Skip to content

Commit

Permalink
Make all of test_bytes pass (except pickling, which is too badly bust…
Browse files Browse the repository at this point in the history 
…ed).
  • Loading branch information
@gvanrossum
gvanrossum committed May 4, 2007
1 parent 6c1e674 commit 4355a47
Show file tree
Hide file tree
Showing 3 changed files with 55 additions and 57 deletions.
76 changes: 38 additions & 38 deletions Lib/test/test_bytes.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -102,35 +102,35 @@ def test_compare(self):
self.failIf(b3 <= b2)

def test_compare_to_str(self):
self.assertEqual(b"abc" == "abc", True)
self.assertEqual(b"ab" != "abc", True)
self.assertEqual(b"ab" <= "abc", True)
self.assertEqual(b"ab" < "abc", True)
self.assertEqual(b"abc" >= "ab", True)
self.assertEqual(b"abc" > "ab", True)

self.assertEqual(b"abc" != "abc", False)
self.assertEqual(b"ab" == "abc", False)
self.assertEqual(b"ab" > "abc", False)
self.assertEqual(b"ab" >= "abc", False)
self.assertEqual(b"abc" < "ab", False)
self.assertEqual(b"abc" <= "ab", False)

self.assertEqual("abc" == b"abc", True)
self.assertEqual("ab" != b"abc", True)
self.assertEqual("ab" <= b"abc", True)
self.assertEqual("ab" < b"abc", True)
self.assertEqual("abc" >= b"ab", True)
self.assertEqual("abc" > b"ab", True)

self.assertEqual("abc" != b"abc", False)
self.assertEqual("ab" == b"abc", False)
self.assertEqual("ab" > b"abc", False)
self.assertEqual("ab" >= b"abc", False)
self.assertEqual("abc" < b"ab", False)
self.assertEqual("abc" <= b"ab", False)

# But they should never compare equal to Unicode!
self.assertEqual(b"abc" == str8("abc"), True)
self.assertEqual(b"ab" != str8("abc"), True)
self.assertEqual(b"ab" <= str8("abc"), True)
self.assertEqual(b"ab" < str8("abc"), True)
self.assertEqual(b"abc" >= str8("ab"), True)
self.assertEqual(b"abc" > str8("ab"), True)

self.assertEqual(b"abc" != str8("abc"), False)
self.assertEqual(b"ab" == str8("abc"), False)
self.assertEqual(b"ab" > str8("abc"), False)
self.assertEqual(b"ab" >= str8("abc"), False)
self.assertEqual(b"abc" < str8("ab"), False)
self.assertEqual(b"abc" <= str8("ab"), False)

self.assertEqual(str8("abc") == b"abc", True)
self.assertEqual(str8("ab") != b"abc", True)
self.assertEqual(str8("ab") <= b"abc", True)
self.assertEqual(str8("ab") < b"abc", True)
self.assertEqual(str8("abc") >= b"ab", True)
self.assertEqual(str8("abc") > b"ab", True)

self.assertEqual(str8("abc") != b"abc", False)
self.assertEqual(str8("ab") == b"abc", False)
self.assertEqual(str8("ab") > b"abc", False)
self.assertEqual(str8("ab") >= b"abc", False)
self.assertEqual(str8("abc") < b"ab", False)
self.assertEqual(str8("abc") <= b"ab", False)

# Bytes should never compare equal to Unicode!
# Test this for all expected byte orders and Unicode character sizes
self.assertEqual(b"\0a\0b\0c" == "abc", False)
self.assertEqual(b"\0\0\0a\0\0\0b\0\0\0c" == "abc", False)
Expand Down Expand Up @@ -326,7 +326,7 @@ def test_encoding(self):
sample = "Hello world\n\u1234\u5678\u9abc\udef0"
for enc in ("utf8", "utf16"):
b = bytes(sample, enc)
self.assertEqual(b, bytes(map(ord, sample.encode(enc))))
self.assertEqual(b, bytes(sample.encode(enc)))
self.assertRaises(UnicodeEncodeError, bytes, sample, "latin1")
b = bytes(sample, "latin1", "ignore")
self.assertEqual(b, bytes(sample[:-4]))
Expand All @@ -342,7 +342,7 @@ def test_decode(self):
self.assertEqual(b.decode("utf8", "ignore"), "Hello world\n")

def test_from_buffer(self):
sample = "Hello world\n\x80\x81\xfe\xff"
sample = str8("Hello world\n\x80\x81\xfe\xff")
buf = buffer(sample)
b = bytes(buf)
self.assertEqual(b, bytes(map(ord, sample)))
Expand All @@ -364,8 +364,8 @@ def test_concat(self):
b1 = bytes("abc")
b2 = bytes("def")
self.assertEqual(b1 + b2, bytes("abcdef"))
self.assertEqual(b1 + "def", bytes("abcdef"))
self.assertEqual("def" + b1, bytes("defabc"))
self.assertEqual(b1 + str8("def"), bytes("abcdef"))
self.assertEqual(str8("def") + b1, bytes("defabc"))
self.assertRaises(TypeError, lambda: b1 + "def")
self.assertRaises(TypeError, lambda: "abc" + b2)

