This is an archive of the discontinued Mercurial Phabricator instance.

Differential D6954

sidedatacopies: move various copies related function to the copies modules
ClosedPublic

Authored by marmoute on Oct 3 2019, 1:55 AM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG54e943b28101: sidedatacopies: move various copies related function to the copies modules
Summary

We will need to access these logic form the copies module. So we move them from
their higher level module to the lower level copies module. We cannot use them
from their top level module as it would create cycles.

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.Oct 3 2019, 1:55 AM
marmoute updated this revision to Diff 16955.Oct 7 2019, 8:38 PM
marmoute updated this revision to Diff 17009.Oct 9 2019, 5:31 PM
marmoute updated this revision to Diff 17024.Oct 9 2019, 6:43 PM
marmoute added a commit: rHG54e943b28101: sidedatacopies: move various copies related function to the copies modules.Oct 9 2019, 7:47 PM
This revision was not accepted when it landed; it landed in state Needs Review.
Closed by commit rHG54e943b28101: sidedatacopies: move various copies related function to the copies modules (authored by marmoute). · Explain Why
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/changelog.py (72 lines)
Mmercurial/context.py (4 lines)
Mmercurial/copies.py (76 lines)
Mmercurial/scmutil.py (20 lines)

Diff 17028

mercurial/changelog.py

from .node import ( from .node import (
bin, bin,
hex, hex,
nullid, nullid,
) )
from .thirdparty import attr from .thirdparty import attr
from . import ( from . import (
copies,
encoding, encoding,
error, error,
pycompat, pycompat,
revlog, revlog,
util, util,
) )
from .utils import ( from .utils import (
dateutil, dateutil,
# keys must be sorted to produce a deterministic changelog entry # keys must be sorted to produce a deterministic changelog entry
items = [ items = [
_string_escape(b'%s:%s' % (k, pycompat.bytestr(d[k]))) _string_escape(b'%s:%s' % (k, pycompat.bytestr(d[k])))
for k in sorted(d) for k in sorted(d)
] ]
return b"\0".join(items) return b"\0".join(items)
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
def stripdesc(desc): def stripdesc(desc):
"""strip trailing whitespace and leading and trailing empty lines""" """strip trailing whitespace and leading and trailing empty lines"""
return b'\n'.join([l.rstrip() for l in desc.splitlines()]).strip(b'\n') return b'\n'.join([l.rstrip() for l in desc.splitlines()]).strip(b'\n')
class appender(object): class appender(object):
'''the changelog index must be updated last on disk, so we use this class '''the changelog index must be updated last on disk, so we use this class
to delay writes to it''' to delay writes to it'''
@property @property
def filesadded(self): def filesadded(self):
if sidedatamod.SD_FILESADDED in self._sidedata: if sidedatamod.SD_FILESADDED in self._sidedata:
rawindices = self._sidedata.get(sidedatamod.SD_FILESADDED) rawindices = self._sidedata.get(sidedatamod.SD_FILESADDED)
else: else:
rawindices = self.extra.get(b'filesadded') rawindices = self.extra.get(b'filesadded')
if rawindices is None: if rawindices is None:
return None return None
return decodefileindices(self.files, rawindices) return copies.decodefileindices(self.files, rawindices)
@property @property
