mercurial/i18n.py

revset: optimize baseset.__sub__ (issue4313)

dd716807fd23 regressed performance of baseset.__sub__ by introducing
a lazyset. This patch restores that lost performance by eagerly
evaluating baseset.__sub__ if the other set is a baseset.

revsetbenchmark.py results impacted by this change:

revset #6: roots(0::tip)
0) wall 2.923473 comb 2.920000 user 2.920000 sys 0.000000 (best of 4)
1) wall 0.077614 comb 0.080000 user 0.080000 sys 0.000000 (best of 100)

revset #23: roots((0:tip)::)
0) wall 2.875178 comb 2.880000 user 2.880000 sys 0.000000 (best of 4)
1) wall 0.154519 comb 0.150000 user 0.150000 sys 0.000000 (best of 61)

On the author's machine, this slowdown manifested during evaluation of
'roots(%ln::)' in phases.retractboundary after unbundling the Firefox
repository. Using `time hg unbundle firefox.hg` as a benchmark:

Before: 8:00
After:  4:28
Delta: -3:32

For reference, the subset and cs baseset instances impacted by this
change were of lengths 193634 and 193627, respectively.

Explicit test coverage of roots(%ln::), while similar to the existing
roots(0::tip) benchmark, has been added.

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[e-mail]>
#
# 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, sys, os

# modelled after templater.templatepath:
if getattr(sys, 'frozen', None) is not None:
    module = sys.executable
else:
    module = __file__

base = os.path.dirname(module)
for dir in ('.', '..'):
    localedir = os.path.join(base, dir, 'locale')
    if os.path.isdir(localedir):
        break

t = gettext.translation('hg', localedir, fallback=True)

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:
        return message

    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 t.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.
        return u.encode(encoding.encoding, "replace")
    except LookupError:
        # An unknown encoding results in a LookupError.
        return 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