Expand All @@ -388,7 +388,7 @@ def test_iconcat(self):
self.assertEqual(b, bytes("abcdef"))
self.assertEqual(b, b1)
self.failUnless(b is b1)
b += "xyz"
b += str8("xyz")
self.assertEqual(b, b"abcdefxyz")
try:
b += ""
Expand Down Expand Up @@ -456,8 +456,8 @@ def test_fromhex(self):
b = bytes([0x1a, 0x2b, 0x30])
self.assertEquals(bytes.fromhex('1a2B30'), b)
self.assertEquals(bytes.fromhex(' 1A 2B 30 '), b)
self.assertEquals(bytes.fromhex(buffer('')), bytes())
self.assertEquals(bytes.fromhex(buffer('0000')), bytes([0, 0]))
self.assertEquals(bytes.fromhex(buffer(b'')), bytes())
self.assertEquals(bytes.fromhex(buffer(b'0000')), bytes([0, 0]))
self.assertRaises(ValueError, bytes.fromhex, 'a')
self.assertRaises(ValueError, bytes.fromhex, 'rt')
self.assertRaises(ValueError, bytes.fromhex, '1a b cd')
Expand Down Expand Up @@ -717,5 +717,5 @@ def test_main():


if __name__ == "__main__":
test_main()
##unittest.main()
##test_main()
unittest.main()
30 changes: 11 additions & 19 deletions Objects/bytesobject.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -218,6 +218,7 @@ bytes_iconcat(PyBytesObject *self, PyObject *other)
Py_ssize_t mysize;
Py_ssize_t size;

/* XXX What if other == self? */
osize = _getbuffer(other, &optr);
if (osize < 0) {
PyErr_Format(PyExc_TypeError,
Expand Down Expand Up @@ -698,34 +699,25 @@ bytes_init(PyBytesObject *self, PyObject *args, PyObject *kwds)

if (PyUnicode_Check(arg)) {
/* Encode via the codec registry */
PyObject *encoded;
char *bytes;
Py_ssize_t size;
PyObject *encoded, *new;
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
encoded = PyCodec_Encode(arg, encoding, errors);
if (encoded == NULL)
return -1;
if (!PyString_Check(encoded)) {
if (!PyBytes_Check(encoded) && !PyString_Check(encoded)) {
PyErr_Format(PyExc_TypeError,
"encoder did not return a string object (type=%.400s)",
"encoder did not return a str8 or bytes object (type=%.400s)",
encoded->ob_type->tp_name);
Py_DECREF(encoded);
return -1;
}
bytes = PyString_AS_STRING(encoded);
size = PyString_GET_SIZE(encoded);
if (size < self->ob_alloc) {
self->ob_size = size;
self->ob_bytes[self->ob_size] = '\0'; /* Trailing null byte */
}
else if (PyBytes_Resize((PyObject *)self, size) < 0) {
Py_DECREF(encoded);
return -1;
}
memcpy(self->ob_bytes, bytes, size);
Py_DECREF(encoded);
return 0;
new = bytes_iconcat(self, encoded);
Py_DECREF(encoded);
if (new == NULL)
return -1;
Py_DECREF(new);
return 0;
}

/* If it's not unicode, there can't be encoding or errors */
Expand Down Expand Up @@ -2689,7 +2681,7 @@ bytes_fromhex(PyObject *cls, PyObject *args)
return NULL;
buf = PyBytes_AS_STRING(newbytes);

for (i = j = 0; ; i += 2) {
for (i = j = 0; i < len; i += 2) {
/* skip over spaces in the input */
while (Py_CHARMASK(hex[i]) == ' ')
i++;
Expand Down
6 changes: 6 additions & 0 deletions Objects/unicodeobject.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5634,6 +5634,12 @@ unicode_encode(PyUnicodeObject *self, PyObject *args)
if (v == NULL)
goto onError;
if (!PyBytes_Check(v)) {
if (PyString_Check(v)) {
/* Old codec, turn it into bytes */
PyObject *b = PyBytes_FromObject(v);
Py_DECREF(v);
return b;
}
PyErr_Format(PyExc_TypeError,
"encoder did not return a bytes object "
"(type=%.400s)",
Expand Down

0 comments on commit 4355a47

Please sign in to comment.