[KoCo-CVS] [Commit] KoreanCodecs/test CodecTestBase.py test_all.py test_cp949.py test_euc_kr.py test
Brought to you by:
perky
Menu
▾
▴
[KoCo-CVS] [Commit] KoreanCodecs/test CodecTestBase.py test_all.py test_cp949.py test_euc_kr.py test_hangul.py test_iso_2022_kr.py test_johab.py test_mackorean.py test_qwerty2bul.py test_unijohab.py
|
From: Hye-Shik C. <pe...@us...> - 2003-01-12 22:54:14
|
perky 03/01/12 14:54:13
Modified: test CodecTestBase.py test_all.py test_cp949.py
test_euc_kr.py test_hangul.py test_iso_2022_kr.py
test_johab.py test_mackorean.py test_qwerty2bul.py
test_unijohab.py
Log:
Remove selective framework for two implementations, 'C' and 'Python'.
We'll maintain only 1 implementation from now.
Accordingly, --with[out]-extension options is removed, too.
Revision Changes Path
1.10 +6 -3 KoreanCodecs/test/CodecTestBase.py
Index: CodecTestBase.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/CodecTestBase.py,v
retrieving revision 1.9
retrieving revision 1.10
diff -u -r1.9 -r1.10
--- CodecTestBase.py 10 Jan 2003 06:08:21 -0000 1.9
+++ CodecTestBase.py 12 Jan 2003 22:54:13 -0000 1.10
@@ -16,7 +16,7 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: CodecTestBase.py,v 1.9 2003/01/10 06:08:21 perky Exp $
+# $Id: CodecTestBase.py,v 1.10 2003/01/12 22:54:13 perky Exp $
#
import StringIO
@@ -46,8 +46,11 @@
def setUp(self):
if not self.textfile_chunk:
- self.textfile_chunk = ('texts/' + self.encoding,
- 'texts/%s.utf-8' % self.encoding) or self.textfile_stream
+ self.textfile_chunk = ('texts/' +
+ self.encoding.replace('korean.', ''),
+ 'texts/%s.utf-8' %
+ self.encoding.replace('korean.', '')
+ ) or self.textfile_stream
if not self.textfile_stream:
self.textfile_stream = self.textfile_chunk # checked above. :)
1.8 +5 -5 KoreanCodecs/test/test_all.py
Index: test_all.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_all.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -u -r1.7 -r1.8
--- test_all.py 10 Jan 2003 03:15:25 -0000 1.7
+++ test_all.py 12 Jan 2003 22:54:13 -0000 1.8
@@ -16,20 +16,20 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_all.py,v 1.7 2003/01/10 03:15:25 perky Exp $
+# $Id: test_all.py,v 1.8 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
-from test_cp949 import TestCP949_CExtension, TestCP949_PurePython
-from test_euc_kr import TestEUCKR_CExtension, TestEUCKR_PurePython
-from test_mackorean import TestMacKorean_PurePython
+from test_cp949 import TestCP949
+from test_euc_kr import TestEUCKR
+from test_mackorean import TestMacKorean
from test_iso_2022_kr import TestISO_2022_KR
from test_johab import TestJOHAB
from test_qwerty2bul import TestQWERTY2BUL
from test_unijohab import TestUNIJOHAB
-from test_hangul import TestHangul_CExtension, TestHangul_PurePython
+from test_hangul import TestHangul
if __name__ == '__main__':
CodecTestBase.main()
1.12 +40 -47 KoreanCodecs/test/test_cp949.py
Index: test_cp949.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_cp949.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -r1.11 -r1.12
--- test_cp949.py 11 Jan 2003 15:01:56 -0000 1.11
