sidedata: replace sidedata upgrade mechanism with the new one

Note: this is split into a separate change (like some other patches in this
series) because it's not easy to have all patches work 100% and this seemed
easier for reviewers.

When cloning or upgrading a repo, we may need to compute (or remove) sidedata.
This is the same mechanism that is used in exchange, so we re-use the new
system to simplify the code and fix the remaining issues (correctly dropping
flags and handling partial removal, etc.).

This also highlighted an issue with `test-copies-in-changeset.t` that kept
sidedata categories that are not relevant anymore. They should probably be
dropped entirely, but that would be for another patch.

Differential Revision: https://phab.mercurial-scm.org/D10359

mercurial/metadata.py

@@ -1,967 +1,922 b''
 # coding: utf-8
 # metadata.py -- code related to various metadata computation and access.
 #
 # Copyright 2019 Google, Inc <[e-mail]>
 # Copyright 2020 Pierre-Yves David <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import, print_function
 
 import multiprocessing
 import struct
 
 from .node import nullrev
 from . import (
     error,
-    pycompat,
     requirements as requirementsmod,
     util,
 )
 
 from .revlogutils import (
     constants as revlogconst,
     flagutil as sidedataflag,
     sidedata as sidedatamod,
 )
 
 
 class ChangingFiles(object):
     """A class recording the changes made to files by a changeset
 
     Actions performed on files are gathered into 3 sets:
 
     - added:   files actively added in the changeset.
     - merged:  files whose history got merged
     - removed: files removed in the revision
     - salvaged: files that might have been deleted by a merge but were not
     - touched: files affected by the merge
 
     and copies information is held by 2 mappings
 
     - copied_from_p1: {"<new-name>": "<source-name-in-p1>"} mapping for copies
     - copied_from_p2: {"<new-name>": "<source-name-in-p2>"} mapping for copies
 
     See their inline help for details.
     """
 
     def __init__(
         self,
         touched=None,
         added=None,
         removed=None,
         merged=None,
         salvaged=None,
         p1_copies=None,
         p2_copies=None,
     ):
         self._added = set(() if added is None else added)
         self._merged = set(() if merged is None else merged)
         self._removed = set(() if removed is None else removed)
         self._touched = set(() if touched is None else touched)
         self._salvaged = set(() if salvaged is None else salvaged)
         self._touched.update(self._added)
         self._touched.update(self._merged)
         self._touched.update(self._removed)
         self._p1_copies = dict(() if p1_copies is None else p1_copies)
         self._p2_copies = dict(() if p2_copies is None else p2_copies)
 
     def __eq__(self, other):
         return (
             self.added == other.added
             and self.merged == other.merged
             and self.removed == other.removed
             and self.salvaged == other.salvaged
             and self.touched == other.touched
             and self.copied_from_p1 == other.copied_from_p1
             and self.copied_from_p2 == other.copied_from_p2
         )
 
     @property
     def has_copies_info(self):
         return bool(
             self.removed
             or self.merged
             or self.salvaged
             or self.copied_from_p1
             or self.copied_from_p2
         )
 
     @util.propertycache
     def added(self):
         """files actively added in the changeset
 
         Any file present in that revision that was absent in all the changeset's
         parents.
 
         In case of merge, this means a file absent in one of the parents but
         existing in the other will *not* be contained in this set. (They were
         added by an ancestor)
         """
         return frozenset(self._added)
 
     def mark_added(self, filename):
         if 'added' in vars(self):
             del self.added
         self._added.add(filename)
         self.mark_touched(filename)
 
     def update_added(self, filenames):
         for f in filenames:
             self.mark_added(f)
 
     @util.propertycache
     def merged(self):
         """files actively merged during a merge
 
         Any modified files which had modification on both size that needed merging.
 
         In this case a new filenode was created and it has two parents.
         """
         return frozenset(self._merged)
 
     def mark_merged(self, filename):
         if 'merged' in vars(self):
             del self.merged
         self._merged.add(filename)
         self.mark_touched(filename)
 
     def update_merged(self, filenames):
         for f in filenames:
             self.mark_merged(f)
 
     @util.propertycache
     def removed(self):
         """files actively removed by the changeset
 
         In case of merge this will only contain the set of files removing "new"
         content. For any file absent in the current changeset:
 
         a) If the file exists in both parents, it is clearly "actively" removed
         by this changeset.
 
         b) If a file exists in only one parent and in none of the common
         ancestors, then the file was newly added in one of the merged branches
         and then got "actively" removed.
 
         c) If a file exists in only one parent and at least one of the common
         ancestors using the same filenode, then the file was unchanged on one
         side and deleted on the other side. The merge "passively" propagated
         that deletion, but didn't "actively" remove the file. In this case the
         file is *not* included in the `removed` set.
 
         d) If a file exists in only one parent and at least one of the common
         ancestors using a different filenode, then the file was changed on one
         side and removed on the other side. The merge process "actively"
         decided to drop the new change and delete the file. Unlike in the
         previous case, (c), the file included in the `removed` set.
 
         Summary table for merge:
 
         case | exists in parents | exists in gca || removed
          (a) |       both        |     *         ||   yes
          (b) |       one         |     none      ||   yes
          (c) |       one         | same filenode ||   no
          (d) |       one         |  new filenode ||   yes
         """
         return frozenset(self._removed)
 
     def mark_removed(self, filename):
         if 'removed' in vars(self):
             del self.removed
         self._removed.add(filename)
         self.mark_touched(filename)
 
     def update_removed(self, filenames):
         for f in filenames:
             self.mark_removed(f)
 
     @util.propertycache
     def salvaged(self):
         """files that might have been deleted by a merge, but still exists.
 
         During a merge, the manifest merging might select some files for
         removal, or for a removed/changed conflict. If at commit time the file
         still exists, its removal was "reverted" and the file is "salvaged"
         """
         return frozenset(self._salvaged)
 
     def mark_salvaged(self, filename):
         if "salvaged" in vars(self):
             del self.salvaged
         self._salvaged.add(filename)
         self.mark_touched(filename)
 
     def update_salvaged(self, filenames):
         for f in filenames:
             self.mark_salvaged(f)
 
     @util.propertycache
     def touched(self):
         """files either actively modified, added or removed"""
         return frozenset(self._touched)
 
     def mark_touched(self, filename):
         if 'touched' in vars(self):
             del self.touched
         self._touched.add(filename)
 
     def update_touched(self, filenames):
         for f in filenames:
             self.mark_touched(f)
 
     @util.propertycache
     def copied_from_p1(self):
         return self._p1_copies.copy()
 
     def mark_copied_from_p1(self, source, dest):
         if 'copied_from_p1' in vars(self):
             del self.copied_from_p1
         self._p1_copies[dest] = source
 
     def update_copies_from_p1(self, copies):
         for dest, source in copies.items():
             self.mark_copied_from_p1(source, dest)
 
     @util.propertycache
     def copied_from_p2(self):
         return self._p2_copies.copy()
 
     def mark_copied_from_p2(self, source, dest):
         if 'copied_from_p2' in vars(self):
             del self.copied_from_p2
         self._p2_copies[dest] = source
 
     def update_copies_from_p2(self, copies):
         for dest, source in copies.items():
             self.mark_copied_from_p2(source, dest)
 
 
 def compute_all_files_changes(ctx):
     """compute the files changed by a revision"""
     p1 = ctx.p1()
     p2 = ctx.p2()
     if p1.rev() == nullrev and p2.rev() == nullrev:
         return _process_root(ctx)
     elif p1.rev() != nullrev and p2.rev() == nullrev:
         return _process_linear(p1, ctx)
     elif p1.rev() == nullrev and p2.rev() != nullrev:
         # In the wild, one can encounter changeset where p1 is null but p2 is not
         return _process_linear(p1, ctx, parent=2)
     elif p1.rev() == p2.rev():
         # In the wild, one can encounter such "non-merge"
         return _process_linear(p1, ctx)
     else:
         return _process_merge(p1, p2, ctx)
 
 
 def _process_root(ctx):
     """compute the appropriate changed files for a changeset with no parents"""
     # Simple, there was nothing before it, so everything is added.
     md = ChangingFiles()
     manifest = ctx.manifest()
     for filename in manifest:
         md.mark_added(filename)
     return md
 
 
 def _process_linear(parent_ctx, children_ctx, parent=1):
     """compute the appropriate changed files for a changeset with a single parent"""
     md = ChangingFiles()
     parent_manifest = parent_ctx.manifest()
     children_manifest = children_ctx.manifest()
 
     copies_candidate = []
 
     for filename, d in parent_manifest.diff(children_manifest).items():
         if d[1][0] is None:
             # no filenode for the "new" value, file is absent
             md.mark_removed(filename)
         else:
             copies_candidate.append(filename)
             if d[0][0] is None:
                 # not filenode for the "old" value file was absent
                 md.mark_added(filename)
             else:
                 # filenode for both "old" and "new"
                 md.mark_touched(filename)
 
     if parent == 1:
         copied = md.mark_copied_from_p1
     elif parent == 2:
         copied = md.mark_copied_from_p2
     else:
         assert False, "bad parent value %d" % parent
 
     for filename in copies_candidate:
         copy_info = children_ctx[filename].renamed()
         if copy_info:
             source, srcnode = copy_info
             copied(source, filename)
 
     return md
 
 
 def _process_merge(p1_ctx, p2_ctx, ctx):
     """compute the appropriate changed files for a changeset with two parents
 
     This is a more advance case. The information we need to record is summarise
     in the following table:
 
     ┌──────────────┬──────────────┬──────────────┬──────────────┬──────────────┐
     │ diff ╲  diff │       ø      │ (Some, None) │ (None, Some) │ (Some, Some) │
     │  p2   ╲  p1  │              │              │              │              │
     ├──────────────┼──────────────┼──────────────┼──────────────┼──────────────┤
     │              │              │🄱  No Changes │🄳  No Changes │              │
     │  ø           │🄰  No Changes │      OR      │     OR       │🄵  No Changes │
     │              │              │🄲  Deleted[1] │🄴  Salvaged[2]│     [3]      │
     ├──────────────┼──────────────┼──────────────┼──────────────┼──────────────┤
     │              │🄶  No Changes │              │              │              │
     │ (Some, None) │      OR      │🄻  Deleted    │       ø      │      ø       │
     │              │🄷  Deleted[1] │              │              │              │
     ├──────────────┼──────────────┼──────────────┼──────────────┼──────────────┤
     │              │🄸  No Changes │              │              │   🄽 Touched  │
     │ (None, Some) │     OR       │      ø       │🄼   Added     │OR 🅀 Salvaged │
     │              │🄹  Salvaged[2]│              │   (copied?)  │   (copied?)  │
     ├──────────────┼──────────────┼──────────────┼──────────────┼──────────────┤
     │              │              │              │   🄾 Touched  │   🄿 Merged   │
     │ (Some, Some) │🄺  No Changes │      ø       │OR 🅁 Salvaged │OR 🅂 Touched  │
     │              │     [3]      │              │   (copied?)  │   (copied?)  │
     └──────────────┴──────────────┴──────────────┴──────────────┴──────────────┘
 
     Special case [1]:
 
       The situation is:
         - parent-A:     file exists,
         - parent-B:     no file,
         - working-copy: no file.
 
       Detecting a "deletion" will depend on the presence of actual change on
       the "parent-A" branch:
 
       Subcase 🄱 or 🄶 : if the state of the file in "parent-A" is unchanged
       compared to the merge ancestors, then parent-A branch left the file
       untouched while parent-B deleted it. We simply apply the change from
       "parent-B" branch the file was automatically dropped.
       The result is:
           - file is not recorded as touched by the merge.
 
       Subcase 🄲 or 🄷 : otherwise, the change from parent-A branch were explicitly dropped and
       the file was "deleted again". From a user perspective, the message
       about "locally changed" while "remotely deleted" (or the other way
       around) was issued and the user chose to deleted the file.
       The result:
           - file is recorded as touched by the merge.
 
 
     Special case [2]:
 
       The situation is:
         - parent-A:     no file,
         - parent-B:     file,
         - working-copy: file (same content as parent-B).
 
       There are three subcases depending on the ancestors contents:
 
       - A) the file is missing in all ancestors,
       - B) at least one ancestor has the file with filenode ≠ from parent-B,
       - C) all ancestors use the same filenode as parent-B,
 
       Subcase (A) is the simpler, nothing happend on parent-A side while
       parent-B added it.
 
         The result:
             - the file is not marked as touched by the merge.
 
       Subcase (B) is the counter part of "Special case [1]", the file was
         modified on parent-B side, while parent-A side deleted it. However this
         time, the conflict was solved by keeping the file (and its
         modification). We consider the file as "salvaged".
 
         The result:
             - the file is marked as "salvaged" by the merge.
 
