view mercurial/similar.py @ 23575:a2f139d25845

subrepo: drop the 'ui' parameter to archive()

The current state of subrepo methods is to pass a 'ui' object to some methods,
which has the effect of overriding the subrepo configuration since it is the
root repo's 'ui' that is passed along as deep as there are subrepos.  Other
subrepo method are *not* passed the root 'ui', and instead delegate to their
repo object's 'ui'.  Even in the former case where the root 'ui' is available,
some methods are inconsistent in their use of both the root 'ui' and the local
repo's 'ui'.  (Consider hg._incoming() uses the root 'ui' for path expansion
and some status messages, but also calls bundlerepo.getremotechanges(), which
eventually calls discovery.findcommonincoming(), which calls
setdiscovery.findcommonheads(), which calls status() on the local repo 'ui'.)

This inconsistency with respect to the configured output level is probably
always hidden, because --verbose, --debug and --quiet, along with their 'ui.xxx'
equivalents in the global and user level hgrc files are propagated from the
parent repo to the subrepo via 'baseui'.  The 'ui.xxx' settings in the parent
repo hgrc file are not propagated, but that seems like an unusual thing to set
on a per repo config file.  Any 'ui.xxx' options changed by --config are also
not propagated, because they are set on repo.ui by dispatch.py, not repo.baseui.

The goal here is to cleanup the subrepo methods by dropping the 'ui' parameter,
which in turn prevents mixing subtly different 'ui' instances on a given subrepo
level.  Some methods use more than just the output level settings in 'ui' (add
for example ends up calling scmutil.checkportabilityalert() with both the root
and local repo's 'ui' at different points).  This series just goes for the low
hanging fruit and switches methods that only use the output level.

If we really care about not letting a subrepo config override the root repo's
output level, we can propagate the verbose, debug and quiet settings to the
subrepo in the same way 'ui.commitsubrepos' is in hgsubrepo.__init__.

Archive only uses the 'ui' object to call its progress() method, and gitsubrepo
calls status().

# 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)