b', b'\1\n')
   > write('c', b'\1\n\0')
   > write('d', b'xx')
   > EOF
   $ hg add a b c d
   $ hg diff --stat
    a |  Bin 
    b |    1 +
    c |  Bin 
    d |    1 +
    4 files changed, 2 insertions(+), 0 deletions(-)
   $ hg commit -m binarytest
   $ cat > $TESTTMP/dumpbinary.py << EOF
   > from mercurial.utils import (
   >     stringutil,
   > )
   > def reposetup(ui, repo):
   >     for n in (b'a', b'b', b'c', b'd'):
   >         ui.write((b'%s: binary=%s\n')
   >                   % (n, stringutil.pprint(repo[b'.'][n].isbinary())))
   > EOF
   $ hg --config extensions.dumpbinary=$TESTTMP/dumpbinary.py id --trace
   a: binary=True
   b: binary=False
   c: binary=True
   d: binary=False
   b55353847f02 tip
 
 Binary blobs don't need to be present to be skipped in filesets.  (And their
 absence doesn't cause an abort.)
 
   $ rm .hg/store/lfs/objects/96/a296d224f285c67bee93c30f8a309157f0daa35dc5b87e410b78630a09cfc7
   $ rm .hg/store/lfs/objects/92/f76135a4baf4faccb8586a60faf830c2bdfce147cefa188aaf4b790bd01b7e
 
   $ hg files --debug -r . 'set:eol("unix")' --config 'experimental.lfs.disableusercache=True'
   lfs: found c04b5bb1a5b2eb3e9cd4805420dba5a9d133da5b7adeeafb5474c4adae9faa80 in the local lfs store
            2   b
   lfs: found 5dde896887f6754c9b15bfe3a441ae4806df2fde94001311e08bf110622e0bbe in the local lfs store
 
   $ hg files --debug -r . 'set:binary()' --config 'experimental.lfs.disableusercache=True'
            2   a
            3   c
 
   $ cd ..
 
 # Test fctx.cmp fastpath - diff without LFS blobs
 
   $ hg init repo12
   $ cd repo12
   $ cat >> .hg/hgrc <<EOF
   > [lfs]
   > threshold=1
   > EOF
   $ cat > ../patch.diff <<EOF
   > # HG changeset patch
   > 2
   > 
   > diff --git a/a b/a
   > old mode 100644
   > new mode 100755
   > EOF
 
   $ for i in 1 2 3; do
   >     cp ../repo10/a a
   >     if [ $i = 3 ]; then
   >         # make a content-only change
   >         hg import -q --bypass ../patch.diff
   >         hg update -q
   >         rm ../patch.diff
   >     else
   >         echo $i >> a
   >         hg commit -m $i -A a
   >     fi
   > done
   $ [ -d .hg/store/lfs/objects ]
 
   $ cd ..
 
   $ hg clone repo12 repo13 --noupdate
   $ cd repo13
   $ hg log --removed -p a -T '{desc}\n' --config diff.nobinary=1 --git
   2
   diff --git a/a b/a
   old mode 100644
   new mode 100755
   
   2
   diff --git a/a b/a
   Binary file a has changed
   
   1
   diff --git a/a b/a
   new file mode 100644
   Binary file a has changed
   
   $ [ -d .hg/store/lfs/objects ]
   [1]
 
   $ cd ..
 
 # Test filter
 
   $ hg init repo11
   $ cd repo11
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=(**.a & size(">5B")) | (**.b & !size(">5B"))
   >      | (**.c & "path:d" & !"path:d/c.c") | size(">10B")
   > EOF
 
   $ mkdir a
   $ echo aaaaaa > a/1.a
   $ echo a > a/2.a
   $ echo aaaaaa > 1.b
   $ echo a > 2.b
   $ echo a > 1.c
   $ mkdir d
   $ echo a > d/c.c
   $ echo a > d/d.c
   $ echo aaaaaaaaaaaa > x
   $ hg add . -q
   $ hg commit -m files
 
   $ for p in a/1.a a/2.a 1.b 2.b 1.c d/c.c d/d.c x; do
   >   if hg debugdata $p 0 2>&1 | grep git-lfs >/dev/null; then
   >     echo "${p}: is lfs"
   >   else
   >     echo "${p}: not lfs"
   >   fi
   > done
   a/1.a: is lfs
   a/2.a: not lfs
   1.b: not lfs
   2.b: is lfs
   1.c: not lfs
   d/c.c: not lfs
   d/d.c: is lfs
   x: is lfs
 
   $ cd ..
 