       Subcase (C) is subtle variation of the case above. In this case, the
         file in unchanged on the parent-B side and actively removed on the
         parent-A side. So the merge machinery correctly decide it should be
         removed. However, the file was explicitly restored to its parent-B
         content before the merge was commited. The file is be marked
         as salvaged too. From the merge result perspective, this is similar to
         Subcase (B), however from the merge resolution perspective they differ
         since in (C), there was some conflict not obvious solution to the
         merge (That got reversed)
 
     Special case [3]:
 
       The situation is:
         - parent-A:     file,
         - parent-B:     file (different filenode as parent-A),
         - working-copy: file (same filenode as parent-B).
 
       This case is in theory much simple, for this to happens, this mean the
       filenode in parent-A is purely replacing the one in parent-B (either a
       descendant, or a full new file history, see changeset). So the merge
       introduce no changes, and the file is not affected by the merge...
 
       However, in the wild it is possible to find commit with the above is not
       True. For example repository have some commit where the *new* node is an
       ancestor of the node in parent-A, or where parent-A and parent-B are two
       branches of the same file history, yet not merge-filenode were created
       (while the "merge" should have led to a "modification").
 
       Detecting such cases (and not recording the file as modified) would be a
       nice bonus. However do not any of this yet.
     """
 
     repo = ctx.repo()
     md = ChangingFiles()
 
     m = ctx.manifest()
     p1m = p1_ctx.manifest()
     p2m = p2_ctx.manifest()
     diff_p1 = p1m.diff(m)
     diff_p2 = p2m.diff(m)
 
     cahs = ctx.repo().changelog.commonancestorsheads(
         p1_ctx.node(), p2_ctx.node()
     )
     if not cahs:
         cahs = [nullrev]
     mas = [ctx.repo()[r].manifest() for r in cahs]
 
     copy_candidates = []
 
     # Dealing with case 🄰 happens automatically.  Since there are no entry in
     # d1 nor d2, we won't iterate on it ever.
 
     # Iteration over d1 content will deal with all cases, but the one in the
     # first column of the table.
     for filename, d1 in diff_p1.items():
 
         d2 = diff_p2.pop(filename, None)
 
         if d2 is None:
             # this deal with the first line of the table.
             _process_other_unchanged(md, mas, filename, d1)
         else:
 
             if d1[0][0] is None and d2[0][0] is None:
                 # case 🄼 — both deleted the file.
                 md.mark_added(filename)
                 copy_candidates.append(filename)
             elif d1[1][0] is None and d2[1][0] is None:
                 # case 🄻 — both deleted the file.
                 md.mark_removed(filename)
             elif d1[1][0] is not None and d2[1][0] is not None:
                 if d1[0][0] is None or d2[0][0] is None:
                     if any(_find(ma, filename) is not None for ma in mas):
                         # case 🅀 or 🅁
                         md.mark_salvaged(filename)
                     else:
                         # case 🄽 🄾 : touched
                         md.mark_touched(filename)
                 else:
                     fctx = repo.filectx(filename, fileid=d1[1][0])
                     if fctx.p2().rev() == nullrev:
                         # case 🅂
                         # lets assume we can trust the file history. If the
                         # filenode is not a merge, the file was not merged.
                         md.mark_touched(filename)
                     else:
                         # case 🄿
                         md.mark_merged(filename)
                 copy_candidates.append(filename)
             else:
                 # Impossible case, the post-merge file status cannot be None on
                 # one side and Something on the other side.
                 assert False, "unreachable"
 
     # Iteration over remaining d2 content deal with the first column of the
     # table.
     for filename, d2 in diff_p2.items():
         _process_other_unchanged(md, mas, filename, d2)
 
     for filename in copy_candidates:
         copy_info = ctx[filename].renamed()
         if copy_info:
             source, srcnode = copy_info
             if source in p1_ctx and p1_ctx[source].filenode() == srcnode:
                 md.mark_copied_from_p1(source, filename)
             elif source in p2_ctx and p2_ctx[source].filenode() == srcnode:
                 md.mark_copied_from_p2(source, filename)
     return md
 
 
 def _find(manifest, filename):
     """return the associate filenode or None"""
     if filename not in manifest:
         return None
     return manifest.find(filename)[0]
 
 
 def _process_other_unchanged(md, mas, filename, diff):
     source_node = diff[0][0]
     target_node = diff[1][0]
 
     if source_node is not None and target_node is None:
         if any(not _find(ma, filename) == source_node for ma in mas):
             # case 🄲 of 🄷
             md.mark_removed(filename)
         # else, we have case 🄱 or 🄶 : no change need to be recorded
     elif source_node is None and target_node is not None:
         if any(_find(ma, filename) is not None for ma in mas):
             # case 🄴 or 🄹
             md.mark_salvaged(filename)
         # else, we have case 🄳 or 🄸 : simple merge without intervention
     elif source_node is not None and target_node is not None:
         # case 🄵  or 🄺 : simple merge without intervention
         #
         # In buggy case where source_node is not an ancestors of target_node.
         # There should have a been a new filenode created, recording this as
         # "modified". We do not deal with them yet.
         pass
     else:
         # An impossible case, the diff algorithm should not return entry if the
         # file is missing on both side.
         assert False, "unreachable"
 
 
 def _missing_from_all_ancestors(mas, filename):
     return all(_find(ma, filename) is None for ma in mas)
 
 
 def computechangesetfilesadded(ctx):
     """return the list of files added in a changeset"""
     added = []
     for f in ctx.files():
         if not any(f in p for p in ctx.parents()):
             added.append(f)
     return added
 
 
 def get_removal_filter(ctx, x=None):
     """return a function to detect files "wrongly" detected as `removed`
 
     When a file is removed relative to p1 in a merge, this
     function determines whether the absence is due to a
     deletion from a parent, or whether the merge commit
     itself deletes the file. We decide this by doing a
     simplified three way merge of the manifest entry for
     the file. There are two ways we decide the merge
     itself didn't delete a file:
     - neither parent (nor the merge) contain the file
     - exactly one parent contains the file, and that
       parent has the same filelog entry as the merge
       ancestor (or all of them if there two). In other
       words, that parent left the file unchanged while the
       other one deleted it.
     One way to think about this is that deleting a file is
     similar to emptying it, so the list of changed files
     should be similar either way. The computation
     described above is not done directly in _filecommit
     when creating the list of changed files, however
     it does something very similar by comparing filelog
     nodes.
     """
 
     if x is not None:
         p1, p2, m1, m2 = x
     else:
         p1 = ctx.p1()
         p2 = ctx.p2()
         m1 = p1.manifest()
         m2 = p2.manifest()
 
     @util.cachefunc
     def mas():
         p1n = p1.node()
         p2n = p2.node()
         cahs = ctx.repo().changelog.commonancestorsheads(p1n, p2n)
         if not cahs:
             cahs = [nullrev]
         return [ctx.repo()[r].manifest() for r in cahs]
 
     def deletionfromparent(f):
         if f in m1:
             return f not in m2 and all(
                 f in ma and ma.find(f) == m1.find(f) for ma in mas()
             )
         elif f in m2:
             return all(f in ma and ma.find(f) == m2.find(f) for ma in mas())
         else:
             return True
 
     return deletionfromparent
 
 
 def computechangesetfilesremoved(ctx):
     """return the list of files removed in a changeset"""
     removed = []
     for f in ctx.files():
         if f not in ctx:
             removed.append(f)
     if removed:
         rf = get_removal_filter(ctx)
         removed = [r for r in removed if not rf(r)]
     return removed
 
 
 def computechangesetfilesmerged(ctx):
     """return the list of files merged in a changeset"""
     merged = []
     if len(ctx.parents()) < 2:
         return merged
     for f in ctx.files():
         if f in ctx:
             fctx = ctx[f]
             parents = fctx._filelog.parents(fctx._filenode)
             if parents[1] != ctx.repo().nullid:
                 merged.append(f)
     return merged
 
 
 def computechangesetcopies(ctx):
     """return the copies data for a changeset
 
     The copies data are returned as a pair of dictionnary (p1copies, p2copies).
 
     Each dictionnary are in the form: `{newname: oldname}`
     """
     p1copies = {}
     p2copies = {}
     p1 = ctx.p1()
     p2 = ctx.p2()
     narrowmatch = ctx._repo.narrowmatch()
     for dst in ctx.files():
         if not narrowmatch(dst) or dst not in ctx:
             continue
         copied = ctx[dst].renamed()
         if not copied:
             continue
         src, srcnode = copied
         if src in p1 and p1[src].filenode() == srcnode:
             p1copies[dst] = src
         elif src in p2 and p2[src].filenode() == srcnode:
             p2copies[dst] = src
     return p1copies, p2copies
 
 
 def encodecopies(files, copies):
     items = []
     for i, dst in enumerate(files):
         if dst in copies:
             items.append(b'%d\0%s' % (i, copies[dst]))
     if len(items) != len(copies):
         raise error.ProgrammingError(
             b'some copy targets missing from file list'
         )
     return b"\n".join(items)
 
 
 def decodecopies(files, data):
     try:
         copies = {}
         if not data:
             return copies
         for l in data.split(b'\n'):
             strindex, src = l.split(b'\0')
             i = int(strindex)
             dst = files[i]
             copies[dst] = src
         return copies
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "p1copies") and
         # used different syntax for the value.
         return None
 
 
 def encodefileindices(files, subset):
     subset = set(subset)
     indices = []
     for i, f in enumerate(files):
         if f in subset:
             indices.append(b'%d' % i)
     return b'\n'.join(indices)
 
 
 def decodefileindices(files, data):
     try:
         subset = []
         if not data:
             return subset
         for strindex in data.split(b'\n'):
             i = int(strindex)
             if i < 0 or i >= len(files):
                 return None
             subset.append(files[i])
         return subset
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "added") and
         # used different syntax for the value.
         return None
 
 
 # see mercurial/helptext/internals/revlogs.txt for details about the format
 
 ACTION_MASK = int("111" "00", 2)
 # note: untouched file used as copy source will as `000` for this mask.
 ADDED_FLAG = int("001" "00", 2)
 MERGED_FLAG = int("010" "00", 2)
 REMOVED_FLAG = int("011" "00", 2)
 SALVAGED_FLAG = int("100" "00", 2)
 TOUCHED_FLAG = int("101" "00", 2)
 
 COPIED_MASK = int("11", 2)
 COPIED_FROM_P1_FLAG = int("10", 2)
 COPIED_FROM_P2_FLAG = int("11", 2)
 
 # structure is <flag><filename-end><copy-source>
 INDEX_HEADER = struct.Struct(">L")
 INDEX_ENTRY = struct.Struct(">bLL")
 
 
 def encode_files_sidedata(files):
     all_files = set(files.touched)
     all_files.update(files.copied_from_p1.values())
     all_files.update(files.copied_from_p2.values())
     all_files = sorted(all_files)
     file_idx = {f: i for (i, f) in enumerate(all_files)}
     file_idx[None] = 0
 
     chunks = [INDEX_HEADER.pack(len(all_files))]
 
     filename_length = 0
     for f in all_files:
         filename_size = len(f)
         filename_length += filename_size
         flag = 0
         if f in files.added:
             flag |= ADDED_FLAG
         elif f in files.merged:
             flag |= MERGED_FLAG
         elif f in files.removed:
             flag |= REMOVED_FLAG
         elif f in files.salvaged:
             flag |= SALVAGED_FLAG
         elif f in files.touched:
             flag |= TOUCHED_FLAG
 
         copy = None
         if f in files.copied_from_p1:
             flag |= COPIED_FROM_P1_FLAG
             copy = files.copied_from_p1.get(f)
         elif f in files.copied_from_p2:
             copy = files.copied_from_p2.get(f)
             flag |= COPIED_FROM_P2_FLAG
         copy_idx = file_idx[copy]
         chunks.append(INDEX_ENTRY.pack(flag, filename_length, copy_idx))
     chunks.extend(all_files)
     return {sidedatamod.SD_FILES: b''.join(chunks)}
 
 
 def decode_files_sidedata(sidedata):
     md = ChangingFiles()
     raw = sidedata.get(sidedatamod.SD_FILES)
 
     if raw is None:
         return md
 
     copies = []
     all_files = []
 
     assert len(raw) >= INDEX_HEADER.size
     total_files = INDEX_HEADER.unpack_from(raw, 0)[0]
 
     offset = INDEX_HEADER.size
     file_offset_base = offset + (INDEX_ENTRY.size * total_files)
     file_offset_last = file_offset_base
 
     assert len(raw) >= file_offset_base
 
     for idx in range(total_files):
         flag, file_end, copy_idx = INDEX_ENTRY.unpack_from(raw, offset)
         file_end += file_offset_base
         filename = raw[file_offset_last:file_end]
         filesize = file_end - file_offset_last
         assert len(filename) == filesize
         offset += INDEX_ENTRY.size
         file_offset_last = file_end
         all_files.append(filename)
         if flag & ACTION_MASK == ADDED_FLAG:
             md.mark_added(filename)
         elif flag & ACTION_MASK == MERGED_FLAG:
             md.mark_merged(filename)
         elif flag & ACTION_MASK == REMOVED_FLAG:
             md.mark_removed(filename)
         elif flag & ACTION_MASK == SALVAGED_FLAG:
             md.mark_salvaged(filename)
         elif flag & ACTION_MASK == TOUCHED_FLAG:
             md.mark_touched(filename)
 
         copied = None
         if flag & COPIED_MASK == COPIED_FROM_P1_FLAG:
             copied = md.mark_copied_from_p1
         elif flag & COPIED_MASK == COPIED_FROM_P2_FLAG:
             copied = md.mark_copied_from_p2
 
         if copied is not None:
             copies.append((copied, filename, copy_idx))
 
     for copied, filename, copy_idx in copies:
         copied(all_files[copy_idx], filename)
 
     return md
 
 
 def _getsidedata(srcrepo, rev):
     ctx = srcrepo[rev]
     files = compute_all_files_changes(ctx)
     return encode_files_sidedata(files), files.has_copies_info
 
 
 def copies_sidedata_computer(repo, revlog, rev, existing_sidedata):
     sidedata, has_copies_info = _getsidedata(repo, rev)
     flags_to_add = sidedataflag.REVIDX_HASCOPIESINFO if has_copies_info else 0
     return sidedata, (flags_to_add, 0)
 
 
 def set_sidedata_spec_for_repo(repo):
     if requirementsmod.COPIESSDC_REQUIREMENT in repo.requirements:
         repo.register_wanted_sidedata(sidedatamod.SD_FILES)
     repo.register_sidedata_computer(
         revlogconst.KIND_CHANGELOG,
         sidedatamod.SD_FILES,
         (sidedatamod.SD_FILES,),
         copies_sidedata_computer,
         sidedataflag.REVIDX_HASCOPIESINFO,
     )
 
