rust-revlog: teach the revlog opening code to read the repo options

This will become necessary as we start writing revlog data from Rust.

mercurial/revlog.py

@@ -1,4056 +1,4059 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 functools
 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):
+def parse_index_v1_mixed(data, inline, default_header):
     index, cache = parse_index_v1(data, inline)
-    return rustrevlog.MixedIndex(index, data), cache
+    return rustrevlog.MixedIndex(index, data, default_header), 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)
 
     # The size of the uncompressed cache compared to the largest revision seen.
     uncompressed_cache_factor = attr.ib(default=None)
 
     # The number of chunk cached
     uncompressed_cache_count = attr.ib(default=None)
 
     # 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 _InnerRevlog:
     """An inner layer of the revlog object
 
     That layer exist to be able to delegate some operation to Rust, its
     boundaries are arbitrary and based on what we can delegate to Rust.
     """
 
     def __init__(
         self,
         opener,
         index,
         index_file,
         data_file,
         sidedata_file,
         inline,
         data_config,
         delta_config,
         feature_config,
         chunk_cache,
         default_compression_header,
     ):
         self.opener = opener
         self.index = index
 
         self.index_file = index_file
         self.data_file = data_file
         self.sidedata_file = sidedata_file
         self.inline = inline
         self.data_config = data_config
         self.delta_config = delta_config
         self.feature_config = feature_config
 
         # used during diverted write.
         self._orig_index_file = None
 
         self._default_compression_header = default_compression_header
 
         # index
 
         # 3-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._segmentfile = randomaccessfile.randomaccessfile(
             self.opener,
             (self.index_file if self.inline else self.data_file),
             self.data_config.chunk_cache_size,
             chunk_cache,
         )
         self._segmentfile_sidedata = randomaccessfile.randomaccessfile(
             self.opener,
             self.sidedata_file,
             self.data_config.chunk_cache_size,
         )
 
         # revlog header -> revlog compressor
         self._decompressors = {}
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
 
         # cache some uncompressed chunks
         # rev → uncompressed_chunk
         #
         # the max cost is dynamically updated to be proportionnal to the
         # size of revision we actually encounter.
         self._uncompressed_chunk_cache = None
         if self.data_config.uncompressed_cache_factor is not None:
             self._uncompressed_chunk_cache = util.lrucachedict(
                 self.data_config.uncompressed_cache_count,
                 maxcost=65536,  # some arbitrary initial value
             )
 
         self._delay_buffer = None
 
     def __len__(self):
         return len(self.index)
 
     def clear_cache(self):
         assert not self.is_delaying
         self._revisioncache = None
         if self._uncompressed_chunk_cache is not None:
             self._uncompressed_chunk_cache.clear()
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
 
     @property
     def canonical_index_file(self):
         if self._orig_index_file is not None:
             return self._orig_index_file
         return self.index_file
 
     @property
     def is_delaying(self):
         """is the revlog is currently delaying the visibility of written data?
 
         The delaying mechanism can be either in-memory or written on disk in a
         side-file."""
         return (self._delay_buffer is not None) or (
             self._orig_index_file is not None
         )
 
     # Derived from index values.
 
     def start(self, rev):
         """the offset of the data chunk for this revision"""
         return int(self.index[rev][0] >> 16)
 
     def length(self, rev):
         """the length of the data chunk for this revision"""
         return self.index[rev][1]
 
     def end(self, rev):
         """the end of the data chunk for this revision"""
         return self.start(rev) + self.length(rev)
 
     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.delta_config.sparse_revlog:
             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 _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
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self.feature_config.compression_engine]
         return engine.revlogcompressor(
             self.feature_config.compression_engine_options
         )
 
     @util.propertycache
     def _decompressor(self):
         """the default decompressor"""
         if self._default_compression_header is None:
             return None
         t = self._default_compression_header
         c = self._get_decompressor(t)
         return c.decompress
 
     def _get_decompressor(self, t):
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(
                     self.feature_config.compression_engine_options
                 )
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
         return compressor
 
     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)
 
     @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
         elif self._delay_buffer is not None and self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         else:
             with self._segmentfile.reading():
                 with self._segmentfile_sidedata.reading():
                     yield
 
     @property
     def is_writing(self):
         """True is a writing context is open"""
         return self._writinghandles is not None
 
     @property
     def is_open(self):
         """True if any file handle is being held
 
         Used for assert and debug in the python code"""
         return self._segmentfile.is_open or self._segmentfile_sidedata.is_open
 
     @contextlib.contextmanager
     def writing(self, transaction, data_end=None, sidedata_end=None):
         """Open the revlog files for writing
 
         Add content to a revlog should be done within such context.
         """
         if self.is_writing:
             yield
         else:
             ifh = dfh = sdfh = None
             try:
                 r = len(self.index)
                 # opening the data file.
                 dsize = 0
                 if r:
                     dsize = self.end(r - 1)
                 dfh = None
                 if not self.inline:
                     try:
                         dfh = self.opener(self.data_file, mode=b"r+")
                         if data_end is None:
                             dfh.seek(0, os.SEEK_END)
                         else:
                             dfh.seek(data_end, os.SEEK_SET)
                     except FileNotFoundError:
                         dfh = self.opener(self.data_file, mode=b"w+")
                     transaction.add(self.data_file, dsize)
                 if self.sidedata_file is not None:
                     assert sidedata_end is not None
                     # revlog-v2 does not inline, help Pytype
                     assert dfh is not None
                     try:
                         sdfh = self.opener(self.sidedata_file, mode=b"r+")
                         dfh.seek(sidedata_end, os.SEEK_SET)
                     except FileNotFoundError:
                         sdfh = self.opener(self.sidedata_file, mode=b"w+")
                     transaction.add(self.sidedata_file, sidedata_end)
 
                 # opening the index file.
                 isize = r * self.index.entry_size
                 ifh = self.__index_write_fp()
                 if self.inline:
                     transaction.add(self.index_file, dsize + isize)
                 else:
                     transaction.add(self.index_file, 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
             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 __index_write_fp(self, index_end=None):
         """internal method to open the index file for writing
 
         You should not use this directly and use `_writing` instead
         """
         try:
             if self._delay_buffer is None:
                 f = self.opener(
                     self.index_file,
                     mode=b"r+",
                     checkambig=self.data_config.check_ambig,
                 )
             else:
                 # check_ambig affect we way we open file for writing, however
                 # here, we do not actually open a file for writting as write
                 # will appened to a delay_buffer. So check_ambig is not
                 # meaningful and unneeded here.
                 f = randomaccessfile.appender(
                     self.opener, self.index_file, b"r+", self._delay_buffer
                 )
             if index_end is None:
                 f.seek(0, os.SEEK_END)
             else:
                 f.seek(index_end, os.SEEK_SET)
             return f
         except FileNotFoundError:
             if self._delay_buffer is None:
                 return self.opener(
                     self.index_file,
                     mode=b"w+",
                     checkambig=self.data_config.check_ambig,
                 )
             else:
                 return randomaccessfile.appender(
                     self.opener, self.index_file, b"w+", self._delay_buffer
                 )
 
     def __index_new_fp(self):
         """internal method to create a new index file for writing
 
         You should not use this unless you are upgrading from inline revlog
         """
         return self.opener(
             self.index_file,
             mode=b"w",
             checkambig=self.data_config.check_ambig,
             atomictemp=True,
         )
 
     def split_inline(self, tr, header, new_index_file_path=None):
         """split the data of an inline revlog into an index and a data file"""
         assert self._delay_buffer is None
         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
 
         new_dfh = self.opener(self.data_file, mode=b"w+")
         new_dfh.truncate(0)  # drop any potentially existing data
         try:
             with self.reading():
                 for r in range(len(self.index)):
                     new_dfh.write(self.get_segment_for_revs(r, r)[1])
                 new_dfh.flush()
 
             if new_index_file_path is not None:
                 self.index_file = new_index_file_path
             with self.__index_new_fp() as fp:
                 self.inline = False
                 for i in range(len(self.index)):
                     e = self.index.entry_binary(i)
                     if i == 0:
                         packed_header = self.index.pack_header(header)
                         e = packed_header + e
                     fp.write(e)
 
                 # If we don't use side-write, the temp file replace the real
                 # index when we exit the context manager
 
             self._segmentfile = randomaccessfile.randomaccessfile(
                 self.opener,
                 self.data_file,
                 self.data_config.chunk_cache_size,
             )
 
             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()
         return self.index_file
 
     def get_segment_for_revs(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.
 
         API: we should consider making this a private part of the InnerRevlog
         at some point.
         """
         # 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.
         """
         if self._uncompressed_chunk_cache is not None:
             uncomp = self._uncompressed_chunk_cache.get(rev)
             if uncomp is not None:
                 return uncomp
 
         compression_mode = self.index[rev][10]
         data = self.get_segment_for_revs(rev, rev)[1]
         if compression_mode == COMP_MODE_PLAIN:
             uncomp = data
         elif compression_mode == COMP_MODE_DEFAULT:
             uncomp = self._decompressor(data)
         elif compression_mode == COMP_MODE_INLINE:
             uncomp = self.decompress(data)
         else:
             msg = b'unknown compression mode %d'
             msg %= compression_mode
             raise error.RevlogError(msg)
         if self._uncompressed_chunk_cache is not None:
             self._uncompressed_chunk_cache.insert(rev, uncomp, cost=len(uncomp))
         return uncomp
 
     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
 
         fetched_revs = []
         fadd = fetched_revs.append
 
         chunks = []
         ladd = chunks.append
 
         if self._uncompressed_chunk_cache is None:
             fetched_revs = revs
         else:
             for rev in revs:
                 cached_value = self._uncompressed_chunk_cache.get(rev)
                 if cached_value is None:
                     fadd(rev)
                 else:
                     ladd((rev, cached_value))
 
         if not fetched_revs:
             slicedchunks = ()
         elif not self.data_config.with_sparse_read:
             slicedchunks = (fetched_revs,)
         else:
             slicedchunks = deltautil.slicechunk(
                 self,
                 fetched_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.get_segment_for_revs(firstrev, lastrev)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 for rev in revschunk:
                     ladd((rev, self._chunk(rev)))
 
             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:
                     c = c
                 elif comp_mode == COMP_MODE_INLINE:
                     c = decomp(c)
                 elif comp_mode == COMP_MODE_DEFAULT:
                     c = def_decomp(c)
                 else:
                     msg = b'unknown compression mode %d'
                     msg %= comp_mode
                     raise error.RevlogError(msg)
                 ladd((rev, c))
                 if self._uncompressed_chunk_cache is not None:
                     self._uncompressed_chunk_cache.insert(rev, c, len(c))
 
         chunks.sort()
         return [x[1] for x in chunks]
 
     def raw_text(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:
             cachedrev = self._revisioncache[1]
 
         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._inner._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         if self._uncompressed_chunk_cache is not None:
             # dynamically update the uncompressed_chunk_cache size to the
             # largest revision we saw in this revlog.
             factor = self.data_config.uncompressed_cache_factor
             candidate_size = rawsize * factor
             if candidate_size > self._uncompressed_chunk_cache.maxcost:
                 self._uncompressed_chunk_cache.maxcost = candidate_size
 
         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, sidedata_end):
         """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 sidedata_end < sidedata_offset + sidedata_size:
             filename = self.sidedata_file
             end = 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 write_entry(
         self,
         transaction,
         entry,
         data,
         link,
         offset,
         sidedata,
         sidedata_offset,
         index_end,
         data_end,
         sidedata_end,
     ):
         # 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 index_end is None:
             ifh.seek(0, os.SEEK_END)
         else:
             ifh.seek(index_end, os.SEEK_SET)
         if dfh:
             if data_end is None:
                 dfh.seek(0, os.SEEK_END)
             else:
                 dfh.seek(data_end, os.SEEK_SET)
         if sdfh:
             sdfh.seek(sidedata_end, os.SEEK_SET)
 
         curr = len(self.index) - 1
         if not self.inline:
             transaction.add(self.data_file, offset)
             if self.sidedata_file:
                 transaction.add(self.sidedata_file, sidedata_offset)
             transaction.add(self.canonical_index_file, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 sdfh.write(sidedata)
             if self._delay_buffer is None:
                 ifh.write(entry)
             else:
                 self._delay_buffer.append(entry)
         elif self._delay_buffer is not None:
             msg = b'invalid delayed write on inline revlog'
             raise error.ProgrammingError(msg)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self.canonical_index_file, offset)
             assert not sidedata
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
         return (
             ifh.tell(),
             dfh.tell() if dfh else None,
             sdfh.tell() if sdfh else None,
         )
 
     def _divert_index(self):
         return self.index_file + b'.a'
 
     def delay(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         if self._delay_buffer is not None or self._orig_index_file is not None:
             # delay or divert already in place
             return None
         elif len(self.index) == 0:
             self._orig_index_file = self.index_file
             self.index_file = self._divert_index()
             assert self._orig_index_file is not None
             assert self.index_file is not None
             if self.opener.exists(self.index_file):
                 self.opener.unlink(self.index_file)
             return self.index_file
         else:
             self._delay_buffer = []
             return None
 
     def write_pending(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         if self._orig_index_file is not None:
             return None, True
         any_pending = False
         pending_index_file = self._divert_index()
         if self.opener.exists(pending_index_file):
             self.opener.unlink(pending_index_file)
         util.copyfile(
             self.opener.join(self.index_file),
             self.opener.join(pending_index_file),
         )
         if self._delay_buffer:
             with self.opener(pending_index_file, b'r+') as ifh:
                 ifh.seek(0, os.SEEK_END)
                 ifh.write(b"".join(self._delay_buffer))
             any_pending = True
         self._delay_buffer = None
         self._orig_index_file = self.index_file
         self.index_file = pending_index_file
         return self.index_file, any_pending
 
     def finalize_pending(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
 
         delay = self._delay_buffer is not None
         divert = self._orig_index_file is not None
 
         if delay and divert:
             assert False, "unreachable"
         elif delay:
             if self._delay_buffer:
                 with self.opener(self.index_file, b'r+') as ifh:
                     ifh.seek(0, os.SEEK_END)
                     ifh.write(b"".join(self._delay_buffer))
             self._delay_buffer = None
         elif divert:
             if self.opener.exists(self.index_file):
                 self.opener.rename(
                     self.index_file,
                     self._orig_index_file,
                     checkambig=True,
                 )
             self.index_file = self._orig_index_file
             self._orig_index_file = None
         else:
             msg = b"not delay or divert found on this revlog"
             raise error.ProgrammingError(msg)
         return self.canonical_index_file
 
 
 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"""
         if len(header_bytes) == 0:
             return True
 
         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,
         data_config=None,
         delta_config=None,
         feature_config=None,
         may_inline=True,  # may inline new revlog
     ):
         """
         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.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._may_inline = may_inline
         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 feature_config is not None:
             self.feature_config = feature_config.copy()
         elif 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 data_config is not None:
             self.data_config = data_config.copy()
         elif 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 delta_config is not None:
             self.delta_config = delta_config.copy()
         elif b'delta-config' in self.opener.options:
             self.delta_config = self.opener.options[b'delta-config'].copy()
         else:
             self.delta_config = DeltaConfig()
         self.delta_config.upper_bound_comp = upperboundcomp
 
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
 
         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)
         # prevent nesting of addgroup
         self._adding_group = None
 
         chunk_cache = self._loadindex()
         self._load_inner(chunk_cache)
         self._concurrencychecker = concurrencychecker
 
     def _init_opts(self):
         """process options (from above/config) to setup associated default revlog mode
 
         These values might be affected when actually reading on disk information.
 
         The relevant values are returned for use in _loadindex().
 
         * newversionflags:
             version header to use if we need to create a new revlog
 
         * mmapindexthreshold:
             minimal index size for start to use mmap
 
         * force_nodemap:
             force the usage of a "development" version of the nodemap code
         """
         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
             if self._may_inline:
                 new_header |= 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.data_config.mmap_large_index:
             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.opener(self._indexfile, mode=b"r") 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._inner.get_segment_for_revs(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.opener(self._indexfile, mode=b"r") 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
+            self._parse_index = functools.partial(
+                parse_index_v1_mixed, default_header=new_header
+            )
         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
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
 
         return chunkcache
 
     def _load_inner(self, chunk_cache):
         if self._docket is None:
             default_compression_header = None
         else:
             default_compression_header = self._docket.default_compression_header
 
         self._inner = _InnerRevlog(
             opener=self.opener,
             index=self.index,
             index_file=self._indexfile,
             data_file=self._datafile,
             sidedata_file=self._sidedatafile,
             inline=self._inline,
             data_config=self.data_config,
             delta_config=self.delta_config,
             feature_config=self.feature_config,
             chunk_cache=chunk_cache,
             default_compression_header=default_compression_header,
         )
 
     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 _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self._datafile, mode=mode)
 
     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._chainbasecache.clear()
         self._inner.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.feature_config.has_side_data:
             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.feature_config.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.feature_config.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):
         return self._inner._deltachain(rev, stoprev=stoprev)
 
     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 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"""
         ret = self._inner.issnapshot(rev)
         self.issnapshot = self._inner.issnapshot
         return ret
 
     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._inner._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._inner._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 _rawtext(self, node, rev):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._inner._revisioncache:
             if self._inner._revisioncache[0] == node:
                 return (rev, self._inner._revisioncache[2], True)
 
         if rev is None:
             rev = self.rev(node)
 
         return self._inner.raw_text(node, 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._inner._revisioncache = (node, rev, rawtext)
 
         return text
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         sidedata_end = None
         if self._docket is not None:
             sidedata_end = self._docket.sidedata_end
         return self._inner.sidedata(rev, sidedata_end)
 
     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._inner._revisioncache
                     and self._inner._revisioncache[0] == node
                 ):
                     self._inner._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.feature_config.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 (self._may_inline and total_size < _maxinline):
             return
 
         if self._docket is not None:
             msg = b"inline revlog should not have a docket"
             raise error.ProgrammingError(msg)
 
         # In the common case, we enforce inline size because the revlog has
         # been appened too. And in such case, it must have an initial offset
         # recorded in the transaction.
         troffset = tr.findoffset(self._inner.canonical_index_file)
         pre_touched = troffset is not None
         if not pre_touched and self.target[0] != KIND_CHANGELOG:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self._indexfile
             )
 
         tr.addbackup(self._inner.canonical_index_file, for_offset=pre_touched)
         tr.add(self._datafile, 0)
 
         new_index_file_path = None
         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
                     maybe_self._inner.index_file = maybe_self._indexfile
 
             def abort_callback(tr):
                 maybe_self = weak_self()
                 if maybe_self is not None:
                     maybe_self._indexfile = old_index_file_path
                     maybe_self._inner.inline = True
                     maybe_self._inner.index_file = 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)
 
         self._format_flags &= ~FLAG_INLINE_DATA
         self._inner.split_inline(
             tr,
             self._format_flags | self._format_version,
             new_index_file_path=new_index_file_path,
         )
 
         self._inline = False
         if new_index_file_path is not None:
             self._indexfile = new_index_file_path
 
         nodemaputil.setup_persistent_nodemap(tr, self)
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     @contextlib.contextmanager
     def reading(self):
         with self._inner.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._inner.is_writing:
             yield
         else:
             data_end = None
             sidedata_end = None
             if self._docket is not None:
                 data_end = self._docket.data_end
                 sidedata_end = self._docket.sidedata_end
             with self._inner.writing(
                 transaction,
                 data_end=data_end,
                 sidedata_end=sidedata_end,
             ):
                 yield
                 if self._docket is not None:
                     self._write_docket(transaction)
 
     @property
     def is_delaying(self):
         return self._inner.is_delaying
 
     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.feature_config.has_side_data:
             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):
         return self._inner.compress(data)
 
     def decompress(self, data):
         return self._inner.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._inner._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._inner._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.delta_config.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.feature_config.has_side_data:
             sidedata_compression_mode = COMP_MODE_PLAIN
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = self._docket.sidedata_end
             h, comp_sidedata = self._inner.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.feature_config.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._inner._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.
         index_end = data_end = sidedata_end = None
         if self._docket is not None:
             index_end = self._docket.index_end
             data_end = self._docket.data_end
             sidedata_end = self._docket.sidedata_end
 
         files_end = self._inner.write_entry(
             transaction,
             entry,
             data,
             link,
             offset,
             sidedata,
             sidedata_offset,
             index_end,
             data_end,
             sidedata_end,
         )
         self._enforceinlinesize(transaction)
         if self._docket is not None:
             self._docket.index_end = files_end[0]
             self._docket.data_end = files_end[1]
             self._docket.sidedata_end = files_end[2]
 
         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.delta_config.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.feature_config.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.feature_config.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._chaininfocache = util.lrucachedict(500)
         self._inner.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):
         """return list of files that compose this revlog"""
         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(), destrevlog._writing(tr):
                 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.delta_config.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.delta_config.lazy_delta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._inner._chunk(rev)))
 
                 sidedata = None
                 if not cachedelta:
                     try:
                         rawtext = self._revisiondata(rev)
                     except error.CensoredNodeError as censored:
                         assert flags & REVIDX_ISCENSORED
                         rawtext = censored.tombstone
                     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]
 
                 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.feature_config.has_side_data:
             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._inner._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.feature_config.has_side_data:
                     sidedata_compression_mode = COMP_MODE_PLAIN
                     h, comp_sidedata = self._inner.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)

rust/hg-core/src/operations/debugdata.rs

@@ -1,38 +1,38 b''
 // debugdata.rs
 //
 // Copyright 2020 Antoine Cezar <[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.
 
 use crate::repo::Repo;
-use crate::requirements;
 use crate::revlog::{Revlog, RevlogError};
 
 /// Kind of data to debug
-#[derive(Debug, Copy, Clone)]
+#[derive(Debug, Copy, Clone, PartialEq, Eq)]
 pub enum DebugDataKind {
     Changelog,
     Manifest,
 }
 
 /// Dump the contents data of a revision.
 pub fn debug_data(
     repo: &Repo,
     revset: &str,
     kind: DebugDataKind,
 ) -> Result<Vec<u8>, RevlogError> {
     let index_file = match kind {
         DebugDataKind::Changelog => "00changelog.i",
         DebugDataKind::Manifest => "00manifest.i",
     };
-    let use_nodemap = repo
-        .requirements()
-        .contains(requirements::NODEMAP_REQUIREMENT);
-    let revlog =
-        Revlog::open(&repo.store_vfs(), index_file, None, use_nodemap)?;
+    let revlog = Revlog::open(
+        &repo.store_vfs(),
+        index_file,
+        None,
+        repo.default_revlog_options(kind == DebugDataKind::Changelog)?,
+    )?;
     let rev =
         crate::revset::resolve_rev_number_or_hex_prefix(revset, &revlog)?;
     let data = revlog.get_rev_data_for_checked_rev(rev)?;
     Ok(data.into_owned())
 }

rust/hg-core/src/repo.rs

@@ -1,782 +1,820 b''
 use crate::changelog::Changelog;
 use crate::config::{Config, ConfigError, ConfigParseError};
 use crate::dirstate::DirstateParents;
 use crate::dirstate_tree::dirstate_map::DirstateMapWriteMode;
 use crate::dirstate_tree::on_disk::Docket as DirstateDocket;
 use crate::dirstate_tree::owning::OwningDirstateMap;
 use crate::errors::HgResultExt;
 use crate::errors::{HgError, IoResultExt};
 use crate::lock::{try_with_lock_no_wait, LockError};
 use crate::manifest::{Manifest, Manifestlog};
+use crate::requirements::{
+    CHANGELOGV2_REQUIREMENT, GENERALDELTA_REQUIREMENT, NODEMAP_REQUIREMENT,
+    REVLOGV1_REQUIREMENT, REVLOGV2_REQUIREMENT,
+};
 use crate::revlog::filelog::Filelog;
 use crate::revlog::RevlogError;
 use crate::utils::debug::debug_wait_for_file_or_print;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::utils::SliceExt;
 use crate::vfs::{is_dir, is_file, Vfs};
-use crate::DirstateError;
-use crate::{requirements, NodePrefix, UncheckedRevision};
+use crate::{
+    requirements, NodePrefix, RevlogVersionOptions, UncheckedRevision,
+};
+use crate::{DirstateError, RevlogOpenOptions};
 use std::cell::{Ref, RefCell, RefMut};
 use std::collections::HashSet;
 use std::io::Seek;
 use std::io::SeekFrom;
 use std::io::Write as IoWrite;
 use std::path::{Path, PathBuf};
 
 const V2_MAX_READ_ATTEMPTS: usize = 5;
 
 type DirstateMapIdentity = (Option<u64>, Option<Vec<u8>>, usize);
 
