revlog: remove legacy usage of `_checkambig`

All core code is now getting the setting from the DataConfig object.

mercurial/revlog.py

@@ -1,3714 +1,3718 b''
 # revlog.py - storage back-end for mercurial
 # coding: utf8
 #
 # 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.
 """
 
 
 import binascii
 import collections
 import contextlib
 import io
 import os
 import struct
 import weakref
 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 .revlogutils.constants import (
     ALL_KINDS,
     CHANGELOGV2,
     COMP_MODE_DEFAULT,
     COMP_MODE_INLINE,
     COMP_MODE_PLAIN,
     DELTA_BASE_REUSE_NO,
     DELTA_BASE_REUSE_TRY,
     ENTRY_RANK,
     FEATURES_BY_VERSION,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     KIND_CHANGELOG,
     KIND_FILELOG,
     RANK_UNKNOWN,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
     SUPPORTED_FLAGS,
 )
 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,
     revlogutils,
     templatefilters,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     docket as docketutil,
     flagutil,
     nodemap as nodemaputil,
     randomaccessfile,
     revlogv0,
     rewrite,
     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
 CHANGELOGV2
 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 inline data embedded into a revlog
 _maxinline = 131072
 
 # 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 _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 hasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta:
     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:
     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, format=REVLOGV2)
     return index, cache
 
 
 def parse_index_cl_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, format=CHANGELOGV2)
     return index, cache
 
 
 if hasattr(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
 
 FILE_TOO_SHORT_MSG = _(
     b'cannot read from revlog %s;'
     b'  expected %d bytes from offset %d, data size is %d'
 )
 
 hexdigits = b'0123456789abcdefABCDEF'
 
 
 class _Config:
     def copy(self):
         return self.__class__(**self.__dict__)
 
 
 @attr.s()
 class FeatureConfig(_Config):
     """Hold configuration values about the available revlog features"""
 
     # the default compression engine
     compression_engine = attr.ib(default=b'zlib')
     # compression engines options
     compression_engine_options = attr.ib(default=attr.Factory(dict))
 
     # can we use censor on this revlog
     censorable = attr.ib(default=False)
     # does this revlog use the "side data" feature
     has_side_data = attr.ib(default=False)
     # might remove rank configuration once the computation has no impact
     compute_rank = attr.ib(default=False)
     # parent order is supposed to be semantically irrelevant, so we
     # normally resort parents to ensure that the first parent is non-null,
     # if there is a non-null parent at all.
     # filelog abuses the parent order as flag to mark some instances of
     # meta-encoded files, so allow it to disable this behavior.
     canonical_parent_order = attr.ib(default=False)
     # can ellipsis commit be used
     enable_ellipsis = attr.ib(default=False)
 
     def copy(self):
         new = super().copy()
         new.compression_engine_options = self.compression_engine_options.copy()
         return new
 
 
 @attr.s()
 class DataConfig(_Config):
     """Hold configuration value about how the revlog data are read"""
 
     # should we try to open the "pending" version of the revlog
     try_pending = attr.ib(default=False)
     # should we try to open the "splitted" version of the revlog
     try_split = attr.ib(default=False)
     #  When True, indexfile should be opened with checkambig=True at writing,
     #  to avoid file stat ambiguity.
     check_ambig = attr.ib(default=False)
 
     # If true, use mmap instead of reading to deal with large index
     mmap_large_index = attr.ib(default=False)
     # how much data is large
     mmap_index_threshold = attr.ib(default=None)
     # How much data to read and cache into the raw revlog data cache.
     chunk_cache_size = attr.ib(default=65536)
 
     # Allow sparse reading of the revlog data
     with_sparse_read = attr.ib(default=False)
     # minimal density of a sparse read chunk
     sr_density_threshold = attr.ib(default=0.50)
     # minimal size of data we skip when performing sparse read
     sr_min_gap_size = attr.ib(default=262144)
 
     # are delta encoded against arbitrary bases.
     generaldelta = attr.ib(default=False)
 
 
 @attr.s()
 class DeltaConfig(_Config):
     """Hold configuration value about how new delta are computed
 
     Some attributes are duplicated from DataConfig to help havign each object
     self contained.
     """
 
     # can delta be encoded against arbitrary bases.
     general_delta = attr.ib(default=False)
     # Allow sparse writing of the revlog data
     sparse_revlog = attr.ib(default=False)
     # maximum length of a delta chain
     max_chain_len = attr.ib(default=None)
     # Maximum distance between delta chain base start and end
     max_deltachain_span = attr.ib(default=-1)
     # If `upper_bound_comp` is not None, this is the expected maximal gain from
     # compression for the data content.
     upper_bound_comp = attr.ib(default=None)
     # Should we try a delta against both parent
     delta_both_parents = attr.ib(default=True)
     # Test delta base candidate group by chunk of this maximal size.
     candidate_group_chunk_size = attr.ib(default=0)
     # Should we display debug information about delta computation
     debug_delta = attr.ib(default=False)
     # trust incoming delta by default
     lazy_delta = attr.ib(default=True)
     # trust the base of incoming delta by default
     lazy_delta_base = attr.ib(default=False)
 
 
 class revlog:
     """
     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).
 
     See mercurial/revlogutils/contants.py for details about the content of an
     index entry.
     """
 
     _flagserrorclass = error.RevlogError
 
     @staticmethod
     def is_inline_index(header_bytes):
         """Determine if a revlog is inline from the initial bytes of the index"""
         header = INDEX_HEADER.unpack(header_bytes)[0]
 
         _format_flags = header & ~0xFFFF
         _format_version = header & 0xFFFF
 
         features = FEATURES_BY_VERSION[_format_version]
         return features[b'inline'](_format_flags)
 
     def __init__(
         self,
         opener,
         target,
         radix,
         postfix=None,  # only exist for `tmpcensored` now
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
         trypending=False,
         try_split=False,
         canonical_parent_order=True,
     ):
         """
         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
 
         self._docket_file = None
         self._indexfile = None
         self._datafile = None
         self._sidedatafile = None
         self._nodemap_file = None
         self.postfix = postfix
         self._trypending = trypending
         self._try_split = try_split
         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
         if b'feature-config' in self.opener.options:
             self.feature_config = self.opener.options[b'feature-config'].copy()
         else:
             self.feature_config = FeatureConfig()
         self.feature_config.censorable = censorable
         self.feature_config.canonical_parent_order = canonical_parent_order
         if b'data-config' in self.opener.options:
             self.data_config = self.opener.options[b'data-config'].copy()
         else:
             self.data_config = DataConfig()
         self.data_config.check_ambig = checkambig
         self.data_config.mmap_large_index = mmaplargeindex
         if b'delta-config' in self.opener.options:
             self.delta_config = self.opener.options[b'delta-config'].copy()
         else:
             self.delta_config = DeltaConfig()
 
         # 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'')
 
         self.index = None
         self._docket = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
 
         # other optionnals features
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
 
         # 3-tuple of file handles being used for active writing.
         self._writinghandles = None
         # prevent nesting of addgroup
         self._adding_group = None
 
         self._loadindex()
 
         self._concurrencychecker = concurrencychecker
 
     @property
     def _generaldelta(self):
         """temporary compatibility proxy"""
         return self.delta_config.general_delta
 
     @property
     def _checkambig(self):
         """temporary compatibility proxy"""
         return self.data_config.check_ambig
 
     @property
     def _mmaplargeindex(self):
         """temporary compatibility proxy"""
         return self.data_config.mmap_large_index
 
     @property
     def _censorable(self):
         """temporary compatibility proxy"""
         return self.feature_config.censorable
 
     @property
     def _chunkcachesize(self):
         """temporary compatibility proxy"""
         return self.data_config.chunk_cache_size
 
     @property
     def _maxchainlen(self):
         """temporary compatibility proxy"""
         return self.delta_config.max_chain_len
 
     @property
     def _deltabothparents(self):
         """temporary compatibility proxy"""
         return self.delta_config.delta_both_parents
 
     @property
     def _candidate_group_chunk_size(self):
         """temporary compatibility proxy"""
         return self.delta_config.candidate_group_chunk_size
 
     @property
     def _debug_delta(self):
         """temporary compatibility proxy"""
         return self.delta_config.debug_delta
 
     @property
     def _compengine(self):
         """temporary compatibility proxy"""
         return self.feature_config.compression_engine
 
     @property
     def _compengineopts(self):
         """temporary compatibility proxy"""
         return self.feature_config.compression_engine_options
 
     @property
     def _maxdeltachainspan(self):
         """temporary compatibility proxy"""
         return self.delta_config.max_deltachain_span
 
     @property
     def _withsparseread(self):
         """temporary compatibility proxy"""
         return self.data_config.with_sparse_read
 
     @property
     def _sparserevlog(self):
         """temporary compatibility proxy"""
         return self.delta_config.sparse_revlog
 
     @property
     def hassidedata(self):
         """temporary compatibility proxy"""
         return self.feature_config.has_side_data
 
