merge: introduce new format for the state file
This new format will allow us to address common bugs while doing special merge
(graft, backout, rebaseā¦) and record user choice during conflict resolution.
The format is open so we can add more record for future usage.
This file still store hexified version of node to help human willing to debug
it by hand. The overhead or oversize are not expected be an issue.
The old format is still used. It will be written to disk along side the newer
format. And at parse time we detect if the data from old version of the
mergestate are different from the one in the new version file. If its the same,
both have most likely be written at the same time and you can trust the extra
data from the new file. If it differs, the old file have been written by an
older version of mercurial that did not knew about the new file. In that case we
use the content of the old file.
# similar.py - mechanisms for finding similar files
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import _
import util
import mdiff
import bdiff
def _findexactmatches(repo, added, removed):
'''find renamed files that have no changes
Takes a list of new filectxs and a list of removed filectxs, and yields
(before, after) tuples of exact matches.
'''
numfiles = len(added) + len(removed)
# Get hashes of removed files.
hashes = {}
for i, fctx in enumerate(removed):
repo.ui.progress(_('searching for exact renames'), i, total=numfiles)
h = util.sha1(fctx.data()).digest()
hashes[h] = fctx
# For each added file, see if it corresponds to a removed file.
for i, fctx in enumerate(added):
repo.ui.progress(_('searching for exact renames'), i + len(removed),
total=numfiles)
h = util.sha1(fctx.data()).digest()
if h in hashes:
yield (hashes[h], fctx)
# Done
repo.ui.progress(_('searching for exact renames'), None)
def _findsimilarmatches(repo, added, removed, threshold):
'''find potentially renamed files based on similar file content
Takes a list of new filectxs and a list of removed filectxs, and yields
(before, after, score) tuples of partial matches.
'''
copies = {}
for i, r in enumerate(removed):
repo.ui.progress(_('searching for similar files'), i,
total=len(removed))
# lazily load text
@util.cachefunc
def data():
orig = r.data()
return orig, mdiff.splitnewlines(orig)
def score(text):
orig, lines = data()
# bdiff.blocks() returns blocks of matching lines
# count the number of bytes in each
equal = 0
matches = bdiff.blocks(text, orig)
for x1, x2, y1, y2 in matches:
for line in lines[y1:y2]:
equal += len(line)
lengths = len(text) + len(orig)
return equal * 2.0 / lengths
for a in added:
bestscore = copies.get(a, (None, threshold))[1]
myscore = score(a.data())
if myscore >= bestscore:
copies[a] = (r, myscore)
repo.ui.progress(_('searching'), None)
for dest, v in copies.iteritems():
source, score = v
yield source, dest, score
def findrenames(repo, added, removed, threshold):
'''find renamed files -- yields (before, after, score) tuples'''
parentctx = repo['.']
workingctx = repo[None]
# Zero length files will be frequently unrelated to each other, and
# tracking the deletion/addition of such a file will probably cause more
# harm than good. We strip them out here to avoid matching them later on.
addedfiles = set([workingctx[fp] for fp in added
if workingctx[fp].size() > 0])
removedfiles = set([parentctx[fp] for fp in removed
if fp in parentctx and parentctx[fp].size() > 0])
# Find exact matches.
for (a, b) in _findexactmatches(repo,
sorted(addedfiles), sorted(removedfiles)):
addedfiles.remove(b)
yield (a.path(), b.path(), 1.0)
# If the user requested similar files to be matched, search for them also.
if threshold < 1.0:
for (a, b, score) in _findsimilarmatches(repo,
sorted(addedfiles), sorted(removedfiles), threshold):
yield (a.path(), b.path(), score)