 /// A repository on disk
 pub struct Repo {
     working_directory: PathBuf,
     dot_hg: PathBuf,
     store: PathBuf,
     requirements: HashSet<String>,
     config: Config,
     dirstate_parents: LazyCell<DirstateParents>,
     dirstate_map: LazyCell<OwningDirstateMap>,
     changelog: LazyCell<Changelog>,
     manifestlog: LazyCell<Manifestlog>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum RepoError {
     NotFound {
         at: PathBuf,
     },
     #[from]
     ConfigParseError(ConfigParseError),
     #[from]
     Other(HgError),
 }
 
 impl From<ConfigError> for RepoError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 impl Repo {
     /// tries to find nearest repository root in current working directory or
     /// its ancestors
     pub fn find_repo_root() -> Result<PathBuf, RepoError> {
         let current_directory = crate::utils::current_dir()?;
         // ancestors() is inclusive: it first yields `current_directory`
         // as-is.
         for ancestor in current_directory.ancestors() {
             if is_dir(ancestor.join(".hg"))? {
                 return Ok(ancestor.to_path_buf());
             }
         }
         Err(RepoError::NotFound {
             at: current_directory,
         })
     }
 
     /// Find a repository, either at the given path (which must contain a `.hg`
     /// sub-directory) or by searching the current directory and its
     /// ancestors.
     ///
     /// A method with two very different "modes" like this usually a code smell
     /// to make two methods instead, but in this case an `Option` is what rhg
     /// sub-commands get from Clap for the `-R` / `--repository` CLI argument.
     /// Having two methods would just move that `if` to almost all callers.
     pub fn find(
         config: &Config,
         explicit_path: Option<PathBuf>,
     ) -> Result<Self, RepoError> {
         if let Some(root) = explicit_path {
             if is_dir(root.join(".hg"))? {
                 Self::new_at_path(root, config)
             } else if is_file(&root)? {
                 Err(HgError::unsupported("bundle repository").into())
             } else {
                 Err(RepoError::NotFound { at: root })
             }
         } else {
             let root = Self::find_repo_root()?;
             Self::new_at_path(root, config)
         }
     }
 
     /// To be called after checking that `.hg` is a sub-directory
     fn new_at_path(
         working_directory: PathBuf,
         config: &Config,
     ) -> Result<Self, RepoError> {
         let dot_hg = working_directory.join(".hg");
 
         let mut repo_config_files =
             vec![dot_hg.join("hgrc"), dot_hg.join("hgrc-not-shared")];
 
         let hg_vfs = Vfs { base: &dot_hg };
         let mut reqs = requirements::load_if_exists(hg_vfs)?;
         let relative =
             reqs.contains(requirements::RELATIVE_SHARED_REQUIREMENT);
         let shared =
             reqs.contains(requirements::SHARED_REQUIREMENT) || relative;
 
         // From `mercurial/localrepo.py`:
         //
         // if .hg/requires contains the sharesafe requirement, it means
         // there exists a `.hg/store/requires` too and we should read it
         // NOTE: presence of SHARESAFE_REQUIREMENT imply that store requirement
         // is present. We never write SHARESAFE_REQUIREMENT for a repo if store
         // is not present, refer checkrequirementscompat() for that
         //
         // However, if SHARESAFE_REQUIREMENT is not present, it means that the
         // repository was shared the old way. We check the share source
         // .hg/requires for SHARESAFE_REQUIREMENT to detect whether the
         // current repository needs to be reshared
         let share_safe = reqs.contains(requirements::SHARESAFE_REQUIREMENT);
 
         let store_path;
         if !shared {
             store_path = dot_hg.join("store");
         } else {
             let bytes = hg_vfs.read("sharedpath")?;
             let mut shared_path =
                 get_path_from_bytes(bytes.trim_end_matches(|b| b == b'\n'))
                     .to_owned();
             if relative {
                 shared_path = dot_hg.join(shared_path)
             }
             if !is_dir(&shared_path)? {
                 return Err(HgError::corrupted(format!(
                     ".hg/sharedpath points to nonexistent directory {}",
                     shared_path.display()
                 ))
                 .into());
             }
 
             store_path = shared_path.join("store");
 
             let source_is_share_safe =
                 requirements::load(Vfs { base: &shared_path })?
                     .contains(requirements::SHARESAFE_REQUIREMENT);
 
             if share_safe != source_is_share_safe {
                 return Err(HgError::unsupported("share-safe mismatch").into());
             }
 
             if share_safe {
                 repo_config_files.insert(0, shared_path.join("hgrc"))
             }
         }
         if share_safe {
             reqs.extend(requirements::load(Vfs { base: &store_path })?);
         }
 
         let repo_config = if std::env::var_os("HGRCSKIPREPO").is_none() {
             config.combine_with_repo(&repo_config_files)?
         } else {
             config.clone()
         };
 
         let repo = Self {
             requirements: reqs,
             working_directory,
             store: store_path,
             dot_hg,
             config: repo_config,
             dirstate_parents: LazyCell::new(),
             dirstate_map: LazyCell::new(),
             changelog: LazyCell::new(),
             manifestlog: LazyCell::new(),
         };
 
         requirements::check(&repo)?;
 
         Ok(repo)
     }
 
     pub fn working_directory_path(&self) -> &Path {
         &self.working_directory
     }
 
     pub fn requirements(&self) -> &HashSet<String> {
         &self.requirements
     }
 
     pub fn config(&self) -> &Config {
         &self.config
     }
 
     /// For accessing repository files (in `.hg`), except for the store
     /// (`.hg/store`).
     pub fn hg_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.dot_hg }
     }
 
     /// For accessing repository store files (in `.hg/store`)
     pub fn store_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.store }
     }
 
     /// For accessing the working copy
     pub fn working_directory_vfs(&self) -> Vfs<'_> {
         Vfs {
             base: &self.working_directory,
         }
     }
 
     pub fn try_with_wlock_no_wait<R>(
         &self,
         f: impl FnOnce() -> R,
     ) -> Result<R, LockError> {
         try_with_lock_no_wait(self.hg_vfs(), "wlock", f)
     }
 
     /// Whether this repo should use dirstate-v2.
     /// The presence of `dirstate-v2` in the requirements does not mean that
     /// the on-disk dirstate is necessarily in version 2. In most cases,
     /// a dirstate-v2 file will indeed be found, but in rare cases (like the
     /// upgrade mechanism being cut short), the on-disk version will be a
     /// v1 file.
     /// Semantically, having a requirement only means that a client cannot
     /// properly understand or properly update the repo if it lacks the support
     /// for the required feature, but not that that feature is actually used
     /// in all occasions.
     pub fn use_dirstate_v2(&self) -> bool {
         self.requirements
             .contains(requirements::DIRSTATE_V2_REQUIREMENT)
     }
 
     pub fn has_sparse(&self) -> bool {
         self.requirements.contains(requirements::SPARSE_REQUIREMENT)
     }
 
     pub fn has_narrow(&self) -> bool {
         self.requirements.contains(requirements::NARROW_REQUIREMENT)
     }
 
     pub fn has_nodemap(&self) -> bool {
         self.requirements
             .contains(requirements::NODEMAP_REQUIREMENT)
     }
 
     fn dirstate_file_contents(&self) -> Result<Vec<u8>, HgError> {
         Ok(self
             .hg_vfs()
             .read("dirstate")
             .io_not_found_as_none()?
             .unwrap_or_default())
     }
 
     fn dirstate_identity(&self) -> Result<Option<u64>, HgError> {
         use std::os::unix::fs::MetadataExt;
         Ok(self
             .hg_vfs()
             .symlink_metadata("dirstate")
             .io_not_found_as_none()?
             .map(|meta| meta.ino()))
     }
 
     pub fn dirstate_parents(&self) -> Result<DirstateParents, HgError> {
         Ok(*self
             .dirstate_parents
             .get_or_init(|| self.read_dirstate_parents())?)
     }
 
     fn read_dirstate_parents(&self) -> Result<DirstateParents, HgError> {
         let dirstate = self.dirstate_file_contents()?;
         let parents = if dirstate.is_empty() {
             DirstateParents::NULL
         } else if self.use_dirstate_v2() {
             let docket_res =
                 crate::dirstate_tree::on_disk::read_docket(&dirstate);
             match docket_res {
                 Ok(docket) => docket.parents(),
                 Err(_) => {
                     log::info!(
                         "Parsing dirstate docket failed, \
                         falling back to dirstate-v1"
                     );
                     *crate::dirstate::parsers::parse_dirstate_parents(
                         &dirstate,
                     )?
                 }
             }
         } else {
             *crate::dirstate::parsers::parse_dirstate_parents(&dirstate)?
         };
         self.dirstate_parents.set(parents);
         Ok(parents)
     }
 
     /// Returns the information read from the dirstate docket necessary to
     /// check if the data file has been updated/deleted by another process
     /// since we last read the dirstate.
     /// Namely, the inode, data file uuid and the data size.
     fn get_dirstate_data_file_integrity(
         &self,
     ) -> Result<DirstateMapIdentity, HgError> {
         assert!(
             self.use_dirstate_v2(),
             "accessing dirstate data file ID without dirstate-v2"
         );
         // Get the identity before the contents since we could have a race
         // between the two. Having an identity that is too old is fine, but
         // one that is younger than the content change is bad.
         let identity = self.dirstate_identity()?;
         let dirstate = self.dirstate_file_contents()?;
         if dirstate.is_empty() {
             self.dirstate_parents.set(DirstateParents::NULL);
             Ok((identity, None, 0))
         } else {
             let docket_res =
                 crate::dirstate_tree::on_disk::read_docket(&dirstate);
             match docket_res {
                 Ok(docket) => {
                     self.dirstate_parents.set(docket.parents());
                     Ok((
                         identity,
                         Some(docket.uuid.to_owned()),
                         docket.data_size(),
                     ))
                 }
                 Err(_) => {
                     log::info!(
                         "Parsing dirstate docket failed, \
                         falling back to dirstate-v1"
                     );
                     let parents =
                         *crate::dirstate::parsers::parse_dirstate_parents(
                             &dirstate,
                         )?;
                     self.dirstate_parents.set(parents);
                     Ok((identity, None, 0))
                 }
             }
         }
     }
 
     fn new_dirstate_map(&self) -> Result<OwningDirstateMap, DirstateError> {
         if self.use_dirstate_v2() {
             // The v2 dirstate is split into a docket and a data file.
             // Since we don't always take the `wlock` to read it
             // (like in `hg status`), it is susceptible to races.
             // A simple retry method should be enough since full rewrites
             // only happen when too much garbage data is present and
             // this race is unlikely.
             let mut tries = 0;
 
             while tries < V2_MAX_READ_ATTEMPTS {
                 tries += 1;
                 match self.read_docket_and_data_file() {
                     Ok(m) => {
                         return Ok(m);
                     }
                     Err(e) => match e {
                         DirstateError::Common(HgError::RaceDetected(
                             context,
                         )) => {
                             log::info!(
                                 "dirstate read race detected {} (retry {}/{})",
                                 context,
                                 tries,
                                 V2_MAX_READ_ATTEMPTS,
                             );
                             continue;
                         }
                         _ => {
                             log::info!(
                                 "Reading dirstate v2 failed, \
                                 falling back to v1"
                             );
                             return self.new_dirstate_map_v1();
                         }
                     },
                 }
             }
             let error = HgError::abort(
                 format!("dirstate read race happened {tries} times in a row"),
                 255,
                 None,
             );
             Err(DirstateError::Common(error))
         } else {
             self.new_dirstate_map_v1()
         }
     }
 
     fn new_dirstate_map_v1(&self) -> Result<OwningDirstateMap, DirstateError> {
         debug_wait_for_file_or_print(self.config(), "dirstate.pre-read-file");
         let identity = self.dirstate_identity()?;
         let dirstate_file_contents = self.dirstate_file_contents()?;
         if dirstate_file_contents.is_empty() {
             self.dirstate_parents.set(DirstateParents::NULL);
             Ok(OwningDirstateMap::new_empty(Vec::new()))
         } else {
             let (map, parents) =
                 OwningDirstateMap::new_v1(dirstate_file_contents, identity)?;
             self.dirstate_parents.set(parents);
             Ok(map)
         }
     }
 
     fn read_docket_and_data_file(
         &self,
     ) -> Result<OwningDirstateMap, DirstateError> {
         debug_wait_for_file_or_print(self.config(), "dirstate.pre-read-file");
         let dirstate_file_contents = self.dirstate_file_contents()?;
         let identity = self.dirstate_identity()?;
         if dirstate_file_contents.is_empty() {
             self.dirstate_parents.set(DirstateParents::NULL);
             return Ok(OwningDirstateMap::new_empty(Vec::new()));
         }
         let docket = crate::dirstate_tree::on_disk::read_docket(
             &dirstate_file_contents,
         )?;
         debug_wait_for_file_or_print(
             self.config(),
             "dirstate.post-docket-read-file",
         );
         self.dirstate_parents.set(docket.parents());
         let uuid = docket.uuid.to_owned();
         let data_size = docket.data_size();
 
         let context = "between reading dirstate docket and data file";
         let race_error = HgError::RaceDetected(context.into());
         let metadata = docket.tree_metadata();
 
         let mut map = if crate::vfs::is_on_nfs_mount(docket.data_filename()) {
             // Don't mmap on NFS to prevent `SIGBUS` error on deletion
             let contents = self.hg_vfs().read(docket.data_filename());
             let contents = match contents {
                 Ok(c) => c,
                 Err(HgError::IoError { error, context }) => {
                     match error.raw_os_error().expect("real os error") {
                         // 2 = ENOENT, No such file or directory
                         // 116 = ESTALE, Stale NFS file handle
                         //
                         // TODO match on `error.kind()` when
                         // `ErrorKind::StaleNetworkFileHandle` is stable.
                         2 | 116 => {
                             // Race where the data file was deleted right after
                             // we read the docket, try again
                             return Err(race_error.into());
                         }
                         _ => {
                             return Err(
                                 HgError::IoError { error, context }.into()
                             )
                         }
                     }
                 }
                 Err(e) => return Err(e.into()),
             };
             OwningDirstateMap::new_v2(
                 contents, data_size, metadata, uuid, identity,
             )
         } else {
             match self
                 .hg_vfs()
                 .mmap_open(docket.data_filename())
                 .io_not_found_as_none()
             {
                 Ok(Some(data_mmap)) => OwningDirstateMap::new_v2(
                     data_mmap, data_size, metadata, uuid, identity,
                 ),
                 Ok(None) => {
                     // Race where the data file was deleted right after we
                     // read the docket, try again
                     return Err(race_error.into());
                 }
                 Err(e) => return Err(e.into()),
             }
         }?;
 
         let write_mode_config = self
             .config()
             .get_str(b"devel", b"dirstate.v2.data_update_mode")
             .unwrap_or(Some("auto"))
             .unwrap_or("auto"); // don't bother for devel options
         let write_mode = match write_mode_config {
             "auto" => DirstateMapWriteMode::Auto,
             "force-new" => DirstateMapWriteMode::ForceNewDataFile,
             "force-append" => DirstateMapWriteMode::ForceAppend,
             _ => DirstateMapWriteMode::Auto,
         };
 
         map.with_dmap_mut(|m| m.set_write_mode(write_mode));
 
         Ok(map)
     }
 
     pub fn dirstate_map(
         &self,
     ) -> Result<Ref<OwningDirstateMap>, DirstateError> {
         self.dirstate_map.get_or_init(|| self.new_dirstate_map())
     }
 
     pub fn dirstate_map_mut(
         &self,
     ) -> Result<RefMut<OwningDirstateMap>, DirstateError> {
         self.dirstate_map
             .get_mut_or_init(|| self.new_dirstate_map())
     }
 
     fn new_changelog(&self) -> Result<Changelog, HgError> {
-        Changelog::open(&self.store_vfs(), self.has_nodemap())
+        Changelog::open(&self.store_vfs(), self.default_revlog_options(true)?)
     }
 
     pub fn changelog(&self) -> Result<Ref<Changelog>, HgError> {
         self.changelog.get_or_init(|| self.new_changelog())
     }
 
     pub fn changelog_mut(&self) -> Result<RefMut<Changelog>, HgError> {
         self.changelog.get_mut_or_init(|| self.new_changelog())
     }
 
     fn new_manifestlog(&self) -> Result<Manifestlog, HgError> {
-        Manifestlog::open(&self.store_vfs(), self.has_nodemap())
+        Manifestlog::open(
+            &self.store_vfs(),
+            self.default_revlog_options(false)?,
+        )
     }
 
     pub fn manifestlog(&self) -> Result<Ref<Manifestlog>, HgError> {
         self.manifestlog.get_or_init(|| self.new_manifestlog())
     }
 
     pub fn manifestlog_mut(&self) -> Result<RefMut<Manifestlog>, HgError> {
         self.manifestlog.get_mut_or_init(|| self.new_manifestlog())
     }
 
     /// Returns the manifest of the *changeset* with the given node ID
     pub fn manifest_for_node(
         &self,
         node: impl Into<NodePrefix>,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_node(node.into())?
                 .manifest_node()?
                 .into(),
         )
     }
 
     /// Returns the manifest of the *changeset* with the given revision number
     pub fn manifest_for_rev(
         &self,
         revision: UncheckedRevision,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_rev(revision)?
                 .manifest_node()?
                 .into(),
         )
     }
 
     pub fn has_subrepos(&self) -> Result<bool, DirstateError> {
         if let Some(entry) = self.dirstate_map()?.get(HgPath::new(".hgsub"))? {
             Ok(entry.tracked())
         } else {
             Ok(false)
         }
     }
 
     pub fn filelog(&self, path: &HgPath) -> Result<Filelog, HgError> {
-        Filelog::open(self, path)
+        Filelog::open(self, path, self.default_revlog_options(false)?)
     }
 
     /// Write to disk any updates that were made through `dirstate_map_mut`.
     ///
     /// The "wlock" must be held while calling this.
     /// See for example `try_with_wlock_no_wait`.
     ///
     /// TODO: have a `WritableRepo` type only accessible while holding the
     /// lock?
     pub fn write_dirstate(&self) -> Result<(), DirstateError> {
         let map = self.dirstate_map()?;
         // TODO: Maintain a `DirstateMap::dirty` flag, and return early here if
         // it’s unset
         let parents = self.dirstate_parents()?;
         let (packed_dirstate, old_uuid_to_remove) = if self.use_dirstate_v2() {
             let (identity, uuid, data_size) =
                 self.get_dirstate_data_file_integrity()?;
             let identity_changed = identity != map.old_identity();
             let uuid_changed = uuid.as_deref() != map.old_uuid();
             let data_length_changed = data_size != map.old_data_size();
 
             if identity_changed || uuid_changed || data_length_changed {
                 // If any of identity, uuid or length have changed since
                 // last disk read, don't write.
                 // This is fine because either we're in a command that doesn't
                 // write anything too important (like `hg status`), or we're in
                 // `hg add` and we're supposed to have taken the lock before
                 // reading anyway.
                 //
                 // TODO complain loudly if we've changed anything important
                 // without taking the lock.
                 // (see `hg help config.format.use-dirstate-tracked-hint`)
                 log::debug!(
                     "dirstate has changed since last read, not updating."
                 );
                 return Ok(());
             }
 
             let uuid_opt = map.old_uuid();
             let write_mode = if uuid_opt.is_some() {
                 DirstateMapWriteMode::Auto
             } else {
                 DirstateMapWriteMode::ForceNewDataFile
             };
             let (data, tree_metadata, append, old_data_size) =
                 map.pack_v2(write_mode)?;
 
             // Reuse the uuid, or generate a new one, keeping the old for
             // deletion.
             let (uuid, old_uuid) = match uuid_opt {
                 Some(uuid) => {
                     let as_str = std::str::from_utf8(uuid)
                         .map_err(|_| {
                             HgError::corrupted(
                                 "non-UTF-8 dirstate data file ID",
                             )
                         })?
                         .to_owned();
                     if append {
                         (as_str, None)
                     } else {
                         (DirstateDocket::new_uid(), Some(as_str))
                     }
                 }
                 None => (DirstateDocket::new_uid(), None),
             };
 
             let data_filename = format!("dirstate.{}", uuid);
             let data_filename = self.hg_vfs().join(data_filename);
             let mut options = std::fs::OpenOptions::new();
             options.write(true);
 
             // Why are we not using the O_APPEND flag when appending?
             //
             // - O_APPEND makes it trickier to deal with garbage at the end of
             //   the file, left by a previous uncommitted transaction. By
             //   starting the write at [old_data_size] we make sure we erase
             //   all such garbage.
             //
             // - O_APPEND requires to special-case 0-byte writes, whereas we
             //   don't need that.
             //
             // - Some OSes have bugs in implementation O_APPEND:
             //   revlog.py talks about a Solaris bug, but we also saw some ZFS
             //   bug: https://github.com/openzfs/zfs/pull/3124,
             //   https://github.com/openzfs/zfs/issues/13370
             //
             if !append {
                 log::trace!("creating a new dirstate data file");
                 options.create_new(true);
             } else {
                 log::trace!("appending to the dirstate data file");
             }
 
             let data_size = (|| {
                 // TODO: loop and try another random ID if !append and this
                 // returns `ErrorKind::AlreadyExists`? Collision chance of two
                 // random IDs is one in 2**32
                 let mut file = options.open(&data_filename)?;
                 if append {
                     file.seek(SeekFrom::Start(old_data_size as u64))?;
                 }
                 file.write_all(&data)?;
                 file.flush()?;
                 file.stream_position()
             })()
             .when_writing_file(&data_filename)?;
 
             let packed_dirstate = DirstateDocket::serialize(
                 parents,
                 tree_metadata,
                 data_size,
                 uuid.as_bytes(),
             )
             .map_err(|_: std::num::TryFromIntError| {
                 HgError::corrupted("overflow in dirstate docket serialization")
             })?;
 
