mercurial/similar.py
author Joerg Sonnenberger <joerg@bec.de>
Mon, 08 Jul 2024 22:46:04 +0200
changeset 51896 8583d138f436
parent 51863 f4733654f144
permissions -rw-r--r--
exchange: improve computation of relevant markers for large repos Compute the candidate nodes with relevant markers directly from keys of the predecessors/successors/children dictionaries of obsstore. This is faster than iterating over all nodes directly. This test could be further improved for repositories with relative few markers compared to the repository size, but this is no longer hot already. With the current loop structure, the obshashrange use works as well as before as it passes lists with a single node. Adjust the interface by allowing revision lists as well as node lists. This helps cases that computes ancestors as it reduces the materialisation cost. Use this in _pushdiscoveryobsmarker and _getbundleobsmarkerpart. Improve the latter further by directly using ancestors(). Performance benchmarks show notable and welcome improvement to no-op push and pull (that would also apply to other push/pull). This apply to push and pull done without evolve. ### push/pull Benchmark parameter # bin-env-vars.hg.flavor = default # benchmark.variants.explicit-rev = none # benchmark.variants.protocol = ssh # benchmark.variants.revs = none ## benchmark.name = hg.command.pull # data-env-vars.name = mercurial-devel-2024-03-22-zstd-sparse-revlog before: 5.968537 seconds after: 5.668507 seconds (-5.03%, -0.30) # data-env-vars.name = tryton-devel-2024-03-22-zstd-sparse-revlog before: 1.446232 seconds after: 0.835553 seconds (-42.23%, -0.61) # data-env-vars.name = netbsd-src-draft-2024-09-19-zstd-sparse-revlog before: 5.777412 seconds after: 2.523454 seconds (-56.32%, -3.25) ## benchmark.name = hg.command.push # data-env-vars.name = mercurial-devel-2024-03-22-zstd-sparse-revlog before: 6.155501 seconds after: 5.885072 seconds (-4.39%, -0.27) # data-env-vars.name = tryton-devel-2024-03-22-zstd-sparse-revlog before: 1.491054 seconds after: 0.934882 seconds (-37.30%, -0.56) # data-env-vars.name = netbsd-src-draft-2024-09-19-zstd-sparse-revlog before: 5.902494 seconds after: 2.957644 seconds (-49.89%, -2.94) There is not notable different in these result using the "rust" flavor instead of the "default". The performance impact on the same operation when using evolve were also tested and no impact was noted.

# similar.py - mechanisms for finding similar files
#
# Copyright 2005-2007 Olivia Mackall <olivia@selenic.com>
#
# 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 annotations

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)