This is an archive of the discontinued Mercurial Phabricator instance.

Differential D9117

copies: directly pass a changes object to the copy tracing code
ClosedPublic

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

Details

Reviewers
Alphare
pulkit
Group Reviewers
hg-reviewers
Commits
rHG2693659c2b34: copies: directly pass a changes object to the copy tracing code
Summary

The object contains all the data we need. For example, the is_merged callback
can now use the associated precomputed data.

This will be useful again soon when the salvaged set will be introduce to
solve the issue with delete file reverted during a merge. See 4b582a93316a and
14be07d5603c for details.

Diff Detail

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

Event Timeline

marmoute created this revision.Sep 28 2020, 12:32 PM
Alphare accepted this revision.Oct 2 2020, 4:47 AM
Alphare added a subscriber: Alphare.
Alphare added inline comments.
mercurial/copies.py
174

I'd suggest "returns a function that returns the following data given a <rev>"

178

/s/ChangingGiles/ChangingFiles/

marmoute updated this revision to Diff 22989.Oct 2 2020, 5:08 AM
pulkit accepted this revision.Oct 6 2020, 4:24 AM
This revision is now accepted and ready to land.Oct 6 2020, 4:24 AM

Revision Contents
Changeset List

PathPackages
Mmercurial/copies.py (56 lines)

Diff 22906

mercurial/copies.py

dbg( dbg(
b'debug.copies: time: %f seconds\n' b'debug.copies: time: %f seconds\n'
% (util.timer() - start) % (util.timer() - start)
) )
return cm return cm
def _revinfo_getter(repo): def _revinfo_getter(repo):
"""return a function that return multiple data given a <rev>"i """return a function that return multiple data given a <rev>"
AlphareUnsubmitted
Not Done

I'd suggest "returns a function that returns the following data given a <rev>"

Alphare: I'd suggest "returns a function that returns the following data given a <rev>"
* p1: revision number of first parent * p1: revision number of first parent
* p2: revision number of first parent * p2: revision number of first parent
* p1copies: mapping of copies from p1 * changes: a ChangingGiles object
AlphareUnsubmitted
Not Done

