view mercurial/i18n.py @ 45637:ad6ebb6f0dfe

copies: make two version of the changeset centric algorithm

They are two main ways to run the changeset-centric copy-tracing algorithm. One
fed from data stored in side-data and still in development, and one based on
data stored in extra (with a "compatibility" mode).

The `extra` based is used in production at Google, but still experimental in
code. It is mostly unsuitable for other users because it affects the hash.

The side-data based storage and algorithm have been evolving to store more data, cover more cases
(mostly around merge, that Google do not really care about) and use lower level
storage for efficiency.

All this changes make is increasingly hard to maintain de common code base,
without impacting code complexity and performance. For example, the
compatibility mode requires to keep things at different level than what we
need for side-data.

So, I am duplicating the involved functions. The newly added `_extra` variants
will be kept as today, while I will do some deeper rework of the side data
versions.

Long terms, the side-data version should be more featureful and performant than
the extra based version, so I expect the duplicated `_extra` functions to
eventually get dropped.

Differential Revision: https://phab.mercurial-scm.org/D9114

# 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.

from __future__ import absolute_import

import gettext as gettextmod
import locale
import os
import sys

from .pycompat import getattr
from .utils import resourceutil
from . import (
    encoding,
    pycompat,
)

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

_languages = None
if (
    pycompat.iswindows
    and b'LANGUAGE' not in encoding.environ
    and b'LC_ALL' not in encoding.environ
    and b'LC_MESSAGES' not in encoding.environ
    and b'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


datapath = pycompat.fsdecode(resourceutil.datapath)
localedir = os.path.join(datapath, 'locale')
t = gettextmod.translation('hg', localedir, _languages, fallback=True)
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 pycompat.unicode:
            # goofy unicode docstrings in test
            paragraphs = message.split(u'\n\n')
        else:
            # should be ascii, but we have unicode docstrings in test, which
            # are converted to utf-8 bytes on Python 3.
            paragraphs = [p.decode("utf-8") for p in message.split(b'\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 (
        b'HGPLAIN' not in encoding.environ
        and b'HGPLAINEXCEPT' not in encoding.environ
    ):
        return False
    exceptions = encoding.environ.get(b'HGPLAINEXCEPT', b'').strip().split(b',')
    return b'i18n' not in exceptions


if _plain():
    _ = lambda message: message
else:
    _ = gettext