summaryrefslogtreecommitdiff
path: root/Python/peephole.c
diff options
context:
space:
mode:
authorEzio Melotti <ezio.melotti@gmail.com>2011-04-15 16:50:41 +0300
committerEzio Melotti <ezio.melotti@gmail.com>2011-04-15 16:50:41 +0300
commit3913ad265314731c5a8c42b30ca7b7699db94b23 (patch)
tree4fbd008c444f639c4f66960ede6af576bcb8db60 /Python/peephole.c
parentc824d930e6aa56c572dbfd91692f21e264049812 (diff)
parentdeff9f132dec6e792190bd2ea59ee6fc26a4751d (diff)
downloadcpython-3913ad265314731c5a8c42b30ca7b7699db94b23.tar.gz
#5057: Merge with 3.1.
Diffstat (limited to 'Python/peephole.c')
-rw-r--r--Python/peephole.c18
1 files changed, 18 insertions, 0 deletions
diff --git a/Python/peephole.c b/Python/peephole.c
index 6985043917..359eda833b 100644
--- a/Python/peephole.c
+++ b/Python/peephole.c
@@ -133,6 +133,24 @@ fold_binops_on_constants(unsigned char *codestr, PyObject *consts)
break;
case BINARY_SUBSCR:
newconst = PyObject_GetItem(v, w);
+ /* #5057: if v is unicode, there might be differences between
+ wide and narrow builds in cases like '\U00012345'[0].
+ Wide builds will return a non-BMP char, whereas narrow builds
+ will return a surrogate. In both the cases skip the
+ optimization in order to produce compatible pycs.
+ */
+ if (newconst != NULL &&
+ PyUnicode_Check(v) && PyUnicode_Check(newconst)) {
+ Py_UNICODE ch = PyUnicode_AS_UNICODE(newconst)[0];
+#ifdef Py_UNICODE_WIDE
+ if (ch > 0xFFFF) {
+#else
+ if (ch >= 0xD800 && ch <= 0xDFFF) {
+#endif
+ Py_DECREF(newconst);
+ return 0;
+ }
+ }
break;
case BINARY_LSHIFT:
newconst = PyNumber_Lshift(v, w);