From a1ce93f87cb221be9a7466c2f9d2b7dc494f458d Mon Sep 17 00:00:00 2001 From: Barry Warsaw Date: Fri, 11 Apr 2003 18:36:43 +0000 Subject: From http://mail.python.org/pipermail/i18n-sig/2003-April/001557.html - Expose NullTranslations and GNUTranslations to __all__ - Set the default charset to iso-8859-1. It used to be None, which would cause problems with .ugettext() if the file had no charset parameter. Arguably, the po/mo file would be broken, but I still think iso-8859-1 is a reasonable default. - Add a "coerce" default argument to GNUTranslations's constructor. The reason for this is that in Zope, we want all msgids and msgstrs to be Unicode. For the latter, we could use .ugettext() but there isn't currently a mechanism for Unicode-ifying msgids. The plan then is that the charset parameter specifies the encoding for both the msgids and msgstrs, and both are decoded to Unicode when read. For example, we might encode po files with utf-8. I think the GNU gettext tools don't care. Since this could potentially break code [*] that wants to use the encoded interface .gettext(), the constructor flag is added, defaulting to False. Most code I suspect will want to set this to True and use .ugettext(). - A few other minor changes from the Zope project, including asserting that a zero-length msgid must have a Project-ID-Version header for it to be counted as the metadata record. --- Doc/lib/libgettext.tex | 36 ++++-- Lib/gettext.py | 43 +++++-- Lib/test/test_gettext.py | 305 ++++++++++++++++++++++++++++------------------- 3 files changed, 238 insertions(+), 146 deletions(-) diff --git a/Doc/lib/libgettext.tex b/Doc/lib/libgettext.tex index 924af45..d386a69 100644 --- a/Doc/lib/libgettext.tex +++ b/Doc/lib/libgettext.tex @@ -285,13 +285,17 @@ The \module{gettext} module provides one additional class derived from \class{NullTranslations}: \class{GNUTranslations}. This class overrides \method{_parse()} to enable reading GNU \program{gettext} format \file{.mo} files in both big-endian and little-endian format. - -It also parses optional meta-data out of the translation catalog. It -is convention with GNU \program{gettext} to include meta-data as the -translation for the empty string. This meta-data is in \rfc{822}-style -\code{key: value} pairs. If the key \code{Content-Type} is found, -then the \code{charset} property is used to initialize the -``protected'' \member{_charset} instance variable. The entire set of +It also adds the ability to coerce both message ids and message +strings to Unicode. + +\class{GNUTranslations} parses optional meta-data out of the +translation catalog. It is convention with GNU \program{gettext} to +include meta-data as the translation for the empty string. This +meta-data is in \rfc{822}-style \code{key: value} pairs, and must +contain the \code{Project-Id-Version}. If the key +\code{Content-Type} is found, then the \code{charset} property is used +to initialize the ``protected'' \member{_charset} instance variable, +defaulting to \code{iso-8859-1} if not found. The entire set of key/value pairs are placed into a dictionary and set as the ``protected'' \member{_info} instance variable. @@ -302,11 +306,27 @@ can raise \exception{IOError}. The other usefully overridden method is \method{ugettext()}, which returns a Unicode string by passing both the translated message string and the value of the ``protected'' \member{_charset} variable to the -builtin \function{unicode()} function. +builtin \function{unicode()} function. Note that if you use +\method{ugettext()} you probably also want your message ids to be +Unicode. To do this, set the variable \var{coerce} to \code{True} in +the \class{GNUTranslations} constructor. This ensures that both the +message ids and message strings are decoded to Unicode when the file +is read, using the file's \code{charset} value. If