 # Verify the repos
 
   $ cat > $TESTTMP/dumpflog.py << EOF
   > # print raw revision sizes, flags, and hashes for certain files
   > import hashlib
   > from mercurial.node import short
   > from mercurial import (
   >     pycompat,
   >     revlog,
   > )
   > from mercurial.utils import (
   >     procutil,
   >     stringutil,
   > )
   > def hash(rawtext):
   >     h = hashlib.sha512()
   >     h.update(rawtext)
   >     return pycompat.sysbytes(h.hexdigest()[:4])
   > def reposetup(ui, repo):
   >     # these 2 files are interesting
   >     for name in [b'l', b's']:
   >         fl = repo.file(name)
   >         if len(fl) == 0:
   >             continue
   >         sizes = [fl._revlog.rawsize(i) for i in fl]
   >         texts = [fl.rawdata(i) for i in fl]
   >         flags = [int(fl._revlog.flags(i)) for i in fl]
   >         hashes = [hash(t) for t in texts]
   >         procutil.stdout.write(b'  %s: rawsizes=%r flags=%r hashes=%s\n'
   >                               % (name, sizes, flags, stringutil.pprint(hashes)))
   > EOF
 
   $ for i in client client2 server repo3 repo4 repo5 repo6 repo7 repo8 repo9 \
   >          repo10; do
   >   echo 'repo:' $i
   >   hg --cwd $i verify --config extensions.dumpflog=$TESTTMP/dumpflog.py -q
   > done
   repo: client
   repo: client2
   repo: server
   repo: repo3
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo4
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo5
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo6
   repo: repo7
   repo: repo8
   repo: repo9
   repo: repo10
 
 repo13 doesn't have any cached lfs files and its source never pushed its
 files.  Therefore, the files don't exist in the remote store.  Use the files in
 the user cache.
 
   $ test -d $TESTTMP/repo13/.hg/store/lfs/objects
   [1]
 
   $ hg --config extensions.share= share repo13 repo14
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R repo14 -q verify
 
   $ hg clone repo13 repo15
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R repo15 -q verify
 
 If the source repo doesn't have the blob (maybe it was pulled or cloned with
 --noupdate), the blob is still accessible via the global cache to send to the
 remote store.
 
   $ rm -rf $TESTTMP/repo15/.hg/store/lfs
   $ hg init repo16
   $ hg -R repo15 push repo16
   pushing to repo16
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 2 changes to 1 files
   $ hg -R repo15 -q verify
 
 Test damaged file scenarios.  (This also damages the usercache because of the
 hardlinks.)
 
   $ echo 'damage' >> repo5/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
 
 Repo with damaged lfs objects in any revision will fail verification.
 
   $ hg -R repo5 verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
-   l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
-   large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
+   l@1: unpacking 46a2f24864bc: integrity check failed on data/l:0
+   large@0: unpacking 2c531e0992ff: integrity check failed on data/large:0
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
 Updates work after cloning a damaged repo, if the damaged lfs objects aren't in
 the update destination.  Those objects won't be added to the new repo's store
 because they aren't accessed.
 
   $ hg clone -v repo5 fromcorrupt
   updating to branch default
   resolving manifests
   getting l
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the usercache
   getting s
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ test -f fromcorrupt/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   [1]
 
 Verify will not try to download lfs blobs, if told not to process lfs content.
 The extension makes sure that the filelog.renamed() path is taken on a missing
 blob, and the output shows that it isn't fetched.
 
   $ cat > $TESTTMP/lfsrename.py <<EOF
   > import sys
   > 
   > from mercurial import (
   >     exthelper,
   >     pycompat,
   > )
   > 
   > from hgext.lfs import (
   >     pointer,
   >     wrapper,
   > )
   > 
   > eh = exthelper.exthelper()
   > uisetup = eh.finaluisetup
   > 
   > @eh.wrapfunction(wrapper, b'filelogrenamed')
   > def filelogrenamed(orig, orig1, self, node):
   >     ret = orig(orig1, self, node)
   >     if wrapper._islfs(self._revlog, node) and ret:
   >         rawtext = self._revlog.rawdata(node)
   >         metadata = pointer.deserialize(rawtext)
   >         print('lfs blob %s renamed %s -> %s'
   >               % (pycompat.sysstr(metadata[b'oid']),
   >                  pycompat.sysstr(ret[0]),
   >                  pycompat.fsdecode(self._revlog.filename)))
   >         sys.stdout.flush()
   >     return ret
   > EOF
 