     @property
     def _srdensitythreshold(self):
         """temporary compatibility proxy"""
         return self.data_config.sr_density_threshold
 
     @property
     def _srmingapsize(self):
         """temporary compatibility proxy"""
         return self.data_config.sr_min_gap_size
 
     @property
     def _compute_rank(self):
         """temporary compatibility proxy"""
         return self.feature_config.compute_rank
 
     @property
     def canonical_parent_order(self):
         """temporary compatibility proxy"""
         return self.feature_config.canonical_parent_order
 
     @property
     def _lazydelta(self):
         """temporary compatibility proxy"""
         return self.delta_config.lazy_delta
 
     @property
     def _lazydeltabase(self):
         """temporary compatibility proxy"""
         return self.delta_config.lazy_delta_base
 
     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
         """
         opts = self.opener.options
 
         if b'changelogv2' in opts and self.revlog_kind == KIND_CHANGELOG:
             new_header = CHANGELOGV2
             compute_rank = opts.get(b'changelogv2.compute-rank', True)
             self.feature_config.compute_rank = compute_rank
         elif b'revlogv2' in opts:
             new_header = REVLOGV2
         elif b'revlogv1' in opts:
             new_header = REVLOGV1 | FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 new_header |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             new_header = REVLOGV0
         else:
             new_header = REVLOG_DEFAULT_VERSION
 
         mmapindexthreshold = None
         if self._mmaplargeindex:
             mmapindexthreshold = self.data_config.mmap_index_threshold
         if self.feature_config.enable_ellipsis:
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in opts.get(b'flagprocessors', {}).items():
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         chunk_cache_size = self.data_config.chunk_cache_size
         if chunk_cache_size <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % chunk_cache_size
             )
         elif chunk_cache_size & (chunk_cache_size - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % chunk_cache_size
             )
         force_nodemap = opts.get(b'devel-force-nodemap', False)
         return new_header, mmapindexthreshold, force_nodemap
 
     def _get_data(self, filepath, mmap_threshold, size=None):
         """return a file content with or without mmap
 
         If the file is missing return the empty string"""
         try:
             with self.opener(filepath) as fp:
                 if mmap_threshold is not None:
                     file_size = self.opener.fstat(fp).st_size
                     if file_size >= mmap_threshold:
                         if size is not None:
                             # avoid potentiel mmap crash
                             size = min(file_size, size)
                         # TODO: should .close() to release resources without
                         # relying on Python GC
                         if size is None:
                             return util.buffer(util.mmapread(fp))
                         else:
                             return util.buffer(util.mmapread(fp, size))
                 if size is None:
                     return fp.read()
                 else:
                     return fp.read(size)
         except FileNotFoundError:
             return b''
 
     def get_streams(self, max_linkrev, force_inline=False):
         """return a list of streams that represent this revlog
 
         This is used by stream-clone to do bytes to bytes copies of a repository.
 
         This streams data for all revisions that refer to a changelog revision up
         to `max_linkrev`.
 
         If `force_inline` is set, it enforces that the stream will represent an inline revlog.
 
         It returns is a list of three-tuple:
 
             [
                 (filename, bytes_stream, stream_size),
                 …
             ]
         """
         n = len(self)
         index = self.index
         while n > 0:
             linkrev = index[n - 1][4]
             if linkrev < max_linkrev:
                 break
             # note: this loop will rarely go through multiple iterations, since
             # it only traverses commits created during the current streaming
             # pull operation.
             #
             # If this become a problem, using a binary search should cap the
             # runtime of this.
             n = n - 1
         if n == 0:
             # no data to send
             return []
         index_size = n * index.entry_size
         data_size = self.end(n - 1)
 
         # XXX we might have been split (or stripped) since the object
         # initialization, We need to close this race too, but having a way to
         # pre-open the file we feed to the revlog and never closing them before
         # we are done streaming.
 
         if self._inline:
 
             def get_stream():
                 with self._indexfp() as fp:
                     yield None
                     size = index_size + data_size
                     if size <= 65536:
                         yield fp.read(size)
                     else:
                         yield from util.filechunkiter(fp, limit=size)
 
             inline_stream = get_stream()
             next(inline_stream)
             return [
                 (self._indexfile, inline_stream, index_size + data_size),
             ]
         elif force_inline:
 
             def get_stream():
                 with self.reading():
                     yield None
 
                     for rev in range(n):
                         idx = self.index.entry_binary(rev)
                         if rev == 0 and self._docket is None:
                             # re-inject the inline flag
                             header = self._format_flags
                             header |= self._format_version
                             header |= FLAG_INLINE_DATA
                             header = self.index.pack_header(header)
                             idx = header + idx
                         yield idx
                         yield self._getsegmentforrevs(rev, rev)[1]
 
             inline_stream = get_stream()
             next(inline_stream)
             return [
                 (self._indexfile, inline_stream, index_size + data_size),
             ]
         else:
 
             def get_index_stream():
                 with self._indexfp() as fp:
                     yield None
                     if index_size <= 65536:
                         yield fp.read(index_size)
                     else:
                         yield from util.filechunkiter(fp, limit=index_size)
 
             def get_data_stream():
                 with self._datafp() as fp:
                     yield None
                     if data_size <= 65536:
                         yield fp.read(data_size)
                     else:
                         yield from util.filechunkiter(fp, limit=data_size)
 
             index_stream = get_index_stream()
             next(index_stream)
             data_stream = get_data_stream()
             next(data_stream)
             return [
                 (self._datafile, data_stream, data_size),
                 (self._indexfile, index_stream, index_size),
             ]
 
     def _loadindex(self, docket=None):
 
         new_header, mmapindexthreshold, force_nodemap = self._init_opts()
 
         if self.postfix is not None:
             entry_point = b'%s.i.%s' % (self.radix, self.postfix)
         elif self._trypending and self.opener.exists(b'%s.i.a' % self.radix):
             entry_point = b'%s.i.a' % self.radix
         elif self._try_split and self.opener.exists(self._split_index_file):
             entry_point = self._split_index_file
         else:
             entry_point = b'%s.i' % self.radix
 
         if docket is not None:
             self._docket = docket
             self._docket_file = entry_point
         else:
             self._initempty = True
             entry_data = self._get_data(entry_point, mmapindexthreshold)
             if len(entry_data) > 0:
                 header = INDEX_HEADER.unpack(entry_data[:4])[0]
                 self._initempty = False
             else:
                 header = new_header
 
             self._format_flags = header & ~0xFFFF
             self._format_version = header & 0xFFFF
 
             supported_flags = SUPPORTED_FLAGS.get(self._format_version)
             if supported_flags is None:
                 msg = _(b'unknown version (%d) in revlog %s')
                 msg %= (self._format_version, self.display_id)
                 raise error.RevlogError(msg)
             elif self._format_flags & ~supported_flags:
                 msg = _(b'unknown flags (%#04x) in version %d revlog %s')
                 display_flag = self._format_flags >> 16
                 msg %= (display_flag, self._format_version, self.display_id)
                 raise error.RevlogError(msg)
 
             features = FEATURES_BY_VERSION[self._format_version]
             self._inline = features[b'inline'](self._format_flags)
             self.delta_config.general_delta = features[b'generaldelta'](
                 self._format_flags
             )
             self.feature_config.has_side_data = features[b'sidedata']
 
             if not features[b'docket']:
                 self._indexfile = entry_point
                 index_data = entry_data
             else:
                 self._docket_file = entry_point
                 if self._initempty:
                     self._docket = docketutil.default_docket(self, header)
                 else:
                     self._docket = docketutil.parse_docket(
                         self, entry_data, use_pending=self._trypending
                     )
 
         if self._docket is not None:
             self._indexfile = self._docket.index_filepath()
             index_data = b''
             index_size = self._docket.index_end
             if index_size > 0:
                 index_data = self._get_data(
                     self._indexfile, mmapindexthreshold, size=index_size
                 )
                 if len(index_data) < index_size:
                     msg = _(b'too few index data for %s: got %d, expected %d')
                     msg %= (self.display_id, len(index_data), index_size)
                     raise error.RevlogError(msg)
 
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self.delta_config.general_delta = True
             # the logic for persistent nodemap will be dealt with within the
             # main docket, so disable it for now.
             self._nodemap_file = None
 
         if self._docket is not None:
             self._datafile = self._docket.data_filepath()
             self._sidedatafile = self._docket.sidedata_filepath()
         elif self.postfix is None:
             self._datafile = b'%s.d' % self.radix
         else:
             self._datafile = b'%s.d.%s' % (self.radix, self.postfix)
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self.delta_config.general_delta:
             self.delta_config.sparse_revlog = 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 self._format_version == REVLOGV2:
             self._parse_index = parse_index_v2
         elif self._format_version == CHANGELOGV2:
             self._parse_index = parse_index_cl_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(index_data, self._inline)
             index, chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self._nodemap_file is not None
                 and hasattr(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 = index
         self._segmentfile = randomaccessfile.randomaccessfile(
             self.opener,
             (self._indexfile if self._inline else self._datafile),
             self._chunkcachesize,
             chunkcache,
         )
         self._segmentfile_sidedata = randomaccessfile.randomaccessfile(
             self.opener,
             self._sidedatafile,
             self._chunkcachesize,
         )
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     def get_revlog(self):
         """simple function to mirror API of other not-really-revlog API"""
         return self
 
