##// END OF EJS Templates
ssh: avoid reading beyond the end of stream when using compression...
ssh: avoid reading beyond the end of stream when using compression Compressed streams can be used as part of getbundle. The normal read() operation of bufferedinputpipe will try to fulfill the request exactly and can deadlock if the server sends less as it is done. At the same time, the bundle2 logic will stop reading when it believes it has gotten all parts of the bundle, which can leave behind end of stream markers as used by bzip2 and zstd. To solve this, introduce a new optional unbufferedread interface and provided it in bufferedinputpipe and doublepipe. If there is buffered data left, it will be returned, otherwise it will issue a single read request and return whatever it obtains. Reorganize the decompression handlers to try harder to read until the end of stream, especially if the requested read can already be fulfilled. Check for end of stream is messy with Python 2, none of the standard compression modules properly exposes it. At least with zstd and bzip2, decompressing will remember EOS and fail for empty input after the EOS has been seen. For zlib, the only way to detect it with Python 2 is to duplicate the decompressobj and force some additional data into it. The common handler can be further optimized, but works as PoC. Differential Revision: https://phab.mercurial-scm.org/D3937

File last commit:

r34972:38637dd3 default
r38735:27391d74 default
Show More
automv.py
110 lines | 3.5 KiB | text/x-python | PythonLexer
# 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