Skip to content

gh-155742: Use PyBytesWriter in decode_unicode_with_escapes() #157587

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

Open
vstinner wants to merge 2 commits into
base: main
Choose a base branch
from
+31 −14
Open

gh-155742: Use PyBytesWriter in decode_unicode_with_escapes() #157587

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
84be0c4
gh-155742: Use PyBytesWriter in decode_unicode_with_escapes()
vstinner Sep 15, 2026
6ba0045
Add two more tests
vstinner Sep 16, 2026
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
19 changes: 18 additions & 1 deletion Lib/test/test_string_literals.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,10 @@
assert ord(h) == 0x1d120
i = r'\U0001d120'
assert list(map(ord, i)) == [92, 85, 48, 48, 48, 49, 100, 49, 50, 48]
j = 'ä'
assert list(map(ord, j)) == [228]
k = '\ä'
assert list(map(ord, k)) == [92, 228]
"""


Expand All @@ -76,7 +80,7 @@ def test_template(self):
# Check that the template doesn't contain any non-printables
# except for \n.
for c in TEMPLATE:
assert c == '\n' or ' ' <= c <= '~', repr(c)
assert c == '\n' or ' ' <= c <= '~' or c == 'ä', repr(c)

def test_eval_str_normal(self):
self.assertEqual(eval(""" 'x' """), 'x')
Expand All @@ -89,6 +93,19 @@ def test_eval_str_normal(self):
self.assertEqual(eval(r""" '\U0001d120' """), chr(0x1d120))
self.assertEqual(eval(""" '\U0001d120' """), chr(0x1d120))

def test_eval_str_unicode(self):
for s in (
'ϼўТλФЙ',
'A͏B ﬖ̳AA̝',
'\U00100000\U0010ffff\U0010fffd',
'ä',
'\\ä',
"\\П",
"áàäéèęöő.\\n",
):
with self.subTest(s=s):
self.assertEqual(eval(f"{s!r}"), s)

def test_eval_str_incomplete(self):
self.assertRaises(SyntaxError, eval, r""" '\x' """)
self.assertRaises(SyntaxError, eval, r""" '\x0' """)
Expand Down
26 changes: 13 additions & 13 deletions Parser/string_parser.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,22 +135,22 @@ static PyObject *
decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
{
PyObject *v;
PyObject *u;
char *buf;
char *p;
const char *end;

/* check for integer overflow */
if (len > (size_t)PY_SSIZE_T_MAX / 6) {
if (len > ((size_t)PY_SSIZE_T_MAX - 1) / 6) {
return NULL;
}
/* "ä" (2 bytes) may become "\U000000E4" (10 bytes), or 1:5
"\ä" (3 bytes) may become "\u005c\U000000E4" (16 bytes), or ~1:6 */
u = PyBytes_FromStringAndSize((char *)NULL, (Py_ssize_t)len * 6);
if (u == NULL) {
/* "ä" (2 bytes) may become "\U000000E4" (10 bytes), or 1:5.
* "\ä" (3 bytes) may become "\u005c\U000000E4" (16 bytes), or ~1:6.
* Add +1 to allow writing a trailing null byte (for strcpy/sprintf). */
PyBytesWriter *writer = PyBytesWriter_Create((Py_ssize_t)len * 6 + 1);
if (writer == NULL) {
return NULL;
}
p = buf = PyBytes_AsString(u);
p = buf = PyBytesWriter_GetData(writer);

@methane methane Sep 17, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

How about just PyMem_Malloc()?

if (p == NULL) {
return NULL;
}
Expand All @@ -174,7 +174,7 @@ decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
Py_ssize_t i;
w = decode_utf8(&s, end);
if (w == NULL) {
Py_DECREF(u);
PyBytesWriter_Discard(writer);
return NULL;
}
kind = PyUnicode_KIND(w);
Expand All @@ -186,7 +186,7 @@ decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
p += 10;
}
/* Should be impossible to overflow */
assert(p - buf <= PyBytes_GET_SIZE(u));
assert(p - buf <= PyBytesWriter_GetSize(writer));
Py_DECREF(w);
}
else {
Expand All @@ -206,14 +206,14 @@ decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
// when we are decoding the string but we preserve the line numbers.
if (v != NULL && first_invalid_escape_ptr != NULL && t != NULL) {
if (warn_invalid_escape_sequence(parser, s, first_invalid_escape_ptr, t) < 0) {
/* We have not decref u before because first_invalid_escape_ptr
points inside u. */
Py_XDECREF(u);
/* We have not discarded the writer before because
* first_invalid_escape_ptr points inside the writer buffer. */
PyBytesWriter_Discard(writer);
Py_DECREF(v);
return NULL;
}
}
Py_XDECREF(u);
PyBytesWriter_Discard(writer);
return v;
}

Expand Down
Loading