             (packed_dirstate, old_uuid)
         } else {
             let identity = self.dirstate_identity()?;
             if identity != map.old_identity() {
                 // If identity changed since last disk read, don't write.
                 // This is fine because either we're in a command that doesn't
                 // write anything too important (like `hg status`), or we're in
                 // `hg add` and we're supposed to have taken the lock before
                 // reading anyway.
                 //
                 // TODO complain loudly if we've changed anything important
                 // without taking the lock.
                 // (see `hg help config.format.use-dirstate-tracked-hint`)
                 log::debug!(
                     "dirstate has changed since last read, not updating."
                 );
                 return Ok(());
             }
             (map.pack_v1(parents)?, None)
         };
 
         let vfs = self.hg_vfs();
         vfs.atomic_write("dirstate", &packed_dirstate)?;
         if let Some(uuid) = old_uuid_to_remove {
             // Remove the old data file after the new docket pointing to the
             // new data file was written.
             vfs.remove_file(format!("dirstate.{}", uuid))?;
         }
         Ok(())
     }
+
+    pub fn default_revlog_options(
+        &self,
+        changelog: bool,
+    ) -> Result<RevlogOpenOptions, HgError> {
+        let requirements = self.requirements();
+        let version = if changelog
+            && requirements.contains(CHANGELOGV2_REQUIREMENT)
+        {
+            let compute_rank = self
+                .config()
+                .get_bool(b"experimental", b"changelog-v2.compute-rank")?;
+            RevlogVersionOptions::ChangelogV2 { compute_rank }
+        } else if requirements.contains(REVLOGV2_REQUIREMENT) {
+            RevlogVersionOptions::V2
+        } else if requirements.contains(REVLOGV1_REQUIREMENT) {
+            RevlogVersionOptions::V1 {
+                generaldelta: requirements.contains(GENERALDELTA_REQUIREMENT),
+            }
+        } else {
+            RevlogVersionOptions::V0
+        };
+        Ok(RevlogOpenOptions {
+            version,
+            // We don't need to dance around the slow path like in the Python
+            // implementation since we know we have access to the fast code.
+            use_nodemap: requirements.contains(NODEMAP_REQUIREMENT),
+        })
+    }
 }
 
 /// Lazily-initialized component of `Repo` with interior mutability
 ///
 /// This differs from `OnceCell` in that the value can still be "deinitialized"
 /// later by setting its inner `Option` to `None`. It also takes the
 /// initialization function as an argument when the value is requested, not
 /// when the instance is created.
 struct LazyCell<T> {
     value: RefCell<Option<T>>,
 }
 
 impl<T> LazyCell<T> {
     fn new() -> Self {
         Self {
             value: RefCell::new(None),
         }
     }
 
     fn set(&self, value: T) {
         *self.value.borrow_mut() = Some(value)
     }
 
     fn get_or_init<E>(
         &self,
         init: impl Fn() -> Result<T, E>,
     ) -> Result<Ref<T>, E> {
         let mut borrowed = self.value.borrow();
         if borrowed.is_none() {
             drop(borrowed);
             // Only use `borrow_mut` if it is really needed to avoid panic in
             // case there is another outstanding borrow but mutation is not
             // needed.
             *self.value.borrow_mut() = Some(init()?);
             borrowed = self.value.borrow()
         }
         Ok(Ref::map(borrowed, |option| option.as_ref().unwrap()))
     }
 
     fn get_mut_or_init<E>(
         &self,
         init: impl Fn() -> Result<T, E>,
     ) -> Result<RefMut<T>, E> {
         let mut borrowed = self.value.borrow_mut();
         if borrowed.is_none() {
             *borrowed = Some(init()?);
         }
         Ok(RefMut::map(borrowed, |option| option.as_mut().unwrap()))
     }
 }

rust/hg-core/src/requirements.rs

@@ -1,173 +1,183 b''
 use crate::errors::{HgError, HgResultExt};
 use crate::repo::Repo;
 use crate::utils::join_display;
 use crate::vfs::Vfs;
 use std::collections::HashSet;
 
 fn parse(bytes: &[u8]) -> Result<HashSet<String>, HgError> {
     // The Python code reading this file uses `str.splitlines`
     // which looks for a number of line separators (even including a couple of
     // non-ASCII ones), but Python code writing it always uses `\n`.
     let lines = bytes.split(|&byte| byte == b'\n');
 
     lines
         .filter(|line| !line.is_empty())
         .map(|line| {
             // Python uses Unicode `str.isalnum` but feature names are all
             // ASCII
             if line[0].is_ascii_alphanumeric() && line.is_ascii() {
                 Ok(String::from_utf8(line.into()).unwrap())
             } else {
                 Err(HgError::corrupted("parse error in 'requires' file"))
             }
         })
         .collect()
 }
 
 pub(crate) fn load(hg_vfs: Vfs) -> Result<HashSet<String>, HgError> {
     parse(&hg_vfs.read("requires")?)
 }
 
 pub(crate) fn load_if_exists(hg_vfs: Vfs) -> Result<HashSet<String>, HgError> {
     if let Some(bytes) = hg_vfs.read("requires").io_not_found_as_none()? {
         parse(&bytes)
     } else {
         // Treat a missing file the same as an empty file.
         // From `mercurial/localrepo.py`:
         // > requires file contains a newline-delimited list of
         // > features/capabilities the opener (us) must have in order to use
         // > the repository. This file was introduced in Mercurial 0.9.2,
         // > which means very old repositories may not have one. We assume
         // > a missing file translates to no requirements.
         Ok(HashSet::new())
     }
 }
 
 pub(crate) fn check(repo: &Repo) -> Result<(), HgError> {
     let unknown: Vec<_> = repo
         .requirements()
         .iter()
         .map(String::as_str)
         // .filter(|feature| !ALL_SUPPORTED.contains(feature.as_str()))
         .filter(|feature| {
             !REQUIRED.contains(feature) && !SUPPORTED.contains(feature)
         })
         .collect();
     if !unknown.is_empty() {
         return Err(HgError::unsupported(format!(
             "repository requires feature unknown to this Mercurial: {}",
             join_display(&unknown, ", ")
         )));
     }
     let missing: Vec<_> = REQUIRED
         .iter()
         .filter(|&&feature| !repo.requirements().contains(feature))
         .collect();
     if !missing.is_empty() {
         return Err(HgError::unsupported(format!(
             "repository is missing feature required by this Mercurial: {}",
             join_display(&missing, ", ")
         )));
     }
     Ok(())
 }
 
 /// rhg does not support repositories that are *missing* any of these features
 const REQUIRED: &[&str] = &["revlogv1", "store", "fncache", "dotencode"];
 
 /// rhg supports repository with or without these
 const SUPPORTED: &[&str] = &[
-    "generaldelta",
+    GENERALDELTA_REQUIREMENT,
     SHARED_REQUIREMENT,
     SHARESAFE_REQUIREMENT,
     SPARSEREVLOG_REQUIREMENT,
     RELATIVE_SHARED_REQUIREMENT,
     REVLOG_COMPRESSION_ZSTD,
     DIRSTATE_V2_REQUIREMENT,
     DIRSTATE_TRACKED_HINT_V1,
     // As of this writing everything rhg does is read-only.
     // When it starts writing to the repository, it’ll need to either keep the
     // persistent nodemap up to date or remove this entry:
     NODEMAP_REQUIREMENT,
     // Not all commands support `sparse` and `narrow`. The commands that do
     // not should opt out by checking `has_sparse` and `has_narrow`.
     SPARSE_REQUIREMENT,
     NARROW_REQUIREMENT,
     // rhg doesn't care about bookmarks at all yet
     BOOKMARKS_IN_STORE_REQUIREMENT,
 ];
 
 // Copied from mercurial/requirements.py:
 
 pub const DIRSTATE_V2_REQUIREMENT: &str = "dirstate-v2";
+pub const GENERALDELTA_REQUIREMENT: &str = "generaldelta";
 
 /// A repository that uses the tracked hint dirstate file
 #[allow(unused)]
 pub const DIRSTATE_TRACKED_HINT_V1: &str = "dirstate-tracked-key-v1";
 
 /// When narrowing is finalized and no longer subject to format changes,
 /// we should move this to just "narrow" or similar.
 #[allow(unused)]
 pub const NARROW_REQUIREMENT: &str = "narrowhg-experimental";
 
 /// Bookmarks must be stored in the `store` part of the repository and will be
 /// share accross shares
 #[allow(unused)]
 pub const BOOKMARKS_IN_STORE_REQUIREMENT: &str = "bookmarksinstore";
 
 /// Enables sparse working directory usage
 #[allow(unused)]
 pub const SPARSE_REQUIREMENT: &str = "exp-sparse";
 
 /// Enables the internal phase which is used to hide changesets instead
 /// of stripping them
 #[allow(unused)]
 pub const INTERNAL_PHASE_REQUIREMENT: &str = "internal-phase";
 
 /// Stores manifest in Tree structure
 #[allow(unused)]
 pub const TREEMANIFEST_REQUIREMENT: &str = "treemanifest";
 
+/// Whether to use the "RevlogNG" or V1 of the revlog format
+#[allow(unused)]
+pub const REVLOGV1_REQUIREMENT: &str = "revlogv1";
+
 /// Increment the sub-version when the revlog v2 format changes to lock out old
 /// clients.
 #[allow(unused)]
 pub const REVLOGV2_REQUIREMENT: &str = "exp-revlogv2.1";
 
+/// Increment the sub-version when the revlog v2 format changes to lock out old
+/// clients.
+#[allow(unused)]
+pub const CHANGELOGV2_REQUIREMENT: &str = "exp-changelog-v2";
+
 /// A repository with the sparserevlog feature will have delta chains that
 /// can spread over a larger span. Sparse reading cuts these large spans into
 /// pieces, so that each piece isn't too big.
 /// Without the sparserevlog capability, reading from the repository could use
 /// huge amounts of memory, because the whole span would be read at once,
 /// including all the intermediate revisions that aren't pertinent for the
 /// chain. This is why once a repository has enabled sparse-read, it becomes
 /// required.
 #[allow(unused)]
 pub const SPARSEREVLOG_REQUIREMENT: &str = "sparserevlog";
 
 /// A repository with the the copies-sidedata-changeset requirement will store
 /// copies related information in changeset's sidedata.
 #[allow(unused)]
 pub const COPIESSDC_REQUIREMENT: &str = "exp-copies-sidedata-changeset";
 
 /// The repository use persistent nodemap for the changelog and the manifest.
 #[allow(unused)]
 pub const NODEMAP_REQUIREMENT: &str = "persistent-nodemap";
 
 /// Denotes that the current repository is a share
 #[allow(unused)]
 pub const SHARED_REQUIREMENT: &str = "shared";
 
 /// Denotes that current repository is a share and the shared source path is
 /// relative to the current repository root path
 #[allow(unused)]
 pub const RELATIVE_SHARED_REQUIREMENT: &str = "relshared";
 
 /// A repository with share implemented safely. The repository has different
 /// store and working copy requirements i.e. both `.hg/requires` and
 /// `.hg/store/requires` are present.
 #[allow(unused)]
 pub const SHARESAFE_REQUIREMENT: &str = "share-safe";
 
 /// A repository that use zstd compression inside its revlog
 #[allow(unused)]
 pub const REVLOG_COMPRESSION_ZSTD: &str = "revlog-compression-zstd";

rust/hg-core/src/revlog/changelog.rs

@@ -1,359 +1,363 b''
 use crate::errors::HgError;
 use crate::revlog::Revision;
 use crate::revlog::{Node, NodePrefix};
 use crate::revlog::{Revlog, RevlogEntry, RevlogError};
 use crate::utils::hg_path::HgPath;
 use crate::vfs::Vfs;
-use crate::{Graph, GraphError, UncheckedRevision};
+use crate::{Graph, GraphError, RevlogOpenOptions, UncheckedRevision};
 use itertools::Itertools;
 use std::ascii::escape_default;
 use std::borrow::Cow;
 use std::fmt::{Debug, Formatter};
 
 /// A specialized `Revlog` to work with changelog data format.
 pub struct Changelog {
     /// The generic `revlog` format.
     pub(crate) revlog: Revlog,
 }
 
 impl Changelog {
     /// Open the `changelog` of a repository given by its root.
-    pub fn open(store_vfs: &Vfs, use_nodemap: bool) -> Result<Self, HgError> {
-        let revlog =
-            Revlog::open(store_vfs, "00changelog.i", None, use_nodemap)?;
+    pub fn open(
+        store_vfs: &Vfs,
+        options: RevlogOpenOptions,
+    ) -> Result<Self, HgError> {
+        let revlog = Revlog::open(store_vfs, "00changelog.i", None, options)?;
         Ok(Self { revlog })
     }
 
     /// Return the `ChangelogRevisionData` for the given node ID.
     pub fn data_for_node(
         &self,
         node: NodePrefix,
     ) -> Result<ChangelogRevisionData, RevlogError> {
         let rev = self.revlog.rev_from_node(node)?;
         self.entry_for_checked_rev(rev)?.data()
     }
 
     /// Return the [`ChangelogEntry`] for the given revision number.
     pub fn entry_for_rev(
         &self,
         rev: UncheckedRevision,
     ) -> Result<ChangelogEntry, RevlogError> {
         let revlog_entry = self.revlog.get_entry(rev)?;
         Ok(ChangelogEntry { revlog_entry })
     }
 
     /// Same as [`Self::entry_for_rev`] for checked revisions.
     fn entry_for_checked_rev(
         &self,
         rev: Revision,
     ) -> Result<ChangelogEntry, RevlogError> {
         let revlog_entry = self.revlog.get_entry_for_checked_rev(rev)?;
         Ok(ChangelogEntry { revlog_entry })
     }
 
     /// Return the [`ChangelogRevisionData`] for the given revision number.
     ///
     /// This is a useful shortcut in case the caller does not need the
     /// generic revlog information (parents, hashes etc). Otherwise
     /// consider taking a [`ChangelogEntry`] with
     /// [entry_for_rev](`Self::entry_for_rev`) and doing everything from there.
     pub fn data_for_rev(
         &self,
         rev: UncheckedRevision,
     ) -> Result<ChangelogRevisionData, RevlogError> {
         self.entry_for_rev(rev)?.data()
     }
 
     pub fn node_from_rev(&self, rev: UncheckedRevision) -> Option<&Node> {
         self.revlog.node_from_rev(rev)
     }
 
     pub fn rev_from_node(
         &self,
         node: NodePrefix,
     ) -> Result<Revision, RevlogError> {
         self.revlog.rev_from_node(node)
     }
 }
 
 impl Graph for Changelog {
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         self.revlog.parents(rev)
     }
 }
 
 /// A specialized `RevlogEntry` for `changelog` data format
 ///
 /// This is a `RevlogEntry` with the added semantics that the associated
 /// data should meet the requirements for `changelog`, materialized by
 /// the fact that `data()` constructs a `ChangelogRevisionData`.
 /// In case that promise would be broken, the `data` method returns an error.
 #[derive(Clone)]
 pub struct ChangelogEntry<'changelog> {
     /// Same data, as a generic `RevlogEntry`.
     pub(crate) revlog_entry: RevlogEntry<'changelog>,
 }
 
 impl<'changelog> ChangelogEntry<'changelog> {
     pub fn data<'a>(
         &'a self,
     ) -> Result<ChangelogRevisionData<'changelog>, RevlogError> {
         let bytes = self.revlog_entry.data()?;
         if bytes.is_empty() {
             Ok(ChangelogRevisionData::null())
         } else {
             Ok(ChangelogRevisionData::new(bytes).map_err(|err| {
                 RevlogError::Other(HgError::CorruptedRepository(format!(
                     "Invalid changelog data for revision {}: {:?}",
                     self.revlog_entry.revision(),
                     err
                 )))
             })?)
         }
     }
 
     /// Obtain a reference to the underlying `RevlogEntry`.
     ///
     /// This allows the caller to access the information that is common
     /// to all revlog entries: revision number, node id, parent revisions etc.
     pub fn as_revlog_entry(&self) -> &RevlogEntry {
         &self.revlog_entry
     }
 
     pub fn p1_entry(&self) -> Result<Option<ChangelogEntry>, RevlogError> {
         Ok(self
             .revlog_entry
             .p1_entry()?
             .map(|revlog_entry| Self { revlog_entry }))
     }
 
     pub fn p2_entry(&self) -> Result<Option<ChangelogEntry>, RevlogError> {
         Ok(self
             .revlog_entry
             .p2_entry()?
             .map(|revlog_entry| Self { revlog_entry }))
     }
 }
 
 /// `Changelog` entry which knows how to interpret the `changelog` data bytes.
 #[derive(PartialEq)]
 pub struct ChangelogRevisionData<'changelog> {
     /// The data bytes of the `changelog` entry.
     bytes: Cow<'changelog, [u8]>,
     /// The end offset for the hex manifest (not including the newline)
     manifest_end: usize,
     /// The end offset for the user+email (not including the newline)
     user_end: usize,
     /// The end offset for the timestamp+timezone+extras (not including the
     /// newline)
     timestamp_end: usize,
     /// The end offset for the file list (not including the newline)
     files_end: usize,
 }
 
 impl<'changelog> ChangelogRevisionData<'changelog> {
     fn new(bytes: Cow<'changelog, [u8]>) -> Result<Self, HgError> {
         let mut line_iter = bytes.split(|b| b == &b'\n');
         let manifest_end = line_iter
             .next()
             .expect("Empty iterator from split()?")
             .len();
         let user_slice = line_iter.next().ok_or_else(|| {
             HgError::corrupted("Changeset data truncated after manifest line")
         })?;
         let user_end = manifest_end + 1 + user_slice.len();
         let timestamp_slice = line_iter.next().ok_or_else(|| {
             HgError::corrupted("Changeset data truncated after user line")
         })?;
         let timestamp_end = user_end + 1 + timestamp_slice.len();
         let mut files_end = timestamp_end + 1;
         loop {
             let line = line_iter.next().ok_or_else(|| {
                 HgError::corrupted("Changeset data truncated in files list")
             })?;
             if line.is_empty() {
                 if files_end == bytes.len() {
                     // The list of files ended with a single newline (there
                     // should be two)
                     return Err(HgError::corrupted(
                         "Changeset data truncated after files list",
                     ));
                 }
                 files_end -= 1;
                 break;
             }
             files_end += line.len() + 1;
         }
 
         Ok(Self {
             bytes,
             manifest_end,
             user_end,
             timestamp_end,
             files_end,
         })
     }
 
     fn null() -> Self {
         Self::new(Cow::Borrowed(
             b"0000000000000000000000000000000000000000\n\n0 0\n\n",
         ))
         .unwrap()
     }
 
     /// Return an iterator over the lines of the entry.
     pub fn lines(&self) -> impl Iterator<Item = &[u8]> {
         self.bytes.split(|b| b == &b'\n')
     }
 
     /// Return the node id of the `manifest` referenced by this `changelog`
     /// entry.
     pub fn manifest_node(&self) -> Result<Node, HgError> {
         let manifest_node_hex = &self.bytes[..self.manifest_end];
         Node::from_hex_for_repo(manifest_node_hex)
     }
 
     /// The full user string (usually a name followed by an email enclosed in
     /// angle brackets)
     pub fn user(&self) -> &[u8] {
         &self.bytes[self.manifest_end + 1..self.user_end]
     }
 
     /// The full timestamp line (timestamp in seconds, offset in seconds, and
     /// possibly extras)
     // TODO: We should expose this in a more useful way
     pub fn timestamp_line(&self) -> &[u8] {
         &self.bytes[self.user_end + 1..self.timestamp_end]
     }
 
     /// The files changed in this revision.
     pub fn files(&self) -> impl Iterator<Item = &HgPath> {
         self.bytes[self.timestamp_end + 1..self.files_end]
             .split(|b| b == &b'\n')
             .map(HgPath::new)
     }
 
     /// The change description.
     pub fn description(&self) -> &[u8] {
         &self.bytes[self.files_end + 2..]
     }
 }
 
 impl Debug for ChangelogRevisionData<'_> {
     fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
         f.debug_struct("ChangelogRevisionData")
             .field("bytes", &debug_bytes(&self.bytes))
             .field("manifest", &debug_bytes(&self.bytes[..self.manifest_end]))
             .field(
                 "user",
                 &debug_bytes(
                     &self.bytes[self.manifest_end + 1..self.user_end],
                 ),
             )
             .field(
                 "timestamp",
                 &debug_bytes(
                     &self.bytes[self.user_end + 1..self.timestamp_end],
                 ),
             )
             .field(
                 "files",
                 &debug_bytes(
                     &self.bytes[self.timestamp_end + 1..self.files_end],
                 ),
             )
             .field(
                 "description",
                 &debug_bytes(&self.bytes[self.files_end + 2..]),
             )
             .finish()
     }
 }
 
 fn debug_bytes(bytes: &[u8]) -> String {
     String::from_utf8_lossy(
         &bytes.iter().flat_map(|b| escape_default(*b)).collect_vec(),
     )
     .to_string()
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::vfs::Vfs;
     use crate::NULL_REVISION;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn test_create_changelogrevisiondata_invalid() {
         // Completely empty
         assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd")).is_err());
         // No newline after manifest
         assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd")).is_err());
         // No newline after user
         assert!(ChangelogRevisionData::new(Cow::Borrowed(b"abcd\n")).is_err());
         // No newline after timestamp
         assert!(
             ChangelogRevisionData::new(Cow::Borrowed(b"abcd\n\n0 0")).is_err()
         );
         // Missing newline after files
         assert!(ChangelogRevisionData::new(Cow::Borrowed(
             b"abcd\n\n0 0\nfile1\nfile2"
         ))
         .is_err(),);
         // Only one newline after files
         assert!(ChangelogRevisionData::new(Cow::Borrowed(
             b"abcd\n\n0 0\nfile1\nfile2\n"
         ))
         .is_err(),);
     }
 
     #[test]
     fn test_create_changelogrevisiondata() {
         let data = ChangelogRevisionData::new(Cow::Borrowed(
             b"0123456789abcdef0123456789abcdef01234567
 Some One <[e-mail]>
 0 0
 file1
 file2
 
 some
 commit
 message",
         ))
         .unwrap();
         assert_eq!(
             data.manifest_node().unwrap(),
             Node::from_hex("0123456789abcdef0123456789abcdef01234567")
                 .unwrap()
         );
         assert_eq!(data.user(), b"Some One <[e-mail]>");
         assert_eq!(data.timestamp_line(), b"0 0");
         assert_eq!(
             data.files().collect_vec(),
             vec![HgPath::new("file1"), HgPath::new("file2")]
         );
         assert_eq!(data.description(), b"some\ncommit\nmessage");
     }
 
     #[test]
     fn test_data_from_rev_null() -> Result<(), RevlogError> {
         // an empty revlog will be enough for this case
         let temp = tempfile::tempdir().unwrap();
         let vfs = Vfs { base: temp.path() };
         std::fs::write(temp.path().join("foo.i"), b"").unwrap();
-        let revlog = Revlog::open(&vfs, "foo.i", None, false).unwrap();
+        let revlog =
+            Revlog::open(&vfs, "foo.i", None, RevlogOpenOptions::new())
+                .unwrap();
 
         let changelog = Changelog { revlog };
         assert_eq!(
             changelog.data_for_rev(NULL_REVISION.into())?,
             ChangelogRevisionData::null()
         );
         // same with the intermediate entry object
         assert_eq!(
             changelog.entry_for_rev(NULL_REVISION.into())?.data()?,
             ChangelogRevisionData::null()
         );
         Ok(())
     }
 }

rust/hg-core/src/revlog/filelog.rs

@@ -1,239 +1,245 b''
 use crate::errors::HgError;
 use crate::exit_codes;
 use crate::repo::Repo;
 use crate::revlog::path_encode::path_encode;
 use crate::revlog::NodePrefix;
 use crate::revlog::Revision;
 use crate::revlog::RevlogEntry;
 use crate::revlog::{Revlog, RevlogError};
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::utils::SliceExt;
 use crate::Graph;
 use crate::GraphError;
+use crate::RevlogOpenOptions;
 use crate::UncheckedRevision;
 use std::path::PathBuf;
 
