##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r36710:aeaf9c7f default
r36838:f33a87cf default
Show More
i18n.py
110 lines | 3.7 KiB | text/x-python | PythonLexer
# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# 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
import gettext as gettextmod
import locale
import os
import sys
from . import (
encoding,
pycompat,
)
# modelled after templater.templatepath:
if getattr(sys, 'frozen', None) is not None:
module = pycompat.sysexecutable
else:
module = pycompat.fsencode(__file__)
try:
unicode
except NameError:
unicode = str
_languages = None
if (pycompat.iswindows
and 'LANGUAGE' not in encoding.environ
and 'LC_ALL' not in encoding.environ
and 'LC_MESSAGES' not in encoding.environ
and 'LANG' not in encoding.environ):
# Try to detect UI language by "User Interface Language Management" API
# if no locale variables are set. Note that locale.getdefaultlocale()
# uses GetLocaleInfo(), which may be different from UI language.
# (See http://msdn.microsoft.com/en-us/library/dd374098(v=VS.85).aspx )
try:
import ctypes
langid = ctypes.windll.kernel32.GetUserDefaultUILanguage()
_languages = [locale.windows_locale[langid]]
except (ImportError, AttributeError, KeyError):
# ctypes not found or unknown langid
pass
_ugettext = None
def setdatapath(datapath):
datapath = pycompat.fsdecode(datapath)
localedir = os.path.join(datapath, pycompat.sysstr('locale'))
t = gettextmod.translation(r'hg', localedir, _languages, fallback=True)
global _ugettext
try:
_ugettext = t.ugettext
except AttributeError:
_ugettext = t.gettext
_msgcache = {} # encoding: {message: translation}
def gettext(message):
"""Translate message.
The message is looked up in the catalog to get a Unicode string,
which is encoded in the local encoding before being returned.
Important: message is restricted to characters in the encoding
given by sys.getdefaultencoding() which is most likely 'ascii'.
"""
# If message is None, t.ugettext will return u'None' as the
# translation whereas our callers expect us to return None.
if message is None or not _ugettext:
return message
cache = _msgcache.setdefault(encoding.encoding, {})
if message not in cache:
if type(message) is unicode:
# goofy unicode docstrings in test
paragraphs = message.split(u'\n\n')
else:
paragraphs = [p.decode("ascii") for p in message.split('\n\n')]
# Be careful not to translate the empty string -- it holds the
# meta data of the .po file.
u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs])
try:
# encoding.tolocal cannot be used since it will first try to
# decode the Unicode string. Calling u.decode(enc) really
# means u.encode(sys.getdefaultencoding()).decode(enc). Since
# the Python encoding defaults to 'ascii', this fails if the
# translated string use non-ASCII characters.
encodingstr = pycompat.sysstr(encoding.encoding)
cache[message] = u.encode(encodingstr, "replace")
except LookupError:
# An unknown encoding results in a LookupError.
cache[message] = message
return cache[message]
def _plain():
if ('HGPLAIN' not in encoding.environ
and 'HGPLAINEXCEPT' not in encoding.environ):
return False
exceptions = encoding.environ.get('HGPLAINEXCEPT', '').strip().split(',')
return 'i18n' not in exceptions
if _plain():
_ = lambda message: message
else:
_ = gettext