view mercurial/similar.py @ 39872:733db72f0f54

revlog: move revision verification out of verify

File revision verification is performing low-level checks of file
storage, namely that flags are appropriate and revision data can
be resolved.

Since these checks are somewhat revlog-specific and may not
be appropriate for alternate storage backends, this commit moves
those checks from verify.py to revlog.py.

Because we're now emitting warnings/errors that apply to specific
revisions, we taught the iverifyproblem interface to expose the
problematic node and to report this node in verify output. This
was necessary to prevent unwanted test changes.

After this change, revlog.verifyintegrity() and file verify code
in verify.py both iterate over revisions and resolve their fulltext.
But they do so in separate loops. (verify.py needs to resolve
fulltexts as part of calling renamed() - at least when using revlogs.)
This should add overhead.

But on the mozilla-unified repo:

$ hg verify
before: time: real 700.640 secs (user 585.520+0.000 sys 23.480+0.000)
after:  time: real 682.380 secs (user 570.370+0.000 sys 22.240+0.000)

I'm not sure what's going on. Maybe avoiding the filelog attribute
proxies shaved off enough time to offset the losses? Maybe fulltext
resolution has less overhead than I thought?

I've left a comment indicating the potential for optimization. But
because it doesn't produce a performance regression on a large
repository, I'm not going to worry about it.

Differential Revision: https://phab.mercurial-scm.org/D4745

# 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

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

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.
    '''
    # Build table of removed files: {hash(fctx.data()): [fctx, ...]}.
    # We use hash() to discard fctx.data() from memory.
    hashes = {}
    progress = repo.ui.makeprogress(_('searching for exact renames'),
                                    total=(len(added) + len(removed)),
                                    unit=_('files'))
    for fctx in removed:
        progress.increment()
        h = hash(fctx.data())
        if h not in hashes:
            hashes[h] = [fctx]
        else:
            hashes[h].append(fctx)

    # For each added file, see if it corresponds to a removed file.
    for fctx in added:
        progress.increment()
        adata = fctx.data()
        h = hash(adata)
        for rfctx in hashes.get(h, []):
            # compare between actual file contents for exact identity
            if adata == rfctx.data():
                yield (rfctx, fctx)
                break

    # Done
    progress.complete()

def _ctxdata(fctx):
    # lazily load text
    orig = fctx.data()
    return orig, mdiff.splitnewlines(orig)

def _score(fctx, otherdata):
    orig, lines = otherdata
    text = fctx.data()
    # mdiff.blocks() returns blocks of matching lines
    # count the number of bytes in each
    equal = 0
    matches = mdiff.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

def score(fctx1, fctx2):
    return _score(fctx1, _ctxdata(fctx2))

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 = {}
    progress = repo.ui.makeprogress(_('searching for similar files'),
                         unit=_('files'), total=len(removed))
    for r in removed:
        progress.increment()
        data = None
        for a in added:
            bestscore = copies.get(a, (None, threshold))[1]
            if data is None:
                data = _ctxdata(r)
            myscore = _score(a, data)
            if myscore > bestscore:
                copies[a] = (r, myscore)
    progress.complete()

    for dest, v in copies.iteritems():
        source, bscore = v
        yield source, dest, bscore

def _dropempty(fctxs):
    return [x for x in fctxs if x.size() > 0]

def findrenames(repo, added, removed, threshold):
    '''find renamed files -- yields (before, after, score) tuples'''
    wctx = repo[None]
    pctx = wctx.p1()

    # 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 = _dropempty(wctx[fp] for fp in sorted(added))
    removedfiles = _dropempty(pctx[fp] for fp in sorted(removed) if fp in pctx)

    # Find exact matches.
    matchedfiles = set()
    for (a, b) in _findexactmatches(repo, addedfiles, removedfiles):
        matchedfiles.add(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:
        addedfiles = [x for x in addedfiles if x not in matchedfiles]
        for (a, b, score) in _findsimilarmatches(repo, addedfiles,
                                                 removedfiles, threshold):
            yield (a.path(), b.path(), score)