+++ test_cp949.py 12 Jan 2003 22:54:13 -0000 1.12
@@ -16,7 +16,7 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_cp949.py,v 1.11 2003/01/11 15:01:56 perky Exp $
+# $Id: test_cp949.py,v 1.12 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
@@ -24,53 +24,46 @@
def unichrs(s):
return u''.join(map(unichr, map(eval, s.split('+'))))
-class Shield:
- class TestCP949Base(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
- encoding = 'cp949'
- textfile_chunk = ('texts/cp949', 'texts/cp949.utf-8')
- errortests = (
- # invalid bytes
- ("abc\x80\x80\xc1\xc4", "strict", None),
- ("abc\xc8", "strict", None),
- ("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\uc894"),
- ("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\uc894\ufffd"),
- ("abc\x80\x80\xc1\xc4", "ignore", u"abc\uc894"),
- )
-
- def test_mapping(self):
- import sys, os
-
- if not os.access('CP949.TXT', os.R_OK):
- sys.stdout.write('skipped -- CP949.TXT not found, download from'
- ' http://www.unicode.org/Public/MAPPINGS'
- '/VENDORS/MICSFT/WINDOWS/CP949.TXT ')
- sys.stdout.flush()
- return
-
- for line in open('CP949.TXT'):
- if not line:
- break
- data = line.split('#')[0].strip().split()
- if len(data) != 2:
- continue
-
- cp949val = eval(data[0])
- if cp949val <= 0x7F:
- cp949ch = chr(cp949val & 0xff)
- elif cp949val >= 0x100:
- cp949ch = chr(cp949val >> 8) + chr(cp949val & 0xff)
- else:
- continue
- unich = unichrs(data[1])
+class TestCP949(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
+ encoding = 'korean.cp949'
+ textfile_chunk = ('texts/cp949', 'texts/cp949.utf-8')
+ errortests = (
+ # invalid bytes
+ ("abc\x80\x80\xc1\xc4", "strict", None),
+ ("abc\xc8", "strict", None),
+ ("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\uc894"),
+ ("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\uc894\ufffd"),
+ ("abc\x80\x80\xc1\xc4", "ignore", u"abc\uc894"),
+ )
+
+ def test_mapping(self):
+ import sys, os
+
+ if not os.access('CP949.TXT', os.R_OK):
+ sys.stdout.write('skipped -- CP949.TXT not found, download from'
+ ' http://www.unicode.org/Public/MAPPINGS'
+ '/VENDORS/MICSFT/WINDOWS/CP949.TXT ')
+ sys.stdout.flush()
+ return
+
+ for line in open('CP949.TXT'):
+ if not line:
+ break
+ data = line.split('#')[0].strip().split()
+ if len(data) != 2:
+ continue
+
+ cp949val = eval(data[0])
+ if cp949val <= 0x7F:
+ cp949ch = chr(cp949val & 0xff)
+ elif cp949val >= 0x100:
+ cp949ch = chr(cp949val >> 8) + chr(cp949val & 0xff)
+ else:
+ continue
+ unich = unichrs(data[1])
- self.assertEqual(unich.encode(self.encoding), cp949ch)
- self.assertEqual(unicode(cp949ch, self.encoding), unich)
-
-class TestCP949_CExtension(Shield.TestCP949Base):
- encoding = 'korean.c.cp949'
-
-class TestCP949_PurePython(Shield.TestCP949Base):
- encoding = 'korean.python.cp949'
+ self.assertEqual(unich.encode(self.encoding), cp949ch)
+ self.assertEqual(unicode(cp949ch, self.encoding), unich)
if __name__ == '__main__':
CodecTestBase.main()
1.9 +18 -25 KoreanCodecs/test/test_euc_kr.py
Index: test_euc_kr.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_euc_kr.py,v
