This is an archive of the discontinued Mercurial Phabricator instance.

Differential D10887

deltas: at a `target_rev` parameter to finddeltainfo
ClosedPublic

Authored by marmoute on Jun 20 2021, 5:22 PM.

Details

Reviewers
Alphare
Group Reviewers
hg-reviewers
Commits
rHG93f4e183b3f5: deltas: at a `target_rev` parameter to finddeltainfo
Summary

Otherwise, recomputing a delta for a revision might result in a delta against a
later revision or a full snapshot thinking we are appending a new revision.

We will make use of this during censoring (and later, stripping).

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Event Timeline

marmoute created this revision.Jun 20 2021, 5:22 PM
Alphare accepted this revision.Jun 21 2021, 5:00 AM
This revision is now accepted and ready to land.Jun 21 2021, 5:00 AM
marmoute updated this revision to Diff 28646.Jun 21 2021, 9:10 AM
marmoute added a commit: rHG93f4e183b3f5: deltas: at a `target_rev` parameter to finddeltainfo.Jun 21 2021, 11:16 AM
Closed by commit rHG93f4e183b3f5: deltas: at a `target_rev` parameter to finddeltainfo (authored by marmoute). · Explain Why
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/revlogutils/deltas.py (16 lines)

Diff 28646

mercurial/revlogutils/deltas.py

(header, data), (header, data),
deltabase, deltabase,
chainbase, chainbase,
chainlen, chainlen,
compresseddeltalen, compresseddeltalen,
snapshotdepth, snapshotdepth,
) )
def _fullsnapshotinfo(self, fh, revinfo): def _fullsnapshotinfo(self, fh, revinfo, curr):
curr = len(self.revlog)
rawtext = self.buildtext(revinfo, fh) rawtext = self.buildtext(revinfo, fh)
data = self.revlog.compress(rawtext) data = self.revlog.compress(rawtext)
compresseddeltalen = deltalen = dist = len(data[1]) + len(data[0]) compresseddeltalen = deltalen = dist = len(data[1]) + len(data[0])
deltabase = chainbase = curr deltabase = chainbase = curr
snapshotdepth = 0 snapshotdepth = 0
chainlen = 1 chainlen = 1
return _deltainfo( return _deltainfo(
dist, dist,
deltalen, deltalen,
data, data,
deltabase, deltabase,
chainbase, chainbase,
chainlen, chainlen,
compresseddeltalen, compresseddeltalen,
snapshotdepth, snapshotdepth,
) )
def finddeltainfo(self, revinfo, fh, excluded_bases=None): def finddeltainfo(self, revinfo, fh, excluded_bases=None, target_rev=None):
"""Find an acceptable delta against a candidate revision """Find an acceptable delta against a candidate revision
revinfo: information about the revision (instance of _revisioninfo) revinfo: information about the revision (instance of _revisioninfo)
fh: file handle to either the .i or the .d revlog file, fh: file handle to either the .i or the .d revlog file,
depending on whether it is inlined or not depending on whether it is inlined or not
Returns the first acceptable candidate revision, as ordered by Returns the first acceptable candidate revision, as ordered by
_candidategroups _candidategroups
If no suitable deltabase is found, we return delta info for a full If no suitable deltabase is found, we return delta info for a full
snapshot. snapshot.
`excluded_bases` is an optional set of revision that cannot be used as `excluded_bases` is an optional set of revision that cannot be used as
a delta base. Use this to recompute delta suitable in censor or strip a delta base. Use this to recompute delta suitable in censor or strip
context. context.
""" """
if target_rev is None:
curr = len(self.revlog)
if not revinfo.textlen: if not revinfo.textlen:
return self._fullsnapshotinfo(fh, revinfo) return self._fullsnapshotinfo(fh, revinfo, target_rev)
if excluded_bases is None: if excluded_bases is None:
excluded_bases = set() excluded_bases = set()
# no delta for flag processor revision (see "candelta" for why) # no delta for flag processor revision (see "candelta" for why)
# not calling candelta since only one revision needs test, also to # not calling candelta since only one revision needs test, also to
# avoid overhead fetching flags again. # avoid overhead fetching flags again.
if revinfo.flags & REVIDX_RAWTEXT_CHANGING_FLAGS: if revinfo.flags & REVIDX_RAWTEXT_CHANGING_FLAGS:
return self._fullsnapshotinfo(fh, revinfo) return self._fullsnapshotinfo(fh, revinfo, target_rev)
cachedelta = revinfo.cachedelta cachedelta = revinfo.cachedelta
p1 = revinfo.p1 p1 = revinfo.p1
p2 = revinfo.p2 p2 = revinfo.p2
revlog = self.revlog revlog = self.revlog
deltainfo = None deltainfo = None
p1r, p2r = revlog.rev(p1), revlog.rev(p2) p1r, p2r = revlog.rev(p1), revlog.rev(p2)
groups = _candidategroups( groups = _candidategroups(
self.revlog, revinfo.textlen, p1r, p2r, cachedelta self.revlog, revinfo.textlen, p1r, p2r, cachedelta
) )
candidaterevs = next(groups) candidaterevs = next(groups)
while candidaterevs is not None: while candidaterevs is not None:
nominateddeltas = [] nominateddeltas = []
if deltainfo is not None: if deltainfo is not None:
# if we already found a good delta, # if we already found a good delta,
# challenge it against refined candidates # challenge it against refined candidates
nominateddeltas.append(deltainfo) nominateddeltas.append(deltainfo)
for candidaterev in candidaterevs: for candidaterev in candidaterevs:
if candidaterev in excluded_bases: if candidaterev in excluded_bases:
continue continue
if candidaterev >= target_rev:
continue
candidatedelta = self._builddeltainfo(revinfo, candidaterev, fh) candidatedelta = self._builddeltainfo(revinfo, candidaterev, fh)
if candidatedelta is not None: if candidatedelta is not None:
if isgooddeltainfo(self.revlog, candidatedelta, revinfo): if isgooddeltainfo(self.revlog, candidatedelta, revinfo):
nominateddeltas.append(candidatedelta) nominateddeltas.append(candidatedelta)
if nominateddeltas: if nominateddeltas:
deltainfo = min(nominateddeltas, key=lambda x: x.deltalen) deltainfo = min(nominateddeltas, key=lambda x: x.deltalen)
if deltainfo is not None: if deltainfo is not None:
candidaterevs = groups.send(deltainfo.base) candidaterevs = groups.send(deltainfo.base)
else: else:
candidaterevs = next(groups) candidaterevs = next(groups)
if deltainfo is None: if deltainfo is None:
deltainfo = self._fullsnapshotinfo(fh, revinfo) deltainfo = self._fullsnapshotinfo(fh, revinfo, target_rev)
return deltainfo return deltainfo
def delta_compression(default_compression_header, deltainfo): def delta_compression(default_compression_header, deltainfo):
"""return (COMPRESSION_MODE, deltainfo) """return (COMPRESSION_MODE, deltainfo)
used by revlog v2+ format to dispatch between PLAIN and DEFAULT used by revlog v2+ format to dispatch between PLAIN and DEFAULT
compression. compression.