view mercurial/i18n.py @ 16230:d4d35fd0889d stable

update: don't translate the abort message twice The string representation of util.Abort() is translated when merge.update() raises the exception. For languages with characters out of the valid ascii range, if we feed them again to i18n.gettext() mercurial dies with: [...] File "/home/javi/src/mercurial/mercurial/hg-mpm/mercurial/commands.py", line 4287, in postincoming ui.warn(_("not updating: %s\n" % str(inst))) File "/home/javi/src/mercurial/mercurial/hg-mpm/mercurial/i18n.py", line 42, in gettext u = u'\n\n'.join([p and t.ugettext(p) or '' for p in paragraphs]) File "/usr/lib/python2.7/gettext.py", line 404, in ugettext return unicode(message) UnicodeDecodeError: 'ascii' codec can't decode byte 0xd0 in position 14: ordinal not in range(128) To reproduce this error, just try to pull a changeset that crosses branches with LANG=ru_RU.UTF-8
author Javi Merino <cibervicho@gmail.com>
date Wed, 07 Mar 2012 23:21:11 +0000
parents b64538363dbe
children 2d47d81c79fb
line wrap: on
line source

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Matt Mackall <mpm@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 encoding
import gettext, sys, os

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

base = os.path.dirname(module)
for dir in ('.', '..'):
    localedir = os.path.join(base, dir, 'locale')
    if os.path.isdir(localedir):
        break

t = gettext.translation('hg', localedir, fallback=True)

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:
        return message

    paragraphs = 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 t.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.
        return u.encode(encoding.encoding, "replace")
    except LookupError:
        # An unknown encoding results in a LookupError.
        return 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