Issue #17223: Fix PyUnicode_FromUnicode() on Windows (16-bit wchar_t type)
to reject invalid UTF-16 surrogate.
diff --git a/Misc/NEWS b/Misc/NEWS
index a0dd2f6..d858cd2 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,9 @@
Core and Builtins
-----------------
+- Issue #17223: Fix PyUnicode_FromUnicode() on Windows (16-bit wchar_t type)
+ to reject invalid UTF-16 surrogate.
+
- Issue #17032: The "global" in the "NameError: global name 'x' is not defined"
error message has been removed. Patch by Ram Rachum.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 2175655..00a6a36 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1384,13 +1384,18 @@
for (iter = begin; iter < end; ) {
#if SIZEOF_WCHAR_T == 2
- if (Py_UNICODE_IS_HIGH_SURROGATE(iter[0])
- && (iter+1) < end
- && Py_UNICODE_IS_LOW_SURROGATE(iter[1]))
- {
- ch = Py_UNICODE_JOIN_SURROGATES(iter[0], iter[1]);
- ++(*num_surrogates);
- iter += 2;
+ if (Py_UNICODE_IS_HIGH_SURROGATE(iter[0])) {
+ if ((iter+1) < end
+ && Py_UNICODE_IS_LOW_SURROGATE(iter[1]))
+ {
+ ch = Py_UNICODE_JOIN_SURROGATES(iter[0], iter[1]);
+ ++(*num_surrogates);
+ iter += 2;
+ }
+ else {
+ PyErr_SetString(PyExc_ValueError, "illegal UTF-16 surrogate");
+ return -1;
+ }
}
else
#endif