def test_basics(self):
s = u"abc123" # all codecs should be able to encode these
for encoding in all_unicode_encodings:
name = codecs.lookup(encoding).name
if encoding.endswith("_codec"):
name += "_codec"
elif encoding == "latin_1":
name = "latin_1"
self.assertEqual(encoding.replace("_", "-"),
name.replace("_", "-"))
(bytes, size) = codecs.getencoder(encoding)(s)
if encoding != "unicode_internal":
self.assertEqual(
size, len(s),
"%r != %r (encoding=%r)" % (size, len(s), encoding))
(chars, size) = codecs.getdecoder(encoding)(bytes)
self.assertEqual(chars, s,
"%r != %r (encoding=%r)" % (chars, s, encoding))
if encoding not in broken_unicode_with_streams:
# check stream reader/writer
q = Queue()
writer = codecs.getwriter(encoding)(q)
encodedresult = ""
for c in s:
writer.write(c)
encodedresult += q.read()
q = Queue()
reader = codecs.getreader(encoding)(q)
decodedresult = u""
for c in encodedresult:
q.write(c)
decodedresult += reader.read()
self.assertEqual(
decodedresult, s,
"%r != %r (encoding=%r)" % (decodedresult, s, encoding))
# check incremental decoder/encoder (fetched via the Python
# and C API) and iterencode()/iterdecode()
try:
encoder = codecs.getincrementalencoder(encoding)()
cencoder = _testcapi.codec_incrementalencoder(encoding)
except LookupError: # no IncrementalEncoder
pass
else:
# check incremental decoder/encoder
encodedresult = ""
for c in s:
encodedresult += encoder.encode(c)
encodedresult += encoder.encode(u"", True)
decoder = codecs.getincrementaldecoder(encoding)()
decodedresult = u""
for c in encodedresult:
decodedresult += decoder.decode(c)
decodedresult += decoder.decode("", True)
self.assertEqual(
decodedresult, s, "%r != %r (encoding=%r)" %
(decodedresult, s, encoding))
# check C API
encodedresult = ""
for c in s:
encodedresult += cencoder.encode(c)
encodedresult += cencoder.encode(u"", True)
cdecoder = _testcapi.codec_incrementaldecoder(encoding)
decodedresult = u""
for c in encodedresult:
decodedresult += cdecoder.decode(c)
decodedresult += cdecoder.decode("", True)
self.assertEqual(
decodedresult, s, "%r != %r (encoding=%r)" %
(decodedresult, s, encoding))
# check iterencode()/iterdecode()
result = u"".join(
codecs.iterdecode(codecs.iterencode(s, encoding),
encoding))
self.assertEqual(
result, s,
"%r != %r (encoding=%r)" % (result, s, encoding))
# check iterencode()/iterdecode() with empty string
result = u"".join(
codecs.iterdecode(codecs.iterencode(u"", encoding),
encoding))
self.assertEqual(result, u"")
def test_basics(self):
s = u"abc123" # all codecs should be able to encode these
for encoding in all_unicode_encodings:
name = codecs.lookup(encoding).name
if encoding.endswith("_codec"):
name += "_codec"
elif encoding == "latin_1":
name = "latin_1"
self.assertEqual(encoding.replace("_", "-"), name.replace("_", "-"))
(bytes, size) = codecs.getencoder(encoding)(s)
if encoding != "unicode_internal":
self.assertEqual(size, len(s), "%r != %r (encoding=%r)" % (size, len(s), encoding))
(chars, size) = codecs.getdecoder(encoding)(bytes)
self.assertEqual(chars, s, "%r != %r (encoding=%r)" % (chars, s, encoding))
if encoding not in broken_unicode_with_streams:
# check stream reader/writer
q = Queue()
writer = codecs.getwriter(encoding)(q)
encodedresult = ""
for c in s:
writer.write(c)
encodedresult += q.read()
q = Queue()
reader = codecs.getreader(encoding)(q)
decodedresult = u""
for c in encodedresult:
q.write(c)
decodedresult += reader.read()
self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding))
# check incremental decoder/encoder (fetched via the Python
# and C API) and iterencode()/iterdecode()
try:
encoder = codecs.getincrementalencoder(encoding)()
cencoder = _testcapi.codec_incrementalencoder(encoding)
except LookupError: # no IncrementalEncoder
pass
else:
# check incremental decoder/encoder
encodedresult = ""
for c in s:
encodedresult += encoder.encode(c)
encodedresult += encoder.encode(u"", True)
decoder = codecs.getincrementaldecoder(encoding)()
decodedresult = u""
for c in encodedresult:
decodedresult += decoder.decode(c)
decodedresult += decoder.decode("", True)
self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding))
# check C API
encodedresult = ""
for c in s:
encodedresult += cencoder.encode(c)
encodedresult += cencoder.encode(u"", True)
cdecoder = _testcapi.codec_incrementaldecoder(encoding)
decodedresult = u""
for c in encodedresult:
decodedresult += cdecoder.decode(c)
decodedresult += cdecoder.decode("", True)
self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding))
# check iterencode()/iterdecode()
result = u"".join(codecs.iterdecode(codecs.iterencode(s, encoding), encoding))
self.assertEqual(result, s, "%r != %r (encoding=%r)" % (result, s, encoding))
# check iterencode()/iterdecode() with empty string
result = u"".join(codecs.iterdecode(codecs.iterencode(u"", encoding), encoding))
self.assertEqual(result, u"")