retrieving revision 1.8
retrieving revision 1.9
diff -u -r1.8 -r1.9
--- test_euc_kr.py 9 Jan 2003 23:23:31 -0000 1.8
+++ test_euc_kr.py 12 Jan 2003 22:54:13 -0000 1.9
@@ -16,37 +16,30 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_euc_kr.py,v 1.8 2003/01/09 23:23:31 perky Exp $
+# $Id: test_euc_kr.py,v 1.9 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
-class Shield:
- class TestEUCKR_Base(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
- encoding = 'euc-kr'
- textfile_chunk = ('texts/euc-kr', 'texts/euc-kr.utf-8')
- errortests = (
- # invalid bytes
- ("abc\x80\x80\xc1\xc4", "strict", None),
- ("abc\xc8", "strict", None),
- ("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\uc894"),
- ("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\uc894\ufffd"),
- ("abc\x80\x80\xc1\xc4", "ignore", u"abc\uc894"),
- ("\xc1\x64", "strict", None), # cp949 code H-AE-H
- )
+class TestEUCKR(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
+ encoding = 'korean.euc-kr'
+ textfile_chunk = ('texts/euc-kr', 'texts/euc-kr.utf-8')
+ errortests = (
+ # invalid bytes
+ ("abc\x80\x80\xc1\xc4", "strict", None),
+ ("abc\xc8", "strict", None),
+ ("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\uc894"),
+ ("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\uc894\ufffd"),
+ ("abc\x80\x80\xc1\xc4", "ignore", u"abc\uc894"),
+ ("\xc1\x64", "strict", None), # cp949 code H-AE-H
+ )
- def test_ksx1001_1998(self):
- self.assertEqual(unicode('\xa2\xe6', self.encoding), u'\u20ac')
- self.assertEqual(unicode('\xa2\xe7', self.encoding), u'\u00ae')
- self.assertEqual(u'\u20ac'.encode(self.encoding), '\xa2\xe6')
- self.assertEqual(u'\u00ae'.encode(self.encoding), '\xa2\xe7')
+ def test_ksx1001_1998(self):
+ self.assertEqual(unicode('\xa2\xe6', self.encoding), u'\u20ac')
+ self.assertEqual(unicode('\xa2\xe7', self.encoding), u'\u00ae')
+ self.assertEqual(u'\u20ac'.encode(self.encoding), '\xa2\xe6')
+ self.assertEqual(u'\u00ae'.encode(self.encoding), '\xa2\xe7')
-
-class TestEUCKR_CExtension(Shield.TestEUCKR_Base):
- encoding = 'korean.c.euc-kr'
-
-class TestEUCKR_PurePython(Shield.TestEUCKR_Base):
- encoding = 'korean.python.euc-kr'
if __name__ == '__main__':
CodecTestBase.main()
1.11 +38 -44 KoreanCodecs/test/test_hangul.py
Index: test_hangul.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_hangul.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -u -r1.10 -r1.11
--- test_hangul.py 9 Jan 2003 21:31:44 -0000 1.10
+++ test_hangul.py 12 Jan 2003 22:54:13 -0000 1.11
@@ -16,94 +16,88 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_hangul.py,v 1.10 2003/01/09 21:31:44 perky Exp $
+# $Id: test_hangul.py,v 1.11 2003/01/12 22:54:13 perky Exp $
#
import unittest
+from korean import hangul
-class Shield:
- class TestHangul(unittest.TestCase):
+class TestHangul(unittest.TestCase):
def test_joinsplit(self):
- self.assertEqual(self.h.join([self.h.J, self.h.WA, self.h.L]), u'\uc894')
- self.assertEqual(self.h.join([self.h.JJ, self.h.Null, self.h.Null]), u'\u3149')
- self.assertEqual(self.h.join((self.h.Null, self.h.YI, self.h.Null)), u'\u3162')