 
-def getsidedataadder(srcrepo, destrepo):
-    use_w = srcrepo.ui.configbool(b'experimental', b'worker.repository-upgrade')
-    if pycompat.iswindows or not use_w:
-        return _get_simple_sidedata_adder(srcrepo, destrepo)
-    else:
-        return _get_worker_sidedata_adder(srcrepo, destrepo)
-
-
 def _sidedata_worker(srcrepo, revs_queue, sidedata_queue, tokens):
     """The function used by worker precomputing sidedata
 
     It read an input queue containing revision numbers
     It write in an output queue containing (rev, <sidedata-map>)
 
     The `None` input value is used as a stop signal.
 
     The `tokens` semaphore is user to avoid having too many unprocessed
     entries. The workers needs to acquire one token before fetching a task.
     They will be released by the consumer of the produced data.
     """
     tokens.acquire()
     rev = revs_queue.get()
     while rev is not None:
         data = _getsidedata(srcrepo, rev)
         sidedata_queue.put((rev, data))
         tokens.acquire()
         rev = revs_queue.get()
     # processing of `None` is completed, release the token.
     tokens.release()
 
 
 BUFF_PER_WORKER = 50
 
 
 def _get_worker_sidedata_adder(srcrepo, destrepo):
     """The parallel version of the sidedata computation
 
     This code spawn a pool of worker that precompute a buffer of sidedata
     before we actually need them"""
     # avoid circular import copies -> scmutil -> worker -> copies
     from . import worker
 
     nbworkers = worker._numworkers(srcrepo.ui)
 
     tokens = multiprocessing.BoundedSemaphore(nbworkers * BUFF_PER_WORKER)
     revsq = multiprocessing.Queue()
     sidedataq = multiprocessing.Queue()
 
     assert srcrepo.filtername is None
     # queue all tasks beforehand, revision numbers are small and it make
     # synchronisation simpler
     #
     # Since the computation for each node can be quite expensive, the overhead
     # of using a single queue is not revelant. In practice, most computation
     # are fast but some are very expensive and dominate all the other smaller
     # cost.
     for r in srcrepo.changelog.revs():
         revsq.put(r)
     # queue the "no more tasks" markers
     for i in range(nbworkers):
         revsq.put(None)
 
     allworkers = []
     for i in range(nbworkers):
         args = (srcrepo, revsq, sidedataq, tokens)
         w = multiprocessing.Process(target=_sidedata_worker, args=args)
         allworkers.append(w)
         w.start()
 
     # dictionnary to store results for revision higher than we one we are
     # looking for. For example, if we need the sidedatamap for 42, and 43 is
     # received, when shelve 43 for later use.
     staging = {}
 
-    def sidedata_companion(revlog, rev):
-        data = {}, False
-        if util.safehasattr(revlog, b'filteredrevs'):  # this is a changelog
-            # Is the data previously shelved ?
-            data = staging.pop(rev, None)
-            if data is None:
-                # look at the queued result until we find the one we are lookig
-                # for (shelve the other ones)
+    def sidedata_companion(repo, revlog, rev, old_sidedata):
+        # Is the data previously shelved ?
+        data = staging.pop(rev, None)
+        if data is None:
+            # look at the queued result until we find the one we are lookig
+            # for (shelve the other ones)
+            r, data = sidedataq.get()
+            while r != rev:
+                staging[r] = data
                 r, data = sidedataq.get()
-                while r != rev:
-                    staging[r] = data
-                    r, data = sidedataq.get()
-            tokens.release()
+        tokens.release()
         sidedata, has_copies_info = data
         new_flag = 0
         if has_copies_info:
             new_flag = sidedataflag.REVIDX_HASCOPIESINFO
-        return False, (), sidedata, new_flag, 0
+        return sidedata, (new_flag, 0)
 
     return sidedata_companion
-
-
-def _get_simple_sidedata_adder(srcrepo, destrepo):
-    """The simple version of the sidedata computation
-
-    It just compute it in the same thread on request"""
-
-    def sidedatacompanion(revlog, rev):
-        sidedata, has_copies_info = {}, False
-        if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
-            sidedata, has_copies_info = _getsidedata(srcrepo, rev)
-        new_flag = 0
-        if has_copies_info:
-            new_flag = sidedataflag.REVIDX_HASCOPIESINFO
-
-        return False, (), sidedata, new_flag, 0
-
-    return sidedatacompanion
-
-
-def getsidedataremover(srcrepo, destrepo):
-    def sidedatacompanion(revlog, rev):
-        f = ()
-        if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
-            if revlog.flags(rev) & sidedataflag.REVIDX_SIDEDATA:
-                f = (
-                    sidedatamod.SD_P1COPIES,
-                    sidedatamod.SD_P2COPIES,
-                    sidedatamod.SD_FILESADDED,
-                    sidedatamod.SD_FILESREMOVED,
-                )
-        return False, f, {}, 0, sidedataflag.REVIDX_HASCOPIESINFO
-
-    return sidedatacompanion

mercurial/revlog.py

@@ -1,3145 +1,3129 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import binascii
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
     wdirrev,
 )
 from .i18n import _
 from .pycompat import getattr
 from .revlogutils.constants import (
     ALL_KINDS,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_HASCOPIESINFO,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
 )
 from .thirdparty import attr
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     templatefilters,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     flagutil,
     nodemap as nodemaputil,
     revlogv0,
     sidedata as sidedatautil,
 )
 from .utils import (
     storageutil,
     stringutil,
 )
 
 # blanked usage of all the name to prevent pyflakes constraints
 # We need these name available in the module for extensions.
+
 REVLOGV0
 REVLOGV1
 REVLOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_HASCOPIESINFO
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod('parsers')
 rustancestor = policy.importrust('ancestor')
 rustdagop = policy.importrust('dagop')
 rustrevlog = policy.importrust('revlog')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 
 def offset_type(offset, type):
     if (type & ~flagutil.REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError(b'unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 
 def _verify_revision(rl, skipflags, state, node):
     """Verify the integrity of the given revlog ``node`` while providing a hook
     point for extensions to influence the operation."""
     if skipflags:
         state[b'skipread'].add(node)
     else:
         # Side-effect: read content and verify hash.
         rl.revision(node)
 
 
 # True if a fast implementation for persistent-nodemap is available
 #
 # We also consider we have a "fast" implementation in "pure" python because
 # people using pure don't really have performance consideration (and a
 # wheelbarrow of other slowness source)
 HAS_FAST_PERSISTENT_NODEMAP = rustrevlog is not None or util.safehasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
     node:       expected hash of the revision
     p1, p2:     parent revs of the revision
     btext:      built text cache consisting of a one-element list
     cachedelta: (baserev, uncompressed_delta) or None
     flags:      flags associated to the revision storage
 
     One of btext[0] or cachedelta must be set.
     """
 
     node = attr.ib()
     p1 = attr.ib()
     p2 = attr.ib()
     btext = attr.ib()
     textlen = attr.ib()
     cachedelta = attr.ib()
     flags = attr.ib()
 
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     sidedata = attr.ib()
     protocol_flags = attr.ib()
     linknode = attr.ib(default=None)
 
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class revlogproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 
 def parse_index_v1(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline)
     return index, cache
 
 
 def parse_index_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, revlogv2=True)
     return index, cache
 
 
 if util.safehasattr(parsers, 'parse_index_devel_nodemap'):
 
     def parse_index_v1_nodemap(data, inline):
         index, cache = parsers.parse_index_devel_nodemap(data, inline)
         return index, cache
 
 
 else:
     parse_index_v1_nodemap = None
 
 
 def parse_index_v1_mixed(data, inline):
     index, cache = parse_index_v1(data, inline)
     return rustrevlog.MixedIndex(index), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
 
     `concurrencychecker` is an optional function that receives 3 arguments: a
     file handle, a filename, and an expected position. It should check whether
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
     """
 
     _flagserrorclass = error.RevlogError
 
     def __init__(
         self,
         opener,
         target,
         indexfile=None,
         datafile=None,
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
     ):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
 
         `target`: a (KIND, ID) tuple that identify the content stored in
         this revlog. It help the rest of the code to understand what the revlog
         is about without having to resort to heuristic and index filename
         analysis. Note: that this must be reliably be set by normal code, but
         that test, debug, or performance measurement code might not set this to
         accurate value.
         """
         self.upperboundcomp = upperboundcomp
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + b".d")
         self.nodemap_file = None
         if persistentnodemap:
             self.nodemap_file = nodemaputil.get_nodemap_file(
                 opener, self.indexfile
             )
 
         self.opener = opener
         assert target[0] in ALL_KINDS
         assert len(target) == 2
         self.target = target
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._mmaplargeindex = mmaplargeindex
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, b'')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._compengine = b'zlib'
         self._compengineopts = {}
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
 
         # 2-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._loadindex()
 
         self._concurrencychecker = concurrencychecker
 
     def _loadindex(self):
         mmapindexthreshold = None
         opts = self.opener.options
 
         if b'revlogv2' in opts:
             newversionflags = REVLOGV2 | FLAG_INLINE_DATA
         elif b'revlogv1' in opts:
             newversionflags = REVLOGV1 | FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 newversionflags |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             newversionflags = REVLOGV0
         else:
             newversionflags = REVLOG_DEFAULT_VERSION
 
         if b'chunkcachesize' in opts:
             self._chunkcachesize = opts[b'chunkcachesize']
         if b'maxchainlen' in opts:
             self._maxchainlen = opts[b'maxchainlen']
         if b'deltabothparents' in opts:
             self._deltabothparents = opts[b'deltabothparents']
         self._lazydelta = bool(opts.get(b'lazydelta', True))
         self._lazydeltabase = False
         if self._lazydelta:
             self._lazydeltabase = bool(opts.get(b'lazydeltabase', False))
         if b'compengine' in opts:
             self._compengine = opts[b'compengine']
         if b'zlib.level' in opts:
             self._compengineopts[b'zlib.level'] = opts[b'zlib.level']
         if b'zstd.level' in opts:
             self._compengineopts[b'zstd.level'] = opts[b'zstd.level']
         if b'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts[b'maxdeltachainspan']
         if self._mmaplargeindex and b'mmapindexthreshold' in opts:
             mmapindexthreshold = opts[b'mmapindexthreshold']
         self.hassidedata = bool(opts.get(b'side-data', False))
         self._sparserevlog = bool(opts.get(b'sparse-revlog', False))
         withsparseread = bool(opts.get(b'with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if b'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts[b'sparse-read-density-threshold']
         if b'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts[b'sparse-read-min-gap-size']
         if opts.get(b'enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in pycompat.iteritems(
             opts.get(b'flagprocessors', {})
         ):
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % self._chunkcachesize
             )
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % self._chunkcachesize
             )
 
         indexdata = b''
         self._initempty = True
         try:
             with self._indexfp() as f:
                 if (
                     mmapindexthreshold is not None
                     and self.opener.fstat(f).st_size >= mmapindexthreshold
                 ):
                     # TODO: should .close() to release resources without
                     # relying on Python GC
                     indexdata = util.buffer(util.mmapread(f))
                 else:
                     indexdata = f.read()
             if len(indexdata) > 0:
                 versionflags = INDEX_HEADER.unpack(indexdata[:4])[0]
                 self._initempty = False
             else:
                 versionflags = newversionflags
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
             versionflags = newversionflags
 
         self.version = versionflags
 
         flags = versionflags & ~0xFFFF
         fmt = versionflags & 0xFFFF
 
         if fmt == REVLOGV0:
             if flags:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             self._inline = False
             self._generaldelta = False
 
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             self._inline = versionflags & FLAG_INLINE_DATA
             self._generaldelta = versionflags & FLAG_GENERALDELTA
 
