Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit b8b3e6a

Browse filesBrowse files
serhiy-storchakaserhiy-storchaka
authored
[3.11] gh-99612: Fix PyUnicode_DecodeUTF8Stateful() for ASCII-only data (GH-99613) (GH-107224)
Previously *consumed was not set in this case. (cherry picked from commit f08e52c)
1 parent 058741c commit b8b3e6a
Copy full SHA for b8b3e6a

File tree

Expand file treeCollapse file tree

4 files changed

+95
-1
lines changed
Filter options
Expand file treeCollapse file tree

4 files changed

+95
-1
lines changed

‎Lib/test/test_capi/test_codecs.py

Copy file name to clipboard
+54Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
import unittest
2+
from test.support import import_helper
3+
4+
_testcapi = import_helper.import_module('_testcapi')
5+
6+
7+
class CAPITest(unittest.TestCase):
8+
9+
def test_decodeutf8(self):
10+
"""Test PyUnicode_DecodeUTF8()"""
11+
decodeutf8 = _testcapi.unicode_decodeutf8
12+
13+
for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
14+
b = s.encode('utf-8')
15+
self.assertEqual(decodeutf8(b), s)
16+
self.assertEqual(decodeutf8(b, 'strict'), s)
17+
18+
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\x80')
19+
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xc0')
20+
self.assertRaises(UnicodeDecodeError, decodeutf8, b'\xff')
21+
self.assertRaises(UnicodeDecodeError, decodeutf8, b'a\xf0\x9f')
22+
self.assertEqual(decodeutf8(b'a\xf0\x9f', 'replace'), 'a\ufffd')
23+
self.assertEqual(decodeutf8(b'a\xf0\x9fb', 'replace'), 'a\ufffdb')
24+
25+
self.assertRaises(LookupError, decodeutf8, b'a\x80', 'foo')
26+
# TODO: Test PyUnicode_DecodeUTF8() with NULL as data and
27+
# negative size.
28+
29+
def test_decodeutf8stateful(self):
30+
"""Test PyUnicode_DecodeUTF8Stateful()"""
31+
decodeutf8stateful = _testcapi.unicode_decodeutf8stateful
32+
33+
for s in ['abc', '\xa1\xa2', '\u4f60\u597d', 'a\U0001f600']:
34+
b = s.encode('utf-8')
35+
self.assertEqual(decodeutf8stateful(b), (s, len(b)))
36+
self.assertEqual(decodeutf8stateful(b, 'strict'), (s, len(b)))
37+
38+
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\x80')
39+
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xc0')
40+
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'\xff')
41+
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f'), ('a', 1))
42+
self.assertEqual(decodeutf8stateful(b'a\xf0\x9f', 'replace'), ('a', 1))
43+
self.assertRaises(UnicodeDecodeError, decodeutf8stateful, b'a\xf0\x9fb')
44+
self.assertEqual(decodeutf8stateful(b'a\xf0\x9fb', 'replace'), ('a\ufffdb', 4))
45+
46+
self.assertRaises(LookupError, decodeutf8stateful, b'a\x80', 'foo')
47+
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as data and
48+
# negative size.
49+
# TODO: Test PyUnicode_DecodeUTF8Stateful() with NULL as the address of
50+
# "consumed".
51+
52+
53+
if __name__ == "__main__":
54+
unittest.main()

‎Misc/NEWS.d/next/C API/2022-11-20-09-52-50.gh-issue-99612.eBHksg.rst

Copy file name to clipboard
+2Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
Fix :c:func:`PyUnicode_DecodeUTF8Stateful` for ASCII-only data:
2+
``*consumed`` was not set.

‎Modules/_testcapimodule.c

Copy file name to clipboardExpand all lines: Modules/_testcapimodule.c
+36-1Lines changed: 36 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2307,6 +2307,40 @@ unicode_asutf8andsize(PyObject *self, PyObject *args)
23072307
return Py_BuildValue("(Nn)", result, utf8_len);
23082308
}
23092309

2310+
/* Test PyUnicode_DecodeUTF8() */
2311+
static PyObject *
2312+
unicode_decodeutf8(PyObject *self, PyObject *args)
2313+
{
2314+
const char *data;
2315+
Py_ssize_t size;
2316+
const char *errors = NULL;
2317+
2318+
if (!PyArg_ParseTuple(args, "y#|z", &data, &size, &errors))
2319+
return NULL;
2320+
2321+
return PyUnicode_DecodeUTF8(data, size, errors);
2322+
}
2323+
2324+
/* Test PyUnicode_DecodeUTF8Stateful() */
2325+
static PyObject *
2326+
unicode_decodeutf8stateful(PyObject *self, PyObject *args)
2327+
{
2328+
const char *data;
2329+
Py_ssize_t size;
2330+
const char *errors = NULL;
2331+
Py_ssize_t consumed = 123456789;
2332+
PyObject *result;
2333+
2334+
if (!PyArg_ParseTuple(args, "y#|z", &data, &size, &errors))
2335+
return NULL;
2336+
2337+
result = PyUnicode_DecodeUTF8Stateful(data, size, errors, &consumed);
2338+
if (!result) {
2339+
return NULL;
2340+
}
2341+
return Py_BuildValue("(Nn)", result, consumed);
2342+
}
2343+
23102344
static PyObject *
23112345
unicode_findchar(PyObject *self, PyObject *args)
23122346
{
@@ -6562,7 +6596,8 @@ static PyMethodDef TestMethods[] = {
65626596
{"unicode_asucs4", unicode_asucs4, METH_VARARGS},
65636597
{"unicode_asutf8", unicode_asutf8, METH_VARARGS},
65646598
{"unicode_asutf8andsize", unicode_asutf8andsize, METH_VARARGS},
6565-
{"unicode_findchar", unicode_findchar, METH_VARARGS},
6599+
{"unicode_decodeutf8", unicode_decodeutf8, METH_VARARGS},
6600+
{"unicode_decodeutf8stateful",unicode_decodeutf8stateful, METH_VARARGS}, {"unicode_findchar", unicode_findchar, METH_VARARGS},
65666601
{"unicode_copycharacters", unicode_copycharacters, METH_VARARGS},
65676602
#if USE_UNICODE_WCHAR_CACHE
65686603
{"unicode_legacy_string", unicode_legacy_string, METH_VARARGS},

‎Objects/unicodeobject.c

Copy file name to clipboardExpand all lines: Objects/unicodeobject.c
+3Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5120,6 +5120,9 @@ unicode_decode_utf8(const char *s, Py_ssize_t size,
51205120
}
51215121
s += ascii_decode(s, end, PyUnicode_1BYTE_DATA(u));
51225122
if (s == end) {
5123+
if (consumed) {
5124+
*consumed = size;
5125+
}
51235126
return u;
51245127
}
51255128

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.