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v --no-lfs \
   >                   --config extensions.x=$TESTTMP/lfsrename.py
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs blob sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e renamed large -> l
   checked 5 changesets with 10 changes to 4 files
 
 Verify will not try to download lfs blobs, if told not to by the config option
 
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v \
   >                   --config verify.skipflags=8192 \
   >                   --config extensions.x=$TESTTMP/lfsrename.py
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs blob sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e renamed large -> l
   checked 5 changesets with 10 changes to 4 files
 
 Verify will copy/link all lfs objects into the local store that aren't already
 present.  Bypass the corrupted usercache to show that verify works when fed by
 the (uncorrupted) remote store.
 
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: adding 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e to the usercache
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: adding 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 to the usercache
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: adding b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c to the usercache
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
 
 Verify will not copy/link a corrupted file from the usercache into the local
 store, and poison it.  (The verify with a good remote now works.)
 
   $ rm -r fromcorrupt/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   $ hg -R fromcorrupt verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
-   l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
+   l@1: unpacking 46a2f24864bc: integrity check failed on data/l:0
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
-   large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
+   large@0: unpacking 2c531e0992ff: integrity check failed on data/large:0
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the usercache
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
 
 Damaging a file required by the update destination fails the update.
 
   $ echo 'damage' >> $TESTTMP/dummy-remote/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ hg --config lfs.usercache=emptycache clone -v repo5 fromcorrupt2
   updating to branch default
   resolving manifests
   abort: corrupt remote lfs object: 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [255]
 
 A corrupted lfs blob is not transferred from a file://remotestore to the
 usercache or local store.
 
   $ test -f emptycache/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [1]
   $ test -f fromcorrupt2/.hg/store/lfs/objects/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [1]
 
   $ hg -R fromcorrupt2 verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
-   l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
-   large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
+   l@1: unpacking 46a2f24864bc: integrity check failed on data/l:0
+   large@0: unpacking 2c531e0992ff: integrity check failed on data/large:0
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
 Corrupt local files are not sent upstream.  (The alternate dummy remote
 avoids the corrupt lfs object in the original remote.)
 
   $ mkdir $TESTTMP/dummy-remote2
   $ hg init dest
   $ hg -R fromcorrupt2 --config lfs.url=file:///$TESTTMP/dummy-remote2 push -v dest
   pushing to dest
   searching for changes
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   abort: detected corrupt lfs object: 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   (run hg verify)
   [255]
 
   $ hg -R fromcorrupt2 --config lfs.url=file:///$TESTTMP/dummy-remote2 verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
-   l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
+   l@1: unpacking 46a2f24864bc: integrity check failed on data/l:0
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
-   large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
+   large@0: unpacking 2c531e0992ff: integrity check failed on data/large:0
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
   $ cat $TESTTMP/dummy-remote2/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b | $TESTDIR/f --sha256
   sha256=22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ cat fromcorrupt2/.hg/store/lfs/objects/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b | $TESTDIR/f --sha256
   sha256=22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ test -f $TESTTMP/dummy-remote2/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   [1]
 
 Accessing a corrupt file will complain
 
   $ hg --cwd fromcorrupt2 cat -r 0 large
-  abort: integrity check failed on data/large.i:0
+  abort: integrity check failed on data/large:0
   [50]
 
 lfs -> normal -> lfs round trip conversions are possible.  The 'none()'
 predicate on the command line will override whatever is configured globally and
 locally, and ensures everything converts to a regular file.  For lfs -> normal,
 there's no 'lfs' destination repo requirement.  For normal -> lfs, there is.
 