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             # There is a bug in the transaction handling when going from an
             # inline revlog to a separate index and data file. Turn it off until
             # it's fixed, since v2 revlogs sometimes get rewritten on exchange.
             # See issue6485
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(
                 _(b'unknown version (%d) in revlog %s') % (fmt, self.indexfile)
             )
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self._generaldelta:
             self._sparserevlog = False
 
         self._storedeltachains = True
 
         devel_nodemap = (
             self.nodemap_file
             and opts.get(b'devel-force-nodemap', False)
             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.version == REVLOGV0:
             self._parse_index = revlogv0.parse_index_v0
         elif fmt == REVLOGV2:
             self._parse_index = parse_index_v2
         elif devel_nodemap:
             self._parse_index = parse_index_v1_nodemap
         elif use_rust_index:
             self._parse_index = parse_index_v1_mixed
         try:
             d = self._parse_index(indexdata, self._inline)
             index, _chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self.nodemap_file is not None
                 and util.safehasattr(index, 'update_nodemap_data')
             )
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
                     docket = nodemap_data[0]
                     if (
                         len(d[0]) > docket.tip_rev
                         and d[0][docket.tip_rev][7] == docket.tip_node
                     ):
                         # no changelog tampering
                         self._nodemap_docket = docket
                         index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
                 _(b"index %s is corrupted") % self.indexfile
             )
         self.index, self._chunkcache = d
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def revlog_kind(self):
         return self.target[0]
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     def _indexfp(self, mode=b'r'):
         """file object for the revlog's index file"""
         args = {'mode': mode}
         if mode != b'r':
             args['checkambig'] = self._checkambig
         if mode == b'w':
             args['atomictemp'] = True
         return self.opener(self.indexfile, **args)
 
     def _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self.datafile, mode=mode)
 
     @contextlib.contextmanager
     def _datareadfp(self, existingfp=None):
         """file object suitable to read data"""
         # Use explicit file handle, if given.
         if existingfp is not None:
             yield existingfp
 
         # Use a file handle being actively used for writes, if available.
         # There is some danger to doing this because reads will seek the
         # file. However, _writeentry() performs a SEEK_END before all writes,
         # so we should be safe.
         elif self._writinghandles:
             if self._inline:
                 yield self._writinghandles[0]
             else:
                 yield self._writinghandles[1]
 
         # Otherwise open a new file handle.
         else:
             if self._inline:
                 func = self._indexfp
             else:
                 func = self._datafp
             with func() as fp:
                 yield fp
 
     def tiprev(self):
         return len(self.index) - 1
 
     def tip(self):
         return self.node(self.tiprev())
 
     def __contains__(self, rev):
         return 0 <= rev < len(self)
 
     def __len__(self):
         return len(self.index)
 
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
 
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         return storageutil.iterrevs(len(self), start=start, stop=stop)
 
     @property
     def nodemap(self):
         msg = (
             b"revlog.nodemap is deprecated, "
             b"use revlog.index.[has_node|rev|get_rev]"
         )
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     @property
     def _nodecache(self):
         msg = b"revlog._nodecache is deprecated, use revlog.index.nodemap"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if (self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS) or (
             self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS
         ):
             return False
         return True
 
     def update_caches(self, transaction):
         if self.nodemap_file is not None:
             if transaction is None:
                 nodemaputil.update_persistent_nodemap(self)
             else:
                 nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, b'')
         self._pcache = {}
         self._nodemap_docket = None
         self.index.clearcaches()
         # The python code is the one responsible for validating the docket, we
         # end up having to refresh it here.
         use_nodemap = (
             not self._inline
             and self.nodemap_file is not None
             and util.safehasattr(self.index, 'update_nodemap_data')
         )
         if use_nodemap:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
                 self.index.update_nodemap_data(*nodemap_data)
 
     def rev(self, node):
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if (
                 node == self.nodeconstants.wdirid
                 or node in self.nodeconstants.wdirfilenodeids
             ):
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _(b'no node'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def sidedata_length(self, rev):
         if self.version & 0xFFFF != REVLOGV2:
             return 0
         return self.index[rev][9]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.rawdata(rev)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (flagutil.REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev, raw=False))
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
         if entry[5] == nullrev:
             return entry[6], entry[5]
         else:
             return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         # inline node() to avoid function call overhead
         if d[5] == self.nullid:
             return i[d[6]][7], i[d[5]][7]
         else:
             return i[d[5]][7], i[d[6]][7]
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse revision order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         # first, make sure start revisions aren't filtered
         revs = list(revs)
         checkrev = self.node
         for r in revs:
             checkrev(r)
         # and we're sure ancestors aren't filtered as well
 
         if rustancestor is not None:
             lazyancestors = rustancestor.LazyAncestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         if rustancestor is not None:
             return rustancestor.MissingAncestors(self.index, common)
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [self.nullid]  # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return (
                 [self.node(r) for r in self],
                 [self.nullid],
                 list(self.heads()),
             )
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == self.nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n)  # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update(
                             [p for p in self.parents(n) if p != self.nullid]
                         )
                     elif n in heads:  # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [self.nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in pycompat.iteritems(heads) if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevs()
             except AttributeError:
                 return self._headrevs()
         if rustdagop is not None:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     def computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [self.nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = {self.rev(n) for n in stop or []}
 
         revs = dagop.headrevssubset(
             self.revs, self.parentrevs, startrev=start, stoprevs=stoprevs
         )
 
         return [self.node(rev) for rev in revs]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError):  # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::(<roots> and <roots>::<heads>)))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(
                 minroot, heads, roots, includepath
             )
         except AttributeError:
             return dagop._reachablerootspure(
                 self.parentrevs, minroot, roots, heads, includepath
             )
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return self.nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == self.nodeconstants.nodelen:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node)  # quick search the index
                 return node
             except error.LookupError:
                 pass  # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if b"%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 2 * self.nodeconstants.nodelen:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = self.nodeconstants.wdirhex.startswith(id)
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     raise error.RevlogError
                 return partial
             if maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             return None
         except error.RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise error.AmbiguousPrefixLookupError(
                     id, self.indexfile, _(b'ambiguous identifier')
                 )
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[: l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [
                     n for n in nl if hex(n).startswith(id) and self.hasnode(n)
                 ]
                 if self.nodeconstants.nullhex.startswith(id):
                     nl.append(self.nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.indexfile, _(b'ambiguous identifier')
                     )
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
         - revision number or str(revision number)
         - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise error.LookupError(id, self.indexfile, _(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.indexfile, _(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.indexfile, _(b'no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == self.nodeconstants.wdirid:
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, len(hexnode) + 1):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def _cachesegment(self, offset, data):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _readsegment(self, offset, length, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
 
         Raises if the requested number of bytes could not be read.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (
             (offset + length + cachesize) & ~(cachesize - 1)
         ) - realoffset
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
 
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
             startoffset = offset - realoffset
             if len(d) - startoffset < length:
                 raise error.RevlogError(
                     _(
                         b'partial read of revlog %s; expected %d bytes from '
                         b'offset %d, got %d'
                     )
                     % (
                         self.indexfile if self._inline else self.datafile,
                         length,
                         realoffset,
                         len(d) - startoffset,
                     )
                 )
 
             return util.buffer(d, startoffset, length)
 
         if len(d) < length:
             raise error.RevlogError(
                 _(
                     b'partial read of revlog %s; expected %d bytes from offset '
                     b'%d, got %d'
                 )
                 % (
                     self.indexfile if self._inline else self.datafile,
                     length,
                     offset,
                     len(d),
                 )
             )
 
         return d
 
     def _getsegment(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d  # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._readsegment(offset, length, df=df)
 
     def _getsegmentforrevs(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self.index.entry_size
             end += (endrev + 1) * self.index.entry_size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self.index.entry_size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = deltautil.slicechunk(
                 self, revs, targetsize=targetsize
             )
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, df=df)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev, df=df) for rev in revschunk]
 
             decomp = self.decompress
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(decomp(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         self._chunkcache = (0, b'')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot"""
         if not self._sparserevlog:
             return self.deltaparent(rev) == nullrev
         elif util.safehasattr(self.index, b'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         p2 = entry[6]
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     def snapshotdepth(self, rev):
         """number of snapshot in the chain before this one"""
         if not self.issnapshot(rev):
             raise error.ProgrammingError(b'revision %d not a snapshot')
         return len(self._deltachain(rev)[0]) - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def _processflags(self, text, flags, operation, raw=False):
         """deprecated entry point to access flag processors"""
         msg = b'_processflag(...) use the specialized variant'
         util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         if raw:
             return text, flagutil.processflagsraw(self, text, flags)
         elif operation == b'read':
             return flagutil.processflagsread(self, text, flags)
         else:  # write operation
             return flagutil.processflagswrite(self, text, flags)
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         raw - an optional argument specifying if the revision data is to be
         treated as raw data when applying flag transforms. 'raw' should be set
         to True when generating changegroups or in debug commands.
         """
         if raw:
             msg = (
                 b'revlog.revision(..., raw=True) is deprecated, '
                 b'use revlog.rawdata(...)'
             )
             util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         return self._revisiondata(nodeorrev, _df, raw=raw)[0]
 
     def sidedata(self, nodeorrev, _df=None):
         """a map of extra data related to the changeset but not part of the hash
 
         This function currently return a dictionary. However, more advanced
         mapping object will likely be used in the future for a more
         efficient/lazy code.
         """
         return self._revisiondata(nodeorrev, _df)[1]
 
     def _revisiondata(self, nodeorrev, _df=None, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == self.nullid:
             return b"", {}
 
         # ``rawtext`` is the text as stored inside the revlog. Might be the
         # revision or might need to be processed to retrieve the revision.
         rev, rawtext, validated = self._rawtext(node, rev, _df=_df)
 
         if self.version & 0xFFFF == REVLOGV2:
             if rev is None:
                 rev = self.rev(node)
             sidedata = self._sidedata(rev)
         else:
             sidedata = {}
 
         if raw and validated:
             # if we don't want to process the raw text and that raw
             # text is cached, we can exit early.
             return rawtext, sidedata
         if rev is None:
             rev = self.rev(node)
         # the revlog's flag for this revision
         # (usually alter its state or content)
         flags = self.flags(rev)
 
         if validated and flags == REVIDX_DEFAULT_FLAGS:
             # no extra flags set, no flag processor runs, text = rawtext
             return rawtext, sidedata
 
         if raw:
             validatehash = flagutil.processflagsraw(self, rawtext, flags)
             text = rawtext
         else:
             r = flagutil.processflagsread(self, rawtext, flags)
             text, validatehash = r
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._revisioncache = (node, rev, rawtext)
 
         return text, sidedata
 
     def _rawtext(self, node, rev, _df=None):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
 
         # revision in the cache (could be useful to apply delta)
         cachedrev = None
         # An intermediate text to apply deltas to
         basetext = None
 
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 return (rev, self._revisioncache[2], True)
             cachedrev = self._revisioncache[1]
 
         if rev is None:
             rev = self.rev(node)
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             basetext = self._revisioncache[2]
 
         # drop cache to save memory, the caller is expected to
         # update self._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         bins = self._chunks(chain, df=_df, targetsize=targetsize)
         if basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext  # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         index_entry = self.index[rev]
         sidedata_offset = index_entry[8]
         sidedata_size = index_entry[9]
 
         if self._inline:
             sidedata_offset += self.index.entry_size * (1 + rev)
         if sidedata_size == 0:
             return {}
 
         segment = self._getsegment(sidedata_offset, sidedata_size)
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def rawdata(self, nodeorrev, _df=None):
         """return an uncompressed raw data of a given node or revision number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df, raw=True)[0]
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return storageutil.hashrevisionsha1(text, p1, p2)
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 # Clear the revision cache on hash failure. The revision cache
                 # only stores the raw revision and clearing the cache does have
                 # the side-effect that we won't have a cache hit when the raw
                 # revision data is accessed. But this case should be rare and
                 # it is extra work to teach the cache about the hash
                 # verification state.
                 if self._revisioncache and self._revisioncache[0] == node:
                     self._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(
                     _(b"integrity check failed on %s:%s")
                     % (self.indexfile, pycompat.bytestr(revornode))
                 )
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.indexfile, node, text)
             raise
 
     def _enforceinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         tiprev = len(self) - 1
         if (
             not self._inline
             or (self.start(tiprev) + self.length(tiprev)) < _maxinline
         ):
             return
 
         troffset = tr.findoffset(self.indexfile)
         if troffset is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self.indexfile
             )
         trindex = 0
         tr.add(self.datafile, 0)
 
         if fp:
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
 
         with self._indexfp(b'r') as ifh, self._datafp(b'w') as dfh:
             for r in self:
                 dfh.write(self._getsegmentforrevs(r, r, df=ifh)[1])
                 if troffset <= self.start(r):
                     trindex = r
 