     @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"""
         if self.revlog_kind == KIND_FILELOG:
             # Reference the file without the "data/" prefix, so it is familiar
             # to the user.
             return self.target[1]
         else:
             return self.radix
 
     def _get_decompressor(self, t):
         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
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     @util.propertycache
     def _decompressor(self):
         """the default decompressor"""
         if self._docket is None:
             return None
         t = self._docket.default_compression_header
         c = self._get_decompressor(t)
         return c.decompress
 
     def _indexfp(self):
         """file object for the revlog's index file"""
         return self.opener(self._indexfile, mode=b"r")
 
     def __index_write_fp(self):
         # You should not use this directly and use `_writing` instead
         try:
             f = self.opener(
-                self._indexfile, mode=b"r+", checkambig=self._checkambig
+                self._indexfile,
+                mode=b"r+",
+                checkambig=self.data_config.check_ambig,
             )
             if self._docket is None:
                 f.seek(0, os.SEEK_END)
             else:
                 f.seek(self._docket.index_end, os.SEEK_SET)
             return f
         except FileNotFoundError:
             return self.opener(
-                self._indexfile, mode=b"w+", checkambig=self._checkambig
+                self._indexfile,
+                mode=b"w+",
+                checkambig=self.data_config.check_ambig,
             )
 
     def __index_new_fp(self):
         # You should not use this unless you are upgrading from inline revlog
         return self.opener(
             self._indexfile,
             mode=b"w",
-            checkambig=self._checkambig,
+            checkambig=self.data_config.check_ambig,
             atomictemp=True,
         )
 
     def _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self._datafile, mode=mode)
 
     @contextlib.contextmanager
     def _sidedatareadfp(self):
         """file object suitable to read sidedata"""
         if self._writinghandles:
             yield self._writinghandles[2]
         else:
             with self.opener(self._sidedatafile) 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(range(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)
 
     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):
         """update on disk cache
 
         If a transaction is passed, the update may be delayed to transaction
         commit."""
         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):
         """Clear in-memory caches"""
         self._revisioncache = None
         self._chainbasecache.clear()
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
         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 hasattr(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):
         """return the revision number associated with a <nodeid>"""
         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 sidedata_cut_off(self, rev):
         sd_cut_off = self.index[rev][8]
         if sd_cut_off != 0:
             return sd_cut_off
         # This is some annoying dance, because entries without sidedata
         # currently use 0 as their ofsset. (instead of previous-offset +
         # previous-size)
         #
         # We should reconsider this sidedata → 0 sidata_offset policy.
         # In the meantime, we need this.
         while 0 <= rev:
             e = self.index[rev]
             if e[9] != 0:
                 return e[8] + e[9]
             rev -= 1
         return 0
 
     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))
 
     def fast_rank(self, rev):
         """Return the rank of a revision if already known, or None otherwise.
 
         The rank of a revision is the size of the sub-graph it defines as a
         head. Equivalently, the rank of a revision `r` is the size of the set
         `ancestors(r)`, `r` included.
 
         This method returns the rank retrieved from the revlog in constant
         time. It makes no attempt at computing unknown values for versions of
         the revlog which do not persist the rank.
         """
         rank = self.index[rev][ENTRY_RANK]
         if self._format_version != CHANGELOGV2 or rank == RANK_UNKNOWN:
             return None
         if rev == nullrev:
             return 0  # convention
         return rank
 
     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 self.canonical_parent_order and 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 self.canonical_parent_order and 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.delta_config.general_delta
         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.
         """
         generaldelta = self.delta_config.general_delta
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
 
         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 and self.index.rust_ext_compat:
             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:
             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 and self.index.rust_ext_compat:
             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 heads.items() 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 and self.index.rust_ext_compat:
             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 (binascii.Error, 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)
         ambiguous = False
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     ambiguous = True
                 else:
                     return partial
             elif maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             else:
                 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):
                 ambiguous = True
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key is not hex
             pass
         if ambiguous:
             raise error.AmbiguousPrefixLookupError(
                 id, self.display_id, _(b'ambiguous identifier')
             )
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             # hex(node)[:...]
             l = len(id) // 2 * 2  # grab an even number of digits
             try:
                 # we're dropping the last digit, so let's check that it's hex,
                 # to avoid the expensive computation below if it's not
                 if len(id) % 2 > 0:
                     if not (id[-1] in hexdigits):
                         return None
                 prefix = bin(id[:l])
             except binascii.Error:
                 pass
             else:
                 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
 
     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 _getsegmentforrevs(self, startrev, endrev):
         """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._segmentfile.read_chunk(start, length)
 
     def _chunk(self, rev):
         """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.
         """
         compression_mode = self.index[rev][10]
         data = self._getsegmentforrevs(rev, rev)[1]
         if compression_mode == COMP_MODE_PLAIN:
             return data
         elif compression_mode == COMP_MODE_DEFAULT:
             return self._decompressor(data)
         elif compression_mode == COMP_MODE_INLINE:
             return self.decompress(data)
         else:
             msg = b'unknown compression mode %d'
             msg %= compression_mode
             raise error.RevlogError(msg)
 
     def _chunks(self, revs, 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)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev) for rev in revschunk]
 
             decomp = self.decompress
             # self._decompressor might be None, but will not be used in that case
             def_decomp = self._decompressor
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 comp_mode = self.index[rev][10]
                 c = buffer(data, chunkstart - offset, chunklength)
                 if comp_mode == COMP_MODE_PLAIN:
                     ladd(c)
                 elif comp_mode == COMP_MODE_INLINE:
                     ladd(decomp(c))
                 elif comp_mode == COMP_MODE_DEFAULT:
                     ladd(def_decomp(c))
                 else:
                     msg = b'unknown compression mode %d'
                     msg %= comp_mode
                     raise error.RevlogError(msg)
 
         return l
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self.delta_config.general_delta:
             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 hasattr(self.index, 'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         while self.length(p1) == 0:
             b = self.deltaparent(p1)
             if b == p1:
                 break
             p1 = b
         p2 = entry[6]
         while self.length(p2) == 0:
             b = self.deltaparent(p2)
             if b == p2:
                 break
             p2 = b
         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 revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         return self._revisiondata(nodeorrev)
 
     def sidedata(self, nodeorrev):
         """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.
         """
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
         else:
             rev = self.rev(nodeorrev)
         return self._sidedata(rev)
 
     def _revisiondata(self, nodeorrev, 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)
 
         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
         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
 
         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
 
     def _rawtext(self, node, rev):
         """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, 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 {}
 
         if self._docket.sidedata_end < sidedata_offset + sidedata_size:
             filename = self._sidedatafile
             end = self._docket.sidedata_end
             offset = sidedata_offset
             length = sidedata_size
             m = FILE_TOO_SHORT_MSG % (filename, length, offset, end)
             raise error.RevlogError(m)
 
         comp_segment = self._segmentfile_sidedata.read_chunk(
             sidedata_offset, sidedata_size
         )
 
         comp = self.index[rev][11]
         if comp == COMP_MODE_PLAIN:
             segment = comp_segment
         elif comp == COMP_MODE_DEFAULT:
             segment = self._decompressor(comp_segment)
         elif comp == COMP_MODE_INLINE:
             segment = self.decompress(comp_segment)
         else:
             msg = b'unknown compression mode %d'
             msg %= comp
             raise error.RevlogError(msg)
 
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def rawdata(self, nodeorrev):
         """return an uncompressed raw data of a given node or revision number."""
         return self._revisiondata(nodeorrev, raw=True)
 
     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.display_id, pycompat.bytestr(revornode))
                 )
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.display_id, node, text)
             raise
 
     @property
     def _split_index_file(self):
         """the path where to expect the index of an ongoing splitting operation
 
         The file will only exist if a splitting operation is in progress, but
         it is always expected at the same location."""
         parts = self.radix.split(b'/')
         if len(parts) > 1:
             # adds a '-s' prefix to the ``data/` or `meta/` base
             head = parts[0] + b'-s'
             mids = parts[1:-1]
             tail = parts[-1] + b'.i'
             pieces = [head] + mids + [tail]
             return b'/'.join(pieces)
         else:
             # the revlog is stored at the root of the store (changelog or
             # manifest), no risk of collision.
             return self.radix + b'.i.s'
 
     def _enforceinlinesize(self, tr, side_write=True):
         """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
         total_size = self.start(tiprev) + self.length(tiprev)
         if not self._inline or total_size < _maxinline:
             return
 
         troffset = tr.findoffset(self._indexfile)
         if troffset is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self._indexfile
             )
         if troffset:
             tr.addbackup(self._indexfile, for_offset=True)
         tr.add(self._datafile, 0)
 
         existing_handles = False
         if self._writinghandles is not None:
             existing_handles = True
             fp = self._writinghandles[0]
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
             self._segmentfile.writing_handle = None
             # No need to deal with sidedata writing handle as it is only
             # relevant with revlog-v2 which is never inline, not reaching
             # this code
         if side_write:
             old_index_file_path = self._indexfile
             new_index_file_path = self._split_index_file
             opener = self.opener
             weak_self = weakref.ref(self)
 