   $ hg --config extensions.convert= --config 'lfs.track=none()' \
   >    convert repo8 convert_normal
   initializing destination convert_normal repository
   scanning source...
   sorting...
   converting...
   2 a
   1 b
   0 meta
   $ grep 'lfs' convert_normal/.hg/requires
   [1]
   $ hg --cwd convert_normal cat a1 -r 0 -T '{rawdata}'
   THIS-IS-LFS-BECAUSE-10-BYTES
 
   $ hg --config extensions.convert= --config lfs.threshold=10B \
   >    convert convert_normal convert_lfs
   initializing destination convert_lfs repository
   scanning source...
   sorting...
   converting...
   2 a
   1 b
   0 meta
 
   $ hg --cwd convert_lfs cat -r 0 a1 -T '{rawdata}'
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   $ hg --cwd convert_lfs debugdata a1 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   $ hg --cwd convert_lfs log -r 0 -T "{lfs_files % '{lfspointer % '{key}={value}\n'}'}"
   version=https://git-lfs.github.com/spec/v1
   oid=sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size=29
   x-is-binary=0
   $ hg --cwd convert_lfs log -r 0 \
   >    -T '{lfs_files % "{get(lfspointer, "oid")}\n"}{lfs_files % "{lfspointer.oid}\n"}'
   sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   $ hg --cwd convert_lfs log -r 0 -T '{lfs_files % "{lfspointer}\n"}'
   version=https://git-lfs.github.com/spec/v1 oid=sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024 size=29 x-is-binary=0
   $ hg --cwd convert_lfs \
   >     log -r 'all()' -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}'
   0: a1: 5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   1: a2: 5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   2: a2: 876dadc86a8542f9798048f2c47f51dbf8e4359aed883e8ec80c5db825f0d943
 
   $ grep 'lfs' convert_lfs/.hg/requires
   lfs
 
 The hashes in all stages of the conversion are unchanged.
 
   $ hg -R repo8 log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
   $ hg -R convert_normal log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
   $ hg -R convert_lfs log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
 
 This convert is trickier, because it contains deleted files (via `hg mv`)
 
   $ hg --config extensions.convert= --config lfs.threshold=1000M \
   >    convert repo3 convert_normal2
   initializing destination convert_normal2 repository
   scanning source...
   sorting...
   converting...
   4 commit with lfs content
   3 renames
   2 large to small, small to large
   1 random modifications
   0 switch large and small again
   $ grep 'lfs' convert_normal2/.hg/requires
   [1]
   $ hg --cwd convert_normal2 debugdata large 0
   LONGER-THAN-TEN-BYTES-WILL-TRIGGER-LFS
 
   $ hg --config extensions.convert= --config lfs.threshold=10B \
   >    convert convert_normal2 convert_lfs2
   initializing destination convert_lfs2 repository
   scanning source...
   sorting...
   converting...
   4 commit with lfs content
   3 renames
   2 large to small, small to large
   1 random modifications
   0 switch large and small again
   $ grep 'lfs' convert_lfs2/.hg/requires
   lfs
   $ hg --cwd convert_lfs2 debugdata large 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   size 39
   x-is-binary 0
 
 Committing deleted files works:
 
   $ hg init $TESTTMP/repo-del
   $ cd $TESTTMP/repo-del
   $ echo 1 > A
   $ hg commit -m 'add A' -A A
   $ hg rm A
   $ hg commit -m 'rm A'
 
 Bad .hglfs files will block the commit with a useful message
 
   $ cat > .hglfs << EOF
   > [track]
   > **.test = size(">5B")
   > bad file ... no commit
   > EOF
 
   $ echo x > file.txt
   $ hg ci -Aqm 'should fail'
   config error at .hglfs:3: bad file ... no commit
   [30]
 
   $ cat > .hglfs << EOF
   > [track]
   > **.test = size(">5B")
   > ** = nonexistent()
   > EOF
 
   $ hg ci -Aqm 'should fail'
   abort: parse error in .hglfs: unknown identifier: nonexistent
   [255]
 
 '**' works out to mean all files.
 
