mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-19 09:15:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6
cpython/Lib/test/test_gettext.py
Barry Warsaw a1ce93f87c 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.
2003-04-11 18:36:43 +00:00

393 lines
15 KiB
Python
Raw Blame History

import os
import base64
import shutil
import gettext
import unittest
from test.test_support import run_suite
# TODO:
# - Add new tests, for example for "dgettext"
# - Remove dummy tests, for example testing for single and double quotes
# has no sense, it would have if we were testing a parser (i.e. pygettext)
# - Tests should have only one assert.
GNU_MO_DATA = '''\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==
'''
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')
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(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
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
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
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
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
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
fhccbeg sbe lbhe Clguba cebtenzf ol cebivqvat na vagresnpr gb gur TAH
trggrkg zrffntr pngnybt yvoenel.''')
def test_the_alternative_interface(self):
eq = self.assertEqual
# test the alternative interface
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')
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):
self.assertEqual(gettext.bindtextdomain('gettext'), self.localedir)
def test_textdomain(self):
self.assertEqual(gettext.textdomain(), 'gettext')
def test_some_translations(self):
eq = self.assertEqual
# test some translations
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
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
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
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
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
fhccbeg sbe lbhe Clguba cebtenzf ol cebivqvat na vagresnpr gb gur TAH
trggrkg zrffntr pngnybt yvoenel.''')
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)
eq(x, 'Hay %s fichero')
x = gettext.ngettext('There is %s file', 'There are %s files', 2)
eq(x, 'Hay %s ficheros')
def test_plural_forms2(self):
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)
eq(x, 'Hay %s fichero')
x = t.ngettext('There is %s file', 'There are %s files', 2)
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) ])
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) ])
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) ])
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) ])
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) ])
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) ])
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) ])
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) ])
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) ])
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:
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')
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())
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 the Python test_gettext.py module.
# Copyright (C) 2001 Python Software Foundation
# Barry Warsaw <barry@python.org>, 2000.
#
msgid ""
msgstr ""
"Project-Id-Version: 2.0\n"
"PO-Revision-Date: 2003-04-11 14:32-0400\n"
"Last-Translator: J. David Ibanez <j-david@noos.fr>\n"
"Language-Team: XX <python-dev@python.org>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=iso-8859-1\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: pygettext.py 1.1\n"
"Plural-Forms: nplurals=2; plural=n!=1;\n"
#: test_gettext.py:19 test_gettext.py:25 test_gettext.py:31 test_gettext.py:37
#: test_gettext.py:51 test_gettext.py:80 test_gettext.py:86 test_gettext.py:92
#: test_gettext.py:98
msgid "nudge nudge"
msgstr "wink wink"
#: test_gettext.py:16 test_gettext.py:22 test_gettext.py:28 test_gettext.py:34
#: test_gettext.py:77 test_gettext.py:83 test_gettext.py:89 test_gettext.py:95
msgid "albatross"
msgstr ""
#: test_gettext.py:18 test_gettext.py:24 test_gettext.py:30 test_gettext.py:36
#: test_gettext.py:79 test_gettext.py:85 test_gettext.py:91 test_gettext.py:97
msgid "Raymond Luxury Yach-t"
msgstr "Throatwobbler Mangrove"
#: test_gettext.py:17 test_gettext.py:23 test_gettext.py:29 test_gettext.py:35
#: test_gettext.py:56 test_gettext.py:78 test_gettext.py:84 test_gettext.py:90
#: test_gettext.py:96
msgid "mullusk"
msgstr "bacon"
#: test_gettext.py:40 test_gettext.py:101
msgid ""
"This module provides internationalization and localization\n"
"support for your Python programs by providing an interface to the GNU\n"
"gettext message catalog library."
msgstr ""
"Guvf zbqhyr cebivqrf vagreangvbanyvmngvba naq ybpnyvmngvba\n"
"fhccbeg sbe lbhe Clguba cebtenzf ol cebivqvat na vagresnpr gb gur TAH\n"
"trggrkg zrffntr pngnybt yvoenel."
# Manually added, as neither pygettext nor xgettext support plural forms
# in Python.
msgid "There is %s file"
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 <barry@python.org>, 2000.
#
msgid ""
msgstr ""
"Project-Id-Version: 2.0\n"
"PO-Revision-Date: 2003-04-11 12:42-0400\n"
"Last-Translator: Barry A. WArsaw <barry@python.org>\n"
"Language-Team: XX <python-dev@python.org>\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"
'''
Reference in a new issue View git blame Copy permalink