This is an archive of the discontinued Mercurial Phabricator instance.

Differential D8588

files: extract code for extra filtering of the `removed` entry into copies
ClosedPublic

Authored by marmoute on May 27 2020, 9:17 AM.

Details

Reviewers
durin42
pulkit
Group Reviewers
hg-reviewers
Commits
rHGedd08aa193fb: files: extract code for extra filtering of the `removed` entry into copies
Summary

We want to reduce the set of removed files that to the set of files actually
removed. That removed set is used as of the changeset centric algorithm,
having smaller sets means less processing and faster computation.

In this changeset we extract the code to be a function of it own. We will make
use of it in the next changesets.

Diff Detail

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

Revision Contents
Changeset List

PathPackages
Mmercurial/localrepo.py (48 lines)
Mmercurial/metadata.py (56 lines)

Diff 21546

mercurial/localrepo.py

exchange, exchange,
extensions, extensions,
filelog, filelog,
hook, hook,
lock as lockmod, lock as lockmod,
match as matchmod, match as matchmod,
merge as mergemod, merge as mergemod,
mergeutil, mergeutil,
metadata,
namespaces, namespaces,
narrowspec, narrowspec,
obsolete, obsolete,
pathutil, pathutil,
phases, phases,
pushkey, pushkey,
pycompat, pycompat,
rcutil, rcutil,
raise raise
# update manifest # update manifest
removed = [f for f in removed if f in m1 or f in m2] removed = [f for f in removed if f in m1 or f in m2]
drop = sorted([f for f in removed if f in m]) drop = sorted([f for f in removed if f in m])
for f in drop: for f in drop:
del m[f] del m[f]
if p2.rev() != nullrev: if p2.rev() != nullrev:
rf = metadata.get_removal_filter(ctx, (p1, p2, m1, m2))
@util.cachefunc removed = [f for f in removed if not rf(f)]
def mas():
p1n = p1.node()
p2n = p2.node()
cahs = self.changelog.commonancestorsheads(p1n, p2n)
if not cahs:
cahs = [nullrev]
return [self[r].manifest() for r in cahs]
def deletionfromparent(f):
# 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 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
removed = [f for f in removed if not deletionfromparent(f)]
files = changed + removed files = changed + removed
md = None md = None
if not files: if not files:
# if no "files" actually changed in terms of the changelog, # if no "files" actually changed in terms of the changelog,
# try hard to detect unmodified manifest entry so that the # try hard to detect unmodified manifest entry so that the
# exact same commit can be reproduced later on convert. # exact same commit can be reproduced later on convert.
md = m1.diff(m, scmutil.matchfiles(self, ctx.files())) md = m1.diff(m, scmutil.matchfiles(self, ctx.files()))

mercurial/metadata.py

# metadata.py -- code related to various metadata computation and access. # metadata.py -- code related to various metadata computation and access.
# #
# Copyright 2019 Google, Inc <martinvonz@google.com> # Copyright 2019 Google, Inc <martinvonz@google.com>
# Copyright 2020 Pierre-Yves David <pierre-yves.david@octobus.net> # Copyright 2020 Pierre-Yves David <pierre-yves.david@octobus.net>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function from __future__ import absolute_import, print_function
import multiprocessing import multiprocessing
from . import ( from . import (
error, error,
node,
pycompat, pycompat,
util, util,
) )
from .revlogutils import ( from .revlogutils import (
flagutil as sidedataflag, flagutil as sidedataflag,
sidedata as sidedatamod, sidedata as sidedatamod,
) )
def computechangesetfilesadded(ctx): def computechangesetfilesadded(ctx):
"""return the list of files added in a changeset """return the list of files added in a changeset
""" """
added = [] added = []
for f in ctx.files(): for f in ctx.files():
if not any(f in p for p in ctx.parents()): if not any(f in p for p in ctx.parents()):
added.append(f) added.append(f)
return added 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 = [node.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): def computechangesetfilesremoved(ctx):
"""return the list of files removed in a changeset """return the list of files removed in a changeset
""" """
removed = [] removed = []
for f in ctx.files(): for f in ctx.files():
if f not in ctx: if f not in ctx:
removed.append(f) removed.append(f)
return removed return removed