             # the "split" index replace the real index when the transaction is finalized
             def finalize_callback(tr):
                 opener.rename(
                     new_index_file_path,
                     old_index_file_path,
                     checkambig=True,
                 )
                 maybe_self = weak_self()
                 if maybe_self is not None:
                     maybe_self._indexfile = old_index_file_path
 
             def abort_callback(tr):
                 maybe_self = weak_self()
                 if maybe_self is not None:
                     maybe_self._indexfile = old_index_file_path
 
             tr.registertmp(new_index_file_path)
             if self.target[1] is not None:
                 callback_id = b'000-revlog-split-%d-%s' % self.target
             else:
                 callback_id = b'000-revlog-split-%d' % self.target[0]
             tr.addfinalize(callback_id, finalize_callback)
             tr.addabort(callback_id, abort_callback)
 
         new_dfh = self._datafp(b'w+')
         new_dfh.truncate(0)  # drop any potentially existing data
         try:
             with self.reading():
                 for r in self:
                     new_dfh.write(self._getsegmentforrevs(r, r)[1])
                 new_dfh.flush()
 
             if side_write:
                 self._indexfile = new_index_file_path
             with self.__index_new_fp() as fp:
                 self._format_flags &= ~FLAG_INLINE_DATA
                 self._inline = False
                 for i in self:
                     e = self.index.entry_binary(i)
                     if i == 0 and self._docket is None:
                         header = self._format_flags | self._format_version
                         header = self.index.pack_header(header)
                         e = header + e
                     fp.write(e)
                 if self._docket is not None:
                     self._docket.index_end = fp.tell()
 
                 # If we don't use side-write, the temp file replace the real
                 # index when we exit the context manager
 
             nodemaputil.setup_persistent_nodemap(tr, self)
             self._segmentfile = randomaccessfile.randomaccessfile(
                 self.opener,
                 self._datafile,
                 self._chunkcachesize,
             )
 
             if existing_handles:
                 # switched from inline to conventional reopen the index
                 ifh = self.__index_write_fp()
                 self._writinghandles = (ifh, new_dfh, None)
                 self._segmentfile.writing_handle = new_dfh
                 new_dfh = None
                 # No need to deal with sidedata writing handle as it is only
                 # relevant with revlog-v2 which is never inline, not reaching
                 # this code
         finally:
             if new_dfh is not None:
                 new_dfh.close()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     @contextlib.contextmanager
     def reading(self):
         """Context manager that keeps data and sidedata files open for reading"""
         if len(self.index) == 0:
             yield  # nothing to be read
         else:
             with self._segmentfile.reading():
                 with self._segmentfile_sidedata.reading():
                     yield
 
     @contextlib.contextmanager
     def _writing(self, transaction):
         if self._trypending:
             msg = b'try to write in a `trypending` revlog: %s'
             msg %= self.display_id
             raise error.ProgrammingError(msg)
         if self._writinghandles is not None:
             yield
         else:
             ifh = dfh = sdfh = None
             try:
                 r = len(self)
                 # opening the data file.
                 dsize = 0
                 if r:
                     dsize = self.end(r - 1)
                 dfh = None
                 if not self._inline:
                     try:
                         dfh = self._datafp(b"r+")
                         if self._docket is None:
                             dfh.seek(0, os.SEEK_END)
                         else:
                             dfh.seek(self._docket.data_end, os.SEEK_SET)
                     except FileNotFoundError:
                         dfh = self._datafp(b"w+")
                     transaction.add(self._datafile, dsize)
                 if self._sidedatafile is not None:
                     # revlog-v2 does not inline, help Pytype
                     assert dfh is not None
                     try:
                         sdfh = self.opener(self._sidedatafile, mode=b"r+")
                         dfh.seek(self._docket.sidedata_end, os.SEEK_SET)
                     except FileNotFoundError:
                         sdfh = self.opener(self._sidedatafile, mode=b"w+")
                     transaction.add(
                         self._sidedatafile, self._docket.sidedata_end
                     )
 
                 # opening the index file.
                 isize = r * self.index.entry_size
                 ifh = self.__index_write_fp()
                 if self._inline:
                     transaction.add(self._indexfile, dsize + isize)
                 else:
                     transaction.add(self._indexfile, isize)
                 # exposing all file handle for writing.
                 self._writinghandles = (ifh, dfh, sdfh)
                 self._segmentfile.writing_handle = ifh if self._inline else dfh
                 self._segmentfile_sidedata.writing_handle = sdfh
                 yield
                 if self._docket is not None:
                     self._write_docket(transaction)
             finally:
                 self._writinghandles = None
                 self._segmentfile.writing_handle = None
                 self._segmentfile_sidedata.writing_handle = None
                 if dfh is not None:
                     dfh.close()
                 if sdfh is not None:
                     sdfh.close()
                 # closing the index file last to avoid exposing referent to
                 # potential unflushed data content.
                 if ifh is not None:
                     ifh.close()
 
     def _write_docket(self, transaction):
         """write the current docket on disk
 
         Exist as a method to help changelog to implement transaction logic
 
         We could also imagine using the same transaction logic for all revlog
         since docket are cheap."""
         self._docket.write(transaction)
 
     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.display_id
             )
 
         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.display_id, 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).
         """
         with self._writing(transaction):
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
 
     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)
 
         compressor = self._get_decompressor(t)
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         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.display_id
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%s: attempt to add wdir revision") % self.display_id
             )
         if self._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
 
         offset = self._get_data_offset(prev)
 
         if self._concurrencychecker:
             ifh, dfh, sdfh = self._writinghandles
             # XXX no checking for the sidedata file
             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:
             write_debug = None
             if self._debug_delta:
                 write_debug = transaction._report
             deltacomputer = deltautil.deltacomputer(
                 self, write_debug=write_debug
             )
 
         if cachedelta is not None and len(cachedelta) == 2:
             # If the cached delta has no information about how it should be
             # reused, add the default reuse instruction according to the
             # revlog's configuration.
             if (
                 self.delta_config.general_delta
                 and self.delta_config.lazy_delta_base
             ):
                 delta_base_reuse = DELTA_BASE_REUSE_TRY
             else:
                 delta_base_reuse = DELTA_BASE_REUSE_NO
             cachedelta = (cachedelta[0], cachedelta[1], delta_base_reuse)
 
         revinfo = revlogutils.revisioninfo(
             node,
             p1,
             p2,
             btext,
             textlen,
             cachedelta,
             flags,
         )
 
         deltainfo = deltacomputer.finddeltainfo(revinfo)
 
         compression_mode = COMP_MODE_INLINE
         if self._docket is not None:
             default_comp = self._docket.default_compression_header
             r = deltautil.delta_compression(default_comp, deltainfo)
             compression_mode, deltainfo = r
 
         sidedata_compression_mode = COMP_MODE_INLINE
         if sidedata and self.hassidedata:
             sidedata_compression_mode = COMP_MODE_PLAIN
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = self._docket.sidedata_end
             h, comp_sidedata = self.compress(serialized_sidedata)
             if (
                 h != b'u'
                 and comp_sidedata[0:1] != b'\0'
                 and len(comp_sidedata) < len(serialized_sidedata)
             ):
                 assert not h
                 if (
                     comp_sidedata[0:1]
                     == self._docket.default_compression_header
                 ):
                     sidedata_compression_mode = COMP_MODE_DEFAULT
                     serialized_sidedata = comp_sidedata
                 else:
                     sidedata_compression_mode = COMP_MODE_INLINE
                     serialized_sidedata = comp_sidedata
         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
 
         rank = RANK_UNKNOWN
         if self._compute_rank:
             if (p1r, p2r) == (nullrev, nullrev):
                 rank = 1
             elif p1r != nullrev and p2r == nullrev:
                 rank = 1 + self.fast_rank(p1r)
             elif p1r == nullrev and p2r != nullrev:
                 rank = 1 + self.fast_rank(p2r)
             else:  # merge node
                 if rustdagop is not None and self.index.rust_ext_compat:
                     rank = rustdagop.rank(self.index, p1r, p2r)
                 else:
                     pmin, pmax = sorted((p1r, p2r))
                     rank = 1 + self.fast_rank(pmax)
                     rank += sum(1 for _ in self.findmissingrevs([pmax], [pmin]))
 
         e = revlogutils.entry(
             flags=flags,
             data_offset=offset,
             data_compressed_length=deltainfo.deltalen,
             data_uncompressed_length=textlen,
             data_compression_mode=compression_mode,
             data_delta_base=deltainfo.base,
             link_rev=link,
             parent_rev_1=p1r,
             parent_rev_2=p2r,
             node_id=node,
             sidedata_offset=sidedata_offset,
             sidedata_compressed_length=len(serialized_sidedata),
             sidedata_compression_mode=sidedata_compression_mode,
             rank=rank,
         )
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0 and self._docket is None:
             header = self._format_flags | self._format_version
             header = self.index.pack_header(header)
             entry = header + entry
         self._writeentry(
             transaction,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
             sidedata_offset,
         )
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo)
 