/s/ChangingGiles/ChangingFiles/

Alphare: /s/ChangingGiles/ChangingFiles/
* 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 cl = repo.changelog
parents = cl.parentrevs 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
changelogrevision = cl.changelogrevision changelogrevision = cl.changelogrevision
# 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.
merge_caches = {} merge_caches = {}
def revinfo(rev): def revinfo(rev):
p1, p2 = parents(rev) p1, p2 = parents(rev)
value = None value = None
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) value = (p1, p2, changelogrevision(rev).changes)
p1copies = c.p1copies
p2copies = c.p2copies
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] = ( merge_caches[rev] = value
p1,
p2,
p1copies,
p2copies,
removed,
get_ismerged(rev),
)
if value is None:
value = (p1, p2, p1copies, p2copies, removed, get_ismerged(rev))
return value return value
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 {}
all_copies = {} all_copies = {}
alwaysmatch = match.always() alwaysmatch = match.always()
for r in revs: for r in revs:
copies = all_copies.pop(r, None) copies = all_copies.pop(r, None)
if copies is None: if copies is None:
# this is a root # this is a root
copies = {} copies = {}
for i, c in enumerate(children[r]): for i, c in enumerate(children[r]):
p1, p2, p1copies, p2copies, removed, ismerged = revinfo(c) p1, p2, changes = revinfo(c)
if r == p1: if r == p1:
parent = 1 parent = 1
childcopies = p1copies childcopies = changes.copied_from_p1
else: else:
assert r == p2 assert r == p2
parent = 2 parent = 2
childcopies = p2copies childcopies = changes.copied_from_p2
if not alwaysmatch: if not alwaysmatch:
childcopies = { childcopies = {
dst: src for dst, src in childcopies.items() if match(dst) dst: src for dst, src in childcopies.items() if match(dst)
} }
newcopies = copies newcopies = copies
if childcopies: if childcopies:
newcopies = copies.copy() newcopies = copies.copy()
for dest, source in pycompat.iteritems(childcopies): for dest, source in pycompat.iteritems(childcopies):
prev = copies.get(source) prev = copies.get(source)
if prev is not None and prev[1] is not None: if prev is not None and prev[1] is not None:
source = prev[1] source = prev[1]
newcopies[dest] = (c, source) newcopies[dest] = (c, source)
assert newcopies is not copies assert newcopies is not copies
for f in removed: for f in changes.removed:
if f in newcopies: if f in newcopies:
if newcopies is copies: if newcopies is copies:
# copy on write to avoid affecting potential other # copy on write to avoid affecting potential other
# branches. when there are no other branches, this # branches. when there are no other branches, this
# could be avoided. # could be avoided.
newcopies = copies.copy() newcopies = copies.copy()
newcopies[f] = (c, None) newcopies[f] = (c, None)
othercopies = all_copies.get(c) othercopies = all_copies.get(c)
if othercopies is None: if othercopies is None:
all_copies[c] = newcopies all_copies[c] = newcopies
else: else:
# we are the second parent to work on c, we need to merge our # we are the second parent to work on c, we need to merge our
# work with the other. # work with the other.
# #
# In case of conflict, parent 1 take precedence over parent 2. # In case of conflict, parent 1 take precedence over parent 2.
# This is an arbitrary choice made anew when implementing # This is an arbitrary choice made anew when implementing
# changeset based copies. It was made without regards with # changeset based copies. It was made without regards with
# potential filelog related behavior. # potential filelog related behavior.
if parent == 1: if parent == 1:
_merge_copies_dict( _merge_copies_dict(
othercopies, newcopies, isancestor, ismerged othercopies, newcopies, isancestor, changes
) )
else: else:
_merge_copies_dict( _merge_copies_dict(
newcopies, othercopies, isancestor, ismerged newcopies, othercopies, isancestor, changes
) )
all_copies[c] = newcopies all_copies[c] = newcopies
final_copies = {} final_copies = {}
for dest, (tt, source) in all_copies[targetrev].items(): for dest, (tt, source) in all_copies[targetrev].items():
if source is not None: if source is not None:
final_copies[dest] = source final_copies[dest] = source
return final_copies return final_copies
def _merge_copies_dict(minor, major, isancestor, ismerged): def _merge_copies_dict(minor, major, isancestor, changes):
"""merge two copies-mapping together, minor and major """merge two copies-mapping together, minor and major
In case of conflict, value from "major" will be picked. In case of conflict, value from "major" will be picked.
- `isancestors(low_rev, high_rev)`: callable return True if `low_rev` is an - `isancestors(low_rev, high_rev)`: callable return True if `low_rev` is an
ancestors of `high_rev`, ancestors of `high_rev`,
- `ismerged(path)`: callable return True if `path` have been merged in the - `ismerged(path)`: callable return True if `path` have been merged in the
current revision, current revision,
""" """
for dest, value in major.items(): for dest, value in major.items():
other = minor.get(dest) other = minor.get(dest)
if other is None: if other is None:
minor[dest] = value minor[dest] = value
else: else:
new_tt = value[0] new_tt = value[0]
other_tt = other[0] other_tt = other[0]
if value[1] == other[1]: if value[1] == other[1]:
continue continue
# content from "major" wins, unless it is older # content from "major" wins, unless it is older
# than the branch point or there is a merge # than the branch point or there is a merge
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 dest in changes.merged
): ):
minor[dest] = value minor[dest] = value
def _revinfo_getter_extra(repo): def _revinfo_getter_extra(repo):
"""return a function that return multiple data given a <rev>"i """return a function that return multiple data given a <rev>"i
* p1: revision number of first parent * p1: revision number of first parent