Added test case for UTF-8 encoding bug #541828.

malemburg · malemburg · commit ce0b664af2b4 · 2002-04-10T17:18:02.000Z
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
@@ -508,6 +508,22 @@ def __str__(self):
 verify(u'\udc00'.encode('utf-8') == '\xed\xb0\x80')
 verify((u'\ud800\udc02'*1000).encode('utf-8') ==
        '\xf0\x90\x80\x82'*1000)
+verify(u'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
+       u'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
+       u'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
+       u'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
+       u'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
+       u' Nunstuck git und'.encode('utf-8') == 
+       '\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
+       '\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
+       '\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
+       '\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
+       '\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
+       '\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
+       '\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
+       '\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
+       '\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
+       '\xe3\x80\x8cWenn ist das Nunstuck git und')
 
 # UTF-8 specific decoding tests
 verify(unicode('\xf0\xa3\x91\x96', 'utf-8') == u'\U00023456' )
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
@@ -1224,8 +1224,8 @@ PyObject *PyUnicode_EncodeUTF8(const Py_UNICODE *s,
 		    Py_UCS4 ch2 = s[i];
 		    /* Check for low surrogate */
 		    if (0xDC00 <= ch2 && ch2 <= 0xDFFF) {
-                        ch = ((ch - 0xD800)<<10 | (ch2-0xDC00))+0x10000;
-                        *p++ = (char)((ch >> 18) | 0xf0);
+                        ch = ((ch - 0xD800) << 10 | (ch2 - 0xDC00)) + 0x00010000;
+                        *p++ = (char)(0xf0 | (ch >> 18));
                         *p++ = (char)(0x80 | ((ch >> 12) & 0x3f));
 			*p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
 			*p++ = (char)(0x80 | (ch & 0x3f));