         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._docket is None:
             return self.end(prev)
         else:
             return self._docket.data_end
 
     def _writeentry(
         self, transaction, entry, data, link, offset, sidedata, sidedata_offset
     ):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         if self._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
         ifh, dfh, sdfh = self._writinghandles
         if self._docket is None:
             ifh.seek(0, os.SEEK_END)
         else:
             ifh.seek(self._docket.index_end, os.SEEK_SET)
         if dfh:
             if self._docket is None:
                 dfh.seek(0, os.SEEK_END)
             else:
                 dfh.seek(self._docket.data_end, os.SEEK_SET)
         if sdfh:
             sdfh.seek(self._docket.sidedata_end, os.SEEK_SET)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self._datafile, offset)
             if self._sidedatafile:
                 transaction.add(self._sidedatafile, sidedata_offset)
             transaction.add(self._indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 sdfh.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])
             assert not sidedata
             self._enforceinlinesize(transaction)
         if self._docket is not None:
             # revlog-v2 always has 3 writing handles, help Pytype
             wh1 = self._writinghandles[0]
             wh2 = self._writinghandles[1]
             wh3 = self._writinghandles[2]
             assert wh1 is not None
             assert wh2 is not None
             assert wh3 is not None
             self._docket.index_end = wh1.tell()
             self._docket.data_end = wh2.tell()
             self._docket.sidedata_end = wh3.tell()
 
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         debug_info=None,
         delta_base_reuse_policy=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._adding_group:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         # read the default delta-base reuse policy from revlog config if the
         # group did not specify one.
         if delta_base_reuse_policy is None:
             if (
                 self.delta_config.general_delta
                 and self.delta_config.lazy_delta_base
             ):
                 delta_base_reuse_policy = DELTA_BASE_REUSE_TRY
             else:
                 delta_base_reuse_policy = DELTA_BASE_REUSE_NO
 
         self._adding_group = True
         empty = True
         try:
             with self._writing(transaction):
                 write_debug = None
                 if self._debug_delta:
                     write_debug = transaction._report
                 deltacomputer = deltautil.deltacomputer(
                     self,
                     write_debug=write_debug,
                     debug_info=debug_info,
                 )
                 # 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.display_id, self.node(baserev)
                             )
 
                     if not flags and self._peek_iscensored(baserev, delta):
                         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, delta_base_reuse_policy),
                         alwayscache=alwayscache,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
 
                     if addrevisioncb:
                         addrevisioncb(self, rev)
                     empty = False
         finally:
             self._adding_group = False
         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):
         """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
         data_end = self.start(rev)
         if not self._inline:
             transaction.add(self._datafile, data_end)
             end = rev * self.index.entry_size
         else:
             end = data_end + (rev * self.index.entry_size)
 
         if self._sidedatafile:
             sidedata_end = self.sidedata_cut_off(rev)
             transaction.add(self._sidedatafile, sidedata_end)
 
         transaction.add(self._indexfile, end)
         if self._docket is not None:
             # XXX we could, leverage the docket while stripping. However it is
             # not powerfull enough at the time of this comment
             self._docket.index_end = end
             self._docket.data_end = data_end
             self._docket.sidedata_end = sidedata_end
             self._docket.write(transaction, stripping=True)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = util.lrucachedict(500)
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
 
         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 FileNotFoundError:
             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 FileNotFoundError:
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self._indexfile]
         if self._docket_file is None:
             if not self._inline:
                 res.append(self._datafile)
         else:
             res.append(self._docket_file)
             res.extend(self._docket.old_index_filepaths(include_empty=False))
             if self._docket.data_end:
                 res.append(self._datafile)
             res.extend(self._docket.old_data_filepaths(include_empty=False))
             if self._docket.sidedata_end:
                 res.append(self._sidedatafile)
             res.extend(self._docket.old_sidedata_filepaths(include_empty=False))
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
         debug_info=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.delta_config.general_delta:
             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,
             debug_info=debug_info,
         )
 
     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.
         old_delta_config = destrevlog.delta_config
         destrevlog.delta_config = destrevlog.delta_config.copy()
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog.delta_config.lazy_delta_base = True
                 destrevlog.delta_config.lazy_delta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog.delta_config.lazy_delta_base = False
                 destrevlog.delta_config.lazy_delta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog.delta_config.lazy_delta_base = False
                 destrevlog.delta_config.lazy_delta = False
 
             delta_both_parents = (
                 forcedeltabothparents or old_delta_config.delta_both_parents
             )
             destrevlog.delta_config.delta_both_parents = delta_both_parents
 
             with self.reading():
                 self._clone(
                     tr,
                     destrevlog,
                     addrevisioncb,
                     deltareuse,
                     forcedeltabothparents,
                     sidedata_helpers,
                 )
 
         finally:
             destrevlog.delta_config = old_delta_config
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
         sidedata_helpers,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         write_debug = None
         if self._debug_delta:
             write_debug = tr._report
         deltacomputer = deltautil.deltacomputer(
             destrevlog,
             write_debug=write_debug,
         )
         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 = self._revisiondata(rev)
                 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]
 
                 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 = self._revisiondata(rev)
                     sidedata = self.sidedata(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]
 
                 with destrevlog._writing(tr):
                     destrevlog._addrevision(
                         node,
                         rawtext,
                         tr,
                         linkrev,
                         p1,
                         p2,
                         flags,
                         cachedelta,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
 
             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
             )
         elif self._format_version == REVLOGV1:
             rewrite.v1_censor(self, tr, censornode, tombstone)
         else:
             rewrite.v2_censor(self, tr, censornode, tombstone)
 
     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, transaction, helpers, startrev, endrev):
         if not self.hassidedata:
             return
         # revlog formats with sidedata support does not support inline
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         new_entries = []
         # append the new sidedata
         with self._writing(transaction):
             ifh, dfh, sdfh = self._writinghandles
             dfh.seek(self._docket.sidedata_end, os.SEEK_SET)
 
             current_offset = sdfh.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
                 )
 
                 sidedata_compression_mode = COMP_MODE_INLINE
                 if serialized_sidedata and self.hassidedata:
                     sidedata_compression_mode = COMP_MODE_PLAIN
                     h, comp_sidedata = self.compress(serialized_sidedata)
                     if (
                         h != b'u'
                         and comp_sidedata[0] != b'\0'
                         and len(comp_sidedata) < len(serialized_sidedata)
                     ):
                         assert not h
                         if (
                             comp_sidedata[0]
                             == self._docket.default_compression_header
                         ):
                             sidedata_compression_mode = COMP_MODE_DEFAULT
                             serialized_sidedata = comp_sidedata
                         else:
                             sidedata_compression_mode = COMP_MODE_INLINE
                             serialized_sidedata = comp_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_update = (
                     current_offset,
                     len(serialized_sidedata),
                     new_offset_flags,
                     sidedata_compression_mode,
                 )
 
                 # the sidedata computation might have move the file cursors around
                 sdfh.seek(current_offset, os.SEEK_SET)
                 sdfh.write(serialized_sidedata)
                 new_entries.append(entry_update)
                 current_offset += len(serialized_sidedata)
                 self._docket.sidedata_end = sdfh.tell()
 
             # rewrite the new index entries
             ifh.seek(startrev * self.index.entry_size)
             for i, e in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, *e)
                 packed = self.index.entry_binary(rev)
                 if rev == 0 and self._docket is None:
                     header = self._format_flags | self._format_version
                     header = self.index.pack_header(header)
                     packed = header + packed
                 ifh.write(packed)

mercurial/revlogutils/rewrite.py

@@ -1,875 +1,875 b''
 # censor code related to censoring revision
 # coding: utf8
 #
 # Copyright 2021 Pierre-Yves David <[e-mail]>
 # Copyright 2015 Google, Inc <[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.
 
 import binascii
 import contextlib
 import os
 import struct
 
 from ..node import (
     nullrev,
 )
 from .constants import (
     COMP_MODE_PLAIN,
     ENTRY_DATA_COMPRESSED_LENGTH,
     ENTRY_DATA_COMPRESSION_MODE,
     ENTRY_DATA_OFFSET,
     ENTRY_DATA_UNCOMPRESSED_LENGTH,
     ENTRY_DELTA_BASE,
     ENTRY_LINK_REV,
     ENTRY_NODE_ID,
     ENTRY_PARENT_1,
     ENTRY_PARENT_2,
     ENTRY_SIDEDATA_COMPRESSED_LENGTH,
     ENTRY_SIDEDATA_COMPRESSION_MODE,
     ENTRY_SIDEDATA_OFFSET,
     REVIDX_ISCENSORED,
     REVLOGV0,
     REVLOGV1,
 )
 from ..i18n import _
 
 from .. import (
     error,
     mdiff,
     pycompat,
     revlogutils,
     util,
 )
 from ..utils import (
     storageutil,
 )
 from . import (
     constants,
     deltas,
 )
 
 
 def v1_censor(rl, tr, censornode, tombstone=b''):
     """censors a revision in a "version 1" revlog"""
     assert rl._format_version == constants.REVLOGV1, rl._format_version
 