you do this, you +will not want to use the \method{gettext()} method -- always use +\method{ugettext()} instead. To facilitate plural forms, the methods \method{ngettext} and \method{ungettext} are overridden as well. +\begin{methoddesc}[GNUTranslations]{__init__}{ + \optional{fp\optional{, coerce}} +Constructs and parses a translation catalog in GNU gettext format. +\var{fp} is passed to the base class (\class{NullTranslations}) +constructor. \var{coerce} is a flag specifying whether message ids +and message strings should be converted to Unicode when the file is +parsed. It defaults to \code{False} for backward compatibility. +\end{methoddesc} + \subsubsection{Solaris message catalog support} The Solaris operating system defines its own binary diff --git a/Lib/gettext.py b/Lib/gettext.py index 79a025f..c81f484 100644 --- a/Lib/gettext.py +++ b/Lib/gettext.py @@ -50,8 +50,10 @@ import copy, os, re, struct, sys from errno import ENOENT -__all__ = ["bindtextdomain","textdomain","gettext","dgettext", - "find","translation","install","Catalog"] +__all__ = ['NullTranslations', 'GNUTranslations', 'Catalog', + 'find', 'translation', 'install', 'textdomain', 'bindtextdomain', + 'dgettext', 'dngettext', 'gettext', 'ngettext', + ] _default_localedir = os.path.join(sys.prefix, 'share', 'locale') @@ -170,7 +172,7 @@ def _expand_lang(locale): class NullTranslations: def __init__(self, fp=None): self._info = {} - self._charset = None + self._charset = 'iso-8859-1' self._fallback = None if fp is not None: self._parse(fp) @@ -226,6 +228,12 @@ class GNUTranslations(NullTranslations): LE_MAGIC = 0x950412deL BE_MAGIC = 0xde120495L + def __init__(self, fp=None, coerce=False): + # Set this attribute before calling the base class constructor, since + # the latter calls _parse() which depends on self._coerce. + self._coerce = coerce + NullTranslations.__init__(self, fp) + def _parse(self, fp): """Override this method to support alternative .mo formats.""" unpack = struct.unpack @@ -260,16 +268,22 @@ class GNUTranslations(NullTranslations): # Plural forms msgid1, msgid2 = msg.split('\x00') tmsg = tmsg.split('\x00') + if self._coerce: + msgid1 = unicode(msgid1, self._charset) + tmsg = [unicode(x, self._charset) for x in tmsg] for i in range(len(tmsg)): catalog[(msgid1, i)] = tmsg[i] else: + if self._coerce: + msg = unicode(msg, self._charset) + tmsg = unicode(tmsg, self._charset) catalog[msg] = tmsg else: raise IOError(0, 'File is corrupt', filename) # See if we're looking at GNU .mo conventions for metadata - if mlen == 0: + if mlen == 0 and tmsg.lower().startswith('project-id-version:'): # Catalog description - for item in tmsg.split('\n'): + for item in tmsg.splitlines(): item = item.strip() if not item: continue @@ -297,7 +311,6 @@ class GNUTranslations(NullTranslations): return self._fallback.gettext(message) return message - def ngettext(self, msgid1, msgid2, n): try: return self._catalog[(msgid1, self.plural(n))] @@ -309,16 +322,17 @@ class GNUTranslations(NullTranslations): else: return msgid2 - def ugettext(self, message): - try: - tmsg = self._catalog[message] - except KeyError: + missing = object() + tmsg = self._catalog.get(message, missing) + if tmsg is missing: if self._fallback: return self._fallback.ugettext(message) tmsg = message - return unicode(tmsg, self._charset) - + if not self._coerce: + return unicode(tmsg, self._charset) + # The msgstr is already coerced to Unicode + return tmsg def ungettext(self, msgid1, msgid2, n): try: @@ -330,7 +344,10 @@ class GNUTranslations(NullTranslations): tmsg = msgid1 else: tmsg = msgid2 - return unicode(tmsg, self._charset) + if not self._coerce: + return unicode(tmsg, self._charset) + # The msgstr is already coerced to Unicode + return tmsg # Locate a .mo file using the gettext strategy diff --git a/Lib/test/test_gettext.py