Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-23 01:43:53 +00:00
Code Issues Projects Releases Packages Wiki Activity

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

Browse source 
Replace PyBytes_FromStringAndSize() and _PyBytes_Resize() with the
PyBytesWriter API.
This commit is contained in:
Victor Stinner 2025-09-22 23:46:19 +02:00 • committed by GitHub
parent c497694f77
commit 49e83e31bd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 13 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

37
Objects/unicodeobject.c
View file

@ -7141,41 +7141,34 @@ 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 */
@ -7207,11 +7200,7 @@ 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 ------------------------------------------------------ */