Skip to content

gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data #99613

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Dec 1, 2022
Merged

gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data #99613

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8ff13de
gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data
serhiy-storchaka Nov 20, 2022
b99be83
Move tests to test_capi.test_codecs.
serhiy-storchaka Nov 21, 2022
3d23080
Merge branch 'main' into capi-PyUnicode_DecodeUTF8Stateful
serhiy-storchaka Nov 29, 2022
1c07d9f
Merge branch 'main' into capi-PyUnicode_DecodeUTF8Stateful
serhiy-storchaka Nov 30, 2022
fd8c21d
Address review comments.
serhiy-storchaka Nov 30, 2022
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
54 changes: 54 additions & 0 deletions Lib/test/test_capi/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
import unittest
from test.support import import_helper

_testcapi = import_helper.import_module('_testcapi')


class CAPITest(unittest.TestCase):

def test_decodeutf8(self):
"""Test PyUnicode_DecodeUTF8()"""
decodeutf8 = _testcapi.unicode_decodeutf8

for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8(b), s)
self.assertEqual(decodeutf8(b, 'strict'), s)

self.assertRaises(UnicodeDecodeError, decodeutf8, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xff')
self.assertRaises(UnicodeDecodeError, decodeutf8, b'a\xf0\x9f')
self.assertEqual(decodeutf8(b'a\xf0\x9f', 'replace'), 'a\ufffd')
self.assertEqual(decodeutf8(b'a\xf0\x9fb', 'replace'), 'a\ufffdb')

self.assertRaises(LookupError, decodeutf8, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8() with NULL as data and
# negative size.

def test_decodeutf8stateful(self):
"""Test PyUnicode_DecodeUTF8Stateful()"""
decodeutf8stateful = _testcapi.unicode_decodeutf8stateful

for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
b = s.encode('utf-8')
self.assertEqual(decodeutf8stateful(b), (s, len(b)))
self.assertEqual(decodeutf8stateful(b, 'strict'), (s, len(b)))

self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\x80')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xc0')
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xff')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f'), ('a', 1))
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f', 'replace'), ('a', 1))
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'a\xf0\x9fb')
self.assertEqual(decodeutf8stateful(b'a\xf0\x9fb', 'replace'), ('a\ufffdb', 4))

self.assertRaises(LookupError, decodeutf8stateful, b'a\x80', 'foo')
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as data and
# negative size.
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as the address of
# "consumed".


if __name__ == "__main__":
unittest.main()
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/C API/2022-11-20-09-52-50.gh-issue-99612.eBHksg.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fix :c:func:`PyUnicode_DecodeUTF8Stateful` for ASCII-only data:
``*consumed`` was not set.
36 changes: 36 additions & 0 deletions Modules/_testcapi/unicode.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,6 +239,40 @@ unicode_asutf8andsize(PyObject *self, PyObject *args)
return Py_BuildValue("(Nn)", result, utf8_len);
}

/* Test PyUnicode_DecodeUTF8() */
static PyObject *
unicode_decodeutf8(PyObject *self, PyObject *args)
{
const char *data;
Py_ssize_t size;
const char *errors = NULL;

if (!PyArg_ParseTuple(args, "y#|z", &data, &size, &errors))
return NULL;

return PyUnicode_DecodeUTF8(data, size, errors);
}

/* Test PyUnicode_DecodeUTF8Stateful() */
static PyObject *
unicode_decodeutf8stateful(PyObject *self, PyObject *args)
{
const char *data;
Py_ssize_t size;
const char *errors = NULL;
Py_ssize_t consumed = 123456789;
PyObject *result;

if (!PyArg_ParseTuple(args, "y#|z", &data, &size, &errors))
return NULL;

result = PyUnicode_DecodeUTF8Stateful(data, size, errors, &consumed);
if (!result) {
return NULL;
}
return Py_BuildValue("(Nn)", result, consumed);
}

/* Test PyUnicode_Concat() */
static PyObject *
unicode_concat(PyObject *self, PyObject *args)
Expand Down Expand Up @@ -1025,6 +1059,8 @@ static PyMethodDef TestMethods[] = {
{"unicode_asucs4", unicode_asucs4, METH_VARARGS},
{"unicode_asutf8", unicode_asutf8, METH_VARARGS},
{"unicode_asutf8andsize", unicode_asutf8andsize, METH_VARARGS},
{"unicode_decodeutf8", unicode_decodeutf8, METH_VARARGS},
{"unicode_decodeutf8stateful",unicode_decodeutf8stateful, METH_VARARGS},
{"unicode_concat", unicode_concat, METH_VARARGS},
{"unicode_splitlines", unicode_splitlines, METH_VARARGS},
{"unicode_split", unicode_split, METH_VARARGS},
Expand Down
3 changes: 3 additions & 0 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4530,6 +4530,9 @@ unicode_decode_utf8(const char *s, Py_ssize_t size,
}
s += ascii_decode(s, end, PyUnicode_1BYTE_DATA(u));
if (s == end) {
if (consumed) {
*consumed = size;
}
return u;
}

Expand Down