annotate mercurial/similar.py @ 16719:e7bf09acd410

localrepo: add branchtip() method for faster single-branch lookups

For the PyPy repo with 744 branches and 843 branch heads, this brings
hg log -r default over NFS from:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
        3249            0      1.3222      1.3222   <open>
        3244            0      0.6211      0.6211   <method 'close' of 'file' objects>
        3243            0      0.0800      0.0800   <method 'read' of 'file' objects>
        3241            0      0.0660      0.0660   <method 'seek' of 'file' objects>
        3905            0      0.0476      0.0476   <zlib.decompress>
        3281            0      2.6756      0.0472   mercurial.changelog:182(read)
       +3281            0      2.5256      0.0453   +mercurial.revlog:881(revision)
       +3276            0      0.0389      0.0196   +mercurial.changelog:28(decodeextra)
       +6562            0      0.0123      0.0123   +<method 'split' of 'str' objects>
       +6562            0      0.0408      0.0073   +mercurial.encoding:61(tolocal)
       +3281            0      0.0054      0.0054   +<method 'index' of 'str' objects>
        3241            0      2.2464      0.0456   mercurial.revlog:818(_loadchunk)
       +3241            0      0.6205      0.6205   +<method 'close' of 'file' objects>
       +3241            0      0.0765      0.0765   +<method 'read' of 'file' objects>
       +3241            0      0.0660      0.0660   +<method 'seek' of 'file' objects>
       +3241            0      1.4209      0.0135   +mercurial.store:374(__call__)
       +3241            0      0.0122      0.0107   +mercurial.revlog:810(_addchunk)
        3281            0      2.5256      0.0453   mercurial.revlog:881(revision)
       +3280            0      0.0175      0.0175   +mercurial.revlog:305(rev)
       +3281            0      2.2819      0.0119   +mercurial.revlog:847(_chunkraw)
       +3281            0      0.0603      0.0083   +mercurial.revlog:945(_checkhash)
       +3281            0      0.0051      0.0051   +mercurial.revlog:349(flags)
       +3281            0      0.0040      0.0040   +<mercurial.mpatch.patches>
       13682            0      0.0479      0.0248   <method 'decode' of 'str' objects>
       +7418            0      0.0228      0.0076   +encodings.utf_8:15(decode)
          +1            0      0.0003      0.0000   +encodings:71(search_function)
        3248            0      1.3995      0.0246   mercurial.scmutil:218(__call__)
       +3248            0      1.3222      1.3222   +<open>
       +3248            0      0.0235      0.0184   +os.path:80(split)
       +3248            0      0.0084      0.0068   +mercurial.scmutil:92(__call__)
Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000)

down to:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
          55           31      0.0197      0.0163   <__import__>
          +1            0      0.0006      0.0002   +mercurial.context:8(<module>)
          +1            0      0.0042      0.0001   +mercurial.revlog:12(<module>)
          +1            0      0.0002      0.0001   +mercurial.match:8(<module>)
          +1            0      0.0003      0.0001   +mercurial.dirstate:7(<module>)
          +1            0      0.0057      0.0001   +mercurial.changelog:8(<module>)
           1            0      0.0117      0.0032   mercurial.localrepo:525(_readbranchcache)
        +844            0      0.0015      0.0015   +<binascii.unhexlify>
        +845            0      0.0010      0.0010   +<method 'split' of 'str' objects>
        +843            0      0.0045      0.0009   +mercurial.encoding:61(tolocal)
        +843            0      0.0004      0.0004   +<method 'setdefault' of 'dict' objects>
          +1            0      0.0003      0.0003   +<method 'close' of 'file' objects>
           3            0      0.0029      0.0029   <method 'read' of 'file' objects>
           9            0      0.0018      0.0018   <open>
         990            0      0.0017      0.0017   <binascii.unhexlify>
          53            0      0.0016      0.0016   mercurial.demandimport:43(__init__)
         862            0      0.0015      0.0015   <_codecs.utf_8_decode>
         862            0      0.0037      0.0014   <method 'decode' of 'str' objects>
        +862            0      0.0023      0.0008   +encodings.utf_8:15(decode)
         981            0      0.0011      0.0011   <method 'split' of 'str' objects>
         861            0      0.0046      0.0009   mercurial.encoding:61(tolocal)
        +861            0      0.0037      0.0014   +<method 'decode' of 'str' objects>
         862            0      0.0023      0.0008   encodings.utf_8:15(decode)
        +862            0      0.0015      0.0015   +<_codecs.utf_8_decode>
           4            0      0.0008      0.0008   <method 'close' of 'file' objects>
         179          154      0.0202      0.0004   mercurial.demandimport:83(__getattribute__)
         +36           11      0.0199      0.0003   +mercurial.demandimport:55(_load)
         +72            0      0.0001      0.0001   +mercurial.demandimport:83(__getattribute__)
         +36            0      0.0000      0.0000   +<getattr>
           1            0      0.0015      0.0004   mercurial.tags:148(_readtagcache)
Time: real 0.060 secs (user 0.030+0.000 sys 0.010+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)