def filesremoved(self): def filesremoved(self):
if sidedatamod.SD_FILESREMOVED in self._sidedata: if sidedatamod.SD_FILESREMOVED in self._sidedata:
rawindices = self._sidedata.get(sidedatamod.SD_FILESREMOVED) rawindices = self._sidedata.get(sidedatamod.SD_FILESREMOVED)
else: else:
rawindices = self.extra.get(b'filesremoved') rawindices = self.extra.get(b'filesremoved')
if rawindices is None: if rawindices is None:
return None return None
return decodefileindices(self.files, rawindices) return copies.decodefileindices(self.files, rawindices)
@property @property
def p1copies(self): def p1copies(self):
if sidedatamod.SD_P1COPIES in self._sidedata: if sidedatamod.SD_P1COPIES in self._sidedata:
rawcopies = self._sidedata.get(sidedatamod.SD_P1COPIES) rawcopies = self._sidedata.get(sidedatamod.SD_P1COPIES)
else: else:
rawcopies = self.extra.get(b'p1copies') rawcopies = self.extra.get(b'p1copies')
if rawcopies is None: if rawcopies is None:
return None return None
return decodecopies(self.files, rawcopies) return copies.decodecopies(self.files, rawcopies)
@property @property
def p2copies(self): def p2copies(self):
if sidedatamod.SD_P2COPIES in self._sidedata: if sidedatamod.SD_P2COPIES in self._sidedata:
rawcopies = self._sidedata.get(sidedatamod.SD_P2COPIES) rawcopies = self._sidedata.get(sidedatamod.SD_P2COPIES)
else: else:
rawcopies = self.extra.get(b'p2copies') rawcopies = self.extra.get(b'p2copies')
if rawcopies is None: if rawcopies is None:
return None return None
return decodecopies(self.files, rawcopies) return copies.decodecopies(self.files, rawcopies)
@property @property
def description(self): def description(self):
return encoding.tolocal(self._text[self._offsets[3] + 2 :]) return encoding.tolocal(self._text[self._offsets[3] + 2 :])
class changelog(revlog.revlog): class changelog(revlog.revlog):
def __init__(self, opener, trypending=False): def __init__(self, opener, trypending=False):
for name in ( for name in (
b'p1copies', b'p1copies',
b'p2copies', b'p2copies',
b'filesadded', b'filesadded',
b'filesremoved', b'filesremoved',
): ):
extra.pop(name, None) extra.pop(name, None)
if p1copies is not None: if p1copies is not None:
p1copies = encodecopies(sortedfiles, p1copies) p1copies = copies.encodecopies(sortedfiles, p1copies)
if p2copies is not None: if p2copies is not None:
p2copies = encodecopies(sortedfiles, p2copies) p2copies = copies.encodecopies(sortedfiles, p2copies)
if filesadded is not None: if filesadded is not None:
filesadded = encodefileindices(sortedfiles, filesadded) filesadded = copies.encodefileindices(sortedfiles, filesadded)
if filesremoved is not None: if filesremoved is not None:
filesremoved = encodefileindices(sortedfiles, filesremoved) filesremoved = copies.encodefileindices(sortedfiles, filesremoved)
if self._copiesstorage == b'extra': if self._copiesstorage == b'extra':
extrasentries = p1copies, p2copies, filesadded, filesremoved extrasentries = p1copies, p2copies, filesadded, filesremoved
if extra is None and any(x is not None for x in extrasentries): if extra is None and any(x is not None for x in extrasentries):
extra = {} extra = {}
if p1copies is not None: if p1copies is not None:
extra[b'p1copies'] = p1copies extra[b'p1copies'] = p1copies
if p2copies is not None: if p2copies is not None:
extra[b'p2copies'] = p2copies extra[b'p2copies'] = p2copies