 /// A specialized `Revlog` to work with file data logs.
 pub struct Filelog {
     /// The generic `revlog` format.
     revlog: Revlog,
 }
 
 impl Graph for Filelog {
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         self.revlog.parents(rev)
     }
 }
 
 impl Filelog {
     pub fn open_vfs(
         store_vfs: &crate::vfs::Vfs<'_>,
         file_path: &HgPath,
+        options: RevlogOpenOptions,
     ) -> Result<Self, HgError> {
         let index_path = store_path(file_path, b".i");
         let data_path = store_path(file_path, b".d");
         let revlog =
-            Revlog::open(store_vfs, index_path, Some(&data_path), false)?;
+            Revlog::open(store_vfs, index_path, Some(&data_path), options)?;
         Ok(Self { revlog })
     }
 
-    pub fn open(repo: &Repo, file_path: &HgPath) -> Result<Self, HgError> {
-        Self::open_vfs(&repo.store_vfs(), file_path)
+    pub fn open(
+        repo: &Repo,
+        file_path: &HgPath,
+        options: RevlogOpenOptions,
+    ) -> Result<Self, HgError> {
+        Self::open_vfs(&repo.store_vfs(), file_path, options)
     }
 
     /// The given node ID is that of the file as found in a filelog, not of a
     /// changeset.
     pub fn data_for_node(
         &self,
         file_node: impl Into<NodePrefix>,
     ) -> Result<FilelogRevisionData, RevlogError> {
         let file_rev = self.revlog.rev_from_node(file_node.into())?;
         self.data_for_rev(file_rev.into())
     }
 
     /// The given revision is that of the file as found in a filelog, not of a
     /// changeset.
     pub fn data_for_rev(
         &self,
         file_rev: UncheckedRevision,
     ) -> Result<FilelogRevisionData, RevlogError> {
         let data: Vec<u8> = self.revlog.get_rev_data(file_rev)?.into_owned();
         Ok(FilelogRevisionData(data))
     }
 
     /// The given node ID is that of the file as found in a filelog, not of a
     /// changeset.
     pub fn entry_for_node(
         &self,
         file_node: impl Into<NodePrefix>,
     ) -> Result<FilelogEntry, RevlogError> {
         let file_rev = self.revlog.rev_from_node(file_node.into())?;
         self.entry_for_checked_rev(file_rev)
     }
 
     /// The given revision is that of the file as found in a filelog, not of a
     /// changeset.
     pub fn entry_for_rev(
         &self,
         file_rev: UncheckedRevision,
     ) -> Result<FilelogEntry, RevlogError> {
         Ok(FilelogEntry(self.revlog.get_entry(file_rev)?))
     }
 
     fn entry_for_checked_rev(
         &self,
         file_rev: Revision,
     ) -> Result<FilelogEntry, RevlogError> {
         Ok(FilelogEntry(
             self.revlog.get_entry_for_checked_rev(file_rev)?,
         ))
     }
 }
 
 fn store_path(hg_path: &HgPath, suffix: &[u8]) -> PathBuf {
     let encoded_bytes =
         path_encode(&[b"data/", hg_path.as_bytes(), suffix].concat());
     get_path_from_bytes(&encoded_bytes).into()
 }
 
 pub struct FilelogEntry<'a>(RevlogEntry<'a>);
 
 impl FilelogEntry<'_> {
     /// `self.data()` can be expensive, with decompression and delta
     /// resolution.
     ///
     /// *Without* paying this cost, based on revlog index information
     /// including `RevlogEntry::uncompressed_len`:
     ///
     /// * Returns `true` if the length that `self.data().file_data().len()`
     ///   would return is definitely **not equal** to `other_len`.
     /// * Returns `false` if available information is inconclusive.
     pub fn file_data_len_not_equal_to(&self, other_len: u64) -> bool {
         // Relevant code that implement this behavior in Python code:
         // basefilectx.cmp, filelog.size, storageutil.filerevisioncopied,
         // revlog.size, revlog.rawsize
 
         // Let’s call `file_data_len` what would be returned by
         // `self.data().file_data().len()`.
 
         if self.0.is_censored() {
             let file_data_len = 0;
             return other_len != file_data_len;
         }
 
         if self.0.has_length_affecting_flag_processor() {
             // We can’t conclude anything about `file_data_len`.
             return false;
         }
 
         // Revlog revisions (usually) have metadata for the size of
         // their data after decompression and delta resolution
         // as would be returned by `Revlog::get_rev_data`.
         //
         // For filelogs this is the file’s contents preceded by an optional
         // metadata block.
         let uncompressed_len = if let Some(l) = self.0.uncompressed_len() {
             l as u64
         } else {
             // The field was set to -1, the actual uncompressed len is unknown.
             // We need to decompress to say more.
             return false;
         };
         // `uncompressed_len = file_data_len + optional_metadata_len`,
         // so `file_data_len <= uncompressed_len`.
         if uncompressed_len < other_len {
             // Transitively, `file_data_len < other_len`.
             // So `other_len != file_data_len` definitely.
             return true;
         }
 
         if uncompressed_len == other_len + 4 {
             // It’s possible that `file_data_len == other_len` with an empty
             // metadata block (2 start marker bytes + 2 end marker bytes).
             // This happens when there wouldn’t otherwise be metadata, but
             // the first 2 bytes of file data happen to match a start marker
             // and would be ambiguous.
             return false;
         }
 
         if !self.0.has_p1() {
             // There may or may not be copy metadata, so we can’t deduce more
             // about `file_data_len` without computing file data.
             return false;
         }
 
         // Filelog ancestry is not meaningful in the way changelog ancestry is.
         // It only provides hints to delta generation.
         // p1 and p2 are set to null when making a copy or rename since
         // contents are likely unrelatedto what might have previously existed
         // at the destination path.
         //
         // Conversely, since here p1 is non-null, there is no copy metadata.
         // Note that this reasoning may be invalidated in the presence of
         // merges made by some previous versions of Mercurial that
         // swapped p1 and p2. See <https://bz.mercurial-scm.org/show_bug.cgi?id=6528>
         // and `tests/test-issue6528.t`.
         //
         // Since copy metadata is currently the only kind of metadata
         // kept in revlog data of filelogs,
         // this `FilelogEntry` does not have such metadata:
         let file_data_len = uncompressed_len;
 
         file_data_len != other_len
     }
 
     pub fn data(&self) -> Result<FilelogRevisionData, HgError> {
         let data = self.0.data();
         match data {
             Ok(data) => Ok(FilelogRevisionData(data.into_owned())),
             // Errors other than `HgError` should not happen at this point
             Err(e) => match e {
                 RevlogError::Other(hg_error) => Err(hg_error),
                 revlog_error => Err(HgError::abort(
                     revlog_error.to_string(),
                     exit_codes::ABORT,
                     None,
                 )),
             },
         }
     }
 }
 
 /// The data for one revision in a filelog, uncompressed and delta-resolved.
 pub struct FilelogRevisionData(Vec<u8>);
 
 impl FilelogRevisionData {
     /// Split into metadata and data
     pub fn split(&self) -> Result<(Option<&[u8]>, &[u8]), HgError> {
         const DELIMITER: &[u8; 2] = &[b'\x01', b'\n'];
 
         if let Some(rest) = self.0.drop_prefix(DELIMITER) {
             if let Some((metadata, data)) = rest.split_2_by_slice(DELIMITER) {
                 Ok((Some(metadata), data))
             } else {
                 Err(HgError::corrupted(
                     "Missing metadata end delimiter in filelog entry",
                 ))
             }
         } else {
             Ok((None, &self.0))
         }
     }
 
     /// Returns the file contents at this revision, stripped of any metadata
     pub fn file_data(&self) -> Result<&[u8], HgError> {
         let (_metadata, data) = self.split()?;
         Ok(data)
     }
 
     /// Consume the entry, and convert it into data, discarding any metadata,
     /// if present.
     pub fn into_file_data(self) -> Result<Vec<u8>, HgError> {
         if let (Some(_metadata), data) = self.split()? {
             Ok(data.to_owned())
         } else {
             Ok(self.0)
         }
     }
 }

rust/hg-core/src/revlog/index.rs

@@ -1,775 +1,770 b''
 use std::fmt::Debug;
 use std::ops::Deref;
 
 use byteorder::{BigEndian, ByteOrder};
 use bytes_cast::{unaligned, BytesCast};
 
 use super::REVIDX_KNOWN_FLAGS;
 use crate::errors::HgError;
 use crate::node::{NODE_BYTES_LENGTH, STORED_NODE_ID_BYTES};
 use crate::revlog::node::Node;
 use crate::revlog::{Revision, NULL_REVISION};
 use crate::{Graph, GraphError, RevlogError, RevlogIndex, UncheckedRevision};
 
 pub const INDEX_ENTRY_SIZE: usize = 64;
 pub const COMPRESSION_MODE_INLINE: u8 = 2;
 
 pub struct IndexHeader {
-    header_bytes: [u8; 4],
+    pub(super) header_bytes: [u8; 4],
 }
 
 #[derive(Copy, Clone)]
 pub struct IndexHeaderFlags {
     flags: u16,
 }
 
 /// Corresponds to the high bits of `_format_flags` in python
 impl IndexHeaderFlags {
     /// Corresponds to FLAG_INLINE_DATA in python
     pub fn is_inline(self) -> bool {
         self.flags & 1 != 0
     }
     /// Corresponds to FLAG_GENERALDELTA in python
     pub fn uses_generaldelta(self) -> bool {
         self.flags & 2 != 0
     }
 }
 
 /// Corresponds to the INDEX_HEADER structure,
 /// which is parsed as a `header` variable in `_loadindex` in `revlog.py`
 impl IndexHeader {
     fn format_flags(&self) -> IndexHeaderFlags {
         // No "unknown flags" check here, unlike in python. Maybe there should
         // be.
         IndexHeaderFlags {
             flags: BigEndian::read_u16(&self.header_bytes[0..2]),
         }
     }
 
     /// The only revlog version currently supported by rhg.
     const REVLOGV1: u16 = 1;
 
     /// Corresponds to `_format_version` in Python.
     fn format_version(&self) -> u16 {
         BigEndian::read_u16(&self.header_bytes[2..4])
     }
 
-    const EMPTY_INDEX_HEADER: IndexHeader = IndexHeader {
-        // We treat an empty file as a valid index with no entries.
-        // Here we make an arbitrary choice of what we assume the format of the
-        // index to be (V1, using generaldelta).
-        // This doesn't matter too much, since we're only doing read-only
-        // access. but the value corresponds to the `new_header` variable in
-        // `revlog.py`, `_loadindex`
-        header_bytes: [0, 3, 0, 1],
-    };
-
-    fn parse(index_bytes: &[u8]) -> Result<IndexHeader, HgError> {
+    pub fn parse(index_bytes: &[u8]) -> Result<Option<IndexHeader>, HgError> {
         if index_bytes.is_empty() {
-            return Ok(IndexHeader::EMPTY_INDEX_HEADER);
+            return Ok(None);
         }
         if index_bytes.len() < 4 {
             return Err(HgError::corrupted(
                 "corrupted revlog: can't read the index format header",
             ));
         }
-        Ok(IndexHeader {
+        Ok(Some(IndexHeader {
             header_bytes: {
                 let bytes: [u8; 4] =
                     index_bytes[0..4].try_into().expect("impossible");
                 bytes
             },
-        })
+        }))
     }
 }
 
 /// Abstracts the access to the index bytes since they can be spread between
 /// the immutable (bytes) part and the mutable (added) part if any appends
 /// happened. This makes it transparent for the callers.
 struct IndexData {
     /// Immutable bytes, most likely taken from disk
     bytes: Box<dyn Deref<Target = [u8]> + Send>,
     /// Bytes that were added after reading the index
     added: Vec<u8>,
 }
 
 impl IndexData {
     pub fn new(bytes: Box<dyn Deref<Target = [u8]> + Send>) -> Self {
         Self {
             bytes,
             added: vec![],
         }
     }
 
     pub fn len(&self) -> usize {
         self.bytes.len() + self.added.len()
     }
 }
 
 impl std::ops::Index<std::ops::Range<usize>> for IndexData {
     type Output = [u8];
 
     fn index(&self, index: std::ops::Range<usize>) -> &Self::Output {
         let start = index.start;
         let end = index.end;
         let immutable_len = self.bytes.len();
         if start < immutable_len {
             if end > immutable_len {
                 panic!("index data cannot span existing and added ranges");
             }
             &self.bytes[index]
         } else {
             &self.added[start - immutable_len..end - immutable_len]
         }
     }
 }
 
 pub struct RevisionDataParams {
     flags: u16,
     data_offset: u64,
     data_compressed_length: i32,
     data_uncompressed_length: i32,
     data_delta_base: i32,
     link_rev: i32,
     parent_rev_1: i32,
     parent_rev_2: i32,
     node_id: [u8; NODE_BYTES_LENGTH],
     _sidedata_offset: u64,
     _sidedata_compressed_length: i32,
     data_compression_mode: u8,
     _sidedata_compression_mode: u8,
     _rank: i32,
 }
 
 #[derive(BytesCast)]
 #[repr(C)]
 pub struct RevisionDataV1 {
     data_offset_or_flags: unaligned::U64Be,
     data_compressed_length: unaligned::I32Be,
     data_uncompressed_length: unaligned::I32Be,
     data_delta_base: unaligned::I32Be,
     link_rev: unaligned::I32Be,
     parent_rev_1: unaligned::I32Be,
     parent_rev_2: unaligned::I32Be,
     node_id: [u8; STORED_NODE_ID_BYTES],
 }
 
 fn _static_assert_size_of_revision_data_v1() {
     let _ = std::mem::transmute::<RevisionDataV1, [u8; 64]>;
 }
 
 impl RevisionDataParams {
     pub fn validate(&self) -> Result<(), RevlogError> {
         if self.flags & !REVIDX_KNOWN_FLAGS != 0 {
             return Err(RevlogError::corrupted(format!(
                 "unknown revlog index flags: {}",
                 self.flags
             )));
         }
         if self.data_compression_mode != COMPRESSION_MODE_INLINE {
             return Err(RevlogError::corrupted(format!(
                 "invalid data compression mode: {}",
                 self.data_compression_mode
             )));
         }
         // FIXME isn't this only for v2 or changelog v2?
         if self._sidedata_compression_mode != COMPRESSION_MODE_INLINE {
             return Err(RevlogError::corrupted(format!(
                 "invalid sidedata compression mode: {}",
                 self._sidedata_compression_mode
             )));
         }
         Ok(())
     }
 
     pub fn into_v1(self) -> RevisionDataV1 {
         let data_offset_or_flags = self.data_offset << 16 | self.flags as u64;
         let mut node_id = [0; STORED_NODE_ID_BYTES];
         node_id[..NODE_BYTES_LENGTH].copy_from_slice(&self.node_id);
         RevisionDataV1 {
             data_offset_or_flags: data_offset_or_flags.into(),
             data_compressed_length: self.data_compressed_length.into(),
             data_uncompressed_length: self.data_uncompressed_length.into(),
             data_delta_base: self.data_delta_base.into(),
             link_rev: self.link_rev.into(),
             parent_rev_1: self.parent_rev_1.into(),
             parent_rev_2: self.parent_rev_2.into(),
             node_id,
         }
     }
 }
 
 /// A Revlog index
 pub struct Index {
     bytes: IndexData,
     /// Offsets of starts of index blocks.
     /// Only needed when the index is interleaved with data.
     offsets: Option<Vec<usize>>,
     uses_generaldelta: bool,
 }
 
 impl Debug for Index {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         f.debug_struct("Index")
             .field("offsets", &self.offsets)
             .field("uses_generaldelta", &self.uses_generaldelta)
             .finish()
     }
 }
 
 impl Graph for Index {
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         let err = || GraphError::ParentOutOfRange(rev);
         match self.get_entry(rev) {
             Some(entry) => {
                 // The C implementation checks that the parents are valid
                 // before returning
                 Ok([
                     self.check_revision(entry.p1()).ok_or_else(err)?,
                     self.check_revision(entry.p2()).ok_or_else(err)?,
                 ])
             }
             None => Ok([NULL_REVISION, NULL_REVISION]),
         }
     }
 }
 
 impl Index {
     /// Create an index from bytes.
     /// Calculate the start of each entry when is_inline is true.
     pub fn new(
         bytes: Box<dyn Deref<Target = [u8]> + Send>,
+        default_header: IndexHeader,
     ) -> Result<Self, HgError> {
-        let header = IndexHeader::parse(bytes.as_ref())?;
+        let header =
+            IndexHeader::parse(bytes.as_ref())?.unwrap_or(default_header);
 
         if header.format_version() != IndexHeader::REVLOGV1 {
             // A proper new version should have had a repo/store
             // requirement.
             return Err(HgError::corrupted("unsupported revlog version"));
         }
 
         // This is only correct because we know version is REVLOGV1.
         // In v2 we always use generaldelta, while in v0 we never use
         // generaldelta. Similar for [is_inline] (it's only used in v1).
         let uses_generaldelta = header.format_flags().uses_generaldelta();
 
         if header.format_flags().is_inline() {
             let mut offset: usize = 0;
             let mut offsets = Vec::new();
 
             while offset + INDEX_ENTRY_SIZE <= bytes.len() {
                 offsets.push(offset);
                 let end = offset + INDEX_ENTRY_SIZE;
                 let entry = IndexEntry {
                     bytes: &bytes[offset..end],
                     offset_override: None,
                 };
 
                 offset += INDEX_ENTRY_SIZE + entry.compressed_len() as usize;
             }
 
             if offset == bytes.len() {
                 Ok(Self {
                     bytes: IndexData::new(bytes),
                     offsets: Some(offsets),
                     uses_generaldelta,
                 })
             } else {
                 Err(HgError::corrupted("unexpected inline revlog length"))
             }
         } else {
             Ok(Self {
                 bytes: IndexData::new(bytes),
                 offsets: None,
                 uses_generaldelta,
             })
         }
     }
 
     pub fn uses_generaldelta(&self) -> bool {
         self.uses_generaldelta
     }
 
     /// Value of the inline flag.
     pub fn is_inline(&self) -> bool {
         self.offsets.is_some()
     }
 
     /// Return a slice of bytes if `revlog` is inline. Panic if not.
     pub fn data(&self, start: usize, end: usize) -> &[u8] {
         if !self.is_inline() {
             panic!("tried to access data in the index of a revlog that is not inline");
         }
         &self.bytes[start..end]
     }
 
     /// Return number of entries of the revlog index.
     pub fn len(&self) -> usize {
         if let Some(offsets) = &self.offsets {
             offsets.len()
         } else {
             self.bytes.len() / INDEX_ENTRY_SIZE
         }
     }
 
     /// Returns `true` if the `Index` has zero `entries`.
     pub fn is_empty(&self) -> bool {
         self.len() == 0
     }
 
     /// Return the index entry corresponding to the given revision if it
     /// exists.
     pub fn get_entry(&self, rev: Revision) -> Option<IndexEntry> {
         if rev == NULL_REVISION {
             return None;
         }
         Some(if let Some(offsets) = &self.offsets {
             self.get_entry_inline(rev, offsets)
         } else {
             self.get_entry_separated(rev)
         })
     }
 
     fn get_entry_inline(
         &self,
         rev: Revision,
         offsets: &[usize],
     ) -> IndexEntry {
         let start = offsets[rev.0 as usize];
         let end = start + INDEX_ENTRY_SIZE;
         let bytes = &self.bytes[start..end];
 
         // See IndexEntry for an explanation of this override.
         let offset_override = Some(end);
 
         IndexEntry {
             bytes,
             offset_override,
         }
     }
 
     fn get_entry_separated(&self, rev: Revision) -> IndexEntry {
         let start = rev.0 as usize * INDEX_ENTRY_SIZE;
         let end = start + INDEX_ENTRY_SIZE;
         let bytes = &self.bytes[start..end];
 
         // Override the offset of the first revision as its bytes are used
         // for the index's metadata (saving space because it is always 0)
         let offset_override = if rev == Revision(0) { Some(0) } else { None };
 
         IndexEntry {
             bytes,
             offset_override,
         }
     }
 
     /// TODO move this to the trait probably, along with other things
     pub fn append(
         &mut self,
         revision_data: RevisionDataParams,
     ) -> Result<(), RevlogError> {
         revision_data.validate()?;
         let new_offset = self.bytes.len();
         if let Some(offsets) = self.offsets.as_mut() {
             offsets.push(new_offset)
         }
         self.bytes.added.extend(revision_data.into_v1().as_bytes());
         Ok(())
     }
 }
 
 impl super::RevlogIndex for Index {
     fn len(&self) -> usize {
         self.len()
     }
 
     fn node(&self, rev: Revision) -> Option<&Node> {
         self.get_entry(rev).map(|entry| entry.hash())
     }
 }
 
 #[derive(Debug)]
 pub struct IndexEntry<'a> {
     bytes: &'a [u8],
     /// Allows to override the offset value of the entry.
     ///
     /// For interleaved index and data, the offset stored in the index
     /// corresponds to the separated data offset.
     /// It has to be overridden with the actual offset in the interleaved
     /// index which is just after the index block.
     ///
     /// For separated index and data, the offset stored in the first index
     /// entry is mixed with the index headers.
     /// It has to be overridden with 0.
     offset_override: Option<usize>,
 }
 
 impl<'a> IndexEntry<'a> {
     /// Return the offset of the data.
     pub fn offset(&self) -> usize {
         if let Some(offset_override) = self.offset_override {
             offset_override
         } else {
             let mut bytes = [0; 8];
             bytes[2..8].copy_from_slice(&self.bytes[0..=5]);
             BigEndian::read_u64(&bytes[..]) as usize
         }
     }
 
     pub fn flags(&self) -> u16 {
         BigEndian::read_u16(&self.bytes[6..=7])
     }
 
     /// Return the compressed length of the data.
     pub fn compressed_len(&self) -> u32 {
         BigEndian::read_u32(&self.bytes[8..=11])
     }
 
     /// Return the uncompressed length of the data.
     pub fn uncompressed_len(&self) -> i32 {
         BigEndian::read_i32(&self.bytes[12..=15])
     }
 
     /// Return the revision upon which the data has been derived.
     pub fn base_revision_or_base_of_delta_chain(&self) -> UncheckedRevision {
         // TODO Maybe return an Option when base_revision == rev?
         //      Requires to add rev to IndexEntry
 
         BigEndian::read_i32(&self.bytes[16..]).into()
     }
 
     pub fn link_revision(&self) -> UncheckedRevision {
         BigEndian::read_i32(&self.bytes[20..]).into()
     }
 
     pub fn p1(&self) -> UncheckedRevision {
         BigEndian::read_i32(&self.bytes[24..]).into()
     }
 
     pub fn p2(&self) -> UncheckedRevision {
         BigEndian::read_i32(&self.bytes[28..]).into()
     }
 
     /// Return the hash of revision's full text.
     ///
     /// Currently, SHA-1 is used and only the first 20 bytes of this field
     /// are used.
     pub fn hash(&self) -> &'a Node {
         (&self.bytes[32..52]).try_into().unwrap()
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::node::NULL_NODE;
 