         with self._indexfp(b'w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             for i in self:
                 e = self.index.entry_binary(i)
                 if i == 0:
                     header = self.index.pack_header(self.version)
                     e = header + e
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self.index.entry_size)
         nodemaputil.setup_persistent_nodemap(tr, self)
         self._chunkclear()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     def addrevision(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=None,
         node=None,
         flags=REVIDX_DEFAULT_FLAGS,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         node - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         flags - the known flags to set on the revision
         deltacomputer - an optional deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise error.RevlogError(
                 _(b"attempted to add linkrev -1 to %s") % self.indexfile
             )
 
         if sidedata is None:
             sidedata = {}
-        elif not self.hassidedata:
+        elif sidedata and not self.hassidedata:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _(
                     b"%s: size of %d bytes exceeds maximum revlog storage of 2GiB"
                 )
                 % (self.indexfile, len(rawtext))
             )
 
         node = node or self.hash(rawtext, p1, p2)
         rev = self.index.get_rev(node)
         if rev is not None:
             return rev
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
             sidedata=sidedata,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp(b"a+")
         ifh = self._indexfp(b"a+")
         try:
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 ifh,
                 dfh,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return b'', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return b'', compressed
 
         if data[0:1] == b'\0':
             return b'', data
         return b'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == b'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(
                     _(b'revlog decompress error: %s')
                     % stringutil.forcebytestr(e)
                 )
         # '\0' is more common than 'u' so it goes first.
         elif t == b'\0':
             return data
         elif t == b'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(self._compengineopts)
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         ifh,
         dfh,
         alwayscache=False,
         deltacomputer=None,
         sidedata=None,
     ):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == self.nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self.indexfile
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%s: attempt to add wdir revision") % self.indexfile
             )
 
         if self._inline:
             fh = ifh
         else:
             fh = dfh
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
 
         offset = self._get_data_offset(prev)
 
         if self._concurrencychecker:
             if self._inline:
                 # offset is "as if" it were in the .d file, so we need to add on
                 # the size of the entry metadata.
                 self._concurrencychecker(
                     ifh, self.indexfile, offset + curr * self.index.entry_size
                 )
             else:
                 # Entries in the .i are a consistent size.
                 self._concurrencychecker(
                     ifh, self.indexfile, curr * self.index.entry_size
                 )
                 self._concurrencychecker(dfh, self.datafile, offset)
 
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(
                 revlog.size(self, cachedelta[0]), cachedelta[1]
             )
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         if sidedata and self.version & 0xFFFF == REVLOGV2:
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = offset + deltainfo.deltalen
         else:
             serialized_sidedata = b""
             # Don't store the offset if the sidedata is empty, that way
             # we can easily detect empty sidedata and they will be no different
             # than ones we manually add.
             sidedata_offset = 0
 
         e = (
             offset_type(offset, flags),
             deltainfo.deltalen,
             textlen,
             deltainfo.base,
             link,
             p1r,
             p2r,
             node,
             sidedata_offset,
             len(serialized_sidedata),
         )
 
         if self.version & 0xFFFF != REVLOGV2:
             e = e[:8]
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0:
             header = self.index.pack_header(self.version)
             entry = header + entry
         self._writeentry(
             transaction,
             ifh,
             dfh,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
         )
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo, fh)
 
         if type(rawtext) == bytes:  # only accept immutable objects
             self._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return curr
 
     def _get_data_offset(self, prev):
         """Returns the current offset in the (in-transaction) data file.
         Versions < 2 of the revlog can get this 0(1), revlog v2 needs a docket
         file to store that information: since sidedata can be rewritten to the
         end of the data file within a transaction, you can have cases where, for
         example, rev `n` does not have sidedata while rev `n - 1` does, leading
         to `n - 1`'s sidedata being written after `n`'s data.
 
         TODO cache this in a docket file before getting out of experimental."""
         if self.version & 0xFFFF != REVLOGV2:
             return self.end(prev)
 
         offset = 0
         for rev, entry in enumerate(self.index):
             sidedata_end = entry[8] + entry[9]
             # Sidedata for a previous rev has potentially been written after
             # this rev's end, so take the max.
             offset = max(self.end(rev), offset, sidedata_end)
         return offset
 
     def _writeentry(
         self, transaction, ifh, dfh, entry, data, link, offset, sidedata
     ):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 dfh.write(sidedata)
             ifh.write(entry)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self.indexfile, offset)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             if sidedata:
                 ifh.write(sidedata)
             self._enforceinlinesize(transaction, ifh)
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
     ):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         if self._writinghandles:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp(b"a+")
         isize = r * self.index.entry_size
         if self._inline:
             transaction.add(self.indexfile, end + isize)
             dfh = None
         else:
             transaction.add(self.indexfile, isize)
             transaction.add(self.datafile, end)
             dfh = self._datafp(b"a+")
 
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
         empty = True
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags, sidedata = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 rev = self.index.get_rev(node)
                 if rev is not None:
                     # this can happen if two branches make the same change
                     self._nodeduplicatecallback(transaction, rev)
                     if duplicaterevisioncb:
                         duplicaterevisioncb(self, rev)
                     empty = False
                     continue
 
                 for p in (p1, p2):
                     if not self.index.has_node(p):
                         raise error.LookupError(
                             p, self.indexfile, _(b'unknown parent')
                         )
 
                 if not self.index.has_node(deltabase):
                     raise error.LookupError(
                         deltabase, self.indexfile, _(b'unknown delta base')
                     )
 
                 baserev = self.rev(deltabase)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(b">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(
                             self.indexfile, self.node(baserev)
                         )
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
                 # We're only using addgroup() in the context of changegroup
                 # generation so the revision data can always be handled as raw
                 # by the flagprocessor.
                 rev = self._addrevision(
                     node,
                     None,
                     transaction,
                     link,
                     p1,
                     p2,
                     flags,
                     (baserev, delta),
                     ifh,
                     dfh,
                     alwayscache=alwayscache,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
 
                 if addrevisioncb:
                     addrevisioncb(self, rev)
                 empty = False
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp(b"a+")
                     ifh = self._indexfp(b"a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
         return not empty
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         return storageutil.deltaiscensored(delta, baserev, self.rawsize)
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         return storageutil.resolvestripinfo(
             minlink,
             len(self) - 1,
             self.headrevs(),
             self.linkrev,
             self.parentrevs,
         )
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self.index.entry_size
         else:
             end += rev * self.index.entry_size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = util.lrucachedict(500)
         self._chunkclear()
 
         del self.index[rev:-1]
 
     def checksize(self):
         """Check size of index and data files
 
         return a (dd, di) tuple.
         - dd: extra bytes for the "data" file
         - di: extra bytes for the "index" file
 
         A healthy revlog will return (0, 0).
         """
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, io.SEEK_END)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self.index.entry_size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         if nodesorder not in (b'nodes', b'storage', b'linear', None):
             raise error.ProgrammingError(
                 b'unhandled value for nodesorder: %s' % nodesorder
             )
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = b'storage'
 
         if (
             not self._storedeltachains
             and deltamode != repository.CG_DELTAMODE_PREV
         ):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self,
             nodes,
             nodesorder,
             revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self.candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             sidedata_helpers=sidedata_helpers,
         )
 
     DELTAREUSEALWAYS = b'always'
     DELTAREUSESAMEREVS = b'samerevs'
     DELTAREUSENEVER = b'never'
 
     DELTAREUSEFULLADD = b'fulladd'
 
     DELTAREUSEALL = {b'always', b'samerevs', b'never', b'fulladd'}
 
     def clone(
         self,
         tr,
         destrevlog,
         addrevisioncb=None,
         deltareuse=DELTAREUSESAMEREVS,
         forcedeltabothparents=None,
-        sidedatacompanion=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.
 
-        If not None, the `sidedatacompanion` is callable that accept two
-        arguments:
-
-            (srcrevlog, rev)
-
-        and return a quintet that control changes to sidedata content from the
-        old revision to the new clone result:
-
-            (dropall, filterout, update, new_flags, dropped_flags)
-
-        * if `dropall` is True, all sidedata should be dropped
-        * `filterout` is a set of sidedata keys that should be dropped
-        * `update` is a mapping of additionnal/new key -> value
-        * new_flags is a bitfields of new flags that the revision should get
-        * dropped_flags is a bitfields of new flags that the revision shoudl not longer have
+        See `storageutil.emitrevisions` for the doc on `sidedata_helpers`.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(
                 _(b'value for deltareuse invalid: %s') % deltareuse
             )
 
         if len(destrevlog):
             raise ValueError(_(b'destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_(b'source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_(b'destination revlog has filtered revisions'))
 
         # lazydelta and lazydeltabase controls whether to reuse a cached delta,
         # if possible.
         oldlazydelta = destrevlog._lazydelta
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             self._clone(
                 tr,
                 destrevlog,
                 addrevisioncb,
                 deltareuse,
                 forcedeltabothparents,
-                sidedatacompanion,
+                sidedata_helpers,
             )
 
         finally:
             destrevlog._lazydelta = oldlazydelta
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
-        sidedatacompanion,
+        sidedata_helpers,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         deltacomputer = deltautil.deltacomputer(destrevlog)
         index = self.index
         for rev in self:
             entry = index[rev]
 
             # Some classes override linkrev to take filtered revs into
             # account. Use raw entry from index.
             flags = entry[0] & 0xFFFF
             linkrev = entry[4]
             p1 = index[entry[5]][7]
             p2 = index[entry[6]][7]
             node = entry[7]
 
-            sidedataactions = (False, [], {}, 0, 0)
-            if sidedatacompanion is not None:
-                sidedataactions = sidedatacompanion(self, rev)
-
             # (Possibly) reuse the delta from the revlog if allowed and
             # the revlog chunk is a delta.
             cachedelta = None
             rawtext = None
-            if any(sidedataactions) or deltareuse == self.DELTAREUSEFULLADD:
-                dropall = sidedataactions[0]
-                filterout = sidedataactions[1]
-                update = sidedataactions[2]
-                new_flags = sidedataactions[3]
-                dropped_flags = sidedataactions[4]
+            if deltareuse == self.DELTAREUSEFULLADD:
                 text, sidedata = self._revisiondata(rev)
-                if dropall:
-                    sidedata = {}
-                for key in filterout:
-                    sidedata.pop(key, None)
-                sidedata.update(update)
-                if not sidedata:
-                    sidedata = None
-
-                flags |= new_flags
-                flags &= ~dropped_flags
+
+                if sidedata_helpers is not None:
+                    (sidedata, new_flags) = storageutil.run_sidedata_helpers(
+                        self, sidedata_helpers, sidedata, rev
+                    )
+                    flags = flags | new_flags[0] & ~new_flags[1]
 
                 destrevlog.addrevision(
                     text,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     cachedelta=cachedelta,
                     node=node,
                     flags=flags,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
             else:
                 if destrevlog._lazydelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
+                sidedata = None
                 if not cachedelta:
-                    rawtext = self.rawdata(rev)
+                    rawtext, sidedata = self._revisiondata(rev)
+                if sidedata is None:
+                    sidedata = self.sidedata(rev)
+
+                if sidedata_helpers is not None:
+                    (sidedata, new_flags) = storageutil.run_sidedata_helpers(
+                        self, sidedata_helpers, sidedata, rev
+                    )
+                    flags = flags | new_flags[0] & ~new_flags[1]
 
                 ifh = destrevlog.opener(
                     destrevlog.indexfile, b'a+', checkambig=False
                 )
                 dfh = None
                 if not destrevlog._inline:
                     dfh = destrevlog.opener(destrevlog.datafile, b'a+')
                 try:
                     destrevlog._addrevision(
                         node,
                         rawtext,
                         tr,
                         linkrev,
                         p1,
                         p2,
                         flags,
                         cachedelta,
                         ifh,
                         dfh,
                         deltacomputer=deltacomputer,
+                        sidedata=sidedata,
                     )
                 finally:
                     if dfh:
                         dfh.close()
                     ifh.close()
 
             if addrevisioncb:
                 addrevisioncb(self, rev, node)
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if (self.version & 0xFFFF) == REVLOGV0:
             raise error.RevlogError(
                 _(b'cannot censor with version %d revlogs') % self.version
             )
 
         censorrev = self.rev(censornode)
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(censorrev):
             raise error.Abort(
                 _(b'censor tombstone must be no longer than censored data')
             )
 
         # Rewriting the revlog in place is hard. Our strategy for censoring is
         # to create a new revlog, copy all revisions to it, then replace the
         # revlogs on transaction close.
 
         newindexfile = self.indexfile + b'.tmpcensored'
         newdatafile = self.datafile + b'.tmpcensored'
 
         # This is a bit dangerous. We could easily have a mismatch of state.
         newrl = revlog(
             self.opener,
             target=self.target,
             indexfile=newindexfile,
             datafile=newdatafile,
             censorable=True,
         )
         newrl.version = self.version
         newrl._generaldelta = self._generaldelta
         newrl._parse_index = self._parse_index
 
         for rev in self.revs():
             node = self.node(rev)
             p1, p2 = self.parents(node)
 
             if rev == censorrev:
                 newrl.addrawrevision(
                     tombstone,
                     tr,
                     self.linkrev(censorrev),
                     p1,
                     p2,
                     censornode,
                     REVIDX_ISCENSORED,
                 )
 
                 if newrl.deltaparent(rev) != nullrev:
                     raise error.Abort(
                         _(
                             b'censored revision stored as delta; '
                             b'cannot censor'
                         ),
                         hint=_(
                             b'censoring of revlogs is not '
                             b'fully implemented; please report '
                             b'this bug'
                         ),
                     )
                 continue
 
             if self.iscensored(rev):
                 if self.deltaparent(rev) != nullrev:
                     raise error.Abort(
                         _(
                             b'cannot censor due to censored '
                             b'revision having delta stored'
                         )
                     )
                 rawtext = self._chunk(rev)
             else:
                 rawtext = self.rawdata(rev)
 
             newrl.addrawrevision(
                 rawtext, tr, self.linkrev(rev), p1, p2, node, self.flags(rev)
             )
 
         tr.addbackup(self.indexfile, location=b'store')
         if not self._inline:
             tr.addbackup(self.datafile, location=b'store')
 
         self.opener.rename(newrl.indexfile, self.indexfile)
         if not self._inline:
             self.opener.rename(newrl.datafile, self.datafile)
 
         self.clearcaches()
         self._loadindex()
 
     def verifyintegrity(self, state):
         """Verifies the integrity of the revlog.
 