mercurial/context.py

source = self._repo.ui.config(b'experimental', b'copies.read-from') source = self._repo.ui.config(b'experimental', b'copies.read-from')
if source == b'changeset-only': if source == b'changeset-only':
compute_on_none = False compute_on_none = False
elif source != b'compatibility': elif source != b'compatibility':
# filelog mode, ignore any changelog content # filelog mode, ignore any changelog content
filesadded = None filesadded = None
if filesadded is None: if filesadded is None:
if compute_on_none: if compute_on_none:
filesadded = scmutil.computechangesetfilesadded(self) filesadded = copies.computechangesetfilesadded(self)
else: else:
filesadded = [] filesadded = []
return filesadded return filesadded
def filesremoved(self): def filesremoved(self):
filesremoved = self._changeset.filesremoved filesremoved = self._changeset.filesremoved
compute_on_none = True compute_on_none = True
if self._repo.filecopiesmode == b'changeset-sidedata': if self._repo.filecopiesmode == b'changeset-sidedata':
compute_on_none = False compute_on_none = False
else: else:
source = self._repo.ui.config(b'experimental', b'copies.read-from') source = self._repo.ui.config(b'experimental', b'copies.read-from')
if source == b'changeset-only': if source == b'changeset-only':
compute_on_none = False compute_on_none = False
elif source != b'compatibility': elif source != b'compatibility':
# filelog mode, ignore any changelog content # filelog mode, ignore any changelog content
filesremoved = None filesremoved = None
if filesremoved is None: if filesremoved is None:
if compute_on_none: if compute_on_none:
filesremoved = scmutil.computechangesetfilesremoved(self) filesremoved = copies.computechangesetfilesremoved(self)
else: else:
filesremoved = [] filesremoved = []
return filesremoved return filesremoved
@propertycache @propertycache
def _copies(self): def _copies(self):
p1copies = self._changeset.p1copies p1copies = self._changeset.p1copies
p2copies = self._changeset.p2copies p2copies = self._changeset.p2copies

mercurial/copies.py

# copies.py - copy detection for Mercurial # copies.py - copy detection for Mercurial
# #
# Copyright 2008 Matt Mackall <mpm@selenic.com> # Copyright 2008 Matt Mackall <mpm@selenic.com>
# #
# 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 from __future__ import absolute_import
import collections import collections
import heapq import heapq
import os import os
from .i18n import _ from .i18n import _
from . import ( from . import (
error,
match as matchmod, match as matchmod,
node, node,
pathutil, pathutil,
pycompat, pycompat,
util, util,
) )
from .utils import stringutil from .utils import stringutil
exclude = pathcopies(repo[fromrev], repo[skiprev]) exclude = pathcopies(repo[fromrev], repo[skiprev])
for dst, src in pycompat.iteritems(pathcopies(repo[fromrev], repo[rev])): for dst, src in pycompat.iteritems(pathcopies(repo[fromrev], repo[rev])):
if dst in exclude: if dst in exclude:
continue continue
if dst in wctx: if dst in wctx:
wctx[dst].markcopied(src) wctx[dst].markcopied(src)
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 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)
return removed
def computechangesetcopies(ctx): def computechangesetcopies(ctx):
"""return the copies data for a changeset """return the copies data for a changeset
The copies data are returned as a pair of dictionnary (p1copies, p2copies). The copies data are returned as a pair of dictionnary (p1copies, p2copies).
Each dictionnary are in the form: `{newname: oldname}` Each dictionnary are in the form: `{newname: oldname}`
""" """
p1copies = {} p1copies = {}
p2copies = {} p2copies = {}
p1 = ctx.p1() p1 = ctx.p1()
p2 = ctx.p2() p2 = ctx.p2()
narrowmatch = ctx._repo.narrowmatch() narrowmatch = ctx._repo.narrowmatch()
for dst in ctx.files(): for dst in ctx.files():
if not narrowmatch(dst) or dst not in ctx: if not narrowmatch(dst) or dst not in ctx:
continue continue
copied = ctx[dst].renamed() copied = ctx[dst].renamed()
if not copied: if not copied:
continue continue
src, srcnode = copied src, srcnode = copied
if src in p1 and p1[src].filenode() == srcnode: if src in p1 and p1[src].filenode() == srcnode:
p1copies[dst] = src p1copies[dst] = src
elif src in p2 and p2[src].filenode() == srcnode: elif src in p2 and p2[src].filenode() == srcnode:
p2copies[dst] = src p2copies[dst] = src
return p1copies, p2copies 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

mercurial/scmutil.py

return repo.revs( return repo.revs(
b"ancestors(bookmark(%s)) - " b"ancestors(bookmark(%s)) - "
b"ancestors(head() and not bookmark(%s)) - " b"ancestors(head() and not bookmark(%s)) - "
b"ancestors(bookmark() and not bookmark(%s))", b"ancestors(bookmark() and not bookmark(%s))",
mark, mark,
mark, mark,
mark, mark,
) )
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 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)
return removed