b/Lib/test/test_gettext.py index 2a1f24c..c7840cd 100644 --- a/Lib/test/test_gettext.py +++ b/Lib/test/test_gettext.py @@ -1,9 +1,11 @@ import os import base64 +import shutil import gettext - import unittest -from unittest import TestCase + +from test.test_support import run_suite + # TODO: # - Add new tests, for example for "dgettext" @@ -11,7 +13,6 @@ from unittest import TestCase # has no sense, it would have if we were testing a parser (i.e. pygettext) # - Tests should have only one assert. - GNU_MO_DATA = '''\ 3hIElQAAAAAGAAAAHAAAAEwAAAALAAAAfAAAAAAAAACoAAAAFQAAAKkAAAAjAAAAvwAAAKEAAADj AAAABwAAAIUBAAALAAAAjQEAAEUBAACZAQAAFgAAAN8CAAAeAAAA9gIAAKEAAAAVAwAABQAAALcD @@ -32,263 +33,293 @@ IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1 ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA== ''' +UMO_DATA = '''\ +3hIElQAAAAACAAAAHAAAACwAAAAFAAAAPAAAAAAAAABQAAAABAAAAFEAAAAPAQAAVgAAAAQAAABm +AQAAAQAAAAIAAAAAAAAAAAAAAAAAAAAAYWLDngBQcm9qZWN0LUlkLVZlcnNpb246IDIuMApQTy1S +ZXZpc2lvbi1EYXRlOiAyMDAzLTA0LTExIDEyOjQyLTA0MDAKTGFzdC1UcmFuc2xhdG9yOiBCYXJy +eSBBLiBXQXJzYXcgPGJhcnJ5QHB5dGhvbi5vcmc+Ckxhbmd1YWdlLVRlYW06IFhYIDxweXRob24t +ZGV2QHB5dGhvbi5vcmc+Ck1JTUUtVmVyc2lvbjogMS4wCkNvbnRlbnQtVHlwZTogdGV4dC9wbGFp +bjsgY2hhcnNldD11dGYtOApDb250ZW50LVRyYW5zZmVyLUVuY29kaW5nOiA3Yml0CkdlbmVyYXRl +ZC1CeTogbWFudWFsbHkKAMKkeXoA +''' LOCALEDIR = os.path.join('xx', 'LC_MESSAGES') MOFILE = os.path.join(LOCALEDIR, 'gettext.mo') +UMOFILE = os.path.join(LOCALEDIR, 'ugettext.mo') -def setup(): - os.makedirs(LOCALEDIR) - fp = open(MOFILE, 'wb') - fp.write(base64.decodestring(GNU_MO_DATA)) - fp.close() - os.environ['LANGUAGE'] = 'xx' -def teardown(): - os.environ['LANGUAGE'] = 'en' - os.unlink(MOFILE) - os.removedirs(LOCALEDIR) +class GettextBaseTest(unittest.TestCase): + def setUp(self): + os.makedirs(LOCALEDIR) + fp = open(MOFILE, 'wb') + fp.write(base64.decodestring(GNU_MO_DATA)) + fp.close() + fp = open(UMOFILE, 'wb') + fp.write(base64.decodestring(UMO_DATA)) + fp.close() + os.environ['LANGUAGE'] = 'xx' + + def tearDown(self): + os.environ['LANGUAGE'] = 'en' + shutil.rmtree(LOCALEDIR) -class GettextTestCase1(TestCase): +class GettextTestCase1(GettextBaseTest): def setUp(self): + GettextBaseTest.setUp(self) self.localedir = os.curdir self.mofile = MOFILE - gettext.install('gettext', self.localedir) - def test_some_translations(self): + eq = self.assertEqual # test some translations - assert _('albatross') == 'albatross' - assert _(u'mullusk') == 'bacon' - assert _(r'Raymond Luxury Yach-t') == 'Throatwobbler Mangrove' - assert _(ur'nudge nudge') == 'wink wink' - + eq(_('albatross'), 'albatross') + eq(_(u'mullusk'), 'bacon') + eq(_(r'Raymond Luxury Yach-t'), 'Throatwobbler Mangrove') + eq(_(ur'nudge nudge'), 'wink wink') def test_double_quotes(self): + eq = self.assertEqual # double quotes - assert _("albatross") == 'albatross' - assert _(u"mullusk") == 'bacon' - assert _(r"Raymond Luxury Yach-t") == 'Throatwobbler Mangrove' - assert _(ur"nudge nudge") == 'wink wink' - + eq(_("albatross"), 'albatross') + eq(_(u"mullusk"), 'bacon') + eq(_(r"Raymond Luxury Yach-t"), 'Throatwobbler Mangrove') + eq(_(ur"nudge nudge"), 'wink wink') def test_triple_single_quotes(self): + eq = self.assertEqual # triple single quotes - assert _('''albatross''') == 'albatross' - assert _(u'''mullusk''') == 'bacon' - assert _(r'''Raymond Luxury Yach-t''') == 'Throatwobbler Mangrove' - assert _(ur'''nudge nudge''') == 'wink wink' - + eq(_('''albatross'''), 'albatross') + eq(_(u'''mullusk'''), 'bacon') + eq(_(r'''Raymond Luxury Yach-t'''), 'Throatwobbler Mangrove') + eq(_(ur'''nudge nudge'''), 'wink wink') def test_triple_double_quotes(self): + eq = self.assertEqual # triple double quotes - assert _("""albatross""") == 'albatross' - assert _(u"""mullusk""") == 'bacon' - assert _(r"""Raymond Luxury Yach-t""") == 'Throatwobbler