     #[cfg(test)]
     #[derive(Debug, Copy, Clone)]
     pub struct IndexEntryBuilder {
         is_first: bool,
         is_inline: bool,
         is_general_delta: bool,
         version: u16,
         offset: usize,
         compressed_len: usize,
         uncompressed_len: usize,
         base_revision_or_base_of_delta_chain: Revision,
         link_revision: Revision,
         p1: Revision,
         p2: Revision,
         node: Node,
     }
 
     #[cfg(test)]
     impl IndexEntryBuilder {
         #[allow(clippy::new_without_default)]
         pub fn new() -> Self {
             Self {
                 is_first: false,
                 is_inline: false,
                 is_general_delta: true,
                 version: 1,
                 offset: 0,
                 compressed_len: 0,
                 uncompressed_len: 0,
                 base_revision_or_base_of_delta_chain: Revision(0),
                 link_revision: Revision(0),
                 p1: NULL_REVISION,
                 p2: NULL_REVISION,
                 node: NULL_NODE,
             }
         }
 
         pub fn is_first(&mut self, value: bool) -> &mut Self {
             self.is_first = value;
             self
         }
 
         pub fn with_inline(&mut self, value: bool) -> &mut Self {
             self.is_inline = value;
             self
         }
 
         pub fn with_general_delta(&mut self, value: bool) -> &mut Self {
             self.is_general_delta = value;
             self
         }
 
         pub fn with_version(&mut self, value: u16) -> &mut Self {
             self.version = value;
             self
         }
 
         pub fn with_offset(&mut self, value: usize) -> &mut Self {
             self.offset = value;
             self
         }
 
         pub fn with_compressed_len(&mut self, value: usize) -> &mut Self {
             self.compressed_len = value;
             self
         }
 
         pub fn with_uncompressed_len(&mut self, value: usize) -> &mut Self {
             self.uncompressed_len = value;
             self
         }
 
         pub fn with_base_revision_or_base_of_delta_chain(
             &mut self,
             value: Revision,
         ) -> &mut Self {
             self.base_revision_or_base_of_delta_chain = value;
             self
         }
 
         pub fn with_link_revision(&mut self, value: Revision) -> &mut Self {
             self.link_revision = value;
             self
         }
 
         pub fn with_p1(&mut self, value: Revision) -> &mut Self {
             self.p1 = value;
             self
         }
 
         pub fn with_p2(&mut self, value: Revision) -> &mut Self {
             self.p2 = value;
             self
         }
 
         pub fn with_node(&mut self, value: Node) -> &mut Self {
             self.node = value;
             self
         }
 
         pub fn build(&self) -> Vec<u8> {
             let mut bytes = Vec::with_capacity(INDEX_ENTRY_SIZE);
             if self.is_first {
                 bytes.extend(&match (self.is_general_delta, self.is_inline) {
                     (false, false) => [0u8, 0],
                     (false, true) => [0u8, 1],
                     (true, false) => [0u8, 2],
                     (true, true) => [0u8, 3],
                 });
                 bytes.extend(&self.version.to_be_bytes());
                 // Remaining offset bytes.
                 bytes.extend(&[0u8; 2]);
             } else {
                 // Offset stored on 48 bits (6 bytes)
                 bytes.extend(&(self.offset as u64).to_be_bytes()[2..]);
             }
             bytes.extend(&[0u8; 2]); // Revision flags.
             bytes.extend(&(self.compressed_len as u32).to_be_bytes());
             bytes.extend(&(self.uncompressed_len as u32).to_be_bytes());
             bytes.extend(
                 &self.base_revision_or_base_of_delta_chain.0.to_be_bytes(),
             );
             bytes.extend(&self.link_revision.0.to_be_bytes());
             bytes.extend(&self.p1.0.to_be_bytes());
             bytes.extend(&self.p2.0.to_be_bytes());
             bytes.extend(self.node.as_bytes());
             bytes.extend(vec![0u8; 12]);
             bytes
         }
     }
 
     pub fn is_inline(index_bytes: &[u8]) -> bool {
         IndexHeader::parse(index_bytes)
             .expect("too short")
+            .unwrap()
             .format_flags()
             .is_inline()
     }
 
     pub fn uses_generaldelta(index_bytes: &[u8]) -> bool {
         IndexHeader::parse(index_bytes)
             .expect("too short")
+            .unwrap()
             .format_flags()
             .uses_generaldelta()
     }
 
     pub fn get_version(index_bytes: &[u8]) -> u16 {
         IndexHeader::parse(index_bytes)
             .expect("too short")
+            .unwrap()
             .format_version()
     }
 
     #[test]
     fn flags_when_no_inline_flag_test() {
         let bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_general_delta(false)
             .with_inline(false)
             .build();
 
         assert!(!is_inline(&bytes));
         assert!(!uses_generaldelta(&bytes));
     }
 
     #[test]
     fn flags_when_inline_flag_test() {
         let bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_general_delta(false)
             .with_inline(true)
             .build();
 
         assert!(is_inline(&bytes));
         assert!(!uses_generaldelta(&bytes));
     }
 
     #[test]
     fn flags_when_inline_and_generaldelta_flags_test() {
         let bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_general_delta(true)
             .with_inline(true)
             .build();
 
         assert!(is_inline(&bytes));
         assert!(uses_generaldelta(&bytes));
     }
 
     #[test]
     fn test_offset() {
         let bytes = IndexEntryBuilder::new().with_offset(1).build();
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.offset(), 1)
     }
 
     #[test]
     fn test_with_overridden_offset() {
         let bytes = IndexEntryBuilder::new().with_offset(1).build();
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: Some(2),
         };
 
         assert_eq!(entry.offset(), 2)
     }
 
     #[test]
     fn test_compressed_len() {
         let bytes = IndexEntryBuilder::new().with_compressed_len(1).build();
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.compressed_len(), 1)
     }
 
     #[test]
     fn test_uncompressed_len() {
         let bytes = IndexEntryBuilder::new().with_uncompressed_len(1).build();
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.uncompressed_len(), 1)
     }
 
     #[test]
     fn test_base_revision_or_base_of_delta_chain() {
         let bytes = IndexEntryBuilder::new()
             .with_base_revision_or_base_of_delta_chain(Revision(1))
             .build();
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.base_revision_or_base_of_delta_chain(), 1.into())
     }
 
     #[test]
     fn link_revision_test() {
         let bytes = IndexEntryBuilder::new()
             .with_link_revision(Revision(123))
             .build();
 
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.link_revision(), 123.into());
     }
 
     #[test]
     fn p1_test() {
         let bytes = IndexEntryBuilder::new().with_p1(Revision(123)).build();
 
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.p1(), 123.into());
     }
 
     #[test]
     fn p2_test() {
         let bytes = IndexEntryBuilder::new().with_p2(Revision(123)).build();
 
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(entry.p2(), 123.into());
     }
 
     #[test]
     fn node_test() {
         let node = Node::from_hex("0123456789012345678901234567890123456789")
             .unwrap();
         let bytes = IndexEntryBuilder::new().with_node(node).build();
 
         let entry = IndexEntry {
             bytes: &bytes,
             offset_override: None,
         };
 
         assert_eq!(*entry.hash(), node);
     }
 
     #[test]
     fn version_test() {
         let bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_version(2)
             .build();
 
         assert_eq!(get_version(&bytes), 2)
     }
 }
 
 #[cfg(test)]
 pub use tests::IndexEntryBuilder;

rust/hg-core/src/revlog/manifest.rs

@@ -1,209 +1,213 b''
 use crate::errors::HgError;
 use crate::revlog::{Node, NodePrefix};
 use crate::revlog::{Revlog, RevlogError};
 use crate::utils::hg_path::HgPath;
 use crate::utils::SliceExt;
 use crate::vfs::Vfs;
-use crate::{Graph, GraphError, Revision, UncheckedRevision};
+use crate::{
+    Graph, GraphError, Revision, RevlogOpenOptions, UncheckedRevision,
+};
 
 /// A specialized `Revlog` to work with `manifest` data format.
 pub struct Manifestlog {
     /// The generic `revlog` format.
-    revlog: Revlog,
+    pub(crate) revlog: Revlog,
 }
 
 impl Graph for Manifestlog {
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         self.revlog.parents(rev)
     }
 }
 
 impl Manifestlog {
     /// Open the `manifest` of a repository given by its root.
-    pub fn open(store_vfs: &Vfs, use_nodemap: bool) -> Result<Self, HgError> {
-        let revlog =
-            Revlog::open(store_vfs, "00manifest.i", None, use_nodemap)?;
+    pub fn open(
+        store_vfs: &Vfs,
+        options: RevlogOpenOptions,
+    ) -> Result<Self, HgError> {
+        let revlog = Revlog::open(store_vfs, "00manifest.i", None, options)?;
         Ok(Self { revlog })
     }
 
     /// Return the `Manifest` for the given node ID.
     ///
     /// Note: this is a node ID in the manifestlog, typically found through
     /// `ChangelogEntry::manifest_node`. It is *not* the node ID of any
     /// changeset.
     ///
     /// See also `Repo::manifest_for_node`
     pub fn data_for_node(
         &self,
         node: NodePrefix,
     ) -> Result<Manifest, RevlogError> {
         let rev = self.revlog.rev_from_node(node)?;
         self.data_for_checked_rev(rev)
     }
 
     /// Return the `Manifest` of a given revision number.
     ///
     /// Note: this is a revision number in the manifestlog, *not* of any
     /// changeset.
     ///
     /// See also `Repo::manifest_for_rev`
     pub fn data_for_rev(
         &self,
         rev: UncheckedRevision,
     ) -> Result<Manifest, RevlogError> {
         let bytes = self.revlog.get_rev_data(rev)?.into_owned();
         Ok(Manifest { bytes })
     }
 
     pub fn data_for_checked_rev(
         &self,
         rev: Revision,
     ) -> Result<Manifest, RevlogError> {
         let bytes =
             self.revlog.get_rev_data_for_checked_rev(rev)?.into_owned();
         Ok(Manifest { bytes })
     }
 }
 
 /// `Manifestlog` entry which knows how to interpret the `manifest` data bytes.
 #[derive(Debug)]
 pub struct Manifest {
     /// Format for a manifest: flat sequence of variable-size entries,
     /// sorted by path, each as:
     ///
     /// ```text
     /// <path> \0 <hex_node_id> <flags> \n
     /// ```
     ///
     /// The last entry is also terminated by a newline character.
     /// Flags is one of `b""` (the empty string), `b"x"`, `b"l"`, or `b"t"`.
     bytes: Vec<u8>,
 }
 
 impl Manifest {
     pub fn iter(
         &self,
     ) -> impl Iterator<Item = Result<ManifestEntry, HgError>> {
         self.bytes
             .split(|b| b == &b'\n')
             .filter(|line| !line.is_empty())
             .map(ManifestEntry::from_raw)
     }
 
     /// If the given path is in this manifest, return its filelog node ID
     pub fn find_by_path(
         &self,
         path: &HgPath,
     ) -> Result<Option<ManifestEntry>, HgError> {
         use std::cmp::Ordering::*;
         let path = path.as_bytes();
         // Both boundaries of this `&[u8]` slice are always at the boundary of
         // an entry
         let mut bytes = &*self.bytes;
 
         // Binary search algorithm derived from `[T]::binary_search_by`
         // <https://github.com/rust-lang/rust/blob/1.57.0/library/core/src/slice/mod.rs#L2221>
         // except we don’t have a slice of entries. Instead we jump to the
         // middle of the byte slice and look around for entry delimiters
         // (newlines).
         while let Some(entry_range) = Self::find_entry_near_middle_of(bytes)? {
             let (entry_path, rest) =
                 ManifestEntry::split_path(&bytes[entry_range.clone()])?;
             let cmp = entry_path.cmp(path);
             if cmp == Less {
                 let after_newline = entry_range.end + 1;
                 bytes = &bytes[after_newline..];
             } else if cmp == Greater {
                 bytes = &bytes[..entry_range.start];
             } else {
                 return Ok(Some(ManifestEntry::from_path_and_rest(
                     entry_path, rest,
                 )));
             }
         }
         Ok(None)
     }
 
     /// If there is at least one, return the byte range of an entry *excluding*
     /// the final newline.
     fn find_entry_near_middle_of(
         bytes: &[u8],
     ) -> Result<Option<std::ops::Range<usize>>, HgError> {
         let len = bytes.len();
         if len > 0 {
             let middle = bytes.len() / 2;
             // Integer division rounds down, so `middle < len`.
             let (before, after) = bytes.split_at(middle);
             let is_newline = |&byte: &u8| byte == b'\n';
             let entry_start = match before.iter().rposition(is_newline) {
                 Some(i) => i + 1,
                 None => 0, // We choose the first entry in `bytes`
             };
             let entry_end = match after.iter().position(is_newline) {
                 Some(i) => {
                     // No `+ 1` here to exclude this newline from the range
                     middle + i
                 }
                 None => {
                     // In a well-formed manifest:
                     //
                     // * Since `len > 0`, `bytes` contains at least one entry
                     // * Every entry ends with a newline
                     // * Since `middle < len`, `after` contains at least the
                     //   newline at the end of the last entry of `bytes`.
                     //
                     // We didn’t find a newline, so this manifest is not
                     // well-formed.
                     return Err(HgError::corrupted(
                         "manifest entry without \\n delimiter",
                     ));
                 }
             };
             Ok(Some(entry_start..entry_end))
         } else {
             // len == 0
             Ok(None)
         }
     }
 }
 
 /// `Manifestlog` entry which knows how to interpret the `manifest` data bytes.
 #[derive(Debug)]
 pub struct ManifestEntry<'manifest> {
     pub path: &'manifest HgPath,
     pub hex_node_id: &'manifest [u8],
 
     /// `Some` values are b'x', b'l', or 't'
     pub flags: Option<u8>,
 }
 
 impl<'a> ManifestEntry<'a> {
     fn split_path(bytes: &[u8]) -> Result<(&[u8], &[u8]), HgError> {
         bytes.split_2(b'\0').ok_or_else(|| {
             HgError::corrupted("manifest entry without \\0 delimiter")
         })
     }
 
     fn from_path_and_rest(path: &'a [u8], rest: &'a [u8]) -> Self {
         let (hex_node_id, flags) = match rest.split_last() {
             Some((&b'x', rest)) => (rest, Some(b'x')),
             Some((&b'l', rest)) => (rest, Some(b'l')),
             Some((&b't', rest)) => (rest, Some(b't')),
             _ => (rest, None),
         };
         Self {
             path: HgPath::new(path),
             hex_node_id,
             flags,
         }
     }
 
     fn from_raw(bytes: &'a [u8]) -> Result<Self, HgError> {
         let (path, rest) = Self::split_path(bytes)?;
         Ok(Self::from_path_and_rest(path, rest))
     }
 
     pub fn node_id(&self) -> Result<Node, HgError> {
         Node::from_hex_for_repo(self.hex_node_id)
     }
 }

rust/hg-core/src/revlog/mod.rs

@@ -1,965 +1,1030 b''
 // Copyright 2018-2023 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 //! Mercurial concepts for handling revision history
 
 pub mod node;
 pub mod nodemap;
 mod nodemap_docket;
 pub mod path_encode;
 pub use node::{FromHexError, Node, NodePrefix};
 pub mod changelog;
 pub mod filelog;
 pub mod index;
 pub mod manifest;
 pub mod patch;
 
 use std::borrow::Cow;
 use std::io::Read;
 use std::ops::Deref;
 use std::path::Path;
 
 use flate2::read::ZlibDecoder;
 use sha1::{Digest, Sha1};
 use std::cell::RefCell;
 use zstd;
 
 use self::node::{NODE_BYTES_LENGTH, NULL_NODE};
 use self::nodemap_docket::NodeMapDocket;
 use super::index::Index;
 use super::nodemap::{NodeMap, NodeMapError};
 use crate::errors::HgError;
 use crate::vfs::Vfs;
 
 /// As noted in revlog.c, revision numbers are actually encoded in
 /// 4 bytes, and are liberally converted to ints, whence the i32
 pub type BaseRevision = i32;
 
 /// Mercurial revision numbers
 /// In contrast to the more general [`UncheckedRevision`], these are "checked"
 /// in the sense that they should only be used for revisions that are
 /// valid for a given index (i.e. in bounds).
 #[derive(
     Debug,
     derive_more::Display,
     Clone,
     Copy,
     Hash,
     PartialEq,
     Eq,
     PartialOrd,
     Ord,
 )]
 pub struct Revision(pub BaseRevision);
 
 impl format_bytes::DisplayBytes for Revision {
     fn display_bytes(
         &self,
         output: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         self.0.display_bytes(output)
     }
 }
 
 /// Unchecked Mercurial revision numbers.
 ///
 /// Values of this type have no guarantee of being a valid revision number
 /// in any context. Use method `check_revision` to get a valid revision within
 /// the appropriate index object.
 #[derive(
     Debug,
     derive_more::Display,
     Clone,
     Copy,
     Hash,
     PartialEq,
     Eq,
     PartialOrd,
     Ord,
 )]
 pub struct UncheckedRevision(pub BaseRevision);
 
 impl format_bytes::DisplayBytes for UncheckedRevision {
     fn display_bytes(
         &self,
         output: &mut dyn std::io::Write,
     ) -> std::io::Result<()> {
         self.0.display_bytes(output)
     }
 }
 
 impl From<Revision> for UncheckedRevision {
     fn from(value: Revision) -> Self {
         Self(value.0)
     }
 }
 
 impl From<BaseRevision> for UncheckedRevision {
     fn from(value: BaseRevision) -> Self {
         Self(value)
     }
 }
 
 /// Marker expressing the absence of a parent
 ///
 /// Independently of the actual representation, `NULL_REVISION` is guaranteed
 /// to be smaller than all existing revisions.
 pub const NULL_REVISION: Revision = Revision(-1);
 
 /// Same as `mercurial.node.wdirrev`
 ///
 /// This is also equal to `i32::max_value()`, but it's better to spell
 /// it out explicitely, same as in `mercurial.node`
 #[allow(clippy::unreadable_literal)]
 pub const WORKING_DIRECTORY_REVISION: UncheckedRevision =
     UncheckedRevision(0x7fffffff);
 
 pub const WORKING_DIRECTORY_HEX: &str =
     "ffffffffffffffffffffffffffffffffffffffff";
 
 /// The simplest expression of what we need of Mercurial DAGs.
 pub trait Graph {
     /// Return the two parents of the given `Revision`.
     ///
     /// Each of the parents can be independently `NULL_REVISION`
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError>;
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
 }
 
 /// The Mercurial Revlog Index
 ///
 /// This is currently limited to the minimal interface that is needed for
 /// the [`nodemap`](nodemap/index.html) module
 pub trait RevlogIndex {
     /// Total number of Revisions referenced in this index
     fn len(&self) -> usize;
 
     fn is_empty(&self) -> bool {
         self.len() == 0
     }
 
     /// Return a reference to the Node or `None` for `NULL_REVISION`
     fn node(&self, rev: Revision) -> Option<&Node>;
 
     /// Return a [`Revision`] if `rev` is a valid revision number for this
     /// index
     fn check_revision(&self, rev: UncheckedRevision) -> Option<Revision> {
         let rev = rev.0;
 
         if rev == NULL_REVISION.0 || (rev >= 0 && (rev as usize) < self.len())
         {
             Some(Revision(rev))
         } else {
             None
         }
     }
 }
 
 const REVISION_FLAG_CENSORED: u16 = 1 << 15;
 const REVISION_FLAG_ELLIPSIS: u16 = 1 << 14;
 const REVISION_FLAG_EXTSTORED: u16 = 1 << 13;
 const REVISION_FLAG_HASCOPIESINFO: u16 = 1 << 12;
 
 // Keep this in sync with REVIDX_KNOWN_FLAGS in
 // mercurial/revlogutils/flagutil.py
 const REVIDX_KNOWN_FLAGS: u16 = REVISION_FLAG_CENSORED
     | REVISION_FLAG_ELLIPSIS
     | REVISION_FLAG_EXTSTORED
     | REVISION_FLAG_HASCOPIESINFO;
 
 const NULL_REVLOG_ENTRY_FLAGS: u16 = 0;
 
 #[derive(Debug, derive_more::From, derive_more::Display)]
 pub enum RevlogError {
     InvalidRevision,
     /// Working directory is not supported
     WDirUnsupported,
     /// Found more than one entry whose ID match the requested prefix
     AmbiguousPrefix,
     #[from]
     Other(HgError),
 }
 
 impl From<NodeMapError> for RevlogError {
     fn from(error: NodeMapError) -> Self {
         match error {
             NodeMapError::MultipleResults => RevlogError::AmbiguousPrefix,
             NodeMapError::RevisionNotInIndex(rev) => RevlogError::corrupted(
                 format!("nodemap point to revision {} not in index", rev),
             ),
         }
     }
 }
 
 fn corrupted<S: AsRef<str>>(context: S) -> HgError {
     HgError::corrupted(format!("corrupted revlog, {}", context.as_ref()))
 }
 
 impl RevlogError {
     fn corrupted<S: AsRef<str>>(context: S) -> Self {
         RevlogError::Other(corrupted(context))
     }
 }
 
 /// Read only implementation of revlog.
 pub struct Revlog {
     /// When index and data are not interleaved: bytes of the revlog index.
     /// When index and data are interleaved: bytes of the revlog index and
     /// data.
     index: Index,
     /// When index and data are not interleaved: bytes of the revlog data
     data_bytes: Option<Box<dyn Deref<Target = [u8]> + Send>>,
     /// When present on disk: the persistent nodemap for this revlog
     nodemap: Option<nodemap::NodeTree>,
 }
 
 impl Graph for Revlog {
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError> {
         self.index.parents(rev)
     }
 }
 
+#[derive(Debug, Copy, Clone)]
+pub enum RevlogVersionOptions {
+    V0,
+    V1 { generaldelta: bool },
+    V2,
+    ChangelogV2 { compute_rank: bool },
+}
+
+/// Options to govern how a revlog should be opened, usually from the
+/// repository configuration or requirements.
+#[derive(Debug, Copy, Clone)]
+pub struct RevlogOpenOptions {
+    /// The revlog version, along with any option specific to this version
+    pub version: RevlogVersionOptions,
+    /// Whether the revlog uses a persistent nodemap.
+    pub use_nodemap: bool,
+    // TODO other non-header/version options,
+}
+
+impl RevlogOpenOptions {
+    pub fn new() -> Self {
+        Self {
+            version: RevlogVersionOptions::V1 { generaldelta: true },
+            use_nodemap: false,
+        }
+    }
+
+    fn default_index_header(&self) -> index::IndexHeader {
+        index::IndexHeader {
+            header_bytes: match self.version {
+                RevlogVersionOptions::V0 => [0, 0, 0, 0],
+                RevlogVersionOptions::V1 { generaldelta } => {
+                    [0, if generaldelta { 3 } else { 1 }, 0, 1]
+                }
+                RevlogVersionOptions::V2 => 0xDEADu32.to_be_bytes(),
+                RevlogVersionOptions::ChangelogV2 { compute_rank: _ } => {
+                    0xD34Du32.to_be_bytes()
+                }
+            },
+        }
+    }
+}
+
+impl Default for RevlogOpenOptions {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl Revlog {
     /// Open a revlog index file.
     ///
     /// It will also open the associated data file if index and data are not
     /// interleaved.
     pub fn open(
         store_vfs: &Vfs,
         index_path: impl AsRef<Path>,
         data_path: Option<&Path>,
-        use_nodemap: bool,
+        options: RevlogOpenOptions,
     ) -> Result<Self, HgError> {
-        Self::open_gen(store_vfs, index_path, data_path, use_nodemap, None)
+        Self::open_gen(store_vfs, index_path, data_path, options, None)
     }
 
     fn open_gen(
         store_vfs: &Vfs,
         index_path: impl AsRef<Path>,
         data_path: Option<&Path>,
-        use_nodemap: bool,
+        options: RevlogOpenOptions,
         nodemap_for_test: Option<nodemap::NodeTree>,
     ) -> Result<Self, HgError> {
         let index_path = index_path.as_ref();
         let index = {
             match store_vfs.mmap_open_opt(index_path)? {
-                None => Index::new(Box::<Vec<_>>::default()),
+                None => Index::new(
+                    Box::<Vec<_>>::default(),
+                    options.default_index_header(),
+                ),
                 Some(index_mmap) => {
-                    let index = Index::new(Box::new(index_mmap))?;
+                    let index = Index::new(
+                        Box::new(index_mmap),
+                        options.default_index_header(),
+                    )?;
                     Ok(index)
                 }
             }
         }?;
 
         let default_data_path = index_path.with_extension("d");
 
