mercurial/i18n.py

highlight: ignore Unicode's extra linebreaks (issue4291)

Unicode and Python's unicode.splitlines() treat several extra legacy
ASCII codepoints as linebreaks, even though the vast bulk of computing
and Python's own str.splitlines() do not. Rather than introduce line
numbering confusion, we filter them out when highlighting.

# 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.

import encoding
import gettext as gettextmod, sys, os, locale

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


_languages = None
if (os.name == 'nt'
    and 'LANGUAGE' not in os.environ
    and 'LC_ALL' not in os.environ
    and 'LC_MESSAGES' not in os.environ
    and 'LANG' not in os.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):
    localedir = os.path.join(datapath, 'locale')
    t = gettextmod.translation('hg', localedir, _languages, fallback=True)
    global _ugettext
    _ugettext = t.ugettext

_msgcache = {}

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

    if message not in _msgcache:
        if type(message) is unicode:
            # goofy unicode docstrings in test
            paragraphs = message.split(u'\n\n')
        else:
            paragraphs = [p.decode("ascii") for p in message.split('\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 '' 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.
            _msgcache[message] = u.encode(encoding.encoding, "replace")
        except LookupError:
            # An unknown encoding results in a LookupError.
            _msgcache[message] = message
    return _msgcache[message]

def _plain():
    if 'HGPLAIN' not in os.environ and 'HGPLAINEXCEPT' not in os.environ:
        return False
    exceptions = os.environ.get('HGPLAINEXCEPT', '').strip().split(',')
    return 'i18n' not in exceptions

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