dirstate.walk: don't keep track of normalized files in parallel
Rev
2bb13f2b778c changed the semantics of the work list to store (normalized,
non-normalized) pairs. All the tuple creation and destruction hurts perf: on a
large repo on OS X, 'hg status' went from 3.62 seconds to 3.78.
It also is unnecessary in most cases:
- it is clearly unnecessary on case-sensitive filesystems.
- it is also unnecessary when filenames have been read off of disk rather than
being supplied by the user.
The only case where the non-normalized case is required at all is when the file
is unknown.
To eliminate most of the perf cost, keep trace of whether the directory needs
to be normalized at all with a boolean called 'alreadynormed'. Pay the cost of
directory normalization only when necessary.
For the above large repo, 'hg status' goes to 3.63 seconds.
# 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.
import encoding
import gettext as gettextmod, sys, os, locale
# modelled after templater.templatepath:
if getattr(sys, 'frozen', None) is not None:
module = sys.executable
else:
module = __file__
_languages = None
if (os.name == 'nt'
and 'LANGUAGE' not in os.environ
and 'LC_ALL' not in os.environ
and 'LC_MESSAGES' not in os.environ
and 'LANG' not in os.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):
localedir = os.path.join(datapath, 'locale')
t = gettextmod.translation('hg', localedir, _languages, fallback=True)
global _ugettext
_ugettext = t.ugettext
_msgcache = {}
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
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.
u = u'\n\n'.join([p and _ugettext(p) or '' 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.
_msgcache[message] = u.encode(encoding.encoding, "replace")
except LookupError:
# An unknown encoding results in a LookupError.
_msgcache[message] = message
return _msgcache[message]
def _plain():
if 'HGPLAIN' not in os.environ and 'HGPLAINEXCEPT' not in os.environ:
return False
exceptions = os.environ.get('HGPLAINEXCEPT', '').strip().split(',')
return 'i18n' not in exceptions
if _plain():
_ = lambda message: message
else:
_ = gettext