{
BOOL res = TRUE;
wchar_t *wbuf;
- DWORD len, wlen, n = 0;
+ DWORD len, wlen, orig_len, n = 0;
HANDLE handle;
if (self->fd == -1)
have to reduce and recalculate. */
while (wlen > 32766 / sizeof(wchar_t)) {
len /= 2;
+ orig_len = len;
+ /* Reduce the length until we hit the final byte of a UTF-8 sequence
+ * (top bit is unset). Fix for github issue 82052.
+ */
+ while (len > 0 && (((char *)b->buf)[len-1] & 0x80) != 0)
+ --len;
+ /* If we hit a length of 0, something has gone wrong. This shouldn't
+ * be possible, as valid UTF-8 can have at most 3 non-final bytes
+ * before a final one, and our buffer is way longer than that.
+ * But to be on the safe side, if we hit this issue we just restore
+ * the original length and let the console API sort it out.
+ */
+ if (len == 0) {
+ len = orig_len;
+ }
wlen = MultiByteToWideChar(CP_UTF8, 0, b->buf, len, NULL, 0);
}
Py_END_ALLOW_THREADS