diff options
Diffstat (limited to 'Lib/test/test_codecs.py')
| -rw-r--r-- | Lib/test/test_codecs.py | 60 |
1 files changed, 59 insertions, 1 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 8153979..3c800f8 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -425,6 +425,10 @@ class UTF8SigTest(ReadTest): ] ) + def test_bug1601501(self): + # SF bug #1601501: check that the codec works with a buffer + unicode("\xef\xbb\xbf", "utf-8-sig") + class EscapeDecodeTest(unittest.TestCase): def test_empty(self): self.assertEquals(codecs.escape_decode(""), ("", 0)) @@ -910,6 +914,18 @@ class StreamReaderTest(unittest.TestCase): f = self.reader(self.stream) self.assertEquals(f.readlines(), [u'\ud55c\n', u'\uae00']) +class EncodedFileTest(unittest.TestCase): + + def test_basic(self): + f = StringIO.StringIO('\xed\x95\x9c\n\xea\xb8\x80') + ef = codecs.EncodedFile(f, 'utf-16-le', 'utf-8') + self.assertEquals(ef.read(), '\\\xd5\n\x00\x00\xae') + + f = StringIO.StringIO() + ef = codecs.EncodedFile(f, 'utf-8', 'latin1') + ef.write('\xc3\xbc') + self.assertEquals(f.getvalue(), '\xfc') + class Str2StrTest(unittest.TestCase): def test_read(self): @@ -1050,6 +1066,14 @@ broken_unicode_with_streams = [ "punycode", "unicode_internal" ] +broken_incremental_coders = broken_unicode_with_streams[:] + +# The following encodings only support "strict" mode +only_strict_mode = [ + "idna", + "zlib_codec", + "bz2_codec", +] try: import bz2 @@ -1099,6 +1123,7 @@ class BasicUnicodeTest(unittest.TestCase): decodedresult += reader.read() self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) + if encoding not in broken_incremental_coders: # check incremental decoder/encoder (fetched via the Python # and C API) and iterencode()/iterdecode() try: @@ -1139,6 +1164,24 @@ class BasicUnicodeTest(unittest.TestCase): result = u"".join(codecs.iterdecode(codecs.iterencode(u"", encoding), encoding)) self.assertEqual(result, u"") + if encoding not in only_strict_mode: + # check incremental decoder/encoder with errors argument + try: + encoder = codecs.getincrementalencoder(encoding)("ignore") + cencoder = _testcapi.codec_incrementalencoder(encoding, "ignore") + except LookupError: # no IncrementalEncoder + pass + else: + encodedresult = "".join(encoder.encode(c) for c in s) + decoder = codecs.getincrementaldecoder(encoding)("ignore") + decodedresult = u"".join(decoder.decode(c) for c in encodedresult) + self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) + + encodedresult = "".join(cencoder.encode(c) for c in s) + cdecoder = _testcapi.codec_incrementaldecoder(encoding, "ignore") + decodedresult = u"".join(cdecoder.decode(c) for c in encodedresult) + self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) + def test_seek(self): # all codecs should be able to encode these s = u"%s\n%s\n" % (100*u"abc123", 100*u"def456") @@ -1214,6 +1257,19 @@ class CharmapTest(unittest.TestCase): (u"", len(allbytes)) ) +class WithStmtTest(unittest.TestCase): + def test_encodedfile(self): + f = StringIO.StringIO("\xc3\xbc") + with codecs.EncodedFile(f, "latin-1", "utf-8") as ef: + self.assertEquals(ef.read(), "\xfc") + + def test_streamreaderwriter(self): + f = StringIO.StringIO("\xc3\xbc") + info = codecs.lookup("utf-8") + with codecs.StreamReaderWriter(f, info.streamreader, + info.streamwriter, 'strict') as srw: + self.assertEquals(srw.read(), u"\xfc") + def test_main(): test_support.run_unittest( @@ -1234,10 +1290,12 @@ def test_main(): IDNACodecTest, CodecsModuleTest, StreamReaderTest, + EncodedFileTest, Str2StrTest, BasicUnicodeTest, BasicStrTest, - CharmapTest + CharmapTest, + WithStmtTest, ) |