##// END OF EJS Templates
revlog: make compressed size comparisons consistent...
revlog: make compressed size comparisons consistent revlog.compress() compares the compressed size to the input size and throws away the compressed data if it is larger than the input. This is the correct thing to do, as storing compressed data that is larger than the input takes up more storage space and makes reading slower. However, the comparison was implemented inconsistently. For the streaming compression mode, we threw away the result if it was greater than or equal to the input size. But for the one-shot compression, we threw away the compression only if it was greater than the input size! This patch changes the comparison for the simple case so it is consistent with the streaming case. As a few tests demonstrate, this adds 1 byte to some revlog entries. This is because of an added 'u' header on the chunk. It seems somewhat wrong to increase the revlog size here. However, IMO the cost of 1 byte in storage is insignificant compared to the performance gains of avoiding decompression. This patch should invite questions around the heuristic for throwing away compressed data. For example, I'd argue we should be more liberal about rejecting compressed data, additionally doing so where the number of bytes saved fails to reach a threshold. But we can have this discussion another time.

File last commit:

r30669:10b17ed9 default
r30792:4215dc1b default
Show More
i18n.py
109 lines | 3.6 KiB | text/x-python | PythonLexer
Martin Geisler
put license and copyright info into comment blocks
r8226 # 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
Matt Mackall
Update license to GPLv2+
r10263 # GNU General Public License version 2 or any later version.
Benoit Boissinot
i18n first part: make '_' available for files who need it
r1400
Gregory Szorc
i18n: use absolute_import
r25955 from __future__ import absolute_import
import gettext as gettextmod
import locale
import os
import sys
Pulkit Goyal
py3: convert to unicode to pass into encode()...
r30050 from . import (
encoding,
pycompat,
)
Martin Geisler
i18n: lookup .mo files in private locale/ directory...
r7650
# modelled after templater.templatepath:
Augie Fackler
i18n: use getattr instead of hasattr...
r14975 if getattr(sys, 'frozen', None) is not None:
Pulkit Goyal
py3: replace sys.executable with pycompat.sysexecutable...
r30669 module = pycompat.sysexecutable
Martin Geisler
i18n: lookup .mo files in private locale/ directory...
r7650 else:
module = __file__
timeless
py3: handle ugettext + unicode in i18n
r28674 try:
unicode
except NameError:
unicode = str
Martin Geisler
i18n: lookup .mo files in private locale/ directory...
r7650
Yuya Nishihara
i18n: detect UI language without POSIX-style locale variable on Windows (BC)...
r21987 _languages = None
Pulkit Goyal
py3: replace os.name with pycompat.osname (part 1 of 2)...
r30639 if (pycompat.osname == 'nt'
Yuya Nishihara
py3: make i18n use encoding.environ
r30035 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):
Yuya Nishihara
i18n: detect UI language without POSIX-style locale variable on Windows (BC)...
r21987 # 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
Mads Kiilerich
i18n: use datapath for i18n like for templates and help...
r22638 _ugettext = None
def setdatapath(datapath):
Pulkit Goyal
py3: make util.datapath a bytes variable...
r30301 datapath = pycompat.fsdecode(datapath)
Augie Fackler
i18n: make the locale directory name the same string type as the datapath
r30085 localedir = os.path.join(datapath, pycompat.sysstr('locale'))
Mads Kiilerich
i18n: use datapath for i18n like for templates and help...
r22638 t = gettextmod.translation('hg', localedir, _languages, fallback=True)
global _ugettext
timeless
py3: handle ugettext + unicode in i18n
r28674 try:
_ugettext = t.ugettext
except AttributeError:
_ugettext = t.gettext
Martin Geisler
i18n: encode output in user's local encoding...
r7651
Augie Fackler
i18n: cache the result of every gettext call...
r23031 _msgcache = {}
Martin Geisler
i18n: encode output in user's local encoding...
r7651 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.
Mads Kiilerich
i18n: use datapath for i18n like for templates and help...
r22638 if message is None or not _ugettext:
Martin Geisler
i18n: encode output in user's local encoding...
r7651 return message
Augie Fackler
i18n: cache the result of every gettext call...
r23031 if message not in _msgcache:
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.
Gregory Szorc
i18n: use unicode literal...
r29415 u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs])
Augie Fackler
i18n: cache the result of every gettext call...
r23031 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.
Pulkit Goyal
py3: convert to unicode to pass into encode()...
r30050 encodingstr = pycompat.sysstr(encoding.encoding)
_msgcache[message] = u.encode(encodingstr, "replace")
Augie Fackler
i18n: cache the result of every gettext call...
r23031 except LookupError:
# An unknown encoding results in a LookupError.
_msgcache[message] = message
return _msgcache[message]
Martin Geisler
i18n: encode output in user's local encoding...
r7651
Brodie Rao
HGPLAIN: allow exceptions to plain mode, like i18n, via HGPLAINEXCEPT...
r13849 def _plain():
Yuya Nishihara
py3: make i18n use encoding.environ
r30035 if ('HGPLAIN' not in encoding.environ
and 'HGPLAINEXCEPT' not in encoding.environ):
Brodie Rao
HGPLAIN: allow exceptions to plain mode, like i18n, via HGPLAINEXCEPT...
r13849 return False
Yuya Nishihara
py3: make i18n use encoding.environ
r30035 exceptions = encoding.environ.get('HGPLAINEXCEPT', '').strip().split(',')
Brodie Rao
HGPLAIN: allow exceptions to plain mode, like i18n, via HGPLAINEXCEPT...
r13849 return 'i18n' not in exceptions
if _plain():
Brodie Rao
ui: add HGPLAIN environment variable for easier scripting...
r10455 _ = lambda message: message
else:
_ = gettext