-
- self.assertEqual(self.h.split(u'\uc894'), (self.h.J, self.h.WA, self.h.L))
- self.assertEqual(self.h.split(u'\u3149'), (self.h.JJ, self.h.Null, self.h.Null))
- self.assertEqual(self.h.split(u'\u3162'), (self.h.Null, self.h.YI, self.h.Null))
+ self.assertEqual(hangul.join([hangul.J, hangul.WA, hangul.L]), u'\uc894')
+ self.assertEqual(hangul.join([hangul.JJ, hangul.Null, hangul.Null]), u'\u3149')
+ self.assertEqual(hangul.join((hangul.Null, hangul.YI, hangul.Null)), u'\u3162')
+
+ self.assertEqual(hangul.split(u'\uc894'), (hangul.J, hangul.WA, hangul.L))
+ self.assertEqual(hangul.split(u'\u3149'), (hangul.JJ, hangul.Null, hangul.Null))
+ self.assertEqual(hangul.split(u'\u3162'), (hangul.Null, hangul.YI, hangul.Null))
def test_basicspec(self):
- self.assertEqual(self.h.isJaeum(self.h.J), 1)
- self.assertEqual(self.h.isJaeum(self.h.E), 0)
- self.assertEqual(self.h.isMoeum(self.h.L), 0)
- self.assertEqual(self.h.isMoeum(self.h.O), 1)
- self.assertEqual(self.h.ishangul(u'\uc870'), 1)
- self.assertEqual(self.h.ishangul(u'\u382c'), 0)
+ self.assertEqual(hangul.isJaeum(hangul.J), 1)
+ self.assertEqual(hangul.isJaeum(hangul.E), 0)
+ self.assertEqual(hangul.isMoeum(hangul.L), 0)
+ self.assertEqual(hangul.isMoeum(hangul.O), 1)
+ self.assertEqual(hangul.ishangul(u'\uc870'), 1)
+ self.assertEqual(hangul.ishangul(u'\u382c'), 0)
def test_testlong(self):
- self.assertEqual(self.h.isJaeum(u'\u3131\u3134\u3137\u3139'), 1)
- self.assertEqual(self.h.isJaeum(u'\u3131\u314f\u3134\u314f'), 0)
- self.assertEqual(self.h.isJaeum(u''), 0)
-
- self.assertEqual(self.h.isMoeum(u'\u314f\u3151\u3153\u3155'), 1)
- self.assertEqual(self.h.isMoeum(u'\u3131\u314f\u3134\u314f'), 0)
- self.assertEqual(self.h.isMoeum(u''), 0)
-
- self.assertEqual(self.h.ishangul(u'\ud2f0\ud2f0\ub9c8\uc18c\uc774'), 1)
- self.assertEqual(self.h.ishangul(u'\ud2f0\ud2f0\ub9c8 \uc18c\uc774'), 0)
- self.assertEqual(self.h.ishangul(u''), 0)
+ self.assertEqual(hangul.isJaeum(u'\u3131\u3134\u3137\u3139'), 1)
+ self.assertEqual(hangul.isJaeum(u'\u3131\u314f\u3134\u314f'), 0)
+ self.assertEqual(hangul.isJaeum(u''), 0)
+
+ self.assertEqual(hangul.isMoeum(u'\u314f\u3151\u3153\u3155'), 1)
+ self.assertEqual(hangul.isMoeum(u'\u3131\u314f\u3134\u314f'), 0)
+ self.assertEqual(hangul.isMoeum(u''), 0)
+
+ self.assertEqual(hangul.ishangul(u'\ud2f0\ud2f0\ub9c8\uc18c\uc774'), 1)
+ self.assertEqual(hangul.ishangul(u'\ud2f0\ud2f0\ub9c8 \uc18c\uc774'), 0)
+ self.assertEqual(hangul.ishangul(u''), 0)
def test_format_altsuffix(self):
fmt = u'%s\ub294 %s\ub97c %s\ud55c\ub2e4.'
obj1, obj2 = u'\ud61c\uc2dd', u'\uc544\ub77c'
- self.assertEqual(self.h.format(fmt, obj1, obj2, u'\u2661'),
+ self.assertEqual(hangul.format(fmt, obj1, obj2, u'\u2661'),
u'\ud61c\uc2dd\uc740 \uc544\ub77c\ub97c \u2661\ud55c\ub2e4.')
- self.assertEqual(self.h.format(fmt, obj2, obj1, u'\uc2eb\uc5b4'),
+ self.assertEqual(hangul.format(fmt, obj2, obj1, u'\uc2eb\uc5b4'),
u'\uc544\ub77c\ub294 \ud61c\uc2dd\uc744 \uc2eb\uc5b4\ud55c\ub2e4.')
fmt = u'\ud0dc\ucd08\uc5d0 %s\uc640 %s\uac00 \uc788\uc5c8\ub2e4.'