         Yields ``revlogproblem`` instances describing problems that are
         found.
         """
         dd, di = self.checksize()
         if dd:
             yield revlogproblem(error=_(b'data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_(b'index contains %d extra bytes') % di)
 
         version = self.version & 0xFFFF
 
         # 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.indexfile, version, state[b'expectedversion'])
             )
 
         state[b'skipread'] = set()
         state[b'safe_renamed'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see flagutil.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get(b'skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_(b'unpacked size is %d, %d expected') % (l2, l1),
                         node=node,
                     )
 
             except error.CensoredNodeError:
                 if state[b'erroroncensored']:
                     yield revlogproblem(
                         error=_(b'censored file data'), node=node
                     )
                     state[b'skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_(b'unpacking %s: %s')
                     % (short(node), stringutil.forcebytestr(e)),
                     node=node,
                 )
                 state[b'skipread'].add(node)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         d = {}
 
         if exclusivefiles:
             d[b'exclusivefiles'] = [(self.opener, self.indexfile)]
             if not self._inline:
                 d[b'exclusivefiles'].append((self.opener, self.datafile))
 
         if sharedfiles:
             d[b'sharedfiles'] = []
 
         if revisionscount:
             d[b'revisionscount'] = len(self)
 
         if trackedsize:
             d[b'trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d[b'storedsize'] = sum(
                 self.opener.stat(path).st_size for path in self.files()
             )
 
         return d
 
     def rewrite_sidedata(self, helpers, startrev, endrev):
         if self.version & 0xFFFF != REVLOGV2:
             return
         # inline are not yet supported because they suffer from an issue when
         # rewriting them (since it's not an append-only operation).
         # See issue6485.
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         new_entries = []
         # append the new sidedata
         with self._datafp(b'a+') as fp:
             # Maybe this bug still exists, see revlog._writeentry
             fp.seek(0, os.SEEK_END)
             current_offset = fp.tell()
             for rev in range(startrev, endrev + 1):
                 entry = self.index[rev]
                 new_sidedata, flags = storageutil.run_sidedata_helpers(
                     store=self,
                     sidedata_helpers=helpers,
                     sidedata={},
                     rev=rev,
                 )
 
                 serialized_sidedata = sidedatautil.serialize_sidedata(
                     new_sidedata
                 )
                 if entry[8] != 0 or entry[9] != 0:
                     # rewriting entries that already have sidedata is not
                     # supported yet, because it introduces garbage data in the
                     # revlog.
                     msg = b"Rewriting existing sidedata is not supported yet"
                     raise error.Abort(msg)
 
                 # Apply (potential) flags to add and to remove after running
                 # the sidedata helpers
                 new_offset_flags = entry[0] | flags[0] & ~flags[1]
                 entry = (new_offset_flags,) + entry[1:8]
                 entry += (current_offset, len(serialized_sidedata))
 
                 fp.write(serialized_sidedata)
                 new_entries.append(entry)
                 current_offset += len(serialized_sidedata)
 
         # rewrite the new index entries
         with self._indexfp(b'w+') as fp:
             fp.seek(startrev * self.index.entry_size)
             for i, e in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, e[8], e[9], e[0])
                 packed = self.index.entry_binary(rev)
                 if rev == 0:
                     header = self.index.pack_header(self.version)
                     packed = header + packed
                 fp.write(packed)

mercurial/upgrade_utils/engine.py

@@ -1,593 +1,594 b''
 # upgrade.py - functions for in place upgrade of Mercurial repository
 #
 # Copyright (c) 2016-present, Gregory Szorc
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import stat
 
 from ..i18n import _
 from ..pycompat import getattr
 from .. import (
+    changegroup,
     changelog,
     error,
     filelog,
     manifest,
     metadata,
     pycompat,
     requirements,
-    revlog,
     scmutil,
     store,
     util,
     vfs as vfsmod,
 )
-from ..revlogutils import nodemap
+from ..revlogutils import (
+    constants as revlogconst,
+    flagutil,
+    nodemap,
+    sidedata as sidedatamod,
+)
+
+
+def get_sidedata_helpers(srcrepo, dstrepo):
+    use_w = srcrepo.ui.configbool(b'experimental', b'worker.repository-upgrade')
+    sequential = pycompat.iswindows or not use_w
+    if not sequential:
+        srcrepo.register_sidedata_computer(
+            revlogconst.KIND_CHANGELOG,
+            sidedatamod.SD_FILES,
+            (sidedatamod.SD_FILES,),
+            metadata._get_worker_sidedata_adder(srcrepo, dstrepo),
+            flagutil.REVIDX_HASCOPIESINFO,
+            replace=True,
+        )
+    return changegroup.get_sidedata_helpers(srcrepo, dstrepo._wanted_sidedata)
 
 
 def _revlogfrompath(repo, rl_type, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if rl_type & store.FILEFLAGS_CHANGELOG:
         return changelog.changelog(repo.svfs)
     elif rl_type & store.FILEFLAGS_MANIFESTLOG:
         mandir = b''
         if b'/' in path:
             mandir = path.rsplit(b'/', 1)[0]
         return manifest.manifestrevlog(
             repo.nodeconstants, repo.svfs, tree=mandir
         )
     else:
         # drop the extension and the `data/` prefix
         path = path.rsplit(b'.', 1)[0].split(b'/', 1)[1]
         return filelog.filelog(repo.svfs, path)
 
 
 def _copyrevlog(tr, destrepo, oldrl, rl_type, unencodedname):
     """copy all relevant files for `oldrl` into `destrepo` store
 
     Files are copied "as is" without any transformation. The copy is performed
     without extra checks. Callers are responsible for making sure the copied
     content is compatible with format of the destination repository.
     """
     oldrl = getattr(oldrl, '_revlog', oldrl)
     newrl = _revlogfrompath(destrepo, rl_type, unencodedname)
     newrl = getattr(newrl, '_revlog', newrl)
 
     oldvfs = oldrl.opener
     newvfs = newrl.opener
     oldindex = oldvfs.join(oldrl.indexfile)
     newindex = newvfs.join(newrl.indexfile)
     olddata = oldvfs.join(oldrl.datafile)
     newdata = newvfs.join(newrl.datafile)
 
     with newvfs(newrl.indexfile, b'w'):
         pass  # create all the directories
 
     util.copyfile(oldindex, newindex)
     copydata = oldrl.opener.exists(oldrl.datafile)
     if copydata:
         util.copyfile(olddata, newdata)
 
     if rl_type & store.FILEFLAGS_FILELOG:
         destrepo.svfs.fncache.add(unencodedname)
         if copydata:
             destrepo.svfs.fncache.add(unencodedname[:-2] + b'.d')
 
 
 UPGRADE_CHANGELOG = b"changelog"
 UPGRADE_MANIFEST = b"manifest"
 UPGRADE_FILELOGS = b"all-filelogs"
 
 UPGRADE_ALL_REVLOGS = frozenset(
     [UPGRADE_CHANGELOG, UPGRADE_MANIFEST, UPGRADE_FILELOGS]
 )
 
 
-def getsidedatacompanion(srcrepo, dstrepo):
-    sidedatacompanion = None
-    removedreqs = srcrepo.requirements - dstrepo.requirements
-    addedreqs = dstrepo.requirements - srcrepo.requirements
-    if requirements.SIDEDATA_REQUIREMENT in removedreqs:
-
-        def sidedatacompanion(rl, rev):
-            rl = getattr(rl, '_revlog', rl)
-            if rl.flags(rev) & revlog.REVIDX_SIDEDATA:
-                return True, (), {}, 0, 0
-            return False, (), {}, 0, 0
-
-    elif requirements.COPIESSDC_REQUIREMENT in addedreqs:
-        sidedatacompanion = metadata.getsidedataadder(srcrepo, dstrepo)
-    elif requirements.COPIESSDC_REQUIREMENT in removedreqs:
-        sidedatacompanion = metadata.getsidedataremover(srcrepo, dstrepo)
-    return sidedatacompanion
-
-
 def matchrevlog(revlogfilter, rl_type):
     """check if a revlog is selected for cloning.
 
     In other words, are there any updates which need to be done on revlog
     or it can be blindly copied.
 
     The store entry is checked against the passed filter"""
     if rl_type & store.FILEFLAGS_CHANGELOG:
         return UPGRADE_CHANGELOG in revlogfilter
     elif rl_type & store.FILEFLAGS_MANIFESTLOG:
         return UPGRADE_MANIFEST in revlogfilter
     assert rl_type & store.FILEFLAGS_FILELOG
     return UPGRADE_FILELOGS in revlogfilter
 
 
 def _perform_clone(
     ui,
     dstrepo,
     tr,
     old_revlog,
     rl_type,
     unencoded,
     upgrade_op,
-    sidedatacompanion,
+    sidedata_helpers,
     oncopiedrevision,
 ):
     """ returns the new revlog object created"""
     newrl = None
     if matchrevlog(upgrade_op.revlogs_to_process, rl_type):
         ui.note(
             _(b'cloning %d revisions from %s\n') % (len(old_revlog), unencoded)
         )
         newrl = _revlogfrompath(dstrepo, rl_type, unencoded)
         old_revlog.clone(
             tr,
             newrl,
             addrevisioncb=oncopiedrevision,
             deltareuse=upgrade_op.delta_reuse_mode,
             forcedeltabothparents=upgrade_op.force_re_delta_both_parents,
-            sidedatacompanion=sidedatacompanion,
+            sidedata_helpers=sidedata_helpers,
         )
     else:
         msg = _(b'blindly copying %s containing %i revisions\n')
         ui.note(msg % (unencoded, len(old_revlog)))
         _copyrevlog(tr, dstrepo, old_revlog, rl_type, unencoded)
 
         newrl = _revlogfrompath(dstrepo, rl_type, unencoded)
     return newrl
 
 
 def _clonerevlogs(
     ui,
     srcrepo,
     dstrepo,
     tr,
     upgrade_op,
 ):
     """Copy revlogs between 2 repos."""
     revcount = 0
     srcsize = 0
     srcrawsize = 0
     dstsize = 0
     fcount = 0
     frevcount = 0
     fsrcsize = 0
     frawsize = 0
     fdstsize = 0
     mcount = 0
     mrevcount = 0
     msrcsize = 0
     mrawsize = 0
     mdstsize = 0
     crevcount = 0
     csrcsize = 0
     crawsize = 0
     cdstsize = 0
 
     alldatafiles = list(srcrepo.store.walk())
     # mapping of data files which needs to be cloned
     # key is unencoded filename
     # value is revlog_object_from_srcrepo
     manifests = {}
     changelogs = {}
     filelogs = {}
 
     # Perform a pass to collect metadata. This validates we can open all
     # source files and allows a unified progress bar to be displayed.
     for rl_type, unencoded, encoded, size in alldatafiles:
         if not rl_type & store.FILEFLAGS_REVLOG_MAIN:
             continue
 
         rl = _revlogfrompath(srcrepo, rl_type, unencoded)
 
         info = rl.storageinfo(
             exclusivefiles=True,
             revisionscount=True,
             trackedsize=True,
             storedsize=True,
         )
 
         revcount += info[b'revisionscount'] or 0
         datasize = info[b'storedsize'] or 0
         rawsize = info[b'trackedsize'] or 0
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if rl_type & store.FILEFLAGS_CHANGELOG:
             changelogs[unencoded] = (rl_type, rl)
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif rl_type & store.FILEFLAGS_MANIFESTLOG:
             manifests[unencoded] = (rl_type, rl)
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif rl_type & store.FILEFLAGS_FILELOG:
             filelogs[unencoded] = (rl_type, rl)
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError(b'unknown revlog type')
 
     if not revcount:
         return
 
     ui.status(
         _(
             b'migrating %d total revisions (%d in filelogs, %d in manifests, '
             b'%d in changelog)\n'
         )
         % (revcount, frevcount, mrevcount, crevcount)
     )
     ui.status(
         _(b'migrating %s in store; %s tracked data\n')
         % ((util.bytecount(srcsize), util.bytecount(srcrawsize)))
     )
 
