view mercurial/similar.py @ 30308:d500ddae7494

bdiff: don't check border condition in loop

`plast = a + len - 1`. So, this "for" loop iterates from "a" to "plast",
inclusive. So, `p == plast` can only be true on the final iteration
of the loop. So checking for it on every loop iteration is wasteful.

This patch simply decreases the upper bound of the loop by 1 and
adds an explicit check after iteration for the `p == plast` case.
We can't simply add 1 to the initial value for "i" because that
doesn't do the correct thing on empty input strings.

`perfbdiff -m 3041e4d59df2` on the Firefox repo becomes significantly
faster:

! wall 0.072763 comb 0.070000 user 0.070000 sys 0.000000 (best of 100)
! wall 0.053221 comb 0.060000 user 0.060000 sys 0.000000 (best of 100)

For the curious, this code has its origins in 8b067bde6679, which is
the changeset that introduced bdiff.c in 2005.

Also, GNU diffutils is able to perform a similar line-based diff in
under 20ms. So there's likely more perf wins to be found in this code.
One of them is the hashing algorithm. But it looks like mpm spent
some time testing hash collisions in d0c48891dd4a. I'd like to do the
same before switching away from lyhash, just to be on the safe side.

# 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 __future__ import absolute_import

import hashlib

from .i18n import _
from . import (
    bdiff,
    mdiff,
    util,
)

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,
                         unit=_('files'))
        h = hashlib.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, unit=_('files'))
        h = hashlib.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), unit=_('files'))

        # 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)