Mangrove' - assert _(ur"""nudge nudge""") == 'wink wink' - + eq(_("""albatross"""), 'albatross') + eq(_(u"""mullusk"""), 'bacon') + eq(_(r"""Raymond Luxury Yach-t"""), 'Throatwobbler Mangrove') + eq(_(ur"""nudge nudge"""), 'wink wink') def test_multiline_strings(self): + eq = self.assertEqual # multiline strings - assert _('''This module provides internationalization and localization + eq(_('''This module provides internationalization and localization support for your Python programs by providing an interface to the GNU -gettext message catalog library.''') == '''Guvf zbqhyr cebivqrf vagreangvbanyvmngvba naq ybpnyvmngvba +gettext message catalog library.'''), + '''Guvf zbqhyr cebivqrf vagreangvbanyvmngvba naq ybpnyvmngvba fhccbeg sbe lbhe Clguba cebtenzf ol cebivqvat na vagresnpr gb gur TAH -trggrkg zrffntr pngnybt yvoenel.''' - +trggrkg zrffntr pngnybt yvoenel.''') def test_the_alternative_interface(self): + eq = self.assertEqual # test the alternative interface - fp = open(os.path.join(self.mofile), 'rb') + fp = open(self.mofile, 'rb') t = gettext.GNUTranslations(fp) fp.close() - + # Install the translation object t.install() + eq(_('nudge nudge'), 'wink wink') + # Try unicode return type + t.install(unicode=True) + eq(_('mullusk'), 'bacon') - assert _('nudge nudge') == 'wink wink' - # try unicode return type - t.install(unicode=1) - - assert _('mullusk') == 'bacon' - - -class GettextTestCase2(TestCase): +class GettextTestCase2(GettextBaseTest): def setUp(self): + GettextBaseTest.setUp(self) self.localedir = os.curdir - + # Set up the bindings gettext.bindtextdomain('gettext', self.localedir) gettext.textdomain('gettext') - + # For convenience self._ = gettext.gettext - def test_bindtextdomain(self): - assert gettext.bindtextdomain('gettext') == self.localedir - + self.assertEqual(gettext.bindtextdomain('gettext'), self.localedir) def test_textdomain(self): - assert gettext.textdomain() == 'gettext' - + self.assertEqual(gettext.textdomain(), 'gettext') def test_some_translations(self): + eq = self.assertEqual # test some translations - assert self._('albatross') == 'albatross' - assert self._(u'mullusk') == 'bacon' - assert self._(r'Raymond Luxury Yach-t') == 'Throatwobbler Mangrove' - assert self._(ur'nudge nudge') == 'wink wink' - + eq(self._('albatross'), 'albatross') + eq(self._(u'mullusk'), 'bacon') + eq(self._(r'Raymond Luxury Yach-t'), 'Throatwobbler Mangrove') + eq(self._(ur'nudge nudge'), 'wink wink') def test_double_quotes(self): + eq = self.assertEqual # double quotes - assert self._("albatross") == 'albatross' - assert self._(u"mullusk") == 'bacon' - assert self._(r"Raymond Luxury Yach-t") == 'Throatwobbler Mangrove' - assert self._(ur"nudge nudge") == 'wink wink' - + eq(self._("albatross"), 'albatross') + eq(self._(u"mullusk"), 'bacon') + eq(self._(r"Raymond Luxury Yach-t"), 'Throatwobbler Mangrove') + eq(self._(ur"nudge nudge"), 'wink wink') def test_triple_single_quotes(self): + eq = self.assertEqual # triple single quotes - assert self._('''albatross''') == 'albatross' - assert self._(u'''mullusk''') == 'bacon' - assert self._(r'''Raymond Luxury Yach-t''') == 'Throatwobbler Mangrove' - assert self._(ur'''nudge nudge''') == 'wink wink' - + eq(self._('''albatross'''), 'albatross') + eq(self._(u'''mullusk'''), 'bacon') + eq(self._(r'''Raymond Luxury Yach-t'''), 'Throatwobbler Mangrove') + eq(self._(ur'''nudge nudge'''), 'wink wink') def test_triple_double_quotes(self): + eq = self.assertEqual # triple double quotes - assert self._("""albatross""") == 'albatross' - assert self._(u"""mullusk""") == 'bacon' - assert self._(r"""Raymond Luxury Yach-t""") == 'Throatwobbler Mangrove' - assert self._(ur"""nudge nudge""") == 'wink wink' - + eq(self._("""albatross"""), 'albatross') + eq(self._(u"""mullusk"""), 'bacon') + eq(self._(r"""Raymond Luxury Yach-t"""), 