view hgext/automv.py @ 42590:ab416b5d9b91

tests: add more tests of copy tracing with removed and re-added files

We had a test where the destination of a copy was removed and then
added back. This patch adds similar cases where the break in history
instead happens to the source file. There are three versions of this:

 1. The break happens before the rename.

 2. The break happens on a branch parallel to the rename (where copy
    tracing is done via the merge base)

 3. The source is added on each side of the merge base. The break in
    history is thus in the form of a deletion when going backwards to
    the merge base and the re-add happens on the other branch.

I've also added calls to `hg graft` in these cases to show the
breakage in issue 6163.

Another factor in these cases is matching nodeid (checked in
copies._tracefile()). I've made two copies each of the cases to show
the impact of that. One of these is the same as a test in
test-rename-merge1.t, so I also deleted that test from there.

Some of these tests currently fail, where "fail" is based on my
current thinking of how things should work. I had initially thought
that we should be more strict about not tracing copies across commits
where the file did not exist, but issue 6163 made me reconsider.

The only test case here that behaved differently in 4.9 is the
exact case reported in issue 6163.

Differential Revision: https://phab.mercurial-scm.org/D6599

# 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,
    pycompat,
    registrar,
    scmutil,
    similar
)

configtable = {}
configitem = registrar.configitem(configtable)

configitem('automv', 'similarity',
    default=95,
)

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"""
    opts = pycompat.byteskwargs(opts)
    renames = None
    disabled = opts.pop('no_automv', False)
    if not disabled:
        threshold = ui.configint('automv', 'similarity')
        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)
            uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
            renames = _findrenames(repo, uipathfn, added, removed,
                                   threshold / 100.0)

    with repo.wlock():
        if renames is not None:
            scmutil._markchanges(repo, (), (), renames)
        return orig(ui, repo, *pats, **pycompat.strkwargs(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.added
    removed = stat.removed

    copy = copies.pathcopies(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, uipathfn, 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') % (
                        uipathfn(src), uipathfn(dst), score * 100))
            renames[dst] = src
    if renames:
        repo.ui.status(_('detected move of %d files\n') % len(renames))
    return renames