Skip to content
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 7 additions & 9 deletions Lib/test/test_binascii.py
Original file line number Diff line number Diff line change
Expand Up @@ -240,23 +240,21 @@ def assertNonBase64Data(data, expected, ignorechars):

def test_base64_excess_data(self):
# Test excess data exceptions
def assertExcessData(data, non_strict_expected,
ignore_padchar_expected=None):
def assertExcessData(data, non_strict_expected):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

rename this from non_strict_expected to just expected.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In strict mode you get an error. You get that value only in non-strict mode, either when strict_mode=False, or when ignorechars contains "=".

But I agree that expected is shorter. The old name was even longer: non_strict_mode_expected_result.

assert_regex = r'(?i)Excess data'
data = self.type2test(data)
with self.assertRaisesRegex(binascii.Error, assert_regex):
binascii.a2b_base64(data, strict_mode=True)
self.assertEqual(binascii.a2b_base64(data, strict_mode=False),
non_strict_expected)
if ignore_padchar_expected is not None:
self.assertEqual(binascii.a2b_base64(data, strict_mode=True,
ignorechars=b'='),
ignore_padchar_expected)
self.assertEqual(binascii.a2b_base64(data, strict_mode=True,
ignorechars=b'='),
non_strict_expected)
self.assertEqual(binascii.a2b_base64(data), non_strict_expected)

assertExcessData(b'ab==c', b'i')
assertExcessData(b'ab==cd', b'i', b'i\xb7\x1d')
assertExcessData(b'abc=d', b'i\xb7', b'i\xb7\x1d')
assertExcessData(b'ab==c=', b'i\xb7')
assertExcessData(b'ab==cd', b'i\xb7\x1d')
assertExcessData(b'abc=d', b'i\xb7\x1d')

def test_base64errors(self):
# Test base64 with invalid padding
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
Base64 decoder (see :func:`binascii.a2b_base64`, :func:`base64.b64decode`, etc) no
longer ignores excess data after the first padded quad in non-strict
(default) mode. Instead, in conformance with :rfc:`4648`, it ignores
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess this is in accordance with the MAY in https://datatracker.ietf.org/doc/html/rfc4648#section-3.3 about ignoring PADs as non-alphabet data? it'd be good to cite the specific section.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

the pad character, "=", if it is present before the end of the encoded data.
43 changes: 15 additions & 28 deletions Modules/binascii.c
Original file line number Diff line number Diff line change
Expand Up @@ -640,36 +640,24 @@ binascii_a2b_base64_impl(PyObject *module, Py_buffer *data, int strict_mode,
*/
if (this_ch == BASE64_PAD) {
pads++;

if (strict_mode) {
if (quad_pos >= 2 && quad_pos + pads <= 4) {
continue;
}
if (ignorechar(BASE64_PAD, ignorechars, ignorecache)) {
continue;
}
if (quad_pos == 1) {
/* Set an error below. */
break;
}
state = get_binascii_state(module);
if (state) {
PyErr_SetString(state->Error,
(quad_pos == 0 && ascii_data == data->buf)
? "Leading padding not allowed"
: "Excess padding not allowed");
}
goto error_end;
if (quad_pos >= 2 && quad_pos + pads <= 4) {
continue;
}
else {
if (quad_pos >= 2 && quad_pos + pads >= 4) {
/* A pad sequence means we should not parse more input.
** We've already interpreted the data from the quad at this point.
*/
goto done;
}
if (!strict_mode || ignorechar(BASE64_PAD, ignorechars, ignorecache)) {
continue;
}
if (quad_pos == 1) {
/* Set an error below. */
break;
}
state = get_binascii_state(module);
if (state) {
PyErr_SetString(state->Error,
(quad_pos == 0 && ascii_data == data->buf)
? "Leading padding not allowed"
: "Excess padding not allowed");
}
goto error_end;
}

unsigned char v = table_a2b_base64[this_ch];
Expand Down Expand Up @@ -748,7 +736,6 @@ binascii_a2b_base64_impl(PyObject *module, Py_buffer *data, int strict_mode,
goto error_end;
}

done:
return PyBytesWriter_FinishWithPointer(writer, bin_data);

error_end:
Expand Down
Loading