view hgext/automv.py @ 35553:a77418095530

lfs: remove the verification option when writing to the local store

This partially reverts 417e8e040102 and bb6a80fc969a.  But since there's now a
dedicated download function, there's no functional change.  The last sentence in
the commit message of the latter is wrong- write() didn't need the one time hash
check if verification wasn't requested.  I suspect I missed 'read()' in there
("... but _read()_ also needs to do a one time check..."), because that did fail
without the hash check before linking to the usercache.  The write() method
simply took the same check for consistency.

While here, clarify that the write() method is *only* for storing content
directly from filelog, which has already checked the hash.

If someone can come up with a way to bridge the differences between writing to a
file and sending a urlreq.request across the wire, we can create an upload()
function and cleanup read() in a similar way.  About the only common thread I
see is an open() that verifies the content before returning a file descriptor.

# 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)
            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, **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[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