view mercurial/i18n.py @ 44651:00e0c5c06ed5

pycompat: change argv conversion semantics

Use of os.fsencode() to convert Python's sys.argv back to bytes
was not correct because it isn't the logically inverse operation
from what CPython was doing under the hood.

This commit changes the logic for doing the str -> bytes
conversion. This required a separate implementation for
POSIX and Windows.

The Windows behavior is arguably not ideal. The previous
behavior on Windows was leading to failing tests, such as
test-http-branchmap.t, which defines a utf-8 branch name
via a command argument. Previously, Mercurial's argument
parser looked to be receiving wchar_t bytes in some cases.
After this commit, behavior on Windows is compatible with
Python 2, where CPython did not implement `int wmain()` and
Windows was performing a Unicode to ANSI conversion on the
wchar_t native command line.

Arguably better behavior on Windows would be for Mercurial to
preserve the original Unicode sequence coming from Python and
to wrap this in a bytes-like type so we can round trip safely.
But, this would be new, backwards incompatible behavior. My
goal for this commit was to converge Mercurial behavior on
Python 3 on Windows to fix busted tests. And I believe I was
successful, as this commit fixes 9 tests on my Windows
machine and 14 tests in the AWS CI environment!

Differential Revision: https://phab.mercurial-scm.org/D8337

# 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