   $ cat > .hglfs << EOF
   > [track]
   > path:.hglfs = none()
   > **.test = size(">5B")
   > **.exclude = none()
   > ** = size(">10B")
   > EOF
 
 The LFS policy takes effect without tracking the .hglfs file
 
   $ echo 'largefile' > lfs.test
   $ echo '012345678901234567890' > nolfs.exclude
   $ echo '01234567890123456' > lfs.catchall
   $ hg add *
   $ hg ci -qm 'before add .hglfs'
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   2: lfs.catchall: d4ec46c2869ba22eceb42a729377432052d9dd75d82fc40390ebaadecee87ee9
   lfs.test: 5489e6ced8c36a7b267292bde9fd5242a5f80a7482e8f23fa0477393dfaa4d6c
   
 The .hglfs file works when tracked
 
   $ echo 'largefile2' > lfs.test
   $ echo '012345678901234567890a' > nolfs.exclude
   $ echo '01234567890123456a' > lfs.catchall
   $ hg ci -Aqm 'after adding .hglfs'
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   3: lfs.catchall: 31f43b9c62b540126b0ad5884dc013d21a61c9329b77de1fceeae2fc58511573
   lfs.test: 8acd23467967bc7b8cc5a280056589b0ba0b17ff21dbd88a7b6474d6290378a6
   
 The LFS policy stops when the .hglfs is gone
 
   $ mv .hglfs .hglfs_
   $ echo 'largefile3' > lfs.test
   $ echo '012345678901234567890abc' > nolfs.exclude
   $ echo '01234567890123456abc' > lfs.catchall
   $ hg ci -qm 'file test' -X .hglfs
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   4: 
 
   $ mv .hglfs_ .hglfs
   $ echo '012345678901234567890abc' > lfs.test
   $ hg ci -m 'back to lfs'
   $ hg rm lfs.test
   $ hg ci -qm 'remove lfs'
 
 {lfs_files} will list deleted files too
 
   $ hg log -T "{lfs_files % '{rev} {file}: {lfspointer.oid}\n'}"
   6 lfs.test: 
   5 lfs.test: sha256:43f8f41171b6f62a6b61ba4ce98a8a6c1649240a47ebafd43120aa215ac9e7f6
   3 lfs.catchall: sha256:31f43b9c62b540126b0ad5884dc013d21a61c9329b77de1fceeae2fc58511573
   3 lfs.test: sha256:8acd23467967bc7b8cc5a280056589b0ba0b17ff21dbd88a7b6474d6290378a6
   2 lfs.catchall: sha256:d4ec46c2869ba22eceb42a729377432052d9dd75d82fc40390ebaadecee87ee9
   2 lfs.test: sha256:5489e6ced8c36a7b267292bde9fd5242a5f80a7482e8f23fa0477393dfaa4d6c
 
   $ hg log -r 'file("set:lfs()")' -T '{rev} {join(lfs_files, ", ")}\n'
   2 lfs.catchall, lfs.test
   3 lfs.catchall, lfs.test
   5 lfs.test
   6 lfs.test
 
   $ cd ..
 
 Unbundling adds a requirement to a non-lfs repo, if necessary.
 
   $ hg bundle -R $TESTTMP/repo-del -qr 0 --base null nolfs.hg
   $ hg bundle -R convert_lfs2 -qr tip --base null lfs.hg
   $ hg init unbundle
   $ hg pull -R unbundle -q nolfs.hg
   $ grep lfs unbundle/.hg/requires
   [1]
   $ hg pull -R unbundle -q lfs.hg
   $ grep lfs unbundle/.hg/requires
   lfs
 
   $ hg init no_lfs
   $ cat >> no_lfs/.hg/hgrc <<EOF
   > [experimental]
   > changegroup3 = True
   > [extensions]
   > lfs=!
   > EOF
   $ cp -R no_lfs no_lfs2
 
 Pushing from a local lfs repo to a local repo without an lfs requirement and
 with lfs disabled, fails.
 
   $ hg push -R convert_lfs2 no_lfs
   pushing to no_lfs
   abort: required features are not supported in the destination: lfs
   [255]
   $ grep lfs no_lfs/.hg/requires
   [1]
 
 Pulling from a local lfs repo to a local repo without an lfs requirement and
 with lfs disabled, fails.
 
   $ hg pull -R no_lfs2 convert_lfs2
   pulling from convert_lfs2
   abort: required features are not supported in the destination: lfs
   [255]
   $ grep lfs no_lfs2/.hg/requires
   [1]

tests/test-verify.t

@@ -1,365 +1,365 b''
 #require reporevlogstore
 
 prepare repo
 
   $ hg init a
   $ cd a
   $ echo "some text" > FOO.txt
   $ echo "another text" > bar.txt
   $ echo "more text" > QUICK.txt
   $ hg add
   adding FOO.txt
   adding QUICK.txt
   adding bar.txt
   $ hg ci -mtest1
 