     # avoid cycle
     from .. import revlog
 
     censorrev = rl.rev(censornode)
     tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
     # 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.revlog(
         rl.opener,
         target=rl.target,
         radix=rl.radix,
         postfix=b'tmpcensored',
         censorable=True,
     )
     newrl._format_version = rl._format_version
     newrl._format_flags = rl._format_flags
     newrl.delta_config.general_delta = rl.delta_config.general_delta
     newrl._parse_index = rl._parse_index
 
     for rev in rl.revs():
         node = rl.node(rev)
         p1, p2 = rl.parents(node)
 
         if rev == censorrev:
             newrl.addrawrevision(
                 tombstone,
                 tr,
                 rl.linkrev(censorrev),
                 p1,
                 p2,
                 censornode,
                 constants.REVIDX_ISCENSORED,
             )
 
             if newrl.deltaparent(rev) != nullrev:
                 m = _(b'censored revision stored as delta; cannot censor')
                 h = _(
                     b'censoring of revlogs is not fully implemented;'
                     b' please report this bug'
                 )
                 raise error.Abort(m, hint=h)
             continue
 
         if rl.iscensored(rev):
             if rl.deltaparent(rev) != nullrev:
                 m = _(
                     b'cannot censor due to censored '
                     b'revision having delta stored'
                 )
                 raise error.Abort(m)
             rawtext = rl._chunk(rev)
         else:
             rawtext = rl.rawdata(rev)
 
         newrl.addrawrevision(
             rawtext, tr, rl.linkrev(rev), p1, p2, node, rl.flags(rev)
         )
 
     tr.addbackup(rl._indexfile, location=b'store')
     if not rl._inline:
         tr.addbackup(rl._datafile, location=b'store')
 
     rl.opener.rename(newrl._indexfile, rl._indexfile)
     if not rl._inline:
         rl.opener.rename(newrl._datafile, rl._datafile)
 
     rl.clearcaches()
     rl._loadindex()
 
 
 def v2_censor(revlog, tr, censornode, tombstone=b''):
     """censors a revision in a "version 2" revlog"""
     assert revlog._format_version != REVLOGV0, revlog._format_version
     assert revlog._format_version != REVLOGV1, revlog._format_version
 
     censor_revs = {revlog.rev(censornode)}
     _rewrite_v2(revlog, tr, censor_revs, tombstone)
 
 
 def _rewrite_v2(revlog, tr, censor_revs, tombstone=b''):
     """rewrite a revlog to censor some of its content
 
     General principle
 
     We create new revlog files (index/data/sidedata) to copy the content of
     the existing data without the censored data.
 
     We need to recompute new delta for any revision that used the censored
     revision as delta base. As the cumulative size of the new delta may be
     large, we store them in a temporary file until they are stored in their
     final destination.
 
     All data before the censored data can be blindly copied. The rest needs
     to be copied as we go and the associated index entry needs adjustement.
     """
     assert revlog._format_version != REVLOGV0, revlog._format_version
     assert revlog._format_version != REVLOGV1, revlog._format_version
 
     old_index = revlog.index
     docket = revlog._docket
 
     tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
     first_excl_rev = min(censor_revs)
 
     first_excl_entry = revlog.index[first_excl_rev]
     index_cutoff = revlog.index.entry_size * first_excl_rev
     data_cutoff = first_excl_entry[ENTRY_DATA_OFFSET] >> 16
     sidedata_cutoff = revlog.sidedata_cut_off(first_excl_rev)
 
     with pycompat.unnamedtempfile(mode=b"w+b") as tmp_storage:
         # rev → (new_base, data_start, data_end, compression_mode)
         rewritten_entries = _precompute_rewritten_delta(
             revlog,
             old_index,
             censor_revs,
             tmp_storage,
         )
 
         all_files = _setup_new_files(
             revlog,
             index_cutoff,
             data_cutoff,
             sidedata_cutoff,
         )
 
         # we dont need to open the old index file since its content already
         # exist in a usable form in `old_index`.
         with all_files() as open_files:
             (
                 old_data_file,
                 old_sidedata_file,
                 new_index_file,
                 new_data_file,
                 new_sidedata_file,
             ) = open_files
 
             # writing the censored revision
 
             # Writing all subsequent revisions
             for rev in range(first_excl_rev, len(old_index)):
                 if rev in censor_revs:
                     _rewrite_censor(
                         revlog,
                         old_index,
                         open_files,
                         rev,
                         tombstone,
                     )
                 else:
                     _rewrite_simple(
                         revlog,
                         old_index,
                         open_files,
                         rev,
                         rewritten_entries,
                         tmp_storage,
                     )
     docket.write(transaction=None, stripping=True)
 
 
 def _precompute_rewritten_delta(
     revlog,
     old_index,
     excluded_revs,
     tmp_storage,
 ):
     """Compute new delta for revisions whose delta is based on revision that
     will not survive as is.
 
     Return a mapping: {rev → (new_base, data_start, data_end, compression_mode)}
     """
     dc = deltas.deltacomputer(revlog)
     rewritten_entries = {}
     first_excl_rev = min(excluded_revs)
     with revlog.reading():
         for rev in range(first_excl_rev, len(old_index)):
             if rev in excluded_revs:
                 # this revision will be preserved as is, so we don't need to
                 # consider recomputing a delta.
                 continue
             entry = old_index[rev]
             if entry[ENTRY_DELTA_BASE] not in excluded_revs:
                 continue
             # This is a revision that use the censored revision as the base
             # for its delta. We need a need new deltas
             if entry[ENTRY_DATA_UNCOMPRESSED_LENGTH] == 0:
                 # this revision is empty, we can delta against nullrev
                 rewritten_entries[rev] = (nullrev, 0, 0, COMP_MODE_PLAIN)
             else:
 
                 text = revlog.rawdata(rev)
                 info = revlogutils.revisioninfo(
                     node=entry[ENTRY_NODE_ID],
                     p1=revlog.node(entry[ENTRY_PARENT_1]),
                     p2=revlog.node(entry[ENTRY_PARENT_2]),
                     btext=[text],
                     textlen=len(text),
                     cachedelta=None,
                     flags=entry[ENTRY_DATA_OFFSET] & 0xFFFF,
                 )
                 d = dc.finddeltainfo(
                     info, excluded_bases=excluded_revs, target_rev=rev
                 )
                 default_comp = revlog._docket.default_compression_header
                 comp_mode, d = deltas.delta_compression(default_comp, d)
                 # using `tell` is a bit lazy, but we are not here for speed
                 start = tmp_storage.tell()
                 tmp_storage.write(d.data[1])
                 end = tmp_storage.tell()
                 rewritten_entries[rev] = (d.base, start, end, comp_mode)
     return rewritten_entries
 
 
 def _setup_new_files(
     revlog,
     index_cutoff,
     data_cutoff,
     sidedata_cutoff,
 ):
     """
 
     return a context manager to open all the relevant files:
     - old_data_file,
     - old_sidedata_file,
     - new_index_file,
     - new_data_file,
     - new_sidedata_file,
 
     The old_index_file is not here because it is accessed through the
     `old_index` object if the caller function.
     """
     docket = revlog._docket
     old_index_filepath = revlog.opener.join(docket.index_filepath())
     old_data_filepath = revlog.opener.join(docket.data_filepath())
     old_sidedata_filepath = revlog.opener.join(docket.sidedata_filepath())
 
     new_index_filepath = revlog.opener.join(docket.new_index_file())
     new_data_filepath = revlog.opener.join(docket.new_data_file())
     new_sidedata_filepath = revlog.opener.join(docket.new_sidedata_file())
 
     util.copyfile(old_index_filepath, new_index_filepath, nb_bytes=index_cutoff)
     util.copyfile(old_data_filepath, new_data_filepath, nb_bytes=data_cutoff)
     util.copyfile(
         old_sidedata_filepath,
         new_sidedata_filepath,
         nb_bytes=sidedata_cutoff,
     )
     revlog.opener.register_file(docket.index_filepath())
     revlog.opener.register_file(docket.data_filepath())
     revlog.opener.register_file(docket.sidedata_filepath())
 
     docket.index_end = index_cutoff
     docket.data_end = data_cutoff
     docket.sidedata_end = sidedata_cutoff
 