     # Used to keep track of progress.
     progress = None
 
     def oncopiedrevision(rl, rev, node):
         progress.increment()
 
-    sidedatacompanion = getsidedatacompanion(srcrepo, dstrepo)
+    sidedata_helpers = get_sidedata_helpers(srcrepo, dstrepo)
 
     # Migrating filelogs
     ui.status(
         _(
             b'migrating %d filelogs containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             fcount,
             frevcount,
             util.bytecount(fsrcsize),
             util.bytecount(frawsize),
         )
     )
     progress = srcrepo.ui.makeprogress(_(b'file revisions'), total=frevcount)
     for unencoded, (rl_type, oldrl) in sorted(filelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
-            sidedatacompanion,
+            sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         fdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d filelog revisions across %d '
             b'filelogs; change in size: %s\n'
         )
         % (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
     )
 
     # Migrating manifests
     ui.status(
         _(
             b'migrating %d manifests containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             mcount,
             mrevcount,
             util.bytecount(msrcsize),
             util.bytecount(mrawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'manifest revisions'), total=mrevcount
     )
     for unencoded, (rl_type, oldrl) in sorted(manifests.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
-            sidedatacompanion,
+            sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         mdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d manifest revisions across %d '
             b'manifests; change in size: %s\n'
         )
         % (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
     )
 
     # Migrating changelog
     ui.status(
         _(
             b'migrating changelog containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             crevcount,
             util.bytecount(csrcsize),
             util.bytecount(crawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'changelog revisions'), total=crevcount
     )
     for unencoded, (rl_type, oldrl) in sorted(changelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
-            sidedatacompanion,
+            sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         cdstsize += info[b'storedsize'] or 0
     progress.complete()
     ui.status(
         _(
             b'finished migrating %d changelog revisions; change in size: '
             b'%s\n'
         )
         % (crevcount, util.bytecount(cdstsize - csrcsize))
     )
 
     dstsize = fdstsize + mdstsize + cdstsize
     ui.status(
         _(
             b'finished migrating %d total revisions; total change in store '
             b'size: %s\n'
         )
         % (revcount, util.bytecount(dstsize - srcsize))
     )
 
 
 def _files_to_copy_post_revlog_clone(srcrepo):
     """yields files which should be copied to destination after revlogs
     are cloned"""
     for path, kind, st in sorted(srcrepo.store.vfs.readdir(b'', stat=True)):
         # don't copy revlogs as they are already cloned
         if store.revlog_type(path) is not None:
             continue
         # Skip transaction related files.
         if path.startswith(b'undo'):
             continue
         # Only copy regular files.
         if kind != stat.S_IFREG:
             continue
         # Skip other skipped files.
         if path in (b'lock', b'fncache'):
             continue
         # TODO: should we skip cache too?
 
         yield path
 
 
 def _replacestores(currentrepo, upgradedrepo, backupvfs, upgrade_op):
     """Replace the stores after current repository is upgraded
 
     Creates a backup of current repository store at backup path
     Replaces upgraded store files in current repo from upgraded one
 
     Arguments:
       currentrepo: repo object of current repository
       upgradedrepo: repo object of the upgraded data
       backupvfs: vfs object for the backup path
       upgrade_op: upgrade operation object
                   to be used to decide what all is upgraded
     """
     # TODO: don't blindly rename everything in store
     # There can be upgrades where store is not touched at all
     if upgrade_op.backup_store:
         util.rename(currentrepo.spath, backupvfs.join(b'store'))
     else:
         currentrepo.vfs.rmtree(b'store', forcibly=True)
     util.rename(upgradedrepo.spath, currentrepo.spath)
 
 
 def finishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 
 def upgrade(ui, srcrepo, dstrepo, upgrade_op):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
     backuppath = None
     backupvfs = None
 
     ui.status(
         _(
             b'(it is safe to interrupt this process any time before '
             b'data migration completes)\n'
         )
     )
 
     if upgrade_op.requirements_only:
         ui.status(_(b'upgrading repository requirements\n'))
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     # if there is only one action and that is persistent nodemap upgrade
     # directly write the nodemap file and update requirements instead of going
     # through the whole cloning process
     elif (
         len(upgrade_op.upgrade_actions) == 1
         and b'persistent-nodemap' in upgrade_op._upgrade_actions_names
         and not upgrade_op.removed_actions
     ):
         ui.status(
             _(b'upgrading repository to use persistent nodemap feature\n')
         )
         with srcrepo.transaction(b'upgrade') as tr:
             unfi = srcrepo.unfiltered()
             cl = unfi.changelog
             nodemap.persist_nodemap(tr, cl, force=True)
             # we want to directly operate on the underlying revlog to force
             # create a nodemap file. This is fine since this is upgrade code
             # and it heavily relies on repository being revlog based
             # hence accessing private attributes can be justified
             nodemap.persist_nodemap(
                 tr, unfi.manifestlog._rootstore._revlog, force=True
             )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     elif (
         len(upgrade_op.removed_actions) == 1
         and [
             x
             for x in upgrade_op.removed_actions
             if x.name == b'persistent-nodemap'
         ]
         and not upgrade_op.upgrade_actions
     ):
         ui.status(
             _(b'downgrading repository to not use persistent nodemap feature\n')
         )
         with srcrepo.transaction(b'upgrade') as tr:
             unfi = srcrepo.unfiltered()
             cl = unfi.changelog
             nodemap.delete_nodemap(tr, srcrepo, cl)
             # check comment 20 lines above for accessing private attributes
             nodemap.delete_nodemap(
                 tr, srcrepo, unfi.manifestlog._rootstore._revlog
             )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     else:
         with dstrepo.transaction(b'upgrade') as tr:
             _clonerevlogs(
                 ui,
                 srcrepo,
                 dstrepo,
                 tr,
                 upgrade_op,
             )
 
         # Now copy other files in the store directory.
         for p in _files_to_copy_post_revlog_clone(srcrepo):
             srcrepo.ui.status(_(b'copying %s\n') % p)
             src = srcrepo.store.rawvfs.join(p)
             dst = dstrepo.store.rawvfs.join(p)
             util.copyfile(src, dst, copystat=True)
 
         finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
         ui.status(_(b'data fully upgraded in a temporary repository\n'))
 
         if upgrade_op.backup_store:
             backuppath = pycompat.mkdtemp(
                 prefix=b'upgradebackup.', dir=srcrepo.path
             )
             backupvfs = vfsmod.vfs(backuppath)
 
             # Make a backup of requires file first, as it is the first to be modified.
             util.copyfile(
                 srcrepo.vfs.join(b'requires'), backupvfs.join(b'requires')
             )
 
         # We install an arbitrary requirement that clients must not support
         # as a mechanism to lock out new clients during the data swap. This is
         # better than allowing a client to continue while the repository is in
         # an inconsistent state.
         ui.status(
             _(
                 b'marking source repository as being upgraded; clients will be '
                 b'unable to read from repository\n'
             )
         )
         scmutil.writereporequirements(
             srcrepo, srcrepo.requirements | {b'upgradeinprogress'}
         )
 
         ui.status(_(b'starting in-place swap of repository data\n'))
         if upgrade_op.backup_store:
             ui.status(
                 _(b'replaced files will be backed up at %s\n') % backuppath
             )
 
         # Now swap in the new store directory. Doing it as a rename should make
         # the operation nearly instantaneous and atomic (at least in well-behaved
         # environments).
         ui.status(_(b'replacing store...\n'))
         tstart = util.timer()
         _replacestores(srcrepo, dstrepo, backupvfs, upgrade_op)
         elapsed = util.timer() - tstart
         ui.status(
             _(
                 b'store replacement complete; repository was inconsistent for '
                 b'%0.1fs\n'
             )
             % elapsed
         )
 
         # We first write the requirements file. Any new requirements will lock
         # out legacy clients.
         ui.status(
             _(
                 b'finalizing requirements file and making repository readable '
                 b'again\n'
             )
         )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
 
         if upgrade_op.backup_store:
             # The lock file from the old store won't be removed because nothing has a
             # reference to its new location. So clean it up manually. Alternatively, we
             # could update srcrepo.svfs and other variables to point to the new
             # location. This is simpler.
             assert backupvfs is not None  # help pytype
             backupvfs.unlink(b'store/lock')
 
     return backuppath

tests/test-copies-in-changeset.t

@@ -1,507 +1,503 b''
 #testcases extra sidedata
 
 #if extra
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.write-to=changeset-only
   > copies.read-from=changeset-only
   > [alias]
   > changesetcopies = log -r . -T 'files: {files}
   >   {extras % "{ifcontains("files", key, "{key}: {value}\n")}"}
   >   {extras % "{ifcontains("copies", key, "{key}: {value}\n")}"}'
   > EOF
 #endif
 
 #if sidedata
   $ cat >> $HGRCPATH << EOF
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
 #endif
 
   $ cat >> $HGRCPATH << EOF
   > [alias]
   > showcopies = log -r . -T '{file_copies % "{source} -> {name}\n"}'
   > [extensions]
   > rebase =
   > split =
   > EOF
 
 Check that copies are recorded correctly
 
   $ hg init repo
   $ cd repo
 #if sidedata
   $ hg debugformat -v
   format-variant     repo config default
   fncache:            yes    yes     yes
   dotencode:          yes    yes     yes
   generaldelta:       yes    yes     yes
   share-safe:          no     no      no
   sparserevlog:       yes    yes     yes
   persistent-nodemap:  no     no      no (no-rust !)
   persistent-nodemap: yes    yes      no (rust !)
   copies-sdc:         yes    yes      no
   revlog-v2:          yes    yes      no
   plain-cl-delta:     yes    yes     yes
   compression:        zlib   zlib    zlib (no-zstd !)
   compression:        zstd   zstd    zstd (zstd !)
   compression-level:  default default default
 #else
   $ hg debugformat -v
   format-variant     repo config default
   fncache:            yes    yes     yes
   dotencode:          yes    yes     yes
   generaldelta:       yes    yes     yes
   share-safe:          no     no      no
   sparserevlog:       yes    yes     yes
   persistent-nodemap:  no     no      no (no-rust !)
   persistent-nodemap: yes    yes      no (rust !)
   copies-sdc:          no     no      no
   revlog-v2:           no     no      no
   plain-cl-delta:     yes    yes     yes
   compression:        zlib   zlib    zlib (no-zstd !)
   compression:        zstd   zstd    zstd (zstd !)
   compression-level:  default default default
 #endif
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg cp a b
   $ hg cp a c
   $ hg cp a d
   $ hg ci -m 'copy a to b, c, and d'
 
 #if extra
 
   $ hg changesetcopies
   files: b c d
   filesadded: 0
   1
   2
   
   p1copies: 0\x00a (esc)
   1\x00a (esc)
   2\x00a (esc)
 #else
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 44
     '\x00\x00\x00\x04\x00\x00\x00\x00\x01\x00\x00\x00\x00\x06\x00\x00\x00\x02\x00\x00\x00\x00\x06\x00\x00\x00\x03\x00\x00\x00\x00\x06\x00\x00\x00\x04\x00\x00\x00\x00abcd'
 #endif
 
   $ hg showcopies
   a -> b
   a -> c
   a -> d
 
 #if extra
 
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> b
   a -> c
   a -> d
   $ hg showcopies --config experimental.copies.read-from=filelog-only
 
 #endif
 
 Check that renames are recorded correctly
 
   $ hg mv b b2
   $ hg ci -m 'rename b to b2'
 
 #if extra
 
   $ hg changesetcopies
   files: b b2
   filesadded: 1
   filesremoved: 0
   
   p1copies: 1\x00b (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 25
     '\x00\x00\x00\x02\x0c\x00\x00\x00\x01\x00\x00\x00\x00\x06\x00\x00\x00\x03\x00\x00\x00\x00bb2'
 #endif
 
   $ hg showcopies
   b -> b2
 
 
 Rename onto existing file. This should get recorded in the changeset files list and in the extras,
 even though there is no filelog entry.
 
   $ hg cp b2 c --force
   $ hg st --copies
   M c
     b2
 
 #if extra
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
 
 #else
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 37d9b5d994ea 000000000000 000000000000
 
 #endif
 
 
   $ hg ci -m 'move b onto d'
 
 #if extra
 
   $ hg changesetcopies
   files: c
   
   p1copies: 0\x00b2 (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 25
     '\x00\x00\x00\x02\x00\x00\x00\x00\x02\x00\x00\x00\x00\x16\x00\x00\x00\x03\x00\x00\x00\x00b2c'
 #endif
 
   $ hg showcopies
   b2 -> c
 
 #if extra
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
 
 #else
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 37d9b5d994ea 000000000000 000000000000
        1       3 029625640347 000000000000 000000000000
 
 #endif
 
 Create a merge commit with copying done during merge.
 