'Throatwobbler Mangrove') + eq(self._(ur"""nudge nudge"""), 'wink wink') def test_multiline_strings(self): + eq = self.assertEqual # multiline strings - assert self._('''This module provides internationalization and localization + eq(self._('''This module provides internationalization and localization support for your Python programs by providing an interface to the GNU -gettext message catalog library.''') == '''Guvf zbqhyr cebivqrf vagreangvbanyvmngvba naq ybpnyvmngvba +gettext message catalog library.'''), + '''Guvf zbqhyr cebivqrf vagreangvbanyvmngvba naq ybpnyvmngvba fhccbeg sbe lbhe Clguba cebtenzf ol cebivqvat na vagresnpr gb gur TAH -trggrkg zrffntr pngnybt yvoenel.''' +trggrkg zrffntr pngnybt yvoenel.''') - - -class PluralFormsTestCase(TestCase): +class PluralFormsTestCase(GettextBaseTest): def setUp(self): + GettextBaseTest.setUp(self) self.mofile = MOFILE def test_plural_forms1(self): + eq = self.assertEqual x = gettext.ngettext('There is %s file', 'There are %s files', 1) - assert x == 'Hay %s fichero' - + eq(x, 'Hay %s fichero') x = gettext.ngettext('There is %s file', 'There are %s files', 2) - assert x == 'Hay %s ficheros' - + eq(x, 'Hay %s ficheros') def test_plural_forms2(self): - fp = open(os.path.join(self.mofile), 'rb') + eq = self.assertEqual + fp = open(self.mofile, 'rb') t = gettext.GNUTranslations(fp) fp.close() - x = t.ngettext('There is %s file', 'There are %s files', 1) - assert x == 'Hay %s fichero' - + eq(x, 'Hay %s fichero') x = t.ngettext('There is %s file', 'There are %s files', 2) - assert x == 'Hay %s ficheros' - + eq(x, 'Hay %s ficheros') def test_hu(self): + eq = self.assertEqual f = gettext.c2py('0') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000" - + eq(s, "00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000") def test_de(self): + eq = self.assertEqual f = gettext.c2py('n != 1') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "10111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111" - + eq(s, "10111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111") def test_fr(self): + eq = self.assertEqual f = gettext.c2py('n>1') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "00111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111" - + eq(s, "00111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111") def test_gd(self): + eq = self.assertEqual f = gettext.c2py('n==1 ? 0 : n==2 ? 1 : 2') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "20122222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222" - + eq(s, "20122222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222") def test_gd2(self): + eq = self.assertEqual # Tests the combination of parentheses and "?:" f = gettext.c2py('n==1 ? 0 : (n==2 ? 1 : 2)') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "20122222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222" - + eq(s, "20122222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222222") def test_lt(self): + eq = self.assertEqual f = gettext.c2py('n%10==1 && n%100!=11 ? 0 : n%10>=2 && (n%100<10 || n%100>=20) ? 1 : 2') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "20111111112222222222201111111120111111112011111111201111111120111111112011111111201111111120111111112011111111222222222220111111112011111111201111111120111111112011111111201111111120111111112011111111" - + eq(s, "20111111112222222222201111111120111111112011111111201111111120111111112011111111201111111120111111112011111111222222222220111111112011111111201111111120111111112011111111201111111120111111112011111111") def test_ru(self): + eq = self.assertEqual f = gettext.c2py('n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "20111222222222222222201112222220111222222011122222201112222220111222222011122222201112222220111222222011122222222222222220111222222011122222201112222220111222222011122222201112222220111222222011122222" - + eq(s, "20111222222222222222201112222220111222222011122222201112222220111222222011122222201112222220111222222011122222222222222220111222222011122222201112222220111222222011122222201112222220111222222011122222") def