Issue #5057: fix a bug in the peepholer that led to non-portable pyc files between narrow and wide builds while optimizing BINARY_SUBSCR on non-BMP chars (e.g. "\U00012345"[0]).

1 files changed, 18 insertions, 0 deletions

diff --git a/Python/peephole.c b/Python/peephole.c
index 06e7fe6..c27878c 100644
--- a/Python/peephole.c
+++ b/Python/peephole.c
@@ -124,6 +124,24 @@ 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);