--- a/Python/peephole.c Thu Apr 14 07:51:57 2011 +0300 +++ b/Python/peephole.c Thu Apr 14 15:51:14 2011 +0300 @@ -183,6 +183,23 @@ 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) + return 0; +#else + if (ch >= 0xD800 && ch <= 0xDFFF) + return 0; +#endif + } break; case BINARY_LSHIFT: newconst = PyNumber_Lshift(v, w);