Aren/NetBSD
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Apply SODA Nuriyuki's patch for multibyte support.

Browse Source 
Based on soda-revised2.patch (in private mail) with a change from
soda on tech-userlevel.

Ok christos@.
This commit is contained in:
wiz 2007-06-05 17:48:19 +00:00
parent da51d139a4
commit 8c64f063a1
1 changed files with 77 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

87
bin/ls/util.c
View File

@ -1,4 +1,4 @@
/* $NetBSD: util.c,v 1.30 2006/12/14 14:15:26 christos Exp $ */
/* $NetBSD: util.c,v 1.31 2007/06/05 17:48:19 wiz Exp $ */
/*
* Copyright (c) 1989, 1993, 1994
@ -37,14 +37,13 @@
#if 0
static char sccsid[] = "@(#)util.c 8.5 (Berkeley) 4/28/95";
#else
__RCSID("$NetBSD: util.c,v 1.30 2006/12/14 14:15:26 christos Exp $");
__RCSID("$NetBSD: util.c,v 1.31 2007/06/05 17:48:19 wiz Exp $");
#endif
#endif /* not lint */
#include <sys/types.h>
#include <sys/stat.h>
#include <ctype.h>
#include <err.h>
#include <fts.h>
#include <limits.h>
@ -52,6 +51,8 @@ __RCSID("$NetBSD: util.c,v 1.30 2006/12/14 14:15:26 christos Exp $");
#include <stdlib.h>
#include <string.h>
#include <vis.h>
#include <wchar.h>
#include <wctype.h>
#include "ls.h"
#include "extern.h"
@ -84,17 +85,83 @@ safe_print(const char *src)
/* NOTREACHED */
}
/*
* The reasons why we don't use putwchar(wc) here are:
* - If wc == L'\0', we need to restore the initial shift state, but
* the C language standard doesn't say that putwchar(L'\0') does.
* - It isn't portable to mix a wide-oriented function (i.e. getwchar)
* with byte-oriented functions (printf et al.) in same FILE.
*/
static int
printwc(wchar_t wc, mbstate_t *pst)
{
size_t size;
char buf[MB_LEN_MAX];
size = wcrtomb(buf, wc, pst);
if (size == (size_t)-1) /* This shouldn't happen, but for sure */
return 0;
if (wc == L'\0') {
/* The following condition must be always true, but for sure */
if (size > 0 && buf[size - 1] == '\0')
--size;
}
if (size > 0)
fwrite(buf, 1, size, stdout);
return wc == L'\0' ? 0 : wcwidth(wc);
}
int
printescaped(const char *src)
{
unsigned char c;
int n;
int n = 0;
mbstate_t src_state, stdout_state;
/* The following +1 is to pass '\0' at the end of src to mbrtowc(). */
const char *endptr = src + strlen(src) + 1;
for (n = 0; (c = *src) != '\0'; ++src, ++n)
if (isprint(c))
(void)putchar(c);
else
(void)putchar('?');
/*
* We have to reset src_state each time in this function, because
* the codeset of src pathname may not match with current locale.
* Note that if we pass NULL instead of src_state to mbrtowc(),
* there is no way to reset the state.
*/
memset(&src_state, 0, sizeof(src_state));
memset(&stdout_state, 0, sizeof(stdout_state));
while (src < endptr) {
wchar_t wc;
size_t rv, span = endptr - src;
#if 0
/* soda says:
* Comment this out, because if there are redundant escape sequences
* which exceed 32 bytes, our current implementation doesn't display
* the pathname correctly with above.
*/
if (span > MB_CUR_MAX)
span = MB_CUR_MAX;
#endif
rv = mbrtowc(&wc, src, span, &src_state);
if (rv == 0) { /* assert(wc == L'\0'); */
/* The following may output a shift sequence. */
n += printwc(wc, &stdout_state);
break;
}
if (rv == (size_t)-1) { /* probably errno == EILSEQ */
n += printwc(L'?', &stdout_state);
/* try to skip 1byte, because there is no better way */
src++;
memset(&src_state, 0, sizeof(src_state));
} else if (rv == (size_t)-2) {
if (span < MB_CUR_MAX) { /* incomplete char */
n += printwc(L'?', &stdout_state);
break;
}
src += span; /* a redundant shift sequence? */
} else {
n += printwc(iswprint(wc) ? wc : L'?', &stdout_state);
src += rv;
}
}
return n;
}