         // type annotation required
         // won't recognize Mmap as Deref<Target = [u8]>
         let data_bytes: Option<Box<dyn Deref<Target = [u8]> + Send>> =
             if index.is_inline() {
                 None
             } else {
                 let data_path = data_path.unwrap_or(&default_data_path);
                 let data_mmap = store_vfs.mmap_open(data_path)?;
                 Some(Box::new(data_mmap))
             };
 
-        let nodemap = if index.is_inline() || !use_nodemap {
+        let nodemap = if index.is_inline() || !options.use_nodemap {
             None
         } else {
             NodeMapDocket::read_from_file(store_vfs, index_path)?.map(
                 |(docket, data)| {
                     nodemap::NodeTree::load_bytes(
                         Box::new(data),
                         docket.data_length,
                     )
                 },
             )
         };
 
         let nodemap = nodemap_for_test.or(nodemap);
 
         Ok(Revlog {
             index,
             data_bytes,
             nodemap,
         })
     }
 
     /// Return number of entries of the `Revlog`.
     pub fn len(&self) -> usize {
         self.index.len()
     }
 
     /// Returns `true` if the `Revlog` has zero `entries`.
     pub fn is_empty(&self) -> bool {
         self.index.is_empty()
     }
 
     /// Returns the node ID for the given revision number, if it exists in this
     /// revlog
     pub fn node_from_rev(&self, rev: UncheckedRevision) -> Option<&Node> {
         if rev == NULL_REVISION.into() {
             return Some(&NULL_NODE);
         }
         let rev = self.index.check_revision(rev)?;
         Some(self.index.get_entry(rev)?.hash())
     }
 
     /// Return the revision number for the given node ID, if it exists in this
     /// revlog
     pub fn rev_from_node(
         &self,
         node: NodePrefix,
     ) -> Result<Revision, RevlogError> {
         if let Some(nodemap) = &self.nodemap {
             nodemap
                 .find_bin(&self.index, node)?
                 .ok_or(RevlogError::InvalidRevision)
         } else {
             self.rev_from_node_no_persistent_nodemap(node)
         }
     }
 
     /// Same as `rev_from_node`, without using a persistent nodemap
     ///
     /// This is used as fallback when a persistent nodemap is not present.
     /// This happens when the persistent-nodemap experimental feature is not
     /// enabled, or for small revlogs.
     fn rev_from_node_no_persistent_nodemap(
         &self,
         node: NodePrefix,
     ) -> Result<Revision, RevlogError> {
         // Linear scan of the revlog
         // TODO: consider building a non-persistent nodemap in memory to
         // optimize these cases.
         let mut found_by_prefix = None;
         for rev in (-1..self.len() as BaseRevision).rev() {
             let rev = Revision(rev as BaseRevision);
             let candidate_node = if rev == Revision(-1) {
                 NULL_NODE
             } else {
                 let index_entry =
                     self.index.get_entry(rev).ok_or_else(|| {
                         HgError::corrupted(
                             "revlog references a revision not in the index",
                         )
                     })?;
                 *index_entry.hash()
             };
             if node == candidate_node {
                 return Ok(rev);
             }
             if node.is_prefix_of(&candidate_node) {
                 if found_by_prefix.is_some() {
                     return Err(RevlogError::AmbiguousPrefix);
                 }
                 found_by_prefix = Some(rev)
             }
         }
         found_by_prefix.ok_or(RevlogError::InvalidRevision)
     }
 
     /// Returns whether the given revision exists in this revlog.
     pub fn has_rev(&self, rev: UncheckedRevision) -> bool {
         self.index.check_revision(rev).is_some()
     }
 
     /// Return the full data associated to a revision.
     ///
     /// All entries required to build the final data out of deltas will be
     /// retrieved as needed, and the deltas will be applied to the inital
     /// snapshot to rebuild the final data.
     pub fn get_rev_data(
         &self,
         rev: UncheckedRevision,
     ) -> Result<Cow<[u8]>, RevlogError> {
         if rev == NULL_REVISION.into() {
             return Ok(Cow::Borrowed(&[]));
         };
         self.get_entry(rev)?.data()
     }
 
     /// [`Self::get_rev_data`] for checked revisions.
     pub fn get_rev_data_for_checked_rev(
         &self,
         rev: Revision,
     ) -> Result<Cow<[u8]>, RevlogError> {
         if rev == NULL_REVISION {
             return Ok(Cow::Borrowed(&[]));
         };
         self.get_entry_for_checked_rev(rev)?.data()
     }
 
     /// Check the hash of some given data against the recorded hash.
     pub fn check_hash(
         &self,
         p1: Revision,
         p2: Revision,
         expected: &[u8],
         data: &[u8],
     ) -> bool {
         let e1 = self.index.get_entry(p1);
         let h1 = match e1 {
             Some(ref entry) => entry.hash(),
             None => &NULL_NODE,
         };
         let e2 = self.index.get_entry(p2);
         let h2 = match e2 {
             Some(ref entry) => entry.hash(),
             None => &NULL_NODE,
         };
 
         hash(data, h1.as_bytes(), h2.as_bytes()) == expected
     }
 
     /// Build the full data of a revision out its snapshot
     /// and its deltas.
     fn build_data_from_deltas(
         snapshot: RevlogEntry,
         deltas: &[RevlogEntry],
     ) -> Result<Vec<u8>, HgError> {
         let snapshot = snapshot.data_chunk()?;
         let deltas = deltas
             .iter()
             .rev()
             .map(RevlogEntry::data_chunk)
             .collect::<Result<Vec<_>, _>>()?;
         let patches: Vec<_> =
             deltas.iter().map(|d| patch::PatchList::new(d)).collect();
         let patch = patch::fold_patch_lists(&patches);
         Ok(patch.apply(&snapshot))
     }
 
     /// Return the revlog data.
     fn data(&self) -> &[u8] {
         match &self.data_bytes {
             Some(data_bytes) => data_bytes,
             None => panic!(
                 "forgot to load the data or trying to access inline data"
             ),
         }
     }
 
     pub fn make_null_entry(&self) -> RevlogEntry {
         RevlogEntry {
             revlog: self,
             rev: NULL_REVISION,
             bytes: b"",
             compressed_len: 0,
             uncompressed_len: 0,
             base_rev_or_base_of_delta_chain: None,
             p1: NULL_REVISION,
             p2: NULL_REVISION,
             flags: NULL_REVLOG_ENTRY_FLAGS,
             hash: NULL_NODE,
         }
     }
 
     fn get_entry_for_checked_rev(
         &self,
         rev: Revision,
     ) -> Result<RevlogEntry, RevlogError> {
         if rev == NULL_REVISION {
             return Ok(self.make_null_entry());
         }
         let index_entry = self
             .index
             .get_entry(rev)
             .ok_or(RevlogError::InvalidRevision)?;
         let start = index_entry.offset();
         let end = start + index_entry.compressed_len() as usize;
         let data = if self.index.is_inline() {
             self.index.data(start, end)
         } else {
             &self.data()[start..end]
         };
         let base_rev = self
             .index
             .check_revision(index_entry.base_revision_or_base_of_delta_chain())
             .ok_or_else(|| {
                 RevlogError::corrupted(format!(
                     "base revision for rev {} is invalid",
                     rev
                 ))
             })?;
         let p1 =
             self.index.check_revision(index_entry.p1()).ok_or_else(|| {
                 RevlogError::corrupted(format!(
                     "p1 for rev {} is invalid",
                     rev
                 ))
             })?;
         let p2 =
             self.index.check_revision(index_entry.p2()).ok_or_else(|| {
                 RevlogError::corrupted(format!(
                     "p2 for rev {} is invalid",
                     rev
                 ))
             })?;
         let entry = RevlogEntry {
             revlog: self,
             rev,
             bytes: data,
             compressed_len: index_entry.compressed_len(),
             uncompressed_len: index_entry.uncompressed_len(),
             base_rev_or_base_of_delta_chain: if base_rev == rev {
                 None
             } else {
                 Some(base_rev)
             },
             p1,
             p2,
             flags: index_entry.flags(),
             hash: *index_entry.hash(),
         };
         Ok(entry)
     }
 
     /// Get an entry of the revlog.
     pub fn get_entry(
         &self,
         rev: UncheckedRevision,
     ) -> Result<RevlogEntry, RevlogError> {
         if rev == NULL_REVISION.into() {
             return Ok(self.make_null_entry());
         }
         let rev = self.index.check_revision(rev).ok_or_else(|| {
             RevlogError::corrupted(format!("rev {} is invalid", rev))
         })?;
         self.get_entry_for_checked_rev(rev)
     }
 }
 
 /// The revlog entry's bytes and the necessary informations to extract
 /// the entry's data.
 #[derive(Clone)]
 pub struct RevlogEntry<'revlog> {
     revlog: &'revlog Revlog,
     rev: Revision,
     bytes: &'revlog [u8],
     compressed_len: u32,
     uncompressed_len: i32,
     base_rev_or_base_of_delta_chain: Option<Revision>,
     p1: Revision,
     p2: Revision,
     flags: u16,
     hash: Node,
 }
 
 thread_local! {
   // seems fine to [unwrap] here: this can only fail due to memory allocation
   // failing, and it's normal for that to cause panic.
   static ZSTD_DECODER : RefCell<zstd::bulk::Decompressor<'static>> =
       RefCell::new(zstd::bulk::Decompressor::new().ok().unwrap());
 }
 
 fn zstd_decompress_to_buffer(
     bytes: &[u8],
     buf: &mut Vec<u8>,
 ) -> Result<usize, std::io::Error> {
     ZSTD_DECODER
         .with(|decoder| decoder.borrow_mut().decompress_to_buffer(bytes, buf))
 }
 
 impl<'revlog> RevlogEntry<'revlog> {
     pub fn revision(&self) -> Revision {
         self.rev
     }
 
     pub fn node(&self) -> &Node {
         &self.hash
     }
 
     pub fn uncompressed_len(&self) -> Option<u32> {
         u32::try_from(self.uncompressed_len).ok()
     }
 
     pub fn has_p1(&self) -> bool {
         self.p1 != NULL_REVISION
     }
 
     pub fn p1_entry(
         &self,
     ) -> Result<Option<RevlogEntry<'revlog>>, RevlogError> {
         if self.p1 == NULL_REVISION {
             Ok(None)
         } else {
             Ok(Some(self.revlog.get_entry_for_checked_rev(self.p1)?))
         }
     }
 
     pub fn p2_entry(
         &self,
     ) -> Result<Option<RevlogEntry<'revlog>>, RevlogError> {
         if self.p2 == NULL_REVISION {
             Ok(None)
         } else {
             Ok(Some(self.revlog.get_entry_for_checked_rev(self.p2)?))
         }
     }
 
     pub fn p1(&self) -> Option<Revision> {
         if self.p1 == NULL_REVISION {
             None
         } else {
             Some(self.p1)
         }
     }
 
     pub fn p2(&self) -> Option<Revision> {
         if self.p2 == NULL_REVISION {
             None
         } else {
             Some(self.p2)
         }
     }
 
     pub fn is_censored(&self) -> bool {
         (self.flags & REVISION_FLAG_CENSORED) != 0
     }
 
     pub fn has_length_affecting_flag_processor(&self) -> bool {
         // Relevant Python code: revlog.size()
         // note: ELLIPSIS is known to not change the content
         (self.flags & (REVIDX_KNOWN_FLAGS ^ REVISION_FLAG_ELLIPSIS)) != 0
     }
 
     /// The data for this entry, after resolving deltas if any.
     pub fn rawdata(&self) -> Result<Cow<'revlog, [u8]>, RevlogError> {
         let mut entry = self.clone();
         let mut delta_chain = vec![];
 
         // The meaning of `base_rev_or_base_of_delta_chain` depends on
         // generaldelta. See the doc on `ENTRY_DELTA_BASE` in
         // `mercurial/revlogutils/constants.py` and the code in
         // [_chaininfo] and in [index_deltachain].
         let uses_generaldelta = self.revlog.index.uses_generaldelta();
         while let Some(base_rev) = entry.base_rev_or_base_of_delta_chain {
             entry = if uses_generaldelta {
                 delta_chain.push(entry);
                 self.revlog.get_entry_for_checked_rev(base_rev)?
             } else {
                 let base_rev = UncheckedRevision(entry.rev.0 - 1);
                 delta_chain.push(entry);
                 self.revlog.get_entry(base_rev)?
             };
         }
 
         let data = if delta_chain.is_empty() {
             entry.data_chunk()?
         } else {
             Revlog::build_data_from_deltas(entry, &delta_chain)?.into()
         };
 
         Ok(data)
     }
 
     fn check_data(
         &self,
         data: Cow<'revlog, [u8]>,
     ) -> Result<Cow<'revlog, [u8]>, RevlogError> {
         if self.revlog.check_hash(
             self.p1,
             self.p2,
             self.hash.as_bytes(),
             &data,
         ) {
             Ok(data)
         } else {
             if (self.flags & REVISION_FLAG_ELLIPSIS) != 0 {
                 return Err(HgError::unsupported(
                     "ellipsis revisions are not supported by rhg",
                 )
                 .into());
             }
             Err(corrupted(format!(
                 "hash check failed for revision {}",
                 self.rev
             ))
             .into())
         }
     }
 
     pub fn data(&self) -> Result<Cow<'revlog, [u8]>, RevlogError> {
         let data = self.rawdata()?;
         if self.rev == NULL_REVISION {
             return Ok(data);
         }
         if self.is_censored() {
             return Err(HgError::CensoredNodeError.into());
         }
         self.check_data(data)
     }
 
     /// Extract the data contained in the entry.
     /// This may be a delta. (See `is_delta`.)
     fn data_chunk(&self) -> Result<Cow<'revlog, [u8]>, HgError> {
         if self.bytes.is_empty() {
             return Ok(Cow::Borrowed(&[]));
         }
         match self.bytes[0] {
             // Revision data is the entirety of the entry, including this
             // header.
             b'\0' => Ok(Cow::Borrowed(self.bytes)),
             // Raw revision data follows.
             b'u' => Ok(Cow::Borrowed(&self.bytes[1..])),
             // zlib (RFC 1950) data.
             b'x' => Ok(Cow::Owned(self.uncompressed_zlib_data()?)),
             // zstd data.
             b'\x28' => Ok(Cow::Owned(self.uncompressed_zstd_data()?)),
             // A proper new format should have had a repo/store requirement.
             format_type => Err(corrupted(format!(
                 "unknown compression header '{}'",
                 format_type
             ))),
         }
     }
 
     fn uncompressed_zlib_data(&self) -> Result<Vec<u8>, HgError> {
         let mut decoder = ZlibDecoder::new(self.bytes);
         if self.is_delta() {
             let mut buf = Vec::with_capacity(self.compressed_len as usize);
             decoder
                 .read_to_end(&mut buf)
                 .map_err(|e| corrupted(e.to_string()))?;
             Ok(buf)
         } else {
             let cap = self.uncompressed_len.max(0) as usize;
             let mut buf = vec![0; cap];
             decoder
                 .read_exact(&mut buf)
                 .map_err(|e| corrupted(e.to_string()))?;
             Ok(buf)
         }
     }
 
     fn uncompressed_zstd_data(&self) -> Result<Vec<u8>, HgError> {
         let cap = self.uncompressed_len.max(0) as usize;
         if self.is_delta() {
             // [cap] is usually an over-estimate of the space needed because
             // it's the length of delta-decoded data, but we're interested
             // in the size of the delta.
             // This means we have to [shrink_to_fit] to avoid holding on
             // to a large chunk of memory, but it also means we must have a
             // fallback branch, for the case when the delta is longer than
             // the original data (surprisingly, this does happen in practice)
             let mut buf = Vec::with_capacity(cap);
             match zstd_decompress_to_buffer(self.bytes, &mut buf) {
                 Ok(_) => buf.shrink_to_fit(),
                 Err(_) => {
                     buf.clear();
                     zstd::stream::copy_decode(self.bytes, &mut buf)
                         .map_err(|e| corrupted(e.to_string()))?;
                 }
             };
             Ok(buf)
         } else {
             let mut buf = Vec::with_capacity(cap);
             let len = zstd_decompress_to_buffer(self.bytes, &mut buf)
                 .map_err(|e| corrupted(e.to_string()))?;
             if len != self.uncompressed_len as usize {
                 Err(corrupted("uncompressed length does not match"))
             } else {
                 Ok(buf)
             }
         }
     }
 
     /// Tell if the entry is a snapshot or a delta
     /// (influences on decompression).
     fn is_delta(&self) -> bool {
         self.base_rev_or_base_of_delta_chain.is_some()
     }
 }
 
 /// Calculate the hash of a revision given its data and its parents.
 fn hash(
     data: &[u8],
     p1_hash: &[u8],
     p2_hash: &[u8],
 ) -> [u8; NODE_BYTES_LENGTH] {
     let mut hasher = Sha1::new();
     let (a, b) = (p1_hash, p2_hash);
     if a > b {
         hasher.update(b);
         hasher.update(a);
     } else {
         hasher.update(a);
         hasher.update(b);
     }
     hasher.update(data);
     *hasher.finalize().as_ref()
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use crate::index::{IndexEntryBuilder, INDEX_ENTRY_SIZE};
     use itertools::Itertools;
 
     #[test]
     fn test_empty() {
         let temp = tempfile::tempdir().unwrap();
         let vfs = Vfs { base: temp.path() };
         std::fs::write(temp.path().join("foo.i"), b"").unwrap();
-        let revlog = Revlog::open(&vfs, "foo.i", None, false).unwrap();
+        let revlog =
+            Revlog::open(&vfs, "foo.i", None, RevlogOpenOptions::new())
+                .unwrap();
         assert!(revlog.is_empty());
         assert_eq!(revlog.len(), 0);
         assert!(revlog.get_entry(0.into()).is_err());
         assert!(!revlog.has_rev(0.into()));
         assert_eq!(
             revlog.rev_from_node(NULL_NODE.into()).unwrap(),
             NULL_REVISION
         );
         let null_entry = revlog.get_entry(NULL_REVISION.into()).ok().unwrap();
         assert_eq!(null_entry.revision(), NULL_REVISION);
         assert!(null_entry.data().unwrap().is_empty());
     }
 
     #[test]
     fn test_inline() {
         let temp = tempfile::tempdir().unwrap();
         let vfs = Vfs { base: temp.path() };
         let node0 = Node::from_hex("2ed2a3912a0b24502043eae84ee4b279c18b90dd")
             .unwrap();
         let node1 = Node::from_hex("b004912a8510032a0350a74daa2803dadfb00e12")
             .unwrap();
         let node2 = Node::from_hex("dd6ad206e907be60927b5a3117b97dffb2590582")
             .unwrap();
         let entry0_bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_version(1)
             .with_inline(true)
             .with_offset(INDEX_ENTRY_SIZE)
             .with_node(node0)
             .build();
         let entry1_bytes = IndexEntryBuilder::new()
             .with_offset(INDEX_ENTRY_SIZE)
             .with_node(node1)
             .build();
         let entry2_bytes = IndexEntryBuilder::new()
             .with_offset(INDEX_ENTRY_SIZE)
             .with_p1(Revision(0))
             .with_p2(Revision(1))
             .with_node(node2)
             .build();
         let contents = vec![entry0_bytes, entry1_bytes, entry2_bytes]
             .into_iter()
             .flatten()
             .collect_vec();
         std::fs::write(temp.path().join("foo.i"), contents).unwrap();
-        let revlog = Revlog::open(&vfs, "foo.i", None, false).unwrap();
+        let revlog =
+            Revlog::open(&vfs, "foo.i", None, RevlogOpenOptions::new())
+                .unwrap();
 
         let entry0 = revlog.get_entry(0.into()).ok().unwrap();
         assert_eq!(entry0.revision(), Revision(0));
         assert_eq!(*entry0.node(), node0);
         assert!(!entry0.has_p1());
         assert_eq!(entry0.p1(), None);
         assert_eq!(entry0.p2(), None);
         let p1_entry = entry0.p1_entry().unwrap();
         assert!(p1_entry.is_none());
         let p2_entry = entry0.p2_entry().unwrap();
         assert!(p2_entry.is_none());
 
         let entry1 = revlog.get_entry(1.into()).ok().unwrap();
         assert_eq!(entry1.revision(), Revision(1));
         assert_eq!(*entry1.node(), node1);
         assert!(!entry1.has_p1());
         assert_eq!(entry1.p1(), None);
         assert_eq!(entry1.p2(), None);
         let p1_entry = entry1.p1_entry().unwrap();
         assert!(p1_entry.is_none());
         let p2_entry = entry1.p2_entry().unwrap();
         assert!(p2_entry.is_none());
 
         let entry2 = revlog.get_entry(2.into()).ok().unwrap();
         assert_eq!(entry2.revision(), Revision(2));
         assert_eq!(*entry2.node(), node2);
         assert!(entry2.has_p1());
         assert_eq!(entry2.p1(), Some(Revision(0)));
         assert_eq!(entry2.p2(), Some(Revision(1)));
         let p1_entry = entry2.p1_entry().unwrap();
         assert!(p1_entry.is_some());
         assert_eq!(p1_entry.unwrap().revision(), Revision(0));
         let p2_entry = entry2.p2_entry().unwrap();
         assert!(p2_entry.is_some());
         assert_eq!(p2_entry.unwrap().revision(), Revision(1));
     }
 
     #[test]
     fn test_nodemap() {
         let temp = tempfile::tempdir().unwrap();
         let vfs = Vfs { base: temp.path() };
 
         // building a revlog with a forced Node starting with zeros
         // This is a corruption, but it does not preclude using the nodemap
         // if we don't try and access the data
         let node0 = Node::from_hex("00d2a3912a0b24502043eae84ee4b279c18b90dd")
             .unwrap();
         let node1 = Node::from_hex("b004912a8510032a0350a74daa2803dadfb00e12")
             .unwrap();
         let entry0_bytes = IndexEntryBuilder::new()
             .is_first(true)
             .with_version(1)
             .with_inline(true)
             .with_offset(INDEX_ENTRY_SIZE)
             .with_node(node0)
             .build();
         let entry1_bytes = IndexEntryBuilder::new()
             .with_offset(INDEX_ENTRY_SIZE)
             .with_node(node1)
             .build();
         let contents = vec![entry0_bytes, entry1_bytes]
             .into_iter()
             .flatten()
             .collect_vec();
         std::fs::write(temp.path().join("foo.i"), contents).unwrap();
 
         let mut idx = nodemap::tests::TestNtIndex::new();
         idx.insert_node(Revision(0), node0).unwrap();
         idx.insert_node(Revision(1), node1).unwrap();
 
