[issue3672] Ill-formed surrogates not treated as errors during encoding/decoding - Code Review (original) (raw)

OLD

NEW

1 from test import support

2 import unittest

3 import codecs

4 import sys, _testcapi, io

6 class Queue(object):

7 """

8 queue: write bytes at one end, read bytes from the other end

9 """

10 def __init__(self, buffer):

(...skipping 523 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading...

534 "\x00\xff\u07ff\u0800",

535 "\x00\xff\u07ff\u0800\uffff",

536 ]

537 )

538

539 def test_decoder_state(self):

540 u = "\x00\x7f\x80\xff\u0100\u07ff\u0800\uffff\U0010ffff"

541 self.check_state_handling_decode(self.encoding,

542 u, u.encode(self.encoding))

543

544 def test_surrogates(self):

545 self.assertRaises(UnicodeEncodeError, "\ud800".encode, "utf-8")

546 self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "utf-8")

547 self.assertEquals("\ud800".encode("utf-8", "surrogates"), b"\xed\xa0\x80 ")

548 self.assertEquals(b"\xed\xa0\x80".decode("utf-8", "surrogates"), "\ud800 ")

549 self.assertTrue(codecs.lookup_error("surrogates"))

550

544 class UTF7Test(ReadTest):

551 class UTF7Test(ReadTest):

545 encoding = "utf-7"

552 encoding = "utf-7"

546

553

547 def test_partial(self):

554 def test_partial(self):

548 self.check_partial(

555 self.check_partial(

549 "a+-b",

556 "a+-b",

550 [

557 [

551 "a",

558 "a",

552 "a",

559 "a",

553 "a+",

560 "a+",

(...skipping 462 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading...

1016

1023

1017

1024

1018 class NameprepTest(unittest.TestCase):

1025 class NameprepTest(unittest.TestCase):

1019 def test_nameprep(self):

1026 def test_nameprep(self):

1020 from encodings.idna import nameprep

1027 from encodings.idna import nameprep

1021 for pos, (orig, prepped) in enumerate(nameprep_tests):

1028 for pos, (orig, prepped) in enumerate(nameprep_tests):

1022 if orig is None:

1029 if orig is None:

1023 # Skipped

1030 # Skipped

1024 continue

1031 continue

1025 # The Unicode strings are given in UTF-8

1032 # The Unicode strings are given in UTF-8

1026 orig = str(orig, "utf-8")

1033 orig = str(orig, "utf-8", "surrogates")

1027 if prepped is None:

1034 if prepped is None:

1028 # Input contains prohibited characters

1035 # Input contains prohibited characters

1029 self.assertRaises(UnicodeError, nameprep, orig)

1036 self.assertRaises(UnicodeError, nameprep, orig)

1030 else:

1037 else:

1031 prepped = str(prepped, "utf-8")

1038 prepped = str(prepped, "utf-8", "surrogates")

1032 try:

1039 try:

1033 self.assertEquals(nameprep(orig), prepped)

1040 self.assertEquals(nameprep(orig), prepped)

1034 except Exception as e:

1041 except Exception as e:

1035 raise support.TestFailed("Test 3.%d: %s" % (pos+1, str(e)))

1042 raise support.TestFailed("Test 3.%d: %s" % (pos+1, str(e)))

1036

1043

1037 class IDNACodecTest(unittest.TestCase):

1044 class IDNACodecTest(unittest.TestCase):

1038 def test_builtin_decode(self):

1045 def test_builtin_decode(self):

1039 self.assertEquals(str(b"python.org", "idna"), "python.org")

1046 self.assertEquals(str(b"python.org", "idna"), "python.org")

1040 self.assertEquals(str(b"python.org.", "idna"), "python.org.")

1047 self.assertEquals(str(b"python.org.", "idna"), "python.org.")

1041 self.assertEquals(str(b"xn--pythn-mua.org", "idna"), "pyth\xf6n.org")

1048 self.assertEquals(str(b"xn--pythn-mua.org", "idna"), "pyth\xf6n.org")

(...skipping 488 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading...

1530 EncodedFileTest,

1537 EncodedFileTest,

1531 BasicUnicodeTest,

1538 BasicUnicodeTest,

1532 CharmapTest,

1539 CharmapTest,

1533 WithStmtTest,

1540 WithStmtTest,

1534 TypesTest,

1541 TypesTest,

1535 )

1542 )

1536

1543

1537

1544

1538 if __name__ == "__main__":

1545 if __name__ == "__main__":

1539 test_main()

1546 test_main()

OLD

NEW