annotate mercurial/i18n.py @ 51935:77e2994bd617

mdiff: convert a few block definitions from lists to tuples

These were flagged by adding type hints.  Some places were using a tuple of 4
ints to define a block, and others were using a list of 4.  A tuple is better
for typing, because we can define the length and the type of each entry.  One of
the places had to redefine the tuple, since writing to a tuple at an index isn't
supported.

This change spills out into the tests, and archeology says it was added to the
repo in this state.  There was no reason given for the divergence, and I suspect
it wasn't intentional.

It looks like `splitblock()` is completely unused in the codebase.

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Olivia 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 annotations

import gettext as gettextmod
import locale
import os
import sys

from typing import (
    Dict,
    List,
)

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

        # pytype: disable=module-attr
        langid = ctypes.windll.kernel32.GetUserDefaultUILanguage()
        # pytype: enable=module-attr

        _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  # pytype: disable=attribute-error
except AttributeError:
    _ugettext = t.gettext


_msgcache: Dict[
    bytes, Dict[bytes, bytes]
] = {}  # encoding: {message: translation}


def gettext(message: bytes) -> bytes:
    """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 str:
            # goofy unicode docstrings in test
            paragraphs: List[str] = 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():

    def _(message: bytes) -> bytes:
        return message

else:
    _ = gettext