     # reload the revlog internal information
     revlog.clearcaches()
     revlog._loadindex(docket=docket)
 
     @contextlib.contextmanager
     def all_files_opener():
         # hide opening in an helper function to please check-code, black
         # and various python version at the same time
         with open(old_data_filepath, 'rb') as old_data_file:
             with open(old_sidedata_filepath, 'rb') as old_sidedata_file:
                 with open(new_index_filepath, 'r+b') as new_index_file:
                     with open(new_data_filepath, 'r+b') as new_data_file:
                         with open(
                             new_sidedata_filepath, 'r+b'
                         ) as new_sidedata_file:
                             new_index_file.seek(0, os.SEEK_END)
                             assert new_index_file.tell() == index_cutoff
                             new_data_file.seek(0, os.SEEK_END)
                             assert new_data_file.tell() == data_cutoff
                             new_sidedata_file.seek(0, os.SEEK_END)
                             assert new_sidedata_file.tell() == sidedata_cutoff
                             yield (
                                 old_data_file,
                                 old_sidedata_file,
                                 new_index_file,
                                 new_data_file,
                                 new_sidedata_file,
                             )
 
     return all_files_opener
 
 
 def _rewrite_simple(
     revlog,
     old_index,
     all_files,
     rev,
     rewritten_entries,
     tmp_storage,
 ):
     """append a normal revision to the index after the rewritten one(s)"""
     (
         old_data_file,
         old_sidedata_file,
         new_index_file,
         new_data_file,
         new_sidedata_file,
     ) = all_files
     entry = old_index[rev]
     flags = entry[ENTRY_DATA_OFFSET] & 0xFFFF
     old_data_offset = entry[ENTRY_DATA_OFFSET] >> 16
 
     if rev not in rewritten_entries:
         old_data_file.seek(old_data_offset)
         new_data_size = entry[ENTRY_DATA_COMPRESSED_LENGTH]
         new_data = old_data_file.read(new_data_size)
         data_delta_base = entry[ENTRY_DELTA_BASE]
         d_comp_mode = entry[ENTRY_DATA_COMPRESSION_MODE]
     else:
         (
             data_delta_base,
             start,
             end,
             d_comp_mode,
         ) = rewritten_entries[rev]
         new_data_size = end - start
         tmp_storage.seek(start)
         new_data = tmp_storage.read(new_data_size)
 
     # It might be faster to group continuous read/write operation,
     # however, this is censor, an operation that is not focussed
     # around stellar performance. So I have not written this
     # optimisation yet.
     new_data_offset = new_data_file.tell()
     new_data_file.write(new_data)
 
     sidedata_size = entry[ENTRY_SIDEDATA_COMPRESSED_LENGTH]
     new_sidedata_offset = new_sidedata_file.tell()
     if 0 < sidedata_size:
         old_sidedata_offset = entry[ENTRY_SIDEDATA_OFFSET]
         old_sidedata_file.seek(old_sidedata_offset)
         new_sidedata = old_sidedata_file.read(sidedata_size)
         new_sidedata_file.write(new_sidedata)
 
     data_uncompressed_length = entry[ENTRY_DATA_UNCOMPRESSED_LENGTH]
     sd_com_mode = entry[ENTRY_SIDEDATA_COMPRESSION_MODE]
     assert data_delta_base <= rev, (data_delta_base, rev)
 
     new_entry = revlogutils.entry(
         flags=flags,
         data_offset=new_data_offset,
         data_compressed_length=new_data_size,
         data_uncompressed_length=data_uncompressed_length,
         data_delta_base=data_delta_base,
         link_rev=entry[ENTRY_LINK_REV],
         parent_rev_1=entry[ENTRY_PARENT_1],
         parent_rev_2=entry[ENTRY_PARENT_2],
         node_id=entry[ENTRY_NODE_ID],
         sidedata_offset=new_sidedata_offset,
         sidedata_compressed_length=sidedata_size,
         data_compression_mode=d_comp_mode,
         sidedata_compression_mode=sd_com_mode,
     )
     revlog.index.append(new_entry)
     entry_bin = revlog.index.entry_binary(rev)
     new_index_file.write(entry_bin)
 
     revlog._docket.index_end = new_index_file.tell()
     revlog._docket.data_end = new_data_file.tell()
     revlog._docket.sidedata_end = new_sidedata_file.tell()
 
 
 def _rewrite_censor(
     revlog,
     old_index,
     all_files,
     rev,
     tombstone,
 ):
     """rewrite and append a censored revision"""
     (
         old_data_file,
         old_sidedata_file,
         new_index_file,
         new_data_file,
         new_sidedata_file,
     ) = all_files
     entry = old_index[rev]
 
     # XXX consider trying the default compression too
     new_data_size = len(tombstone)
     new_data_offset = new_data_file.tell()
     new_data_file.write(tombstone)
 
     # we are not adding any sidedata as they might leak info about the censored version
 
     link_rev = entry[ENTRY_LINK_REV]
 
     p1 = entry[ENTRY_PARENT_1]
     p2 = entry[ENTRY_PARENT_2]
 
     new_entry = revlogutils.entry(
         flags=constants.REVIDX_ISCENSORED,
         data_offset=new_data_offset,
         data_compressed_length=new_data_size,
         data_uncompressed_length=new_data_size,
         data_delta_base=rev,
         link_rev=link_rev,
         parent_rev_1=p1,
         parent_rev_2=p2,
         node_id=entry[ENTRY_NODE_ID],
         sidedata_offset=0,
         sidedata_compressed_length=0,
         data_compression_mode=COMP_MODE_PLAIN,
         sidedata_compression_mode=COMP_MODE_PLAIN,
     )
     revlog.index.append(new_entry)
     entry_bin = revlog.index.entry_binary(rev)
     new_index_file.write(entry_bin)
     revlog._docket.index_end = new_index_file.tell()
     revlog._docket.data_end = new_data_file.tell()
 
 
 def _get_filename_from_filelog_index(path):
     # Drop the extension and the `data/` prefix
     path_part = path.rsplit(b'.', 1)[0].split(b'/', 1)
     if len(path_part) < 2:
         msg = _(b"cannot recognize filelog from filename: '%s'")
         msg %= path
         raise error.Abort(msg)
 
     return path_part[1]
 
 
 def _filelog_from_filename(repo, path):
     """Returns the filelog for the given `path`. Stolen from `engine.py`"""
 
     from .. import filelog  # avoid cycle
 
     fl = filelog.filelog(repo.svfs, path)
     return fl
 
 
 def _write_swapped_parents(repo, rl, rev, offset, fp):
     """Swaps p1 and p2 and overwrites the revlog entry for `rev` in `fp`"""
     from ..pure import parsers  # avoid cycle
 
     if repo._currentlock(repo._lockref) is None:
         # Let's be paranoid about it
         msg = "repo needs to be locked to rewrite parents"
         raise error.ProgrammingError(msg)
 
     index_format = parsers.IndexObject.index_format
     entry = rl.index[rev]
     new_entry = list(entry)
     new_entry[5], new_entry[6] = entry[6], entry[5]
     packed = index_format.pack(*new_entry[:8])
     fp.seek(offset)
     fp.write(packed)
 
 
 def _reorder_filelog_parents(repo, fl, to_fix):
     """
     Swaps p1 and p2 for all `to_fix` revisions of filelog `fl` and writes the
     new version to disk, overwriting the old one with a rename.
     """
     from ..pure import parsers  # avoid cycle
 
     ui = repo.ui
     assert len(to_fix) > 0
     rl = fl._revlog
     if rl._format_version != constants.REVLOGV1:
         msg = "expected version 1 revlog, got version '%d'" % rl._format_version
         raise error.ProgrammingError(msg)
 
     index_file = rl._indexfile
     new_file_path = index_file + b'.tmp-parents-fix'
     repaired_msg = _(b"repaired revision %d of 'filelog %s'\n")
 
     with ui.uninterruptible():
         try:
             util.copyfile(
                 rl.opener.join(index_file),
                 rl.opener.join(new_file_path),
-                checkambig=rl._checkambig,
+                checkambig=rl.data_config.check_ambig,
             )
 
             with rl.opener(new_file_path, mode=b"r+") as fp:
                 if rl._inline:
                     index = parsers.InlinedIndexObject(fp.read())
                     for rev in fl.revs():
                         if rev in to_fix:
                             offset = index._calculate_index(rev)
                             _write_swapped_parents(repo, rl, rev, offset, fp)
                             ui.write(repaired_msg % (rev, index_file))
                 else:
                     index_format = parsers.IndexObject.index_format
                     for rev in to_fix:
                         offset = rev * index_format.size
                         _write_swapped_parents(repo, rl, rev, offset, fp)
                         ui.write(repaired_msg % (rev, index_file))
 
             rl.opener.rename(new_file_path, index_file)
             rl.clearcaches()
             rl._loadindex()
         finally:
             util.tryunlink(new_file_path)
 
 
 def _is_revision_affected(fl, filerev, metadata_cache=None):
     full_text = lambda: fl._revlog.rawdata(filerev)
     parent_revs = lambda: fl._revlog.parentrevs(filerev)
     return _is_revision_affected_inner(
         full_text, parent_revs, filerev, metadata_cache
     )
 
 
 def _is_revision_affected_inner(
     full_text,
     parents_revs,
     filerev,
     metadata_cache=None,
 ):
     """Mercurial currently (5.9rc0) uses `p1 == nullrev and p2 != nullrev` as a
     special meaning compared to the reverse in the context of filelog-based
     copytracing. issue6528 exists because new code assumed that parent ordering
     didn't matter, so this detects if the revision contains metadata (since
     it's only used for filelog-based copytracing) and its parents are in the
     "wrong" order."""
     try:
         raw_text = full_text()
     except error.CensoredNodeError:
         # We don't care about censored nodes as they never carry metadata
         return False
 