 verify
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 3 changes to 3 files
 
 verify with journal
 
   $ touch .hg/store/journal
   $ hg verify
   abandoned transaction found - run hg recover
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 3 changes to 3 files
   $ rm .hg/store/journal
 
 introduce some bugs in repo
 
   $ cd .hg/store/data
   $ mv _f_o_o.txt.i X_f_o_o.txt.i
   $ mv bar.txt.i xbar.txt.i
   $ rm _q_u_i_c_k.txt.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    warning: revlog 'data/FOO.txt.i' not in fncache!
    0: empty or missing FOO.txt
    FOO.txt@0: manifest refers to unknown revision f62022d3d590
    warning: revlog 'data/QUICK.txt.i' not in fncache!
    0: empty or missing QUICK.txt
    QUICK.txt@0: manifest refers to unknown revision 88b857db8eba
    warning: revlog 'data/bar.txt.i' not in fncache!
    0: empty or missing bar.txt
    bar.txt@0: manifest refers to unknown revision 256559129457
   checked 1 changesets with 0 changes to 3 files
   3 warnings encountered!
   hint: run "hg debugrebuildfncache" to recover from corrupt fncache
   6 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
   $ cd ../../..
   $ cd ..
 
 Set up a repo for testing missing revlog entries
 
   $ hg init missing-entries
   $ cd missing-entries
   $ echo 0 > file
   $ hg ci -Aqm0
   $ cp -R .hg/store .hg/store-partial
   $ echo 1 > file
   $ hg ci -Aqm1
   $ cp -R .hg/store .hg/store-full
 
 Entire changelog missing
 
   $ rm .hg/store/00changelog.*
   $ hg verify -q
    0: empty or missing changelog
    manifest@0: d0b6632564d4 not in changesets
    manifest@1: 941fc4534185 not in changesets
   3 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Entire manifest log missing
 
   $ rm .hg/store/00manifest.*
   $ hg verify -q
    0: empty or missing manifest
   1 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Entire filelog missing
 
   $ rm .hg/store/data/file.*
   $ hg verify -q
    warning: revlog 'data/file.i' not in fncache!
    0: empty or missing file
    file@0: manifest refers to unknown revision 362fef284ce2
    file@1: manifest refers to unknown revision c10f2164107d
   1 warnings encountered!
   hint: run "hg debugrebuildfncache" to recover from corrupt fncache
   3 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Entire changelog and manifest log missing
 
   $ rm .hg/store/00changelog.*
   $ rm .hg/store/00manifest.*
   $ hg verify -q
   warning: orphan data file 'data/file.i'
   1 warnings encountered!
   $ cp -R .hg/store-full/. .hg/store
 
 Entire changelog and filelog missing
 
   $ rm .hg/store/00changelog.*
   $ rm .hg/store/data/file.*
   $ hg verify -q
    0: empty or missing changelog
    manifest@0: d0b6632564d4 not in changesets
    manifest@1: 941fc4534185 not in changesets
    warning: revlog 'data/file.i' not in fncache!
    ?: empty or missing file
    file@0: manifest refers to unknown revision 362fef284ce2
    file@1: manifest refers to unknown revision c10f2164107d
   1 warnings encountered!
   hint: run "hg debugrebuildfncache" to recover from corrupt fncache
   6 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Entire manifest log and filelog missing
 
   $ rm .hg/store/00manifest.*
   $ rm .hg/store/data/file.*
   $ hg verify -q
    0: empty or missing manifest
    warning: revlog 'data/file.i' not in fncache!
    0: empty or missing file
   1 warnings encountered!
   hint: run "hg debugrebuildfncache" to recover from corrupt fncache
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Changelog missing entry
 
   $ cp -f .hg/store-partial/00changelog.* .hg/store
   $ hg verify -q
    manifest@?: rev 1 points to nonexistent changeset 1
    manifest@?: 941fc4534185 not in changesets
    file@?: rev 1 points to nonexistent changeset 1
    (expected 0)
   1 warnings encountered!
   3 integrity errors encountered!
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Manifest log missing entry
 
   $ cp -f .hg/store-partial/00manifest.* .hg/store
   $ hg verify -q
    manifest@1: changeset refers to unknown revision 941fc4534185
    file@1: c10f2164107d not in manifests
   2 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Filelog missing entry
 
