#8821: do not rely on Unicode strings being terminated with a \u0000, rather explicitly check range before looking for a second surrogate character.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index f2d666d..bfd19eb 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3734,7 +3734,7 @@
ch2 = *s++;
size--;
- if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+ if (ch2 >= 0xDC00 && ch2 <= 0xDFFF && size) {
ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
*p++ = '\\';
*p++ = 'U';
@@ -3976,7 +3976,7 @@
ch2 = *s++;
size--;
- if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+ if (ch2 >= 0xDC00 && ch2 <= 0xDFFF && size) {
ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
*p++ = '\\';
*p++ = 'U';