view mercurial/similar.py @ 51594:e3a5ec2d236a

outgoing: rework the handling of the `missingroots` case to be faster

The previous implementation was slow, to the point it was taking a significant
amount of `hg bundle --type none-streamv2` call. We rework the code to compute
the same value much faster, making the operation disappear from the `hg bundle
--type none-streamv2` profile. Someone would remark that producing a streamclone
does not requires an `outgoing` object. However that is a matter for another
day. There is other user of `missingroots` (non stream `hg bundle` call for
example), and they will also benefit from this rework.

We implement an old TODO in the process, directly computing the missing and
common attribute as we have most element at hand already.

### benchmark.name                = hg.command.bundle
  # bin-env-vars.hg.flavor        = default
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.revs       = all
  # benchmark.variants.type       = none-streamv2
 ## data-env-vars.name            = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 7.750458
after:  6.665565  (-14.00%, -1.08)
 ## data-env-vars.name            = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 0.700229
after:  0.496050  (-29.16%, -0.20)
 ## data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 346.508952
after:  316.749699  (-8.59%, -29.76)
 ## data-env-vars.name            = pypy-2024-03-22-zstd-sparse-revlog
before: 3.401700
after:  2.915810  (-14.28%, -0.49)
 ## data-env-vars.name            = tryton-public-2024-03-22-zstd-sparse-revlog
before: 1.870798
after:  1.461583  (-21.87%, -0.41)



note: this whole `missingroots` of outgoing has a limited number of callers and
could likely be replace by something simpler (like taking an explicit
"missing_revs" set for example). However this is a wider change and we focus on
a small impact, quick rework that does not change the API for now.

# similar.py - mechanisms for finding similar files
#
# Copyright 2005-2007 Olivia 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 _
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(
        _(b'searching for exact renames'),
        total=(len(added) + len(removed)),
        unit=_(b'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(
        _(b'searching for similar files'), unit=_(b'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.items():
        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)