-        let revlog =
-            Revlog::open_gen(&vfs, "foo.i", None, true, Some(idx.nt)).unwrap();
+        let revlog = Revlog::open_gen(
+            &vfs,
+            "foo.i",
+            None,
+            RevlogOpenOptions::new(),
+            Some(idx.nt),
+        )
+        .unwrap();
 
         // accessing the data shows the corruption
         revlog.get_entry(0.into()).unwrap().data().unwrap_err();
 
         assert_eq!(
             revlog.rev_from_node(NULL_NODE.into()).unwrap(),
             Revision(-1)
         );
         assert_eq!(revlog.rev_from_node(node0.into()).unwrap(), Revision(0));
         assert_eq!(revlog.rev_from_node(node1.into()).unwrap(), Revision(1));
         assert_eq!(
             revlog
                 .rev_from_node(NodePrefix::from_hex("000").unwrap())
                 .unwrap(),
             Revision(-1)
         );
         assert_eq!(
             revlog
                 .rev_from_node(NodePrefix::from_hex("b00").unwrap())
                 .unwrap(),
             Revision(1)
         );
         // RevlogError does not implement PartialEq
         // (ultimately because io::Error does not)
         match revlog
             .rev_from_node(NodePrefix::from_hex("00").unwrap())
             .expect_err("Expected to give AmbiguousPrefix error")
         {
             RevlogError::AmbiguousPrefix => (),
             e => {
                 panic!("Got another error than AmbiguousPrefix: {:?}", e);
             }
         };
     }
 }

rust/hg-cpython/src/revlog.rs

@@ -1,561 +1,572 b''
 // revlog.rs
 //
 // Copyright 2019-2020 Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::{
     cindex,
     utils::{node_from_py_bytes, node_from_py_object},
     PyRevision,
 };
 use cpython::{
     buffer::{Element, PyBuffer},
     exc::{IndexError, ValueError},
     ObjectProtocol, PyBytes, PyClone, PyDict, PyErr, PyInt, PyModule,
     PyObject, PyResult, PyString, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::{
+    index::IndexHeader,
     nodemap::{Block, NodeMapError, NodeTree},
     revlog::{nodemap::NodeMap, NodePrefix, RevlogIndex},
     BaseRevision, Revision, UncheckedRevision,
 };
 use std::cell::RefCell;
 
 /// Return a Struct implementing the Graph trait
 pub(crate) fn pyindex_to_graph(
     py: Python,
     index: PyObject,
 ) -> PyResult<cindex::Index> {
     match index.extract::<MixedIndex>(py) {
         Ok(midx) => Ok(midx.clone_cindex(py)),
         Err(_) => cindex::Index::new(py, index),
     }
 }
 
 py_class!(pub class MixedIndex |py| {
     data cindex: RefCell<cindex::Index>;
     data index: RefCell<hg::index::Index>;
     data nt: RefCell<Option<NodeTree>>;
     data docket: RefCell<Option<PyObject>>;
     // Holds a reference to the mmap'ed persistent nodemap data
     data nodemap_mmap: RefCell<Option<PyBuffer>>;
     // Holds a reference to the mmap'ed persistent index data
     data index_mmap: RefCell<Option<PyBuffer>>;
 
     def __new__(
         _cls,
         cindex: PyObject,
-        data: PyObject
+        data: PyObject,
+        default_header: u32,
     ) -> PyResult<MixedIndex> {
-        Self::new(py, cindex, data)
+        Self::new(py, cindex, data, default_header)
     }
 
     /// Compatibility layer used for Python consumers needing access to the C index
     ///
     /// Only use case so far is `scmutil.shortesthexnodeidprefix`,
     /// that may need to build a custom `nodetree`, based on a specified revset.
     /// With a Rust implementation of the nodemap, we will be able to get rid of
     /// this, by exposing our own standalone nodemap class,
     /// ready to accept `MixedIndex`.
     def get_cindex(&self) -> PyResult<PyObject> {
         Ok(self.cindex(py).borrow().inner().clone_ref(py))
     }
 
     // Index API involving nodemap, as defined in mercurial/pure/parsers.py
 
     /// Return Revision if found, raises a bare `error.RevlogError`
     /// in case of ambiguity, same as C version does
     def get_rev(&self, node: PyBytes) -> PyResult<Option<PyRevision>> {
         let opt = self.get_nodetree(py)?.borrow();
         let nt = opt.as_ref().unwrap();
         let idx = &*self.cindex(py).borrow();
         let node = node_from_py_bytes(py, &node)?;
         let res = nt.find_bin(idx, node.into());
         Ok(res.map_err(|e| nodemap_error(py, e))?.map(Into::into))
     }
 
     /// same as `get_rev()` but raises a bare `error.RevlogError` if node
     /// is not found.
     ///
     /// No need to repeat `node` in the exception, `mercurial/revlog.py`
     /// will catch and rewrap with it
     def rev(&self, node: PyBytes) -> PyResult<PyRevision> {
         self.get_rev(py, node)?.ok_or_else(|| revlog_error(py))
     }
 
     /// return True if the node exist in the index
     def has_node(&self, node: PyBytes) -> PyResult<bool> {
         self.get_rev(py, node).map(|opt| opt.is_some())
     }
 
     /// find length of shortest hex nodeid of a binary ID
     def shortest(&self, node: PyBytes) -> PyResult<usize> {
         let opt = self.get_nodetree(py)?.borrow();
         let nt = opt.as_ref().unwrap();
         let idx = &*self.cindex(py).borrow();
         match nt.unique_prefix_len_node(idx, &node_from_py_bytes(py, &node)?)
         {
             Ok(Some(l)) => Ok(l),
             Ok(None) => Err(revlog_error(py)),
             Err(e) => Err(nodemap_error(py, e)),
         }
     }
 
     def partialmatch(&self, node: PyObject) -> PyResult<Option<PyBytes>> {
         let opt = self.get_nodetree(py)?.borrow();
         let nt = opt.as_ref().unwrap();
         let idx = &*self.cindex(py).borrow();
 
         let node_as_string = if cfg!(feature = "python3-sys") {
             node.cast_as::<PyString>(py)?.to_string(py)?.to_string()
         }
         else {
             let node = node.extract::<PyBytes>(py)?;
             String::from_utf8_lossy(node.data(py)).to_string()
         };
 
         let prefix = NodePrefix::from_hex(&node_as_string)
             .map_err(|_| PyErr::new::<ValueError, _>(
                 py, format!("Invalid node or prefix '{}'", node_as_string))
             )?;
 
         nt.find_bin(idx, prefix)
             // TODO make an inner API returning the node directly
             .map(|opt| opt.map(
                 |rev| PyBytes::new(py, idx.node(rev).unwrap().as_bytes())))
             .map_err(|e| nodemap_error(py, e))
 
     }
 
     /// append an index entry
     def append(&self, tup: PyTuple) -> PyResult<PyObject> {
         if tup.len(py) < 8 {
             // this is better than the panic promised by tup.get_item()
             return Err(
                 PyErr::new::<IndexError, _>(py, "tuple index out of range"))
         }
         let node_bytes = tup.get_item(py, 7).extract(py)?;
         let node = node_from_py_object(py, &node_bytes)?;
 
         let mut idx = self.cindex(py).borrow_mut();
 
         // This is ok since we will just add the revision to the index
         let rev = Revision(idx.len() as BaseRevision);
         idx.append(py, tup)?;
 
         self.get_nodetree(py)?.borrow_mut().as_mut().unwrap()
             .insert(&*idx, &node, rev)
             .map_err(|e| nodemap_error(py, e))?;
         Ok(py.None())
     }
 
     def __delitem__(&self, key: PyObject) -> PyResult<()> {
         // __delitem__ is both for `del idx[r]` and `del idx[r1:r2]`
         self.cindex(py).borrow().inner().del_item(py, key)?;
         let mut opt = self.get_nodetree(py)?.borrow_mut();
         let nt = opt.as_mut().unwrap();
         nt.invalidate_all();
         self.fill_nodemap(py, nt)?;
         Ok(())
     }
 
     //
     // Reforwarded C index API
     //
 
     // index_methods (tp_methods). Same ordering as in revlog.c
 
     /// return the gca set of the given revs
     def ancestors(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "ancestors", args, kw)
     }
 
     /// return the heads of the common ancestors of the given revs
     def commonancestorsheads(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "commonancestorsheads", args, kw)
     }
 
     /// Clear the index caches and inner py_class data.
     /// It is Python's responsibility to call `update_nodemap_data` again.
     def clearcaches(&self, *args, **kw) -> PyResult<PyObject> {
         self.nt(py).borrow_mut().take();
         self.docket(py).borrow_mut().take();
         self.nodemap_mmap(py).borrow_mut().take();
         self.call_cindex(py, "clearcaches", args, kw)
     }
 
     /// return the raw binary string representing a revision
     def entry_binary(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "entry_binary", args, kw)
     }
 
     /// return a binary packed version of the header
     def pack_header(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "pack_header", args, kw)
     }
 
     /// get an index entry
     def get(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "get", args, kw)
     }
 
     /// compute phases
     def computephasesmapsets(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "computephasesmapsets", args, kw)
     }
 
     /// reachableroots
     def reachableroots2(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "reachableroots2", args, kw)
     }
 
     /// get head revisions
     def headrevs(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "headrevs", args, kw)
     }
 
     /// get filtered head revisions
     def headrevsfiltered(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "headrevsfiltered", args, kw)
     }
 
     /// True if the object is a snapshot
     def issnapshot(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "issnapshot", args, kw)
     }
 
     /// Gather snapshot data in a cache dict
     def findsnapshots(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "findsnapshots", args, kw)
     }
 
     /// determine revisions with deltas to reconstruct fulltext
     def deltachain(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "deltachain", args, kw)
     }
 
     /// slice planned chunk read to reach a density threshold
     def slicechunktodensity(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "slicechunktodensity", args, kw)
     }
 
     /// stats for the index
     def stats(&self, *args, **kw) -> PyResult<PyObject> {
         self.call_cindex(py, "stats", args, kw)
     }
 
     // index_sequence_methods and index_mapping_methods.
     //
     // Since we call back through the high level Python API,
     // there's no point making a distinction between index_get
     // and index_getitem.
 
     def __len__(&self) -> PyResult<usize> {
         self.cindex(py).borrow().inner().len(py)
     }
 
     def __getitem__(&self, key: PyObject) -> PyResult<PyObject> {
         // this conversion seems needless, but that's actually because
         // `index_getitem` does not handle conversion from PyLong,
         // which expressions such as [e for e in index] internally use.
         // Note that we don't seem to have a direct way to call
         // PySequence_GetItem (does the job), which would possibly be better
         // for performance
         let key = match key.extract::<i32>(py) {
             Ok(rev) => rev.to_py_object(py).into_object(),
             Err(_) => key,
         };
         self.cindex(py).borrow().inner().get_item(py, key)
     }
 
     def __setitem__(&self, key: PyObject, value: PyObject) -> PyResult<()> {
         self.cindex(py).borrow().inner().set_item(py, key, value)
     }
 
     def __contains__(&self, item: PyObject) -> PyResult<bool> {
         // ObjectProtocol does not seem to provide contains(), so
         // this is an equivalent implementation of the index_contains()
         // defined in revlog.c
         let cindex = self.cindex(py).borrow();
         match item.extract::<i32>(py) {
             Ok(rev) => {
                 Ok(rev >= -1 && rev < cindex.inner().len(py)? as BaseRevision)
             }
             Err(_) => {
                 cindex.inner().call_method(
                     py,
                     "has_node",
                     PyTuple::new(py, &[item]),
                     None)?
                 .extract(py)
             }
         }
     }
 
     def nodemap_data_all(&self) -> PyResult<PyBytes> {
         self.inner_nodemap_data_all(py)
     }
 
     def nodemap_data_incremental(&self) -> PyResult<PyObject> {
         self.inner_nodemap_data_incremental(py)
     }
     def update_nodemap_data(
         &self,
         docket: PyObject,
         nm_data: PyObject
     ) -> PyResult<PyObject> {
         self.inner_update_nodemap_data(py, docket, nm_data)
     }
 
     @property
     def entry_size(&self) -> PyResult<PyInt> {
         self.cindex(py).borrow().inner().getattr(py, "entry_size")?.extract::<PyInt>(py)
     }
 
     @property
     def rust_ext_compat(&self) -> PyResult<PyInt> {
         self.cindex(py).borrow().inner().getattr(py, "rust_ext_compat")?.extract::<PyInt>(py)
     }
 
 });
 
 /// Take a (potentially) mmap'ed buffer, and return the underlying Python
 /// buffer along with the Rust slice into said buffer. We need to keep the
 /// Python buffer around, otherwise we'd get a dangling pointer once the buffer
 /// is freed from Python's side.
 ///
 /// # Safety
 ///
 /// The caller must make sure that the buffer is kept around for at least as
 /// long as the slice.
 #[deny(unsafe_op_in_unsafe_fn)]
 unsafe fn mmap_keeparound(
     py: Python,
     data: PyObject,
 ) -> PyResult<(
     PyBuffer,
     Box<dyn std::ops::Deref<Target = [u8]> + Send + 'static>,
 )> {
     let buf = PyBuffer::get(py, &data)?;
     let len = buf.item_count();
 
     // Build a slice from the mmap'ed buffer data
     let cbuf = buf.buf_ptr();
     let bytes = if std::mem::size_of::<u8>() == buf.item_size()
         && buf.is_c_contiguous()
         && u8::is_compatible_format(buf.format())
     {
         unsafe { std::slice::from_raw_parts(cbuf as *const u8, len) }
     } else {
         return Err(PyErr::new::<ValueError, _>(
             py,
             "Nodemap data buffer has an invalid memory representation"
                 .to_string(),
         ));
     };
 
     Ok((buf, Box::new(bytes)))
 }
 
 impl MixedIndex {
     fn new(
         py: Python,
         cindex: PyObject,
         data: PyObject,
+        header: u32,
     ) -> PyResult<MixedIndex> {
         // Safety: we keep the buffer around inside the class as `index_mmap`
         let (buf, bytes) = unsafe { mmap_keeparound(py, data)? };
 
         Self::create_instance(
             py,
             RefCell::new(cindex::Index::new(py, cindex)?),
-            RefCell::new(hg::index::Index::new(bytes).unwrap()),
+            RefCell::new(
+                hg::index::Index::new(
+                    bytes,
+                    IndexHeader::parse(&header.to_be_bytes())
+                        .expect("default header is broken")
+                        .unwrap(),
+                )
+                .unwrap(),
+            ),
             RefCell::new(None),
             RefCell::new(None),
             RefCell::new(None),
             RefCell::new(Some(buf)),
         )
     }
 
     /// This is scaffolding at this point, but it could also become
     /// a way to start a persistent nodemap or perform a
     /// vacuum / repack operation
     fn fill_nodemap(
         &self,
         py: Python,
         nt: &mut NodeTree,
     ) -> PyResult<PyObject> {
         let index = self.cindex(py).borrow();
         for r in 0..index.len() {
             let rev = Revision(r as BaseRevision);
             // in this case node() won't ever return None
             nt.insert(&*index, index.node(rev).unwrap(), rev)
                 .map_err(|e| nodemap_error(py, e))?
         }
         Ok(py.None())
     }
 
     fn get_nodetree<'a>(
         &'a self,
         py: Python<'a>,
     ) -> PyResult<&'a RefCell<Option<NodeTree>>> {
         if self.nt(py).borrow().is_none() {
             let readonly = Box::<Vec<_>>::default();
             let mut nt = NodeTree::load_bytes(readonly, 0);
             self.fill_nodemap(py, &mut nt)?;
             self.nt(py).borrow_mut().replace(nt);
         }
         Ok(self.nt(py))
     }
 
     /// forward a method call to the underlying C index
     fn call_cindex(
         &self,
         py: Python,
         name: &str,
         args: &PyTuple,
         kwargs: Option<&PyDict>,
     ) -> PyResult<PyObject> {
         self.cindex(py)
             .borrow()
             .inner()
             .call_method(py, name, args, kwargs)
     }
 
     pub fn clone_cindex(&self, py: Python) -> cindex::Index {
         self.cindex(py).borrow().clone_ref(py)
     }
 
     /// Returns the full nodemap bytes to be written as-is to disk
     fn inner_nodemap_data_all(&self, py: Python) -> PyResult<PyBytes> {
         let nodemap = self.get_nodetree(py)?.borrow_mut().take().unwrap();
         let (readonly, bytes) = nodemap.into_readonly_and_added_bytes();
 
         // If there's anything readonly, we need to build the data again from
         // scratch
         let bytes = if readonly.len() > 0 {
             let mut nt = NodeTree::load_bytes(Box::<Vec<_>>::default(), 0);
             self.fill_nodemap(py, &mut nt)?;
 
             let (readonly, bytes) = nt.into_readonly_and_added_bytes();
             assert_eq!(readonly.len(), 0);
 
             bytes
         } else {
             bytes
         };
 
         let bytes = PyBytes::new(py, &bytes);
         Ok(bytes)
     }
 
     /// Returns the last saved docket along with the size of any changed data
     /// (in number of blocks), and said data as bytes.
     fn inner_nodemap_data_incremental(
         &self,
         py: Python,
     ) -> PyResult<PyObject> {
         let docket = self.docket(py).borrow();
         let docket = match docket.as_ref() {
             Some(d) => d,
             None => return Ok(py.None()),
         };
 
         let node_tree = self.get_nodetree(py)?.borrow_mut().take().unwrap();
         let masked_blocks = node_tree.masked_readonly_blocks();
         let (_, data) = node_tree.into_readonly_and_added_bytes();
         let changed = masked_blocks * std::mem::size_of::<Block>();
 
         Ok((docket, changed, PyBytes::new(py, &data))
             .to_py_object(py)
             .into_object())
     }
 
     /// Update the nodemap from the new (mmaped) data.
     /// The docket is kept as a reference for later incremental calls.
     fn inner_update_nodemap_data(
         &self,
         py: Python,
         docket: PyObject,
         nm_data: PyObject,
     ) -> PyResult<PyObject> {
         // Safety: we keep the buffer around inside the class as `nodemap_mmap`
         let (buf, bytes) = unsafe { mmap_keeparound(py, nm_data)? };
         let len = buf.item_count();
         self.nodemap_mmap(py).borrow_mut().replace(buf);
 
         let mut nt = NodeTree::load_bytes(bytes, len);
 
         let data_tip = docket
             .getattr(py, "tip_rev")?
             .extract::<BaseRevision>(py)?
             .into();
         self.docket(py).borrow_mut().replace(docket.clone_ref(py));
         let idx = self.cindex(py).borrow();
         let data_tip = idx.check_revision(data_tip).ok_or_else(|| {
             nodemap_error(py, NodeMapError::RevisionNotInIndex(data_tip))
         })?;
         let current_tip = idx.len();
 
         for r in (data_tip.0 + 1)..current_tip as BaseRevision {
             let rev = Revision(r);
             // in this case node() won't ever return None
             nt.insert(&*idx, idx.node(rev).unwrap(), rev)
                 .map_err(|e| nodemap_error(py, e))?
         }
 
         *self.nt(py).borrow_mut() = Some(nt);
 
         Ok(py.None())
     }
 }
 
 fn revlog_error(py: Python) -> PyErr {
     match py
         .import("mercurial.error")
         .and_then(|m| m.get(py, "RevlogError"))
     {
         Err(e) => e,
         Ok(cls) => PyErr::from_instance(
             py,
             cls.call(py, (py.None(),), None).ok().into_py_object(py),
         ),
     }
 }
 
 fn rev_not_in_index(py: Python, rev: UncheckedRevision) -> PyErr {
     PyErr::new::<ValueError, _>(
         py,
         format!(
             "Inconsistency: Revision {} found in nodemap \
              is not in revlog index",
             rev
         ),
     )
 }
 
 /// Standard treatment of NodeMapError
 fn nodemap_error(py: Python, err: NodeMapError) -> PyErr {
     match err {
         NodeMapError::MultipleResults => revlog_error(py),
         NodeMapError::RevisionNotInIndex(r) => rev_not_in_index(py, r),
     }
 }
 
 /// Create the module, with __package__ given from parent
 pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
     let dotted_name = &format!("{}.revlog", package);
     let m = PyModule::new(py, dotted_name)?;
     m.add(py, "__package__", package)?;
     m.add(py, "__doc__", "RevLog - Rust implementations")?;
 
     m.add_class::<MixedIndex>(py)?;
 
     let sys = PyModule::import(py, "sys")?;
     let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
     sys_modules.set_item(py, dotted_name, &m)?;
 
     Ok(m)
 }

rust/rhg/src/commands/status.rs

@@ -1,815 +1,822 b''
 // status.rs
 //
 // Copyright 2020, Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::error::CommandError;
 use crate::ui::{
     format_pattern_file_warning, print_narrow_sparse_warnings, relative_paths,
     RelativePaths, Ui,
 };
 use crate::utils::path_utils::RelativizePaths;
 use clap::Arg;
 use format_bytes::format_bytes;
 use hg::config::Config;
 use hg::dirstate::has_exec_bit;
 use hg::dirstate::status::StatusPath;
 use hg::dirstate::TruncatedTimestamp;
 use hg::errors::{HgError, IoResultExt};
 use hg::filepatterns::parse_pattern_args;
 use hg::lock::LockError;
 use hg::manifest::Manifest;
 use hg::matchers::{AlwaysMatcher, IntersectionMatcher};
 use hg::repo::Repo;
 use hg::utils::debug::debug_wait_for_file;
 use hg::utils::files::{
     get_bytes_from_os_str, get_bytes_from_os_string, get_path_from_bytes,
 };
 use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
-use hg::DirstateStatus;
 use hg::PatternFileWarning;
 use hg::Revision;
 use hg::StatusError;
 use hg::StatusOptions;
 use hg::{self, narrow, sparse};
+use hg::{DirstateStatus, RevlogOpenOptions};
 use log::info;
 use rayon::prelude::*;
 use std::borrow::Cow;
 use std::io;
 use std::mem::take;
 use std::path::PathBuf;
 
 pub const HELP_TEXT: &str = "
 Show changed files in the working directory
 
 This is a pure Rust version of `hg status`.
 