- self.assertEqual(self.h.format(fmt, obj1, obj2),
+ self.assertEqual(hangul.format(fmt, obj1, obj2),
u'\ud0dc\ucd08\uc5d0 \ud61c\uc2dd\uacfc \uc544\ub77c\uac00'
u' \uc788\uc5c8\ub2e4.')
- self.assertEqual(self.h.format(fmt, obj2, obj1),
+ self.assertEqual(hangul.format(fmt, obj2, obj1),
u'\ud0dc\ucd08\uc5d0 \uc544\ub77c\uc640 \ud61c\uc2dd\uc774'
u' \uc788\uc5c8\ub2e4.')
obj1, obj2 = u'Julian', u'Julie'
- self.assertEqual(self.h.format(fmt, obj1, obj2),
+ self.assertEqual(hangul.format(fmt, obj1, obj2),
u'\ud0dc\ucd08\uc5d0 Julian\uacfc Julie\uac00 \uc788\uc5c8\ub2e4.')
- self.assertEqual(self.h.format(fmt, obj2, obj1),
+ self.assertEqual(hangul.format(fmt, obj2, obj1),
u'\ud0dc\ucd08\uc5d0 Julie\uc640 Julian\uc774 \uc788\uc5c8\ub2e4.')
def test_format_idasuffix(self):
fmt = u'%s(\uc785)\ub2c8\ub2e4, %s(\uc778)\ub370, %s(\uc774)\ub2e4'
- self.assertEqual(self.h.format(fmt, *(u'\uc18c\uc774',)*3),
+ self.assertEqual(hangul.format(fmt, *(u'\uc18c\uc774',)*3),
u'\uc18c\uc785\ub2c8\ub2e4, \uc18c\uc778\ub370, \uc18c\uc774\ub2e4')
- self.assertEqual(self.h.format(fmt, *(u'\ub2e4\ub155',)*3),
+ self.assertEqual(hangul.format(fmt, *(u'\ub2e4\ub155',)*3),
u'\ub2e4\ub155\uc785\ub2c8\ub2e4, \ub2e4\ub155\uc778\ub370,'
u' \ub2e4\ub155\uc774\ub2e4')
def test_format_argtypes(self):
fmt = u'%(int)d(\uc785)\ub2c8\ub2e4. %(str)s\uc740 %(str)s\uc5d0' \
u'%(float).2f\uc640'
- self.assertEqual(self.h.format(fmt, int=1, str=u'hmm', float=3.14),
+ self.assertEqual(hangul.format(fmt, int=1, str=u'hmm', float=3.14),
u'1\uc785\ub2c8\ub2e4. hmm\uc740 hmm\uc5d03.14\uc640')
def test_conjoin(self):
- self.assertEqual(self.h.conjoin(u'\u1112\u1161\u11ab\u1100\u1173\u11af\u110b\u1175'
+ self.assertEqual(hangul.conjoin(u'\u1112\u1161\u11ab\u1100\u1173\u11af\u110b\u1175'
u' \u110c\u1169\u11c2\u110b\u1161\u110b\u116d.'),
u'\ud55c\uae00\uc774 \uc88b\uc544\uc694.')
