mercurial/i18n.py
author Manuel Jacob <me@manueljacob.de>
Mon, 11 Jul 2022 01:51:20 +0200
branchstable
changeset 49378 094a5fa3cf52
parent 48934 06de08b36c82
child 50929 18c8c18993f0
permissions -rw-r--r--
procutil: make stream detection in make_line_buffered more correct and strict In make_line_buffered(), we don’t want to wrap the stream if we know that lines get flushed to the underlying raw stream already. Previously, the heuristic was too optimistic. It assumed that any stream which is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there are buffered streams that aren’t instances of io.BufferedIOBase, like Mercurial’s own winstdout. The new logic is different in two ways: First, only for the check, if unwraps any combination of WriteAllWrapper and winstdout. Second, it skips wrapping the stream only if it is an instance of io.RawIOBase (or already wrapped). If it is an instance of io.BufferedIOBase, it gets wrapped. In any other case, the function raises an exception. This ensures that, if an unknown stream is passed or we add another wrapper in the future, we don’t wrap the stream if it’s already line buffered or not wrap the stream if it’s not line buffered. In fact, this was already helpful during development of this change. Without it, I possibly would have forgot that WriteAllWrapper needs to be ignored for the check, leading to unnecessary wrapping if stdout is unbuffered. The alternative would have been to always wrap unknown streams. However, I don’t think that anyone would benefit from being less strict. We can expect streams from the standard library to be subclassing either io.RawIOBase or io.BufferedIOBase, so running Mercurial in the standard way should not regress by this change. Py2exe might replace sys.stdout and sys.stderr, but that currently breaks Mercurial anyway and also these streams don’t claim to be interactive, so this function is not called for them.

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Olivia Mackall <olivia@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 gettext as gettextmod
import locale
import os
import sys

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

if pycompat.TYPE_CHECKING:
    from typing import (
        Callable,
        List,
    )


# 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 = {}  # encoding: {message: translation}


def gettext(message):
    # type: (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 = message.split(u'\n\n')  # type: List[str]
        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  # type: Callable[[bytes], bytes]
else:
    _ = gettext