This is an archive of the discontinued Mercurial Phabricator instance.

Differential D9115

copies: use dedicated `_revinfo_getter` function and call
ClosedPublic

Authored by marmoute on Sep 28 2020, 12:32 PM.

Details

Reviewers
Alphare
pulkit
Group Reviewers
hg-reviewers
Commits
rHG4f876e6b30fa: copies: use dedicated `_revinfo_getter` function and call
Summary

We want to return data in a different form, so we need different revinfo
function. At that point it make sense to have different getter.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

marmoute created this revision.Sep 28 2020, 12:32 PM
Alphare accepted this revision.Oct 1 2020, 12:08 PM
Alphare added a subscriber: Alphare.
Alphare added inline comments.
mercurial/copies.py
423

Typo, extra "i" at the end (if I didn't know you used vim, it would have been my guess ;))

pulkit accepted this revision.Oct 6 2020, 4:21 AM
This revision is now accepted and ready to land.Oct 6 2020, 4:21 AM

Revision Contents
Changeset List

PathPackages
Mmercurial/copies.py (160 lines)

Diff 23049

mercurial/copies.py

nb_parents = 0 nb_parents = 0
for n in parents: for n in parents:
if n != node.nullid: if n != node.nullid:
nb_parents += 1 nb_parents += 1
return nb_parents >= 2 return nb_parents >= 2
return ismerged return ismerged
if repo.filecopiesmode == b'changeset-sidedata':
changelogrevision = cl.changelogrevision changelogrevision = cl.changelogrevision
flags = cl.flags flags = cl.flags
# A small cache to avoid doing the work twice for merges # A small cache to avoid doing the work twice for merges
# #
# In the vast majority of cases, if we ask information for a revision # In the vast majority of cases, if we ask information for a revision
# about 1 parent, we'll later ask it for the other. So it make sense to # about 1 parent, we'll later ask it for the other. So it make sense to
# keep the information around when reaching the first parent of a merge # keep the information around when reaching the first parent of a merge
# and dropping it after it was provided for the second parents. # and dropping it after it was provided for the second parents.
# #
# It exists cases were only one parent of the merge will be walked. It # It exists cases were only one parent of the merge will be walked. It
# happens when the "destination" the copy tracing is descendant from a # happens when the "destination" the copy tracing is descendant from a
# new root, not common with the "source". In that case, we will only walk # new root, not common with the "source". In that case, we will only walk
# through merge parents that are descendant of changesets common # through merge parents that are descendant of changesets common
# between "source" and "destination". # between "source" and "destination".
# #
# With the current case implementation if such changesets have a copy # With the current case implementation if such changesets have a copy
# information, we'll keep them in memory until the end of # information, we'll keep them in memory until the end of
# _changesetforwardcopies. We don't expect the case to be frequent # _changesetforwardcopies. We don't expect the case to be frequent
# enough to matters. # enough to matters.
# #
# In addition, it would be possible to reach pathological case, were # In addition, it would be possible to reach pathological case, were
# many first parent are met before any second parent is reached. In # many first parent are met before any second parent is reached. In
# that case the cache could grow. If this even become an issue one can # that case the cache could grow. If this even become an issue one can
# safely introduce a maximum cache size. This would trade extra CPU/IO # safely introduce a maximum cache size. This would trade extra CPU/IO
# time to save memory. # time to save memory.
merge_caches = {} merge_caches = {}
def revinfo(rev): def revinfo(rev):
p1, p2 = parents(rev) p1, p2 = parents(rev)
value = None value = None
if flags(rev) & REVIDX_SIDEDATA: if flags(rev) & REVIDX_SIDEDATA:
e = merge_caches.pop(rev, None) e = merge_caches.pop(rev, None)
if e is not None: if e is not None:
return e return e
c = changelogrevision(rev) c = changelogrevision(rev)
p1copies = c.p1copies p1copies = c.p1copies
p2copies = c.p2copies p2copies = c.p2copies
removed = c.filesremoved removed = c.filesremoved
if p1 != node.nullrev and p2 != node.nullrev: if p1 != node.nullrev and p2 != node.nullrev:
# XXX some case we over cache, IGNORE # XXX some case we over cache, IGNORE
value = merge_caches[rev] = ( value = merge_caches[rev] = (
p1, p1,
p2, p2,
p1copies, p1copies,
p2copies, p2copies,
removed, removed,
get_ismerged(rev), get_ismerged(rev),
) )
else: else:
p1copies = {} p1copies = {}
p2copies = {} p2copies = {}
removed = [] removed = []
if value is None: if value is None:
value = (p1, p2, p1copies, p2copies, removed, get_ismerged(rev)) value = (p1, p2, p1copies, p2copies, removed, get_ismerged(rev))
return value return value
else:
def revinfo(rev):
p1, p2 = parents(rev)
ctx = repo[rev]
p1copies, p2copies = ctx._copies
removed = ctx.filesremoved()
return p1, p2, p1copies, p2copies, removed, get_ismerged(rev)
return revinfo return revinfo
def _changesetforwardcopies(a, b, match): def _changesetforwardcopies(a, b, match):
if a.rev() in (node.nullrev, b.rev()): if a.rev() in (node.nullrev, b.rev()):
return {} return {}
repo = a.repo().unfiltered() repo = a.repo().unfiltered()
children = {} children = {}
revinfo = _revinfo_getter(repo)
cl = repo.changelog cl = repo.changelog
isancestor = cl.isancestorrev # XXX we should had chaching to this. isancestor = cl.isancestorrev # XXX we should had chaching to this.
missingrevs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()]) missingrevs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()])
mrset = set(missingrevs) mrset = set(missingrevs)
roots = set() roots = set()
for r in missingrevs: for r in missingrevs:
for p in cl.parentrevs(r): for p in cl.parentrevs(r):
iterrevs = set(from_head) iterrevs = set(from_head)
iterrevs &= mrset iterrevs &= mrset
iterrevs.update(roots) iterrevs.update(roots)
iterrevs.remove(b.rev()) iterrevs.remove(b.rev())
revs = sorted(iterrevs) revs = sorted(iterrevs)
if repo.filecopiesmode == b'changeset-sidedata': if repo.filecopiesmode == b'changeset-sidedata':
revinfo = _revinfo_getter(repo)
return _combine_changeset_copies( return _combine_changeset_copies(
revs, children, b.rev(), revinfo, match, isancestor revs, children, b.rev(), revinfo, match, isancestor
) )
else: else:
revinfo = _revinfo_getter_extra(repo)
return _combine_changeset_copies_extra( return _combine_changeset_copies_extra(
revs, children, b.rev(), revinfo, match, isancestor revs, children, b.rev(), revinfo, match, isancestor
) )
def _combine_changeset_copies( def _combine_changeset_copies(
revs, children, targetrev, revinfo, match, isancestor revs, children, targetrev, revinfo, match, isancestor
): ):
if ( if (
new_tt == other_tt new_tt == other_tt
or not isancestor(new_tt, other_tt) or not isancestor(new_tt, other_tt)
or ismerged(dest) or ismerged(dest)
): ):
minor[dest] = value minor[dest] = value
def _revinfo_getter_extra(repo):
"""return a function that return multiple data given a <rev>"i
AlphareUnsubmitted
Not Done