     # raw text can be a `memoryview`, which doesn't implement `startswith`
     has_meta = bytes(raw_text[:2]) == b'\x01\n'
     if metadata_cache is not None:
         metadata_cache[filerev] = has_meta
     if has_meta:
         (p1, p2) = parents_revs()
         if p1 != nullrev and p2 == nullrev:
             return True
     return False
 
 
 def _is_revision_affected_fast(repo, fl, filerev, metadata_cache):
     rl = fl._revlog
     is_censored = lambda: rl.iscensored(filerev)
     delta_base = lambda: rl.deltaparent(filerev)
     delta = lambda: rl._chunk(filerev)
     full_text = lambda: rl.rawdata(filerev)
     parent_revs = lambda: rl.parentrevs(filerev)
     return _is_revision_affected_fast_inner(
         is_censored,
         delta_base,
         delta,
         full_text,
         parent_revs,
         filerev,
         metadata_cache,
     )
 
 
 def _is_revision_affected_fast_inner(
     is_censored,
     delta_base,
     delta,
     full_text,
     parent_revs,
     filerev,
     metadata_cache,
 ):
     """Optimization fast-path for `_is_revision_affected`.
 
     `metadata_cache` is a dict of `{rev: has_metadata}` which allows any
     revision to check if its base has metadata, saving computation of the full
     text, instead looking at the current delta.
 
     This optimization only works if the revisions are looked at in order."""
 
     if is_censored():
         # Censored revisions don't contain metadata, so they cannot be affected
         metadata_cache[filerev] = False
         return False
 
     p1, p2 = parent_revs()
     if p1 == nullrev or p2 != nullrev:
         return False
 
     delta_parent = delta_base()
     parent_has_metadata = metadata_cache.get(delta_parent)
     if parent_has_metadata is None:
         return _is_revision_affected_inner(
             full_text,
             parent_revs,
             filerev,
             metadata_cache,
         )
 
     chunk = delta()
     if not len(chunk):
         # No diff for this revision
         return parent_has_metadata
 
     header_length = 12
     if len(chunk) < header_length:
         raise error.Abort(_(b"patch cannot be decoded"))
 
     start, _end, _length = struct.unpack(b">lll", chunk[:header_length])
 
     if start < 2:  # len(b'\x01\n') == 2
         # This delta does *something* to the metadata marker (if any).
         # Check it the slow way
         is_affected = _is_revision_affected_inner(
             full_text,
             parent_revs,
             filerev,
             metadata_cache,
         )
         return is_affected
 
     # The diff did not remove or add the metadata header, it's then in the same
     # situation as its parent
     metadata_cache[filerev] = parent_has_metadata
     return parent_has_metadata
 
 
 def _from_report(ui, repo, context, from_report, dry_run):
     """
     Fix the revisions given in the `from_report` file, but still checks if the
     revisions are indeed affected to prevent an unfortunate cyclic situation
     where we'd swap well-ordered parents again.
 
     See the doc for `debug_fix_issue6528` for the format documentation.
     """
     ui.write(_(b"loading report file '%s'\n") % from_report)
 
     with context(), open(from_report, mode='rb') as f:
         for line in f.read().split(b'\n'):
             if not line:
                 continue
             filenodes, filename = line.split(b' ', 1)
             fl = _filelog_from_filename(repo, filename)
             to_fix = set(
                 fl.rev(binascii.unhexlify(n)) for n in filenodes.split(b',')
             )
             excluded = set()
 
             for filerev in to_fix:
                 if _is_revision_affected(fl, filerev):
                     msg = b"found affected revision %d for filelog '%s'\n"
                     ui.warn(msg % (filerev, filename))
                 else:
                     msg = _(b"revision %s of file '%s' is not affected\n")
                     msg %= (binascii.hexlify(fl.node(filerev)), filename)
                     ui.warn(msg)
                     excluded.add(filerev)
 
             to_fix = to_fix - excluded
             if not to_fix:
                 msg = _(b"no affected revisions were found for '%s'\n")
                 ui.write(msg % filename)
                 continue
             if not dry_run:
                 _reorder_filelog_parents(repo, fl, sorted(to_fix))
 
 
 def filter_delta_issue6528(revlog, deltas_iter):
     """filter incomind deltas to repaire issue 6528 on the fly"""
     metadata_cache = {}
 
     deltacomputer = deltas.deltacomputer(revlog)
 
     for rev, d in enumerate(deltas_iter, len(revlog)):
         (
             node,
             p1_node,
             p2_node,
             linknode,
             deltabase,
             delta,
             flags,
             sidedata,
         ) = d
 
         if not revlog.index.has_node(deltabase):
             raise error.LookupError(
                 deltabase, revlog.radix, _(b'unknown parent')
             )
         base_rev = revlog.rev(deltabase)
         if not revlog.index.has_node(p1_node):
             raise error.LookupError(p1_node, revlog.radix, _(b'unknown parent'))
         p1_rev = revlog.rev(p1_node)
         if not revlog.index.has_node(p2_node):
             raise error.LookupError(p2_node, revlog.radix, _(b'unknown parent'))
         p2_rev = revlog.rev(p2_node)
 
         is_censored = lambda: bool(flags & REVIDX_ISCENSORED)
         delta_base = lambda: revlog.rev(delta_base)
         delta_base = lambda: base_rev
         parent_revs = lambda: (p1_rev, p2_rev)
 
         def full_text():
             # note: being able to reuse the full text computation in the
             # underlying addrevision would be useful however this is a bit too
             # intrusive the for the "quick" issue6528 we are writing before the
             # 5.8 release
             textlen = mdiff.patchedsize(revlog.size(base_rev), delta)
 
             revinfo = revlogutils.revisioninfo(
                 node,
                 p1_node,
                 p2_node,
                 [None],
                 textlen,
                 (base_rev, delta),
                 flags,
             )
             return deltacomputer.buildtext(revinfo)
 
         is_affected = _is_revision_affected_fast_inner(
             is_censored,
             delta_base,
             lambda: delta,
             full_text,
             parent_revs,
             rev,
             metadata_cache,
         )
         if is_affected:
             d = (
                 node,
                 p2_node,
                 p1_node,
                 linknode,
                 deltabase,
                 delta,
                 flags,
                 sidedata,
             )
         yield d
 
 
 def repair_issue6528(
     ui, repo, dry_run=False, to_report=None, from_report=None, paranoid=False
 ):
     @contextlib.contextmanager
     def context():
         if dry_run or to_report:  # No need for locking
             yield
         else:
             with repo.wlock(), repo.lock():
                 yield
 
     if from_report:
         return _from_report(ui, repo, context, from_report, dry_run)
 
     report_entries = []
 
     with context():
         files = list(
             entry
             for entry in repo.store.data_entries()
             if entry.is_revlog and entry.is_filelog
         )
 
         progress = ui.makeprogress(
             _(b"looking for affected revisions"),
             unit=_(b"filelogs"),
             total=len(files),
         )
         found_nothing = True
 
         for entry in files:
             progress.increment()
             filename = entry.target_id
             fl = _filelog_from_filename(repo, entry.target_id)
 
             # Set of filerevs (or hex filenodes if `to_report`) that need fixing
             to_fix = set()
             metadata_cache = {}
             for filerev in fl.revs():
                 affected = _is_revision_affected_fast(
                     repo, fl, filerev, metadata_cache
                 )
                 if paranoid:
                     slow = _is_revision_affected(fl, filerev)
                     if slow != affected:
                         msg = _(b"paranoid check failed for '%s' at node %s")
                         node = binascii.hexlify(fl.node(filerev))
                         raise error.Abort(msg % (filename, node))
                 if affected:
                     msg = b"found affected revision %d for file '%s'\n"
                     ui.warn(msg % (filerev, filename))
                     found_nothing = False
                     if not dry_run:
                         if to_report:
                             to_fix.add(binascii.hexlify(fl.node(filerev)))
                         else:
                             to_fix.add(filerev)
 
             if to_fix:
                 to_fix = sorted(to_fix)
                 if to_report:
                     report_entries.append((filename, to_fix))
                 else:
                     _reorder_filelog_parents(repo, fl, to_fix)
 
         if found_nothing:
             ui.write(_(b"no affected revisions were found\n"))
 
         if to_report and report_entries:
             with open(to_report, mode="wb") as f:
                 for path, to_fix in report_entries:
                     f.write(b"%s %s\n" % (b",".join(to_fix), path))
 
         progress.complete()