5a0aa3dee2
Although glibc gets by with an 8-byte mbstate_t, OpenBSD uses 12 bytes (of the 128 bytes it reserves!). We can actually implement UTF-8 encoding/decoding with a 0-byte mbstate_t which means we can make things work on LP32 too, as long as we accept the limitation that the caller needs to present us with a complete sequence before we'll process it. Our behavior is fine when going from characters to bytes; we just update the source wchar_t** to say how far through the input we got. I'll come back and use the 4 bytes we do have to cope with byte sequences split across multiple input buffers. The fact that we don't support UTF-8 sequences longer than 4 bytes plus the fact that the first byte of a UTF-8 sequence encodes the length means we shouldn't need the other fields OpenBSD used (at the cost of some recomputation in cases where a sequence is split across buffers). This patch also makes the minimal changes necessary to setlocale(3) to make us behave like glibc when an app requests UTF-8. (The difference being that our "C" locale is the same as our "C.UTF-8" locale.) Change-Id: Ied327a8c4643744b3611bf6bb005a9b389ba4c2f
48 lines
1.7 KiB
C
48 lines
1.7 KiB
C
/* $OpenBSD: wctomb.c,v 1.2 2012/12/05 23:20:00 deraadt Exp $ */
|
|
|
|
/*-
|
|
* Copyright (c) 2002-2004 Tim J. Robbins.
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*/
|
|
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <wchar.h>
|
|
|
|
int
|
|
wctomb(char *s, wchar_t wchar)
|
|
{
|
|
static mbstate_t mbs;
|
|
size_t rval;
|
|
|
|
if (s == NULL) {
|
|
/* No support for state dependent encodings. */
|
|
memset(&mbs, 0, sizeof(mbs));
|
|
return (0);
|
|
}
|
|
if ((rval = wcrtomb(s, wchar, &mbs)) == (size_t)-1)
|
|
return (-1);
|
|
return ((int)rval);
|
|
}
|