view hgext/automv.py @ 29610:754f63671229 stable

rebase: turn rebase revs into set before filtering obsolete When the inhibit extension from mutable-history is enabled, it attempts to iterate over the rebaseset to prevent the nodes being rebased from being marked obsolete. This happens at the same time as rebase's _filterobsoleterevs function trying to iterate over the rebaseset to figure out which ones are obsolete. The two of these iterating over the same revset generatorset cause a 'generator already executing' exception. This is probably a flaw in the revset implementation, since iterating over the same set twice should be supported. This regression was introduced in 5d16ebe7b14, since it changed _filterobsoleterevs to be called before the rebaseset was turned into a set(). For now let’s just make the rebaseset an actual set again before calling that function. This was caught by the inhibit tests. The relevant call stack from test-inhibit.t: File "/tmp/hgtests.jgjrN5/install/lib/python/hgext/rebase.py", line 285, in _preparenewrebase obsrevs = _filterobsoleterevs(self.repo, rebaseset) File "/data/hgbuild/facebook-hg-rpms/mutable-history/hgext/inhibit.py", line 197, in _filterobsoleterevswrap r = orig(repo, rebasesetrevs, *args, **kwargs) File "/tmp/hgtests.jgjrN5/install/lib/python/hgext/rebase.py", line 1380, in _filterobsoleterevs return set(r for r in revs if repo[r].obsolete()) File "/tmp/hgtests.jgjrN5/install/lib/python/hgext/rebase.py", line 1380, in <genexpr> return set(r for r in revs if repo[r].obsolete()) File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3079, in _iterordered val2 = next(iter2) File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3417, in gen yield nextrev() File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3424, in _consumegen for item in self._gen: File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 71, in iterate cl = repo.changelog File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/repoview.py", line 319, in changelog revs = filterrevs(unfi, self.filtername) File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/repoview.py", line 261, in filterrevs repo.filteredrevcache[filtername] = func(repo.unfiltered()) File "/data/hgbuild/facebook-hg-rpms/mutable-history/hgext/directaccess.py", line 65, in _computehidden hidden = repoview.filterrevs(repo, 'visible') File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/repoview.py", line 261, in filterrevs repo.filteredrevcache[filtername] = func(repo.unfiltered()) File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/repoview.py", line 175, in computehidden hideable = hideablerevs(repo) File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/repoview.py", line 33, in hideablerevs return obsolete.getrevs(repo, 'obsolete') File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/obsolete.py", line 1097, in getrevs repo.obsstore.caches[name] = cachefuncs[name](repo) File "/data/hgbuild/facebook-hg-rpms/mutable-history/hgext/inhibit.py", line 255, in _computeobsoleteset if getrev(n) not in blacklist: File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3264, in __contains__ return x in self._r1 or x in self._r2 File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3348, in __contains__ for l in self._consumegen(): File "/tmp/hgtests.jgjrN5/install/lib/python/mercurial/revset.py", line 3424, in _consumegen for item in self._gen: ValueError: generator already executing
author Simon Farnsworth <simonfar@fb.com>
date Tue, 19 Jul 2016 03:29:53 -0700
parents a0939666b836
children e4aefdb58ebe
line wrap: on
line source

# automv.py
#
# Copyright 2013-2016 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Check for unrecorded moves at commit time (EXPERIMENTAL)

This extension checks at commit/amend time if any of the committed files
comes from an unrecorded mv.

The threshold at which a file is considered a move can be set with the
``automv.similarity`` config option. This option takes a percentage between 0
(disabled) and 100 (files must be identical), the default is 95.

"""

# Using 95 as a default similarity is based on an analysis of the mercurial
# repositories of the cpython, mozilla-central & mercurial repositories, as
# well as 2 very large facebook repositories. At 95 50% of all potential
# missed moves would be caught, as well as correspond with 87% of all
# explicitly marked moves.  Together, 80% of moved files are 95% similar or
# more.
#
# See http://markmail.org/thread/5pxnljesvufvom57 for context.

from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import (
    commands,
    copies,
    error,
    extensions,
    scmutil,
    similar
)

def extsetup(ui):
    entry = extensions.wrapcommand(
        commands.table, 'commit', mvcheck)
    entry[1].append(
        ('', 'no-automv', None,
         _('disable automatic file move detection')))

def mvcheck(orig, ui, repo, *pats, **opts):
    """Hook to check for moves at commit time"""
    renames = None
    disabled = opts.pop('no_automv', False)
    if not disabled:
        threshold = ui.configint('automv', 'similarity', 95)
        if not 0 <= threshold <= 100:
            raise error.Abort(_('automv.similarity must be between 0 and 100'))
        if threshold > 0:
            match = scmutil.match(repo[None], pats, opts)
            added, removed = _interestingfiles(repo, match)
            renames = _findrenames(repo, match, added, removed,
                                   threshold / 100.0)

    with repo.wlock():
        if renames is not None:
            scmutil._markchanges(repo, (), (), renames)
        return orig(ui, repo, *pats, **opts)

def _interestingfiles(repo, matcher):
    """Find what files were added or removed in this commit.

    Returns a tuple of two lists: (added, removed). Only files not *already*
    marked as moved are included in the added list.

    """
    stat = repo.status(match=matcher)
    added = stat[1]
    removed = stat[2]

    copy = copies._forwardcopies(repo['.'], repo[None], matcher)
    # remove the copy files for which we already have copy info
    added = [f for f in added if f not in copy]

    return added, removed

def _findrenames(repo, matcher, added, removed, similarity):
    """Find what files in added are really moved files.

    Any file named in removed that is at least similarity% similar to a file
    in added is seen as a rename.

    """
    renames = {}
    if similarity > 0:
        for src, dst, score in similar.findrenames(
                repo, added, removed, similarity):
            if repo.ui.verbose:
                repo.ui.status(
                    _('detected move of %s as %s (%d%% similar)\n') % (
                        matcher.rel(src), matcher.rel(dst), score * 100))
            renames[dst] = src
    if renames:
        repo.ui.status(_('detected move of %d files\n') % len(renames))
    return renames