Print this page
2964 need POSIX 2008 locale object support
Reviewed by: Robert Mustacchi <rm@joyent.com>
Reviewed by: Gordon Ross <gordon.ross@nexenta.com>
Approved by: TBD
   1 /*

   2  * Copyright 2011 Nexenta Systems, Inc.  All rights reserved.
   3  * Copyright (c) 2002-2004 Tim J. Robbins
   4  * All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice, this list of conditions and the following disclaimer.
  11  * 2. Redistributions in binary form must reproduce the above copyright
  12  *    notice, this list of conditions and the following disclaimer in the
  13  *    documentation and/or other materials provided with the distribution.
  14  *
  15  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  16  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  17  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  18  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  19  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  20  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  21  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  22  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  23  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  24  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  25  * SUCH DAMAGE.
  26  */
  27 
  28 #include "lint.h"
  29 #include <errno.h>
  30 #include <limits.h>
  31 #include "runetype.h"
  32 #include <stdlib.h>
  33 #include <string.h>
  34 #include <wchar.h>
  35 #include "mblocal.h"

  36 
  37 static size_t   _UTF8_mbrtowc(wchar_t *_RESTRICT_KYWD,
  38                     const char *_RESTRICT_KYWD,
  39                     size_t, mbstate_t *_RESTRICT_KYWD);
  40 static int      _UTF8_mbsinit(const mbstate_t *);
  41 static size_t   _UTF8_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
  42                     const char **_RESTRICT_KYWD, size_t, size_t,
  43                     mbstate_t *_RESTRICT_KYWD);
  44 static size_t   _UTF8_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  45                     mbstate_t *_RESTRICT_KYWD);
  46 static size_t   _UTF8_wcsnrtombs(char *_RESTRICT_KYWD