test_pl(self): + eq = self.assertEqual f = gettext.c2py('n==1 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "20111222222222222222221112222222111222222211122222221112222222111222222211122222221112222222111222222211122222222222222222111222222211122222221112222222111222222211122222221112222222111222222211122222" - + eq(s, "20111222222222222222221112222222111222222211122222221112222222111222222211122222221112222222111222222211122222222222222222111222222211122222221112222222111222222211122222221112222222111222222211122222") def test_sl(self): + eq = self.assertEqual f = gettext.c2py('n%100==1 ? 0 : n%100==2 ? 1 : n%100==3 || n%100==4 ? 2 : 3') s = ''.join([ str(f(x)) for x in range(200) ]) - assert s == "30122333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333012233333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333" - + eq(s, "30122333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333012233333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333333") def test_security(self): + raises = self.assertRaises # Test for a dangerous expression + raises(ValueError, gettext.c2py, "os.chmod('/etc/passwd',0777)") + + +class UnicodeTranslationsTest(GettextBaseTest): + def setUp(self): + GettextBaseTest.setUp(self) + fp = open(UMOFILE, 'rb') try: - gettext.c2py("os.chmod('/etc/passwd',0777)") - except ValueError: - pass - else: - raise AssertionError + self.t = gettext.GNUTranslations(fp, coerce=True) + finally: + fp.close() + self._ = self.t.ugettext + def test_unicode_msgid(self): + unless = self.failUnless + unless(isinstance(self._(''), unicode)) + unless(isinstance(self._(u''), unicode)) + def test_unicode_msgstr(self): + eq = self.assertEqual + eq(self._(u'ab\xde'), u'\xa4yz') -if __name__ == '__main__': - try: - setup() - unittest.main() - finally: - teardown() +def suite(): + suite = unittest.TestSuite() + suite.addTest(unittest.makeSuite(GettextTestCase1)) + suite.addTest(unittest.makeSuite(GettextTestCase2)) + suite.addTest(unittest.makeSuite(PluralFormsTestCase)) + suite.addTest(unittest.makeSuite(UnicodeTranslationsTest)) + return suite + +def test_main(): + run_suite(suite()) -# For reference, here's the .po file used to created the .mo data above. +if __name__ == '__main__': + test_main() + + +# For reference, here's the .po file used to created the GNU_MO_DATA above. # # The original version was automatically generated from the sources with # pygettext. Later it was manually modified to add plural forms support. ''' -# Dummy translation for Python's test_gettext.py module. +# Dummy translation for the Python test_gettext.py module. # Copyright (C) 2001 Python Software Foundation # Barry Warsaw , 2000. # msgid "" msgstr "" "Project-Id-Version: 2.0\n" -"PO-Revision-Date: 2000-08-29 12:19-04:00\n" +"PO-Revision-Date: 2003-04-11 14:32-0400\n" "Last-Translator: J. David Ibanez \n" "Language-Team: XX \n" "MIME-Version: 1.0\n" @@ -336,3 +367,27 @@ msgid_plural "There are %s files" msgstr[0] "Hay %s fichero" msgstr[1] "Hay %s ficheros" ''' + +# Here's the second example po file example, used to generate the UMO_DATA +# containing utf-8 encoded Unicode strings + +''' +# Dummy translation for the Python test_gettext.py module. +# Copyright (C) 2001 Python Software Foundation +# Barry Warsaw , 2000. +# +msgid "" +msgstr "" +"Project-Id-Version: 2.0\n" +"PO-Revision-Date: 2003-04-11 12:42-0400\n" +"Last-Translator: Barry A. WArsaw \n" +"Language-Team: XX \n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 7bit\n" +"Generated-By: manually\n" + +#: nofile:0 +msgid "ab\xc3\x9e" +msgstr "\xc2\xa4yz" +''' -- cgit v0.12