view mercurial/similar.py @ 31210:e1d035905b2e

similar: compare between actual file contents for exact identity

Before this patch, similarity detection logic (for addremove and
automv) depends entirely on SHA-1 digesting. But this causes incorrect
rename detection, if:

  - removing file A and adding file B occur at same committing, and
  - SHA-1 hash values of file A and B are same

This may prevent security experts from managing sample files for
SHAttered issue in Mercurial repository, for example.

  https://security.googleblog.com/2017/02/announcing-first-sha1-collision.html
  https://shattered.it/

Hash collision itself isn't so serious for core repository
functionality of Mercurial, described by mpm as below, though.

  https://www.mercurial-scm.org/wiki/mpm/SHA1

This patch compares between actual file contents after hash comparison
for exact identity.

Even after this patch, SHA-1 is still used, because it is reasonable
enough to quickly detect existence of "(almost) same" file.

  - replacing SHA-1 causes decreasing performance, and
  - replacement of it has ambiguity, yet

Getting content of removed file (= rfctx.data()) at each exact
comparison should be cheap enough, even though getting content of
added one costs much.

  ======= ============== =====================
  file    fctx           data() reads from
  ======= ============== =====================
  removed filectx        in-memory revlog data
  added   workingfilectx storage
  ======= ============== =====================

# 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

import hashlib

from .i18n import _
from . import (
    bdiff,
    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.
    '''
    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,
                         unit=_('files'))
        h = hashlib.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, unit=_('files'))
        adata = fctx.data()
        h = hashlib.sha1(adata).digest()
        if h in hashes:
            rfctx = hashes[h]
            # compare between actual file contents for exact identity
            if adata == rfctx.data():
                yield (rfctx, fctx)

    # Done
    repo.ui.progress(_('searching for exact renames'), None)

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

def _score(fctx, otherdata):
    orig, lines = otherdata
    text = fctx.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

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 = {}
    for i, r in enumerate(removed):
        repo.ui.progress(_('searching for similar files'), i,
                         total=len(removed), unit=_('files'))

        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)
    repo.ui.progress(_('searching'), None)

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

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)