def test_disjoint(self):
- self.assertEqual(self.h.disjoint(u'\ub9c8\ub140\ubc30\ub2ec\ubd80 \ud0a4\ud0a4'),
+ self.assertEqual(hangul.disjoint(u'\ub9c8\ub140\ubc30\ub2ec\ubd80 \ud0a4\ud0a4'),
u'\u1106\u1161\u1102\u1167\u1107\u1162\u1103\u1161\u11af\u1107\u116e'
u' \u110f\u1175\u110f\u1175')
-
-class TestHangul_CExtension(Shield.TestHangul):
- from korean.c import hangul as h
-
-class TestHangul_PurePython(Shield.TestHangul):
- from korean.python import hangul as h
if __name__ == '__main__':
import sys
1.7 +6 -4 KoreanCodecs/test/test_iso_2022_kr.py
Index: test_iso_2022_kr.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_iso_2022_kr.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -r1.6 -r1.7
--- test_iso_2022_kr.py 10 Jan 2003 06:08:22 -0000 1.6
+++ test_iso_2022_kr.py 12 Jan 2003 22:54:13 -0000 1.7
@@ -16,15 +16,17 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_iso_2022_kr.py,v 1.6 2003/01/10 06:08:22 perky Exp $
+# $Id: test_iso_2022_kr.py,v 1.7 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
class TestISO_2022_KR(CodecTestBase.CodecTestBase):
- encoding = 'iso-2022-kr'
- textfile_chunk = ('texts/%s.roundrobin' % encoding, 'texts/%s.utf-8' % encoding)
- textfile_stream = ('texts/%s.stream' % encoding, 'texts/%s.utf-8' % encoding)
+ encoding = 'korean.iso-2022-kr'
+ textfile_chunk = ('texts/iso-2022-kr.roundrobin',
+ 'texts/iso-2022-kr.utf-8')
+ textfile_stream = ('texts/iso-2022-kr.stream',
+ 'texts/iso-2022-kr.utf-8')
roundtriptest = 0
errortests = (
1.4 +2 -2 KoreanCodecs/test/test_johab.py
Index: test_johab.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_johab.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- test_johab.py 9 Jan 2003 21:31:44 -0000 1.3
+++ test_johab.py 12 Jan 2003 22:54:13 -0000 1.4
@@ -16,13 +16,13 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_johab.py,v 1.3 2003/01/09 21:31:44 perky Exp $
+# $Id: test_johab.py,v 1.4 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
class TestJOHAB(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
- encoding = 'johab'
+ encoding = 'korean.johab'
errortests = (
# invalid bytes
("abc\x80\x80\xc1\xc4", "strict", None),
1.5 +43 -49 KoreanCodecs/test/test_mackorean.py
Index: test_mackorean.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_mackorean.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- test_mackorean.py 11 Jan 2003 15:01:56 -0000 1.4
+++ test_mackorean.py 12 Jan 2003 22:54:13 -0000 1.5
@@ -16,7 +16,7 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_mackorean.py,v 1.4 2003/01/11 15:01:56 perky Exp $
+# $Id: test_mackorean.py,v 1.5 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
@@ -24,56 +24,50 @@
def unichrs(s):
return u''.join(map(unichr, map(eval, s.split('+'))))
-class Shield:
- class TestMacKorean_Base(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
- encoding = 'mackorean'
- textfile_chunk = ('texts/mackorean', 'texts/mackorean.utf-8')
- errortests = (
- # invalid bytes
- # \x90 is expected as one byte character in MacKorean.
- ("abc\x90\x90\xc1\xc4", "strict", None),
- ("abc\xc8", "strict", None),
- ("abc\x90\x90\xc1\xc4", "replace", u"abc\ufffd\ufffd\uc894"),
- ("abc\x90\x90\xc1\xc4\xc8", "replace", u"abc\ufffd\ufffd\uc894\ufffd"),
- ("abc\x90\x90\xc1\xc4", "ignore", u"abc\uc894"),
- ("\xc1\x64", "strict", None), # cp949 code H-AE-H
- )
-
- def test_mapping(self):
- import os, sys
-
- if not os.access('KOREAN.TXT', os.R_OK):
- sys.stdout.write('skipped -- KOREAN.TXT not found, download from'
- ' http://www.unicode.org/Public/MAPPINGS'
- '/VENDORS/APPLE/KOREAN.TXT ')
- sys.stdout.flush()
- return
-
- for line in open('KOREAN.TXT'):
- if not line:
- break
- data = line.split('#')[0].strip().split()
- if len(data) != 2:
- continue
-
- macval = eval(data[0])
-
- if macval <= 0x7F:
- macch = chr(macval & 0xff)
- elif macval >= 0x100:
- macch = chr(macval >> 8) + chr(macval & 0xff)
- else:
- continue
- unich = unichrs(data[1])
+class TestMacKorean(CodecTestBase.TestStreamReader, CodecTestBase.CodecTestBase):
+ encoding = 'korean.mackorean'
+ textfile_chunk = ('texts/mackorean', 'texts/mackorean.utf-8')
+ errortests = (
+ # invalid bytes
+ # \x90 is expected as one byte character in MacKorean.
