Lines Matching refs:encoding
79 def check_state_handling_decode(self, encoding, u, s):
81 d = codecs.getincrementaldecoder(encoding)()
96 d = codecs.getincrementaldecoder(encoding)()
101 def check_state_handling_encode(self, encoding, u, s):
103 d = codecs.getincrementalencoder(encoding)()
106 d = codecs.getincrementalencoder(encoding)()
114 # get a StreamReader for the encoding and feed the bytestring version
119 r = codecs.getreader(self.encoding)(q)
121 for (c, partialresult) in zip(input.encode(self.encoding), partialresults, strict=True):
130 d = codecs.getincrementaldecoder(self.encoding)()
132 for (c, partialresult) in zip(input.encode(self.encoding), partialresults, strict=True):
142 for (c, partialresult) in zip(input.encode(self.encoding), partialresults, strict=True):
150 encoded = input.encode(self.encoding)
153 "".join(codecs.iterdecode([bytes([c]) for c in encoded], self.encoding))
158 stream = io.BytesIO(input.encode(self.encoding))
159 return codecs.getreader(self.encoding)(stream)
222 stream = io.BytesIO(data.encode(self.encoding))
223 return codecs.getreader(self.encoding)(stream)
327 stream = io.BytesIO("".join(s).encode(self.encoding))
328 reader = codecs.getreader(self.encoding)(stream)
334 writer = codecs.getwriter(self.encoding)(q)
335 reader = codecs.getreader(self.encoding)(q)
364 s = (s1+s2+s3).encode(self.encoding)
366 reader = codecs.getreader(self.encoding)(stream)
379 s = (s1+s2+s3+s4+s5).encode(self.encoding)
381 reader = codecs.getreader(self.encoding)(stream)
392 self.assertRaises(UnicodeEncodeError, "\ud800".encode, self.encoding)
393 self.assertEqual("[\uDC80]".encode(self.encoding, "backslashreplace"),
394 "[\\udc80]".encode(self.encoding))
395 self.assertEqual("[\uDC80]".encode(self.encoding, "namereplace"),
396 "[\\udc80]".encode(self.encoding))
397 self.assertEqual("[\uDC80]".encode(self.encoding, "xmlcharrefreplace"),
398 "[�]".encode(self.encoding))
399 self.assertEqual("[\uDC80]".encode(self.encoding, "ignore"),
400 "[]".encode(self.encoding))
401 self.assertEqual("[\uDC80]".encode(self.encoding, "replace"),
402 "[?]".encode(self.encoding))
405 self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "ignore"),
406 "[]".encode(self.encoding))
407 self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "replace"),
408 "[??]".encode(self.encoding))
410 bom = "".encode(self.encoding)
413 before_sequence = before.encode(self.encoding)[len(bom):]
414 after_sequence = after.encode(self.encoding)[len(bom):]
419 self.encoding)
420 self.assertEqual(test_string.encode(self.encoding,
423 self.assertEqual(test_sequence.decode(self.encoding,
426 self.assertEqual(test_sequence.decode(self.encoding, "ignore"),
428 self.assertEqual(test_sequence.decode(self.encoding, "replace"),
432 self.assertEqual(test_sequence.decode(self.encoding, "backslashreplace"),
439 data = '\uD901'.encode(self.encoding, 'surrogatepass')
441 dec = codecs.getincrementaldecoder(self.encoding)('surrogatepass')
445 data = '\uDC02'.encode(self.encoding, 'surrogatepass')
447 dec = codecs.getincrementaldecoder(self.encoding)('surrogatepass')
453 encoding = "utf-32"
467 _,_,reader,writer = codecs.lookup(self.encoding)
483 f = codecs.getreader(self.encoding)(s)
487 f = codecs.getreader(self.encoding)(s)
532 self.check_state_handling_decode(self.encoding,
534 self.check_state_handling_decode(self.encoding,
549 encoding = "utf-32-le"
580 self.assertEqual("\U00010203".encode(self.encoding), b"\x03\x02\x01\x00")
595 encoding = "utf-32-be"
626 self.assertEqual("\U00010203".encode(self.encoding), b"\x00\x01\x02\x03")
641 encoding = "utf-16"
651 _,_,reader,writer = codecs.lookup(self.encoding)
667 f = codecs.getreader(self.encoding)(s)
671 f = codecs.getreader(self.encoding)(s)
706 self.check_state_handling_decode(self.encoding,
