view mercurial/i18n.py @ 43658:0796e266d26b

dirs: resolve fuzzer OOM situation by disallowing deep directory hierarchies

It seems like 2048 directories ought to be enough for any reasonable
use of Mercurial?

A previous version of this patch scanned for slashes before any allocations
occurred. That approach is slower than this in the happy path, but much faster
than this in the case that too many slashes are encountered. We may want to
revisit it in the future using memchr() so it'll be well-optimized by the libc
we're using.

.. bc:

    Mercurial will now defend against OOMs by refusing to operate on
    paths with 2048 or more components. This means that _extremely_
    deep path hierarchies will be rejected, but we anticipate nobody
    is using hierarchies this deep.

Differential Revision: https://phab.mercurial-scm.org/D7411

# 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 . 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

_ugettext = None


def setdatapath(datapath):
    datapath = pycompat.fsdecode(datapath)
    localedir = os.path.join(datapath, 'locale')
    t = gettextmod.translation('hg', localedir, _languages, fallback=True)
    global _ugettext
    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