+ ("abc\x90\x90\xc1\xc4", "strict", None),
+ ("abc\xc8", "strict", None),
+ ("abc\x90\x90\xc1\xc4", "replace", u"abc\ufffd\ufffd\uc894"),
+ ("abc\x90\x90\xc1\xc4\xc8", "replace", u"abc\ufffd\ufffd\uc894\ufffd"),
+ ("abc\x90\x90\xc1\xc4", "ignore", u"abc\uc894"),
+ ("\xc1\x64", "strict", None), # cp949 code H-AE-H
+ )
+
+ def test_mapping(self):
+ import os, sys
+
+ if not os.access('KOREAN.TXT', os.R_OK):
+ sys.stdout.write('skipped -- KOREAN.TXT not found, download from'
+ ' http://www.unicode.org/Public/MAPPINGS'
+ '/VENDORS/APPLE/KOREAN.TXT ')
+ sys.stdout.flush()
+ return
+
+ for line in open('KOREAN.TXT'):
+ if not line:
+ break
+ data = line.split('#')[0].strip().split()
+ if len(data) != 2:
+ continue
+
+ macval = eval(data[0])
+
+ if macval <= 0x7F:
+ macch = chr(macval & 0xff)
+ elif macval >= 0x100:
+ macch = chr(macval >> 8) + chr(macval & 0xff)
+ else:
+ continue
+ unich = unichrs(data[1])
- self.assertEqual(unich.encode(self.encoding), macch)
- self.assertEqual(unicode(macch, self.encoding), unich)
+ self.assertEqual(unich.encode(self.encoding), macch)
+ self.assertEqual(unicode(macch, self.encoding), unich)
-#class TestMacKorean_CExtension(Shield.TestMacKorean_Base):
-# encoding = 'korean.c.mackorean'
-
-class TestMacKorean_PurePython(Shield.TestMacKorean_Base):
- encoding = 'korean.python.mackorean'
if __name__ == '__main__':
CodecTestBase.main()
1.5 +2 -2 KoreanCodecs/test/test_qwerty2bul.py
Index: test_qwerty2bul.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_qwerty2bul.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- test_qwerty2bul.py 9 Jan 2003 21:31:44 -0000 1.4
+++ test_qwerty2bul.py 12 Jan 2003 22:54:13 -0000 1.5
@@ -16,13 +16,13 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_qwerty2bul.py,v 1.4 2003/01/09 21:31:44 perky Exp $
+# $Id: test_qwerty2bul.py,v 1.5 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
class TestQWERTY2BUL(CodecTestBase.CodecTestBase):
- encoding = 'qwerty2bul'
+ encoding = 'korean.qwerty2bul'
errortests = (
# invalid bytes
("123\x80\x80whkf", "strict", None),
1.3 +2 -2 KoreanCodecs/test/test_unijohab.py
Index: test_unijohab.py
===================================================================
RCS file: /cvsroot/koco/KoreanCodecs/test/test_unijohab.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- test_unijohab.py 9 Jan 2003 21:31:44 -0000 1.2
+++ test_unijohab.py 12 Jan 2003 22:54:13 -0000 1.3
@@ -16,13 +16,13 @@
# along with KoreanCodecs; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
-# $Id: test_unijohab.py,v 1.2 2003/01/09 21:31:44 perky Exp $
+# $Id: test_unijohab.py,v 1.3 2003/01/12 22:54:13 perky Exp $
#
import CodecTestBase
class TestUNIJOHAB(CodecTestBase.CodecTestBase):
- encoding = 'unijohab'
+ encoding = 'korean.unijohab'
errortests = () # error handling is relying UTF-8 codec.
if __name__ == '__main__':
|
