summaryrefslogtreecommitdiff
path: root/Lib/test/test_codecs.py
diff options
context:
space:
mode:
authorSenthil Kumaran <senthil@uthcode.com>2015-01-24 19:26:18 -0800
committerSenthil Kumaran <senthil@uthcode.com>2015-01-24 19:26:18 -0800
commit23487ef46988e971aae9abb4f4189d9e1aaa3a88 (patch)
treec7554dc274558e2be0e723f290ab4c1375cce0ef /Lib/test/test_codecs.py
parent1a091835d645e2b82d0396c6bce5a98d393bf683 (diff)
parent1ca81556d041f7ba63c5b55a221f244650f2ee9a (diff)
downloadcpython-23487ef46988e971aae9abb4f4189d9e1aaa3a88.tar.gz
merge from 3.4
Increase http.client.HTTPConnection test coverage. Added a new tunnel test to verify setting of _tunnel_host, _tunnel_port, _tunnel_headers attributes on HTTPConnection object.
Diffstat (limited to 'Lib/test/test_codecs.py')
-rw-r--r--Lib/test/test_codecs.py39
1 files changed, 31 insertions, 8 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index 6629ccd4e2..7fed1f7734 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -349,6 +349,8 @@ class ReadTest(MixInCheckStateHandling):
self.assertRaises(UnicodeEncodeError, "\ud800".encode, self.encoding)
self.assertEqual("[\uDC80]".encode(self.encoding, "backslashreplace"),
"[\\udc80]".encode(self.encoding))
+ self.assertEqual("[\uDC80]".encode(self.encoding, "namereplace"),
+ "[\\udc80]".encode(self.encoding))
self.assertEqual("[\uDC80]".encode(self.encoding, "xmlcharrefreplace"),
"[&#56448;]".encode(self.encoding))
self.assertEqual("[\uDC80]".encode(self.encoding, "ignore"),
@@ -808,6 +810,7 @@ class CP65001Test(ReadTest, unittest.TestCase):
('\udc80', 'ignore', b''),
('\udc80', 'replace', b'?'),
('\udc80', 'backslashreplace', b'\\udc80'),
+ ('\udc80', 'namereplace', b'\\udc80'),
('\udc80', 'surrogatepass', b'\xed\xb2\x80'),
))
else:
@@ -869,6 +872,8 @@ class CP65001Test(ReadTest, unittest.TestCase):
self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "cp65001")
self.assertEqual("[\uDC80]".encode("cp65001", "backslashreplace"),
b'[\\udc80]')
+ self.assertEqual("[\uDC80]".encode("cp65001", "namereplace"),
+ b'[\\udc80]')
self.assertEqual("[\uDC80]".encode("cp65001", "xmlcharrefreplace"),
b'[&#56448;]')
self.assertEqual("[\uDC80]".encode("cp65001", "surrogateescape"),
@@ -890,10 +895,6 @@ class CP65001Test(ReadTest, unittest.TestCase):
"\U00010fff\uD800")
self.assertTrue(codecs.lookup_error("surrogatepass"))
- def test_readline(self):
- self.skipTest("issue #20571: code page 65001 codec does not "
- "support partial decoder yet")
-
class UTF7Test(ReadTest, unittest.TestCase):
encoding = "utf-7"
@@ -1612,6 +1613,12 @@ class CodecsModuleTest(unittest.TestCase):
self.assertEqual(codecs.decode(b'abc'), 'abc')
self.assertRaises(UnicodeDecodeError, codecs.decode, b'\xff', 'ascii')
+ # test keywords
+ self.assertEqual(codecs.decode(obj=b'\xe4\xf6\xfc', encoding='latin-1'),
+ '\xe4\xf6\xfc')
+ self.assertEqual(codecs.decode(b'[\xff]', 'ascii', errors='ignore'),
+ '[]')
+
def test_encode(self):
self.assertEqual(codecs.encode('\xe4\xf6\xfc', 'latin-1'),
b'\xe4\xf6\xfc')
@@ -1620,6 +1627,12 @@ class CodecsModuleTest(unittest.TestCase):