Typo, extra "i" at the end (if I didn't know you used vim, it would have been my guess ;))

Alphare: Typo, extra "i" at the end (if I didn't know you used vim, it would have been my guess ;))
* p1: revision number of first parent
* p2: revision number of first parent
* p1copies: mapping of copies from p1
* p2copies: mapping of copies from p2
* removed: a list of removed files
* ismerged: a callback to know if file was merged in that revision
"""
cl = repo.changelog
parents = cl.parentrevs
def get_ismerged(rev):
ctx = repo[rev]
def ismerged(path):
if path not in ctx.files():
return False
fctx = ctx[path]
parents = fctx._filelog.parents(fctx._filenode)
nb_parents = 0
for n in parents:
if n != node.nullid:
nb_parents += 1
return nb_parents >= 2
return ismerged
def revinfo(rev):
p1, p2 = parents(rev)
ctx = repo[rev]
p1copies, p2copies = ctx._copies
removed = ctx.filesremoved()
return p1, p2, p1copies, p2copies, removed, get_ismerged(rev)
return revinfo
def _combine_changeset_copies_extra( def _combine_changeset_copies_extra(
revs, children, targetrev, revinfo, match, isancestor revs, children, targetrev, revinfo, match, isancestor
): ):
"""version of `_combine_changeset_copies` that works with the Google """version of `_combine_changeset_copies` that works with the Google
specific "extra" based storage for copy information""" specific "extra" based storage for copy information"""
all_copies = {} all_copies = {}
alwaysmatch = match.always() alwaysmatch = match.always()
for r in revs: for r in revs: