view mercurial/similar.py @ 29196:bf7b8157c483 stable

strip: invalidate phase cache after stripping changeset (issue5235)

When we remove a changeset from the changelog, the phase cache must be
invalidated, otherwise it could refer to changesets that are no longer in the
repo.

To reproduce the failure, I created an extension querying the phase cache after
the strip transaction is over.

To do that, I stripped two commits with a bookmark on one of them to force
another transaction (we open a transaction for moving bookmarks)
after the strip transaction.

Without the fix in this patch, the test leads to a stacktrace showing the issue:
      repair.strip(ui, repo, revs, backup)
    File "/Users/lcharignon/facebook-hg-rpms/hg-crew/mercurial/repair.py", line 205, in strip
      tr.close()
    File "/Users/lcharignon/facebook-hg-rpms/hg-crew/mercurial/transaction.py", line 44, in _active
      return func(self, *args, **kwds)
    File "/Users/lcharignon/facebook-hg-rpms/hg-crew/mercurial/transaction.py", line 490, in close
      self._postclosecallback[cat](self)
    File "$TESTTMP/crashstrip2.py", line 4, in test
      [repo.changelog.node(r) for r in repo.revs("not public()")]
    File "/Users/lcharignon/facebook-hg-rpms/hg-crew/mercurial/changelog.py", line 337, in node
      return super(changelog, self).node(rev)
    File "/Users/lcharignon/facebook-hg-rpms/hg-crew/mercurial/revlog.py", line 377, in node
      return self.index[rev][7]
  IndexError: revlog index out of range

The situation was encountered in inhibit (evolve's repo) where we would crash
following the volatile set invalidation submitted by Augie in
e6f490e328635312ee214a12bc7fd3c7d46bf9ce. Before his patch the issue was masked
as we were not accessing the phasecache after stripping a revision.

This bug uncovered another but in histedit (see explanation in issue5235).
I changed the histedit test accordingly to avoid fixing two things at once.

# 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 (
    bdiff,
    mdiff,
    util,
)

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 = 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, unit=_('files'))
        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), unit=_('files'))

        # 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)