   $ hg co 0
   0 files updated, 0 files merged, 3 files removed, 0 files unresolved
   $ hg cp a e
   $ hg cp a f
   $ hg ci -m 'copy a to e and f'
   created new head
   $ hg merge 3
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
 File 'a' exists on both sides, so 'g' could be recorded as being from p1 or p2, but we currently
 always record it as being from p1
   $ hg cp a g
 File 'd' exists only in p2, so 'h' should be from p2
   $ hg cp d h
 File 'f' exists only in p1, so 'i' should be from p1
   $ hg cp f i
   $ hg ci -m 'merge'
 
 #if extra
 
   $ hg changesetcopies
   files: g h i
   filesadded: 0
   1
   2
   
   p1copies: 0\x00a (esc)
   2\x00f (esc)
   p2copies: 1\x00d (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 64
     '\x00\x00\x00\x06\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x06\x00\x00\x00\x04\x00\x00\x00\x00\x07\x00\x00\x00\x05\x00\x00\x00\x01\x06\x00\x00\x00\x06\x00\x00\x00\x02adfghi'
 #endif
 
   $ hg showcopies
   a -> g
   d -> h
   f -> i
 
 Test writing to both changeset and filelog
 
   $ hg cp a j
 #if extra
   $ hg ci -m 'copy a to j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 0
   filesremoved: 
   
   p1copies: 0\x00a (esc)
   p2copies: 
 #else
   $ hg ci -m 'copy a to j'
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 24
     '\x00\x00\x00\x02\x00\x00\x00\x00\x01\x00\x00\x00\x00\x06\x00\x00\x00\x02\x00\x00\x00\x00aj'
 #endif
   $ hg debugdata j 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
   $ hg showcopies
   a -> j
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> j
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> j
 Existing copy information in the changeset gets removed on amend and writing
 copy information on to the filelog
 #if extra
   $ hg ci --amend -m 'copy a to j, v2' \
   > --config experimental.copies.write-to=filelog-only
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/*-*-amend.hg (glob)
   $ hg changesetcopies
   files: j
   
 #else
   $ hg ci --amend -m 'copy a to j, v2'
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/*-*-amend.hg (glob)
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 24
     '\x00\x00\x00\x02\x00\x00\x00\x00\x01\x00\x00\x00\x00\x06\x00\x00\x00\x02\x00\x00\x00\x00aj'
 #endif
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> j
 The entries should be written to extras even if they're empty (so the client
 won't have to fall back to reading from filelogs)
   $ echo x >> j
 #if extra
   $ hg ci -m 'modify j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 
   filesremoved: 
   
   p1copies: 
   p2copies: 
 #else
   $ hg ci -m 'modify j'
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 14
     '\x00\x00\x00\x01\x14\x00\x00\x00\x01\x00\x00\x00\x00j'
 #endif
 
 Test writing only to filelog
 
   $ hg cp a k
 #if extra
   $ hg ci -m 'copy a to k' --config experimental.copies.write-to=filelog-only
 
   $ hg changesetcopies
   files: k
   
 #else
   $ hg ci -m 'copy a to k'
   $ hg debugsidedata -c -v -- -1
   1 sidedata entries
    entry-0014 size 24
     '\x00\x00\x00\x02\x00\x00\x00\x00\x01\x00\x00\x00\x00\x06\x00\x00\x00\x02\x00\x00\x00\x00ak'
 #endif
 
   $ hg debugdata k 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
 #if extra
   $ hg showcopies
 
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> k
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> k
 #else
   $ hg showcopies
   a -> k
 #endif
 
   $ cd ..
 
 Test rebasing a commit with copy information
 
   $ hg init rebase-rename
   $ cd rebase-rename
   $ echo a > a
   $ hg ci -Aqm 'add a'
   $ echo a2 > a
   $ hg ci -m 'modify a'
   $ hg co -q 0
   $ hg mv a b
   $ hg ci -qm 'rename a to b'
 Not only do we want this to run in-memory, it shouldn't fall back to
 on-disk merge (no conflicts), so we force it to be in-memory
 with no fallback.
   $ hg rebase -d 1 --config rebase.experimental.inmemory=yes --config devel.rebase.force-in-memory-merge=yes
   rebasing 2:* tip "rename a to b" (glob)
   merging a and b to b
   saved backup bundle to $TESTTMP/rebase-rename/.hg/strip-backup/*-*-rebase.hg (glob)
   $ hg st --change . --copies
   A b
     a
   R a
   $ cd ..
 
 Test splitting a commit
 
   $ hg init split
   $ cd split
   $ echo a > a
   $ echo b > b
   $ hg ci -Aqm 'add a and b'
   $ echo a2 > a
   $ hg mv b c
   $ hg ci -m 'modify a, move b to c'
   $ hg --config ui.interactive=yes split <<EOF
   > y
   > y
   > n
   > y
   > EOF
   diff --git a/a b/a
   1 hunks, 1 lines changed
   examine changes to 'a'?
   (enter ? for help) [Ynesfdaq?] y
   
   @@ -1,1 +1,1 @@
   -a
   +a2
   record this change to 'a'?
   (enter ? for help) [Ynesfdaq?] y
   
   diff --git a/b b/c
   rename from b
   rename to c
   examine changes to 'b' and 'c'?
   (enter ? for help) [Ynesfdaq?] n
   
   created new head
   diff --git a/b b/c
   rename from b
   rename to c
   examine changes to 'b' and 'c'?
   (enter ? for help) [Ynesfdaq?] y
   
   saved backup bundle to $TESTTMP/split/.hg/strip-backup/*-*-split.hg (glob)
   $ cd ..
 
 Test committing half a rename
 
   $ hg init partial
   $ cd partial
   $ echo a > a
   $ hg ci -Aqm 'add a'
   $ hg mv a b
   $ hg ci -m 'remove a' a
 
 #if sidedata
 
 Test upgrading/downgrading to sidedata storage
 ==============================================
 
-downgrading (keeping some sidedata)
+downgrading
 
   $ hg debugformat -v
   format-variant     repo config default
   fncache:            yes    yes     yes
   dotencode:          yes    yes     yes
   generaldelta:       yes    yes     yes
   share-safe:          no     no      no
   sparserevlog:       yes    yes     yes
   persistent-nodemap:  no     no      no (no-rust !)
   persistent-nodemap: yes    yes      no (rust !)
   copies-sdc:         yes    yes      no
   revlog-v2:          yes    yes      no
   plain-cl-delta:     yes    yes     yes
   compression:        zlib   zlib    zlib (no-zstd !)
   compression:        zstd   zstd    zstd (zstd !)
   compression-level:  default default default
   $ hg debugsidedata -c -- 0
   1 sidedata entries
    entry-0014 size 14
   $ hg debugsidedata -c -- 1
   1 sidedata entries
    entry-0014 size 14
   $ hg debugsidedata -m -- 0
   $ cat << EOF > .hg/hgrc
   > [format]
   > exp-use-side-data = yes
   > exp-use-copies-side-data-changeset = no
   > EOF
   $ hg debugupgraderepo --run --quiet --no-backup > /dev/null
   $ hg debugformat -v
   format-variant     repo config default
   fncache:            yes    yes     yes
   dotencode:          yes    yes     yes
   generaldelta:       yes    yes     yes
   share-safe:          no     no      no
   sparserevlog:       yes    yes     yes
   persistent-nodemap:  no     no      no (no-rust !)
   persistent-nodemap: yes    yes      no (rust !)
   copies-sdc:          no     no      no
   revlog-v2:          yes    yes      no
   plain-cl-delta:     yes    yes     yes
   compression:        zlib   zlib    zlib (no-zstd !)
   compression:        zstd   zstd    zstd (zstd !)
   compression-level:  default default default
   $ hg debugsidedata -c -- 0
-  1 sidedata entries
-   entry-0014 size 14
   $ hg debugsidedata -c -- 1
-  1 sidedata entries
-   entry-0014 size 14
   $ hg debugsidedata -m -- 0
 
 upgrading
 
   $ cat << EOF > .hg/hgrc
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
   $ hg debugupgraderepo --run --quiet --no-backup > /dev/null
   $ hg debugformat -v
   format-variant     repo config default
   fncache:            yes    yes     yes
   dotencode:          yes    yes     yes
   generaldelta:       yes    yes     yes
   share-safe:          no     no      no
   sparserevlog:       yes    yes     yes
   persistent-nodemap:  no     no      no (no-rust !)
   persistent-nodemap: yes    yes      no (rust !)
   copies-sdc:         yes    yes      no
   revlog-v2:          yes    yes      no
   plain-cl-delta:     yes    yes     yes
   compression:        zlib   zlib    zlib (no-zstd !)
   compression:        zstd   zstd    zstd (zstd !)
   compression-level:  default default default
   $ hg debugsidedata -c -- 0
   1 sidedata entries
    entry-0014 size 14
   $ hg debugsidedata -c -- 1
   1 sidedata entries
    entry-0014 size 14
   $ hg debugsidedata -m -- 0
 
 #endif
 
   $ cd ..

tests/testlib/ext-sidedata.py

@@ -1,93 +1,106 b''
 # ext-sidedata.py - small extension to test the sidedata logic
 #
 # Copyright 2019 Pierre-Yves David <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 import struct
 
 from mercurial.node import nullrev
 from mercurial import (
+    changegroup,
     extensions,
     requirements,
     revlog,
 )
 
 from mercurial.upgrade_utils import engine as upgrade_engine
 
+from mercurial.revlogutils import constants
 from mercurial.revlogutils import sidedata
 
 
 def wrapaddrevision(
     orig, self, text, transaction, link, p1, p2, *args, **kwargs
 ):
     if kwargs.get('sidedata') is None:
         kwargs['sidedata'] = {}
     sd = kwargs['sidedata']
     ## let's store some arbitrary data just for testing
     # text length
     sd[sidedata.SD_TEST1] = struct.pack('>I', len(text))
     # and sha2 hashes
     sha256 = hashlib.sha256(text).digest()
     sd[sidedata.SD_TEST2] = struct.pack('>32s', sha256)
     return orig(self, text, transaction, link, p1, p2, *args, **kwargs)
 
 
 def wrap_revisiondata(orig, self, nodeorrev, *args, **kwargs):
     text, sd = orig(self, nodeorrev, *args, **kwargs)
     if getattr(self, 'sidedatanocheck', False):
         return text, sd
     if self.version & 0xFFFF != 2:
         return text, sd
     if nodeorrev != nullrev and nodeorrev != self.nullid:
         cat1 = sd.get(sidedata.SD_TEST1)
         if cat1 is not None and len(text) != struct.unpack('>I', cat1)[0]:
             raise RuntimeError('text size mismatch')
         expected = sd.get(sidedata.SD_TEST2)
         got = hashlib.sha256(text).digest()
         if expected is not None and got != expected:
             raise RuntimeError('sha256 mismatch')
     return text, sd
 
 
-def wrapgetsidedatacompanion(orig, srcrepo, dstrepo):
-    sidedatacompanion = orig(srcrepo, dstrepo)
+def wrapget_sidedata_helpers(orig, srcrepo, dstrepo):
+    repo, computers, removers = orig(srcrepo, dstrepo)
+    assert not computers and not removers  # deal with composition later
     addedreqs = dstrepo.requirements - srcrepo.requirements
+
     if requirements.SIDEDATA_REQUIREMENT in addedreqs:
-        assert sidedatacompanion is None  # deal with composition later
 
-        def sidedatacompanion(revlog, rev):
+        def computer(repo, revlog, rev, old_sidedata):
+            assert not old_sidedata  # not supported yet
             update = {}
             revlog.sidedatanocheck = True
             try:
                 text = revlog.revision(rev)
             finally:
                 del revlog.sidedatanocheck
             ## let's store some arbitrary data just for testing
             # text length
             update[sidedata.SD_TEST1] = struct.pack('>I', len(text))
             # and sha2 hashes
             sha256 = hashlib.sha256(text).digest()
             update[sidedata.SD_TEST2] = struct.pack('>32s', sha256)
-            return False, (), update, 0, 0
+            return update, (0, 0)
 
-    return sidedatacompanion
+        srcrepo.register_sidedata_computer(
+            constants.KIND_CHANGELOG,
+            b"whatever",
+            (sidedata.SD_TEST1, sidedata.SD_TEST2),
+            computer,
+            0,
+        )
+        dstrepo.register_wanted_sidedata(b"whatever")
+
+    return changegroup.get_sidedata_helpers(srcrepo, dstrepo._wanted_sidedata)
 
 
 def extsetup(ui):
     extensions.wrapfunction(revlog.revlog, 'addrevision', wrapaddrevision)
     extensions.wrapfunction(revlog.revlog, '_revisiondata', wrap_revisiondata)
     extensions.wrapfunction(
-        upgrade_engine, 'getsidedatacompanion', wrapgetsidedatacompanion
+        upgrade_engine, 'get_sidedata_helpers', wrapget_sidedata_helpers
     )
 
 
 def reposetup(ui, repo):
     # We don't register sidedata computers because we don't care within these
     # tests
     repo.register_wanted_sidedata(sidedata.SD_TEST1)
     repo.register_wanted_sidedata(sidedata.SD_TEST2)