 Some options might be missing, check the list below.
 ";
 
 pub fn args() -> clap::Command {
     clap::command!("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::new("file")
                 .value_parser(clap::value_parser!(std::ffi::OsString))
                 .help("show only these files")
                 .action(clap::ArgAction::Append),
         )
         .arg(
             Arg::new("all")
                 .help("show status of all files")
                 .short('A')
                 .action(clap::ArgAction::SetTrue)
                 .long("all"),
         )
         .arg(
             Arg::new("modified")
                 .help("show only modified files")
                 .short('m')
                 .action(clap::ArgAction::SetTrue)
                 .long("modified"),
         )
         .arg(
             Arg::new("added")
                 .help("show only added files")
                 .short('a')
                 .action(clap::ArgAction::SetTrue)
                 .long("added"),
         )
         .arg(
             Arg::new("removed")
                 .help("show only removed files")
                 .short('r')
                 .action(clap::ArgAction::SetTrue)
                 .long("removed"),
         )
         .arg(
             Arg::new("clean")
                 .help("show only clean files")
                 .short('c')
                 .action(clap::ArgAction::SetTrue)
                 .long("clean"),
         )
         .arg(
             Arg::new("deleted")
                 .help("show only deleted files")
                 .short('d')
                 .action(clap::ArgAction::SetTrue)
                 .long("deleted"),
         )
         .arg(
             Arg::new("unknown")
                 .help("show only unknown (not tracked) files")
                 .short('u')
                 .action(clap::ArgAction::SetTrue)
                 .long("unknown"),
         )
         .arg(
             Arg::new("ignored")
                 .help("show only ignored files")
                 .short('i')
                 .action(clap::ArgAction::SetTrue)
                 .long("ignored"),
         )
         .arg(
             Arg::new("copies")
                 .help("show source of copied files (DEFAULT: ui.statuscopies)")
                 .short('C')
                 .action(clap::ArgAction::SetTrue)
                 .long("copies"),
         )
         .arg(
             Arg::new("print0")
                 .help("end filenames with NUL, for use with xargs")
                 .short('0')
                 .action(clap::ArgAction::SetTrue)
                 .long("print0"),
         )
         .arg(
             Arg::new("no-status")
                 .help("hide status prefix")
                 .short('n')
                 .action(clap::ArgAction::SetTrue)
                 .long("no-status"),
         )
         .arg(
             Arg::new("verbose")
                 .help("enable additional output")
                 .short('v')
                 .action(clap::ArgAction::SetTrue)
                 .long("verbose"),
         )
         .arg(
             Arg::new("rev")
                 .help("show difference from/to revision")
                 .long("rev")
                 .num_args(1)
                 .action(clap::ArgAction::Append)
                 .value_name("REV"),
         )
 }
 
 fn parse_revpair(
     repo: &Repo,
     revs: Option<Vec<String>>,
 ) -> Result<Option<(Revision, Revision)>, CommandError> {
     let revs = match revs {
         None => return Ok(None),
         Some(revs) => revs,
     };
     if revs.is_empty() {
         return Ok(None);
     }
     if revs.len() != 2 {
         return Err(CommandError::unsupported("expected 0 or 2 --rev flags"));
     }
 
     let rev1 = &revs[0];
     let rev2 = &revs[1];
     let rev1 = hg::revset::resolve_single(rev1, repo)
         .map_err(|e| (e, rev1.as_str()))?;
     let rev2 = hg::revset::resolve_single(rev2, repo)
         .map_err(|e| (e, rev2.as_str()))?;
     Ok(Some((rev1, rev2)))
 }
 
 /// Pure data type allowing the caller to specify file states to display
 #[derive(Copy, Clone, Debug)]
 pub struct DisplayStates {
     pub modified: bool,
     pub added: bool,
     pub removed: bool,
     pub clean: bool,
     pub deleted: bool,
     pub unknown: bool,
     pub ignored: bool,
 }
 
 pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: false,
     deleted: true,
     unknown: true,
     ignored: false,
 };
 
 pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: true,
     deleted: true,
     unknown: true,
     ignored: true,
 };
 
 impl DisplayStates {
     pub fn is_empty(&self) -> bool {
         !(self.modified
             || self.added
             || self.removed
             || self.clean
             || self.deleted
             || self.unknown
             || self.ignored)
     }
 }
 
 fn has_unfinished_merge(repo: &Repo) -> Result<bool, CommandError> {
     Ok(repo.dirstate_parents()?.is_merge())
 }
 
 fn has_unfinished_state(repo: &Repo) -> Result<bool, CommandError> {
     // These are all the known values for the [fname] argument of
     // [addunfinished] function in [state.py]
     let known_state_files: &[&str] = &[
         "bisect.state",
         "graftstate",
         "histedit-state",
         "rebasestate",
         "shelvedstate",
         "transplant/journal",
         "updatestate",
     ];
     if has_unfinished_merge(repo)? {
         return Ok(true);
     };
     for f in known_state_files {
         if repo.hg_vfs().join(f).exists() {
             return Ok(true);
         }
     }
     Ok(false)
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     // TODO: lift these limitations
     if invocation
         .config
         .get(b"commands", b"status.terse")
         .is_some()
     {
         return Err(CommandError::unsupported(
             "status.terse is not yet supported with rhg status",
         ));
     }
 
     let ui = invocation.ui;
     let config = invocation.config;
     let args = invocation.subcommand_args;
 
     let revs = args.get_many::<String>("rev");
     let print0 = args.get_flag("print0");
     let verbose = args.get_flag("verbose")
         || config.get_bool(b"ui", b"verbose")?
         || config.get_bool(b"commands", b"status.verbose")?;
     let verbose = verbose && !print0;
 
     let all = args.get_flag("all");
     let display_states = if all {
         // TODO when implementing `--quiet`: it excludes clean files
         // from `--all`
         ALL_DISPLAY_STATES
     } else {
         let requested = DisplayStates {
             modified: args.get_flag("modified"),
             added: args.get_flag("added"),
             removed: args.get_flag("removed"),
             clean: args.get_flag("clean"),
             deleted: args.get_flag("deleted"),
             unknown: args.get_flag("unknown"),
             ignored: args.get_flag("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
     let no_status = args.get_flag("no-status");
     let list_copies = all
         || args.get_flag("copies")
         || config.get_bool(b"ui", b"statuscopies")?;
 
     let repo = invocation.repo?;
     let revpair = parse_revpair(repo, revs.map(|i| i.cloned().collect()))?;
 
     if verbose && has_unfinished_state(repo)? {
         return Err(CommandError::unsupported(
             "verbose status output is not supported by rhg (and is needed because we're in an unfinished operation)",
         ));
     }
 
     let mut dmap = repo.dirstate_map_mut()?;
 
     let check_exec = hg::checkexec::check_exec(repo.working_directory_path());
 
     let options = StatusOptions {
         check_exec,
         list_clean: display_states.clean,
         list_unknown: display_states.unknown,
         list_ignored: display_states.ignored,
         list_copies,
         collect_traversed_dirs: false,
     };
 
     type StatusResult<'a> =
         Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>;
 
     let relative_status = config
         .get_option(b"commands", b"status.relative")?
         .expect("commands.status.relative should have a default value");
 
     let relativize_paths = relative_status || {
         // See in Python code with `getuipathfn` usage in `commands.py`.
         let legacy_relative_behavior = args.contains_id("file");
         match relative_paths(invocation.config)? {
             RelativePaths::Legacy => legacy_relative_behavior,
             RelativePaths::Bool(v) => v,
         }
     };
 
     let mut output = DisplayStatusPaths {
         ui,
         no_status,
         relativize: if relativize_paths {
             Some(RelativizePaths::new(repo)?)
         } else {
             None
         },
         print0,
     };
 
     let after_status = |res: StatusResult| -> Result<_, CommandError> {
         let (mut ds_status, pattern_warnings) = res?;
         for warning in pattern_warnings {
             ui.write_stderr(&format_pattern_file_warning(&warning, repo))?;
         }
 
         for (path, error) in take(&mut ds_status.bad) {
             let error = match error {
                 hg::BadMatch::OsError(code) => {
                     std::io::Error::from_raw_os_error(code).to_string()
                 }
                 hg::BadMatch::BadType(ty) => {
                     format!("unsupported file type (type is {})", ty)
                 }
             };
             ui.write_stderr(&format_bytes!(
                 b"{}: {}\n",
                 path.as_bytes(),
                 error.as_bytes()
             ))?
         }
         if !ds_status.unsure.is_empty() {
             info!(
                 "Files to be rechecked by retrieval from filelog: {:?}",
                 ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
             );
         }
         let mut fixup = Vec::new();
         if !ds_status.unsure.is_empty()
             && (display_states.modified || display_states.clean)
         {
             let p1 = repo.dirstate_parents()?.p1;
             let manifest = repo.manifest_for_node(p1).map_err(|e| {
                 CommandError::from((e, &*format!("{:x}", p1.short())))
             })?;
             let working_directory_vfs = repo.working_directory_vfs();
             let store_vfs = repo.store_vfs();
+            let revlog_open_options = repo.default_revlog_options(false)?;
             let res: Vec<_> = take(&mut ds_status.unsure)
                 .into_par_iter()
                 .map(|to_check| {
                     // The compiler seems to get a bit confused with complex
                     // inference when using a parallel iterator + map
                     // + map_err + collect, so let's just inline some of the
                     // logic.
                     match unsure_is_modified(
                         working_directory_vfs,
                         store_vfs,
                         check_exec,
                         &manifest,
                         &to_check.path,
+                        revlog_open_options,
                     ) {
                         Err(HgError::IoError { .. }) => {
                             // IO errors most likely stem from the file being
                             // deleted even though we know it's in the
                             // dirstate.
                             Ok((to_check, UnsureOutcome::Deleted))
                         }
                         Ok(outcome) => Ok((to_check, outcome)),
                         Err(e) => Err(e),
                     }
                 })
                 .collect::<Result<_, _>>()?;
             for (status_path, outcome) in res.into_iter() {
                 match outcome {
                     UnsureOutcome::Clean => {
                         if display_states.clean {
                             ds_status.clean.push(status_path.clone());
                         }
                         fixup.push(status_path.path.into_owned())
                     }
                     UnsureOutcome::Modified => {
                         if display_states.modified {
                             ds_status.modified.push(status_path);
                         }
                     }
                     UnsureOutcome::Deleted => {
                         if display_states.deleted {
                             ds_status.deleted.push(status_path);
                         }
                     }
                 }
             }
         }
 
         let dirstate_write_needed = ds_status.dirty;
         let filesystem_time_at_status_start =
             ds_status.filesystem_time_at_status_start;
 
         output.output(display_states, ds_status)?;
 
         Ok((
             fixup,
             dirstate_write_needed,
             filesystem_time_at_status_start,
         ))
     };
     let (narrow_matcher, narrow_warnings) = narrow::matcher(repo)?;
 
     match revpair {
         Some((rev1, rev2)) => {
             let mut ds_status = DirstateStatus::default();
             if list_copies {
                 return Err(CommandError::unsupported(
                     "status --rev --rev with copy information is not implemented yet",
                 ));
             }
 
             let stat = hg::operations::status_rev_rev_no_copies(
                 repo,
                 rev1,
                 rev2,
                 narrow_matcher,
             )?;
             for entry in stat.iter() {
                 let (path, status) = entry?;
                 let path = StatusPath {
                     path: Cow::Borrowed(path),
                     copy_source: None,
                 };
                 match status {
                     hg::operations::DiffStatus::Removed => {
                         if display_states.removed {
                             ds_status.removed.push(path)
                         }
                     }
                     hg::operations::DiffStatus::Added => {
                         if display_states.added {
                             ds_status.added.push(path)
                         }
                     }
                     hg::operations::DiffStatus::Modified => {
                         if display_states.modified {
                             ds_status.modified.push(path)
                         }
                     }
                     hg::operations::DiffStatus::Matching => {
                         if display_states.clean {
                             ds_status.clean.push(path)
                         }
                     }
                 }
             }
             output.output(display_states, ds_status)?;
             return Ok(());
         }
         None => (),
     }
 
     let (sparse_matcher, sparse_warnings) = sparse::matcher(repo)?;
     let matcher = match (repo.has_narrow(), repo.has_sparse()) {
         (true, true) => {
             Box::new(IntersectionMatcher::new(narrow_matcher, sparse_matcher))
         }
         (true, false) => narrow_matcher,
         (false, true) => sparse_matcher,
         (false, false) => Box::new(AlwaysMatcher),
     };
     let matcher = match args.get_many::<std::ffi::OsString>("file") {
         None => matcher,
         Some(files) => {
             let patterns: Vec<Vec<u8>> = files
                 .filter(|s| !s.is_empty())
                 .map(get_bytes_from_os_str)
                 .collect();
             for file in &patterns {
                 if file.starts_with(b"set:") {
                     return Err(CommandError::unsupported("fileset"));
                 }
             }
             let cwd = hg::utils::current_dir()?;
             let root = repo.working_directory_path();
             let ignore_patterns = parse_pattern_args(patterns, &cwd, root)?;
             let files_matcher =
                 hg::matchers::PatternMatcher::new(ignore_patterns)?;
             Box::new(IntersectionMatcher::new(
                 Box::new(files_matcher),
                 matcher,
             ))
         }
     };
 
     print_narrow_sparse_warnings(
         &narrow_warnings,
         &sparse_warnings,
         ui,
         repo,
     )?;
     let (fixup, mut dirstate_write_needed, filesystem_time_at_status_start) =
         dmap.with_status(
             matcher.as_ref(),
             repo.working_directory_path().to_owned(),
             ignore_files(repo, config),
             options,
             after_status,
         )?;
 
     // Development config option to test write races
     if let Err(e) =
         debug_wait_for_file(config, "status.pre-dirstate-write-file")
     {
         ui.write_stderr(e.as_bytes()).ok();
     }
 
     if (fixup.is_empty() || filesystem_time_at_status_start.is_none())
         && !dirstate_write_needed
     {
         // Nothing to update
         return Ok(());
     }
 
     // Update the dirstate on disk if we can
     let with_lock_result =
         repo.try_with_wlock_no_wait(|| -> Result<(), CommandError> {
             if let Some(mtime_boundary) = filesystem_time_at_status_start {
                 for hg_path in fixup {
                     use std::os::unix::fs::MetadataExt;
                     let fs_path = hg_path_to_path_buf(&hg_path)
                         .expect("HgPath conversion");
                     // Specifically do not reuse `fs_metadata` from
                     // `unsure_is_clean` which was needed before reading
                     // contents. Here we access metadata again after reading
                     // content, in case it changed in the meantime.
                     let metadata_res = repo
                         .working_directory_vfs()
                         .symlink_metadata(&fs_path);
                     let fs_metadata = match metadata_res {
                         Ok(meta) => meta,
                         Err(err) => match err {
                             HgError::IoError { .. } => {
                                 // The file has probably been deleted. In any
                                 // case, it was in the dirstate before, so
                                 // let's ignore the error.
                                 continue;
                             }
                             _ => return Err(err.into()),
                         },
                     };
                     if let Some(mtime) =
                         TruncatedTimestamp::for_reliable_mtime_of(
                             &fs_metadata,
                             &mtime_boundary,
                         )
                         .when_reading_file(&fs_path)?
                     {
                         let mode = fs_metadata.mode();
                         let size = fs_metadata.len();
                         dmap.set_clean(&hg_path, mode, size as u32, mtime)?;
                         dirstate_write_needed = true
                     }
                 }
             }
             drop(dmap); // Avoid "already mutably borrowed" RefCell panics
             if dirstate_write_needed {
                 repo.write_dirstate()?
             }
             Ok(())
         });
     match with_lock_result {
         Ok(closure_result) => closure_result?,
         Err(LockError::AlreadyHeld) => {
             // Not updating the dirstate is not ideal but not critical:
             // don’t keep our caller waiting until some other Mercurial
             // process releases the lock.
             log::info!("not writing dirstate from `status`: lock is held")
         }
         Err(LockError::Other(HgError::IoError { error, .. }))
             if error.kind() == io::ErrorKind::PermissionDenied =>
         {
             // `hg status` on a read-only repository is fine
         }
         Err(LockError::Other(error)) => {
             // Report other I/O errors
             Err(error)?
         }
     }
     Ok(())
 }
 
 fn ignore_files(repo: &Repo, config: &Config) -> Vec<PathBuf> {
     let mut ignore_files = Vec::new();
     let repo_ignore = repo.working_directory_vfs().join(".hgignore");
     if repo_ignore.exists() {
         ignore_files.push(repo_ignore)
     }
     for (key, value) in config.iter_section(b"ui") {
         if key == b"ignore" || key.starts_with(b"ignore.") {
             let path = get_path_from_bytes(value);
             // TODO: expand "~/" and environment variable here, like Python
             // does with `os.path.expanduser` and `os.path.expandvars`
 
             let joined = repo.working_directory_path().join(path);
             ignore_files.push(joined);
         }
     }
     ignore_files
 }
 
 struct DisplayStatusPaths<'a> {
     ui: &'a Ui,
     no_status: bool,
     relativize: Option<RelativizePaths>,
     print0: bool,
 }
 
 impl DisplayStatusPaths<'_> {
     // Probably more elegant to use a Deref or Borrow trait rather than
     // harcode HgPathBuf, but probably not really useful at this point
     fn display(
         &self,
         status_prefix: &[u8],
         label: &'static str,
         mut paths: Vec<StatusPath<'_>>,
     ) -> Result<(), CommandError> {
         paths.sort_unstable();
         // TODO: get the stdout lock once for the whole loop
         // instead of in each write
         for StatusPath { path, copy_source } in paths {
             let relative_path;
             let relative_source;
             let (path, copy_source) = if let Some(relativize) =
                 &self.relativize
             {
                 relative_path = relativize.relativize(&path);
                 relative_source =
                     copy_source.as_ref().map(|s| relativize.relativize(s));
                 (&*relative_path, relative_source.as_deref())
             } else {
                 (path.as_bytes(), copy_source.as_ref().map(|s| s.as_bytes()))
             };
             // TODO: Add a way to use `write_bytes!` instead of `format_bytes!`
             // in order to stream to stdout instead of allocating an
             // itermediate `Vec<u8>`.
             if !self.no_status {
                 self.ui.write_stdout_labelled(status_prefix, label)?
             }
             let linebreak = if self.print0 { b"\x00" } else { b"\n" };
             self.ui.write_stdout_labelled(
                 &format_bytes!(b"{}{}", path, linebreak),
                 label,
             )?;
             if let Some(source) = copy_source.filter(|_| !self.no_status) {
                 let label = "status.copied";
                 self.ui.write_stdout_labelled(
                     &format_bytes!(b"  {}{}", source, linebreak),
                     label,
                 )?
             }
         }
         Ok(())
     }
 
     fn output(
         &mut self,
         display_states: DisplayStates,
         ds_status: DirstateStatus,
     ) -> Result<(), CommandError> {
         if display_states.modified {
             self.display(b"M ", "status.modified", ds_status.modified)?;
         }
         if display_states.added {
             self.display(b"A ", "status.added", ds_status.added)?;
         }
         if display_states.removed {
             self.display(b"R ", "status.removed", ds_status.removed)?;
         }
         if display_states.deleted {
             self.display(b"! ", "status.deleted", ds_status.deleted)?;
         }
         if display_states.unknown {
             self.display(b"? ", "status.unknown", ds_status.unknown)?;
         }
         if display_states.ignored {
             self.display(b"I ", "status.ignored", ds_status.ignored)?;
         }
         if display_states.clean {
             self.display(b"C ", "status.clean", ds_status.clean)?;
         }
         Ok(())
     }
 }
 
 /// Outcome of the additional check for an ambiguous tracked file
 enum UnsureOutcome {
     /// The file is actually clean
     Clean,
     /// The file has been modified
     Modified,
     /// The file was deleted on disk (or became another type of fs entry)
     Deleted,
 }
 
 /// Check if a file is modified by comparing actual repo store and file system.
 ///
 /// This meant to be used for those that the dirstate cannot resolve, due
 /// to time resolution limits.
 fn unsure_is_modified(
     working_directory_vfs: hg::vfs::Vfs,
     store_vfs: hg::vfs::Vfs,
     check_exec: bool,
     manifest: &Manifest,
     hg_path: &HgPath,
+    revlog_open_options: RevlogOpenOptions,
 ) -> Result<UnsureOutcome, HgError> {
     let vfs = working_directory_vfs;
     let fs_path = hg_path_to_path_buf(hg_path).expect("HgPath conversion");
     let fs_metadata = vfs.symlink_metadata(&fs_path)?;
     let is_symlink = fs_metadata.file_type().is_symlink();
 
     let entry = manifest
         .find_by_path(hg_path)?
         .expect("ambgious file not in p1");
 
     // TODO: Also account for `FALLBACK_SYMLINK` and `FALLBACK_EXEC` from the
     // dirstate
     let fs_flags = if is_symlink {
         Some(b'l')
     } else if check_exec && has_exec_bit(&fs_metadata) {
         Some(b'x')
     } else {
         None
     };
 
     let entry_flags = if check_exec {
         entry.flags
     } else if entry.flags == Some(b'x') {
         None
     } else {
         entry.flags
     };
 
     if entry_flags != fs_flags {
         return Ok(UnsureOutcome::Modified);
     }
-    let filelog = hg::filelog::Filelog::open_vfs(&store_vfs, hg_path)?;
+    let filelog = hg::filelog::Filelog::open_vfs(
+        &store_vfs,
+        hg_path,
+        revlog_open_options,
+    )?;
     let fs_len = fs_metadata.len();
     let file_node = entry.node_id()?;
     let filelog_entry = filelog.entry_for_node(file_node).map_err(|_| {
         HgError::corrupted(format!(
             "filelog {:?} missing node {:?} from manifest",
             hg_path, file_node
         ))
     })?;
     if filelog_entry.file_data_len_not_equal_to(fs_len) {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(UnsureOutcome::Modified);
     }
 
     let p1_filelog_data = filelog_entry.data()?;
     let p1_contents = p1_filelog_data.file_data()?;
     if p1_contents.len() as u64 != fs_len {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(UnsureOutcome::Modified);
     }
 
     let fs_contents = if is_symlink {
         get_bytes_from_os_string(vfs.read_link(fs_path)?.into_os_string())
     } else {
         vfs.read(fs_path)?
     };
 
     Ok(if p1_contents != &*fs_contents {
         UnsureOutcome::Modified
     } else {
         UnsureOutcome::Clean
     })
 }

tests/test-rust-revlog.py

@@ -1,60 +1,63 b''
+import struct
 import unittest
 
 try:
     from mercurial import rustext
 
     rustext.__name__  # trigger immediate actual import
 except ImportError:
     rustext = None
 else:
     from mercurial.rustext import revlog
 
     # this would fail already without appropriate ancestor.__package__
     from mercurial.rustext.ancestor import LazyAncestors
 
 from mercurial.testing import revlog as revlogtesting
 
+header = struct.unpack(">I", revlogtesting.data_non_inlined[:4])[0]
+
 
 @unittest.skipIf(
     rustext is None,
     "rustext module revlog relies on is not available",
 )
 class RustRevlogIndexTest(revlogtesting.RevlogBasedTestBase):
     def test_heads(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined, header)
         self.assertEqual(rustidx.headrevs(), idx.headrevs())
 
     def test_get_cindex(self):
         # drop me once we no longer need the method for shortest node
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined, header)
         cidx = rustidx.get_cindex()
         self.assertTrue(idx is cidx)
 
     def test_len(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined, header)
         self.assertEqual(len(rustidx), len(idx))
 
     def test_ancestors(self):
         idx = self.parseindex()
-        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined)
+        rustidx = revlog.MixedIndex(idx, revlogtesting.data_non_inlined, header)
         lazy = LazyAncestors(rustidx, [3], 0, True)
         # we have two more references to the index:
         # - in its inner iterator for __contains__ and __bool__
         # - in the LazyAncestors instance itself (to spawn new iterators)
         self.assertTrue(2 in lazy)
         self.assertTrue(bool(lazy))
         self.assertEqual(list(lazy), [3, 2, 1, 0])
         # a second time to validate that we spawn new iterators
         self.assertEqual(list(lazy), [3, 2, 1, 0])
 
         # let's check bool for an empty one
         self.assertFalse(LazyAncestors(idx, [0], 0, False))
 
 
 if __name__ == '__main__':
     import silenttestrunner
 
     silenttestrunner.main(__name__)