diff -r f7eda8165e6f Objects/unicodeobject.c --- a/Objects/unicodeobject.c Sat Jan 26 12:14:02 2013 +0200 +++ b/Objects/unicodeobject.c Sat Jan 26 23:55:55 2013 +0200 @@ -4415,37 +4415,34 @@ end = s + size; while (s < end) { + if (end-s < Py_UNICODE_SIZE) { + endinpos = end-starts; + reason = "truncated input"; + goto error; + } memcpy(p, s, sizeof(Py_UNICODE)); +#ifdef Py_UNICODE_WIDE /* We have to sanity check the raw data, otherwise doom looms for some malformed UCS-4 data. */ - if ( -#ifdef Py_UNICODE_WIDE - *p > unimax || *p < 0 || + if (*p > unimax || *p < 0) { + endinpos = s - starts + Py_UNICODE_SIZE; + reason = "illegal code point (> 0x10FFFF)"; + goto error; + } #endif - end-s < Py_UNICODE_SIZE - ) - { - startinpos = s - starts; - if (end-s < Py_UNICODE_SIZE) { - endinpos = end-starts; - reason = "truncated input"; - } - else { - endinpos = s - starts + Py_UNICODE_SIZE; - reason = "illegal code point (> 0x10FFFF)"; - } - outpos = p - PyUnicode_AS_UNICODE(v); - if (unicode_decode_call_errorhandler( - errors, &errorHandler, - "unicode_internal", reason, - &starts, &end, &startinpos, &endinpos, &exc, &s, - &v, &outpos, &p)) { - goto onError; - } - } - else { - p++; - s += Py_UNICODE_SIZE; + p++; + s += Py_UNICODE_SIZE; + continue; + + error: + startinpos = s - starts; + outpos = p - PyUnicode_AS_UNICODE(v); + if (unicode_decode_call_errorhandler( + errors, &errorHandler, + "unicode_internal", reason, + &starts, &end, &startinpos, &endinpos, &exc, &s, + &v, &outpos, &p)) { + goto onError; } }