--- Objects/unicodeobject.c 2006-03-27 23:32:36.000000000 -0800 +++ /home/bsittler/pkgs/python2.4-2.4.3_unicodeobject.c.patched 2006-08-16 12:37:19.000000000 -0700 @@ -1968,7 +1968,29 @@ static const char *hexdigit = "0123456789abcdef"; - repr = PyString_FromStringAndSize(NULL, 2 + 6*size + 1); + /* Initial allocation is based on the longest-possible unichr + escape. + + In wide (UTF-32) builds '\U00xxxxxx' is 10 chars per source + unichr, so in this case it's the longest unichr escape. In + narrow (UTF-16) builds this is five chars per source unichr + since there are two unichrs in the surrogate pair, so in narrow + (UTF-16) builds it's not the longest unichr escape. + + In wide or narrow builds '\uxxxx' is 6 chars per source unichr, + so in the narrow (UTF-16) build case it's the longest unichr + escape. + + */ + + repr = PyString_FromStringAndSize(NULL, + 2 +#ifdef Py_UNICODE_WIDE + + 10*size +#else + + 6*size +#endif + + 1); if (repr == NULL) return NULL; @@ -1993,15 +2015,6 @@ #ifdef Py_UNICODE_WIDE /* Map 21-bit characters to '\U00xxxxxx' */ else if (ch >= 0x10000) { - int offset = p - PyString_AS_STRING(repr); - - /* Resize the string if necessary */ - if (offset + 12 > PyString_GET_SIZE(repr)) { - if (_PyString_Resize(&repr, PyString_GET_SIZE(repr) + 100)) - return NULL; - p = PyString_AS_STRING(repr) + offset; - } - *p++ = '\\'; *p++ = 'U'; *p++ = hexdigit[(ch >> 28) & 0x0000000F]; @@ -2014,8 +2027,8 @@ *p++ = hexdigit[ch & 0x0000000F]; continue; } -#endif - /* Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes */ +#else + /* Map UTF-16 surrogate pairs to '\U00xxxxxx' */ else if (ch >= 0xD800 && ch < 0xDC00) { Py_UNICODE ch2; Py_UCS4 ucs; @@ -2040,6 +2053,7 @@ s--; size++; } +#endif /* Map 16-bit characters to '\uxxxx' */ if (ch >= 256) {