view mercurial/similar.py @ 20294:243ea5ffdf31

diff: search beyond ancestor when detecting renames

This removes an optimization that was introduced in 91eb4512edd0 but was too
aggressive - as indicated by how it changed test-mq-merge.t .

We are walking filelogs to find copy sources and we can thus not be sure to hit
the base revision and find the renamed file there - it could also be in the
first ancestor of the base ... in the filelog.

We are walking the filelog and can thus not easily know when we hit the first
ancestor of the base revision and which filename to look for there. Instead, we
use _findlimit like mergecopies do: The lower bound for how far we have to go
is found from the lowest changelog revision that is an ancestor of only one of
the compared revisions. Any filelog ancestor with a revision number lower than
that revision will be the ancestor of both compared revisions, and there is
thus no reason to go further back than that.

# similar.py - mechanisms for finding similar files
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# 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)