   $ cp -f .hg/store-partial/data/file.* .hg/store/data
   $ hg verify -q
    file@1: manifest refers to unknown revision c10f2164107d
   1 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Changelog and manifest log missing entry
 
   $ cp -f .hg/store-partial/00changelog.* .hg/store
   $ cp -f .hg/store-partial/00manifest.* .hg/store
   $ hg verify -q
    file@?: rev 1 points to nonexistent changeset 1
    (expected 0)
    file@?: c10f2164107d not in manifests
   1 warnings encountered!
   2 integrity errors encountered!
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Changelog and filelog missing entry
 
   $ cp -f .hg/store-partial/00changelog.* .hg/store
   $ cp -f .hg/store-partial/data/file.* .hg/store/data
   $ hg verify -q
    manifest@?: rev 1 points to nonexistent changeset 1
    manifest@?: 941fc4534185 not in changesets
    file@?: manifest refers to unknown revision c10f2164107d
   3 integrity errors encountered!
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Manifest and filelog missing entry
 
   $ cp -f .hg/store-partial/00manifest.* .hg/store
   $ cp -f .hg/store-partial/data/file.* .hg/store/data
   $ hg verify -q
    manifest@1: changeset refers to unknown revision 941fc4534185
   1 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Corrupt changelog base node to cause failure to read revision
 
   $ printf abcd | dd conv=notrunc of=.hg/store/00changelog.i bs=1 seek=16 \
   >   2> /dev/null
   $ hg verify -q
    0: unpacking changeset 08b1860757c2: * (glob)
    manifest@?: rev 0 points to unexpected changeset 0
    manifest@?: d0b6632564d4 not in changesets
    file@?: rev 0 points to unexpected changeset 0
    (expected 1)
   1 warnings encountered!
   4 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Corrupt manifest log base node to cause failure to read revision
 
   $ printf abcd | dd conv=notrunc of=.hg/store/00manifest.i bs=1 seek=16 \
   >   2> /dev/null
   $ hg verify -q
    manifest@0: reading delta d0b6632564d4: * (glob)
    file@0: 362fef284ce2 not in manifests
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
 Corrupt filelog base node to cause failure to read revision
 
   $ printf abcd | dd conv=notrunc of=.hg/store/data/file.i bs=1 seek=16 \
   >   2> /dev/null
   $ hg verify -q
    file@0: unpacking 362fef284ce2: * (glob)
   1 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -R .hg/store-full/. .hg/store
 
   $ cd ..
 
 test changelog without a manifest
 
   $ hg init b
   $ cd b
   $ hg branch foo
   marked working directory as branch foo
   (branches are permanent and global, did you want a bookmark?)
   $ hg ci -m branchfoo
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 0 changes to 0 files
 
 test revlog corruption
 
   $ touch a
   $ hg add a
   $ hg ci -m a
 
   $ echo 'corrupted' > b
   $ dd if=.hg/store/data/a.i of=start bs=1 count=20 2>/dev/null
   $ cat start b > .hg/store/data/a.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    a@1: broken revlog! (index data/a is corrupted)
   warning: orphan data file 'data/a.i'
   checked 2 changesets with 0 changes to 1 files
   1 warnings encountered!
   1 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
 
   $ cd ..
 
 test revlog format 0
 
   $ revlog-formatv0.py
   $ cd formatv0
   $ hg verify
   repository uses revlog format 0
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 1 changes to 1 files
   $ cd ..
 
 test flag processor and skipflags
 
   $ hg init skipflags
   $ cd skipflags
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > flagprocessor=$RUNTESTDIR/flagprocessorext.py
   > EOF
   $ echo '[BASE64]content' > base64
   $ hg commit -Aqm 'flag processor content' base64
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 1 changes to 1 files
 
   $ cat >> $TESTTMP/break-base64.py <<EOF
   > from __future__ import absolute_import
   > import base64
   > base64.b64decode=lambda x: x
   > EOF
   $ cat >> .hg/hgrc <<EOF
   > breakbase64=$TESTTMP/break-base64.py
   > EOF
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
-   base64@0: unpacking 794cee7777cb: integrity check failed on data/base64.i:0
+   base64@0: unpacking 794cee7777cb: integrity check failed on data/base64:0
   checked 1 changesets with 1 changes to 1 files
   1 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ hg verify --config verify.skipflags=2147483647
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 1 changes to 1 files