708 self.check_state_handling_decode(self.encoding,
712 # If encoding is not None, then
718 s = s1.encode(self.encoding)
723 encoding=self.encoding) as reader:
729 codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
734 codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
740 encoding = "utf-16-le"
778 self.assertEqual("\U00010203".encode(self.encoding),
780 self.assertEqual(b'\x00\xd8\x03\xde'.decode(self.encoding),
784 encoding = "utf-16-be"
822 self.assertEqual("\U00010203".encode(self.encoding),
824 self.assertEqual(b'\xd8\x00\xde\x03'.decode(self.encoding),
828 encoding = "utf-8"
857 self.check_state_handling_decode(self.encoding,
858 u, u.encode(self.encoding))
869 self.assertEqual(data.decode(self.encoding, error_handler),
876 self.assertEqual("[\uDC80]".encode(self.encoding, "surrogateescape"),
880 "[\uDC80\uD800\uDFFF]".encode(self.encoding, "surrogateescape")
885 self.assertEqual("abc\ud800def".encode(self.encoding, "surrogatepass"),
887 self.assertEqual("\U00010fff\uD800".encode(self.encoding, "surrogatepass"),
889 self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "surrogatepass"),
892 self.assertEqual(b"abc\xed\xa0\x80def".decode(self.encoding, "surrogatepass"),
894 self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode(self.encoding, "surrogatepass"),
899 b"abc\xed\xa0".decode(self.encoding, "surrogatepass")
901 b"abc\xed\xa0z".decode(self.encoding, "surrogatepass")
917 dec = codecs.getincrementaldecoder(self.encoding)()
922 encoding = "utf-7"
930 self.assertEqual(set_d.encode(self.encoding), set_d.encode('ascii'))
931 self.assertEqual(set_d.encode('ascii').decode(self.encoding), set_d)
934 self.assertEqual(set_o.encode(self.encoding), set_o.encode('ascii'))
935 self.assertEqual(set_o.encode('ascii').decode(self.encoding), set_o)
937 self.assertEqual('a+b'.encode(self.encoding), b'a+-b')
938 self.assertEqual(b'a+-b'.decode(self.encoding), 'a+b')
941 self.assertEqual(ws.encode(self.encoding), ws.encode('ascii'))
942 self.assertEqual(ws.encode('ascii').decode(self.encoding), ws)
946 self.assertEqual(other_ascii.encode(self.encoding),
1020 self.assertEqual('\U000104A0'.encode(self.encoding), b'+2AHcoA-')
1021 self.assertEqual('\ud801\udca0'.encode(self.encoding), b'+2AHcoA-')
1022 self.assertEqual(b'+2AHcoA-'.decode(self.encoding), '\U000104A0')
1023 self.assertEqual(b'+2AHcoA'.decode(self.encoding), '\U000104A0')
1024 self.assertEqual('\u20ac\U000104A0'.encode(self.encoding), b'+IKzYAdyg-')
1025 self.assertEqual(b'+IKzYAdyg-'.decode(self.encoding), '\u20ac\U000104A0')
1026 self.assertEqual(b'+IKzYAdyg'.decode(self.encoding), '\u20ac\U000104A0')
1027 self.assertEqual('\u20ac\u20ac\U000104A0'.encode(self.encoding),
1029 self.assertEqual(b'+IKwgrNgB3KA-'.decode(self.encoding),
1031 self.assertEqual(b'+IKwgrNgB3KA'.decode(self.encoding),
1080 encoding = "utf-8-sig"
1646 self.assertEqual(codecs.decode(obj=b'\xe4\xf6\xfc', encoding='latin-1'),
1660 self.assertEqual(codecs.encode(obj='\xe4\xf6\xfc', encoding='latin-1'),
1760 codecs.open(os_helper.TESTFN, 'wt', 'invalid-encoding')
1897 # The following encoding is not tested, because it's not supposed
1910 for encoding in all_unicode_encodings:
1911 name = codecs.lookup(encoding).name
1912 if encoding.endswith("_codec"):
1914 elif encoding == "latin_1":
1918 self.assertEqual(encoding.replace("_", "-"),
1921 (b, size) = codecs.getencoder(encoding)(s)
1922 self.assertEqual(size, len(s), "encoding=%r" % encoding)
1923 (chars, size) = codecs.getdecoder(encoding)(b)
1924 self.assertEqual(chars, s, "encoding=%r" % encoding)
1926 if encoding not in broken_unicode_with_stateful:
1929 writer = codecs.getwriter(encoding)(q)
1937 reader = codecs.getreader(encoding)(q)
1942 self.assertEqual(decodedresult, s, "encoding=%r" % encoding)
1944 if encoding not in broken_unicode_with_stateful:
