view mercurial/similar.py @ 44477:ad718271a9eb

git: skeleton of a new extension to _directly_ operate on git repos

This is based in part of work I did years ago in hgit, but it's mostly
new code since I'm using pygit2 instead of dulwich and the hg storage
interfaces have improved. Some cleanup of old hgit code by Pulkit,
which I greatly appreciate.

test-git-interop.t does not cover a whole lot of cases, but it
passes. It includes status, diff, making a new commit, and `hg annotate`
working on the git repository.

This is _not_ (yet) production quality code: this is an
experiment. Known technical debt lurking in this implementation:

 * Writing bookmarks just totally ignores transactions.
 * The way progress is threaded down into the gitstore is awful.
 * Ideally we'd find a way to incrementally reindex DAGs. I'm not sure
   how to do that efficiently, so we might need a "known only fast-forwards"
   mode on the DAG indexer for use on `hg commit` and friends.
 * We don't even _try_ to do anything reasonable for `hg pull` or `hg push`.
 * Mercurial need an interface for the changelog type.

Tests currently require git 2.24 as far as I'm aware: `git status` has
some changed output that I didn't try and handle in a compatible way.

This patch has produced some interesting cleanups, most recently on
the manifest type. I expect continuing down this road will produce
other meritorious cleanups throughout our code.

Differential Revision: https://phab.mercurial-scm.org/D6734

# 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,
    pycompat,
)


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 pycompat.iteritems(copies):
        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)