view mercurial/similar.py @ 20528:1a9ebc83a74c

win32: improve the performance of win32.unlink() over CIFS

Emulating POSIX unlink() behavior with os.rename() and os.unlink() is often slow
especially over CIFS from Windows clients due to its protocol overhead. This
patch changes win32.unlink() to try first an exclusive open with the Win32
delete-on-close flag, and if a sharing violation is detected, to fall back to
the original emulation.

This patch also removes a test with os.path.isdir() since we expect opening a
directory shall fail as os.unlink() would.

Example measurements (repeated 3-times after 1-time calibration):

(Without this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 19.871 secs (user 0.328+0.000 sys 1.794+0.000)
time: real 19.622 secs (user 0.312+0.000 sys 2.044+0.000)
time: real 19.138 secs (user 0.250+0.000 sys 1.872+0.000)

(Without this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 35.158 secs (user 0.156+0.000 sys 2.512+0.000)
time: real 35.272 secs (user 0.250+0.000 sys 2.512+0.000)
time: real 36.569 secs (user 0.203+0.000 sys 2.387+0.000)

(With this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 17.893 secs (user 0.328+0.000 sys 1.700+0.000)
time: real 18.512 secs (user 0.265+0.000 sys 1.529+0.000)
time: real 20.238 secs (user 0.312+0.000 sys 1.685+0.000)

(With this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 12.312 secs (user 0.250+0.000 sys 0.811+0.000)
time: real 12.471 secs (user 0.156+0.000 sys 0.889+0.000)
time: real 9.727 secs (user 0.125+0.000 sys 0.858+0.000)

# 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)