diff options
| author | Marc-André Lemburg <mal@egenix.com> | 2002-04-10 17:18:02 (GMT) |
|---|---|---|
| committer | Marc-André Lemburg <mal@egenix.com> | 2002-04-10 17:18:02 (GMT) |
| commit | ce0b664af2b40c71a094b16d33b8310ff749f9df (patch) | |
| tree | 7d8068117b88f805b76d17a6d2523512d0455fc4 /Objects | |
| parent | a9745611def1d7811210d45626f4b5d91d0b927c (diff) | |
| download | cpython-ce0b664af2b40c71a094b16d33b8310ff749f9df.zip cpython-ce0b664af2b40c71a094b16d33b8310ff749f9df.tar.gz cpython-ce0b664af2b40c71a094b16d33b8310ff749f9df.tar.bz2 | |
Added test case for UTF-8 encoding bug #541828.
Diffstat (limited to 'Objects')
| -rw-r--r-- | Objects/unicodeobject.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index a49ff70..57c031f 100644 --- 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)); |