Skip to content

gh-139156: Use PyBytesWriter in PyUnicode_AsRawUnicodeEscapeString() #139250

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 1 commit into from
Sep 22, 2025
Merged

gh-139156: Use PyBytesWriter in PyUnicode_AsRawUnicodeEscapeString() #139250

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
37 changes: 13 additions & 24 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7155,41 +7155,34 @@ PyUnicode_DecodeRawUnicodeEscape(const char *s,
PyObject *
PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
{
PyObject *repr;
char *p;
Py_ssize_t expandsize, pos;
int kind;
const void *data;
Py_ssize_t len;

if (!PyUnicode_Check(unicode)) {
PyErr_BadArgument();
return NULL;
}
kind = PyUnicode_KIND(unicode);
data = PyUnicode_DATA(unicode);
len = PyUnicode_GET_LENGTH(unicode);
int kind = PyUnicode_KIND(unicode);
const void *data = PyUnicode_DATA(unicode);
Py_ssize_t len = PyUnicode_GET_LENGTH(unicode);
if (len == 0) {
return Py_GetConstant(Py_CONSTANT_EMPTY_BYTES);
}
if (kind == PyUnicode_1BYTE_KIND) {
return PyBytes_FromStringAndSize(data, len);
}

/* 4 byte characters can take up 10 bytes, 2 byte characters can take up 6
bytes, and 1 byte characters 4. */
expandsize = kind * 2 + 2;

Py_ssize_t expandsize = kind * 2 + 2;
if (len > PY_SSIZE_T_MAX / expandsize) {
return PyErr_NoMemory();
}
repr = PyBytes_FromStringAndSize(NULL, expandsize * len);
if (repr == NULL) {

PyBytesWriter *writer = PyBytesWriter_Create(expandsize * len);
if (writer == NULL) {
return NULL;
}
if (len == 0) {
return repr;
}
char *p = PyBytesWriter_GetData(writer);

p = PyBytes_AS_STRING(repr);
for (pos = 0; pos < len; pos++) {
for (Py_ssize_t pos = 0; pos < len; pos++) {
Py_UCS4 ch = PyUnicode_READ(kind, data, pos);

/* U+0000-U+00ff range: Copy 8-bit characters as-is */
Expand Down Expand Up @@ -7221,11 +7214,7 @@ PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
}
}

assert(p > PyBytes_AS_STRING(repr));
if (_PyBytes_Resize(&repr, p - PyBytes_AS_STRING(repr)) < 0) {
return NULL;
}
return repr;
return PyBytesWriter_FinishWithPointer(writer, p);
}

/* --- Latin-1 Codec ------------------------------------------------------ */
Expand Down
Loading