#2834: Change re module semantics, so that str and bytes mixing is forbidden,
and str (unicode) patterns get full unicode matching by default. The re.ASCII
flag is also introduced to ask for ASCII matching instead.
diff --git a/Modules/_sre.c b/Modules/_sre.c
index 64fc513..2a54d8e 100644
--- a/Modules/_sre.c
+++ b/Modules/_sre.c
@@ -1691,7 +1691,7 @@
/* get pointer to string buffer */
view.len = -1;
buffer = Py_TYPE(string)->tp_as_buffer;
- if (!buffer || !buffer->bf_getbuffer ||
+ if (!buffer || !buffer->bf_getbuffer ||
(*buffer->bf_getbuffer)(string, &view, PyBUF_SIMPLE) < 0) {
PyErr_SetString(PyExc_TypeError, "expected string or buffer");
return NULL;
@@ -1717,7 +1717,7 @@
if (PyBytes_Check(string) || bytes == size)
charsize = 1;
#if defined(HAVE_UNICODE)
- else if (bytes == (Py_ssize_t) (size * sizeof(Py_UNICODE)))
+ else if (bytes == (Py_ssize_t) (size * sizeof(Py_UNICODE)))
charsize = sizeof(Py_UNICODE);
#endif
else {
@@ -1729,7 +1729,7 @@
*p_charsize = charsize;
if (ptr == NULL) {
- PyErr_SetString(PyExc_ValueError,
+ PyErr_SetString(PyExc_ValueError,
"Buffer is NULL");
}
return ptr;
@@ -1754,6 +1754,17 @@
if (!ptr)
return NULL;
+ if (charsize == 1 && pattern->charsize > 1) {
+ PyErr_SetString(PyExc_TypeError,
+ "can't use a string pattern on a bytes-like object");
+ return NULL;
+ }
+ if (charsize > 1 && pattern->charsize == 1) {
+ PyErr_SetString(PyExc_TypeError,
+ "can't use a bytes pattern on a string-like object");
+ return NULL;
+ }
+
/* adjust boundaries */
if (start < 0)
start = 0;
@@ -2682,6 +2693,16 @@
return NULL;
}
+ if (pattern == Py_None)
+ self->charsize = -1;
+ else {
+ Py_ssize_t p_length;
+ if (!getstring(pattern, &p_length, &self->charsize)) {
+ PyObject_DEL(self);
+ return NULL;
+ }
+ }
+
Py_INCREF(pattern);
self->pattern = pattern;