self.assertEqual(codecs.encode('abc'), b'abc')
self.assertRaises(UnicodeEncodeError, codecs.encode, '\xffff', 'ascii')
+ # test keywords
+ self.assertEqual(codecs.encode(obj='\xe4\xf6\xfc', encoding='latin-1'),
+ b'\xe4\xf6\xfc')
+ self.assertEqual(codecs.encode('[\xff]', 'ascii', errors='ignore'),
+ b'[]')
+
def test_register(self):
self.assertRaises(TypeError, codecs.register)
self.assertRaises(TypeError, codecs.register, 42)
@@ -1668,6 +1681,7 @@ class CodecsModuleTest(unittest.TestCase):
"register_error", "lookup_error",
"strict_errors", "replace_errors", "ignore_errors",
"xmlcharrefreplace_errors", "backslashreplace_errors",
+ "namereplace_errors",
"open", "EncodedFile",
"iterencode", "iterdecode",
"BOM", "BOM_BE", "BOM_LE",
@@ -2818,15 +2832,15 @@ class CodePageTest(unittest.TestCase):
self.assertRaisesRegex(UnicodeEncodeError, 'cp932',
codecs.code_page_encode, 932, '\xff')
self.assertRaisesRegex(UnicodeDecodeError, 'cp932',
- codecs.code_page_decode, 932, b'\x81\x00')
+ codecs.code_page_decode, 932, b'\x81\x00', 'strict', True)
self.assertRaisesRegex(UnicodeDecodeError, 'CP_UTF8',
- codecs.code_page_decode, self.CP_UTF8, b'\xff')
+ codecs.code_page_decode, self.CP_UTF8, b'\xff', 'strict', True)
def check_decode(self, cp, tests):
for raw, errors, expected in tests:
if expected is not None:
try:
- decoded = codecs.code_page_decode(cp, raw, errors)
+ decoded = codecs.code_page_decode(cp, raw, errors, True)
except UnicodeDecodeError as err:
self.fail('Unable to decode %a from "cp%s" with '
'errors=%r: %s' % (raw, cp, errors, err))
@@ -2838,7 +2852,7 @@ class CodePageTest(unittest.TestCase):
self.assertLessEqual(decoded[1], len(raw))
else:
self.assertRaises(UnicodeDecodeError,
- codecs.code_page_decode, cp, raw, errors)
+ codecs.code_page_decode, cp, raw, errors, True)
def check_encode(self, cp, tests):
for text, errors, expected in tests:
@@ -2866,7 +2880,12 @@ class CodePageTest(unittest.TestCase):
('[\xff]', 'replace', b'[y]'),
('[\u20ac]', 'replace', b'[?]'),
('[\xff]', 'backslashreplace', b'[\\xff]'),
+ ('[\xff]', 'namereplace',
+ b'[\\N{LATIN SMALL LETTER Y WITH DIAERESIS}]'),
('[\xff]', 'xmlcharrefreplace', b'[&#255;]'),
+ ('\udcff', 'strict', None),
+ ('[\udcff]', 'surrogateescape', b'[\xff]'),
+ ('[\udcff]', 'surrogatepass', None),
))
self.check_decode(932, (
(b'abc', 'strict', 'abc'),
@@ -2876,6 +2895,7 @@ class CodePageTest(unittest.TestCase):
(b'[\xff]', 'ignore', '[]'),
(b'[\xff]', 'replace', '[\ufffd]'),
(b'[\xff]', 'surrogateescape', '[\udcff]'),
+ (b'[\xff]', 'surrogatepass', None),
(b'\x81\x00abc', 'strict', None),
(b'\x81\x00abc', 'ignore', '\x00abc'),
(b'\x81\x00abc', 'replace', '\ufffd\x00abc'),
@@ -2886,9 +2906,12 @@ class CodePageTest(unittest.TestCase):
('abc', 'strict', b'abc'),
('\xe9\u20ac', 'strict', b'\xe9\x80'),
('\xff', 'strict', b'\xff'),
+ # test error handlers
('\u0141', 'strict', None),
('\u0141', 'ignore', b''),
('\u0141', 'replace', b'L'),
+ ('\udc98', 'surrogateescape', b'\x98'),
+ ('\udc98', 'surrogatepass', None),
))
self.check_decode(1252, (
(b'abc', 'strict', 'abc'),