1947 encoder = codecs.getincrementalencoder(encoding)()
1956 decoder = codecs.getincrementaldecoder(encoding)()
1962 "encoding=%r" % encoding)
1966 codecs.iterencode(s, encoding), encoding))
1967 self.assertEqual(result, s, "encoding=%r" % encoding)
1971 codecs.iterencode("", encoding), encoding))
1974 if encoding not in ("idna", "mbcs"):
1977 encoder = codecs.getincrementalencoder(encoding)("ignore")
1982 decoder = codecs.getincrementaldecoder(encoding)("ignore")
1986 "encoding=%r" % encoding)
1992 for encoding in all_unicode_encodings:
1993 if encoding not in broken_unicode_with_stateful:
1996 cencoder = _testcapi.codec_incrementalencoder(encoding)
2005 cdecoder = _testcapi.codec_incrementaldecoder(encoding)
2011 "encoding=%r" % encoding)
2013 if encoding not in ("idna", "mbcs"):
2016 cencoder = _testcapi.codec_incrementalencoder(encoding, "ignore")
2021 cdecoder = _testcapi.codec_incrementaldecoder(encoding, "ignore")
2025 "encoding=%r" % encoding)
2030 for encoding in all_unicode_encodings:
2031 if encoding == "idna": # FIXME: See SF bug #1163178
2033 if encoding in broken_unicode_with_stateful:
2035 reader = codecs.getreader(encoding)(io.BytesIO(s.encode(encoding)))
2043 for encoding in all_unicode_encodings:
2044 decoder = codecs.getdecoder(encoding)
2046 if encoding not in ("idna", "punycode"):
2050 for encoding in all_unicode_encodings:
2051 encoder = codecs.getencoder(encoding)
2063 for encoding in all_unicode_encodings:
2064 if encoding not in broken_unicode_with_stateful:
2065 self.check_state_handling_decode(encoding, u, u.encode(encoding))
2066 self.check_state_handling_encode(encoding, u, u.encode(encoding))
2374 encoding = "unicode-escape"
2507 encoding = "raw-unicode-escape"
2653 for encoding in tests:
2655 with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
2664 with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
2673 with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
2683 with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
2692 with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
2735 for encoding in bytes_transform_encodings:
2736 with self.subTest(encoding=encoding):
2738 (o, size) = codecs.getencoder(encoding)(binput)
2740 (i, size) = codecs.getdecoder(encoding)(o)
2745 for encoding in bytes_transform_encodings:
2746 with self.subTest(encoding=encoding):
2747 sin = codecs.encode(b"\x80", encoding)
2748 reader = codecs.getreader(encoding)(io.BytesIO(sin))
2753 for encoding in bytes_transform_encodings:
2754 with self.subTest(encoding=encoding):
2755 sin = codecs.encode(b"\x80", encoding)
2756 reader = codecs.getreader(encoding)(io.BytesIO(sin))
2762 # for encoding and decoding
2765 for encoding in bytes_transform_encodings:
2766 with self.subTest(encoding=encoding):
2769 data = codecs.encode(data, encoding)
2770 view_encoded = codecs.encode(view, encoding)
2773 data = codecs.decode(data, encoding)
2775 view_decoded = codecs.decode(view, encoding)
2781 for encoding in bytes_transform_encodings:
2782 with self.subTest(encoding=encoding):
2783 fmt = (r"{!r} is not a text encoding; "
2785 msg = fmt.format(encoding)
2787 bad_input.encode(encoding)
2792 msg = (r"^'rot_13' is not a text encoding; "
2801 for encoding in bytes_transform_encodings:
2802 with self.subTest(encoding=encoding):
2803 encoded_data = codecs.encode(data, encoding)
2804 fmt = (r"{!r} is not a text encoding; "
2806 msg = fmt.format(encoding)
2808 encoded_data.decode(encoding)
2810 bytearray(encoded_data).decode(encoding)
2816 msg = (r"^'rot_13' is not a text encoding; "
2920 with self.assertWrapped("encoding", exc_type, msg):
2922 with self.assertWrapped("encoding", exc_type, msg):
2988 msg = "^unknown encoding: {}$".format(self.codec_name)
3528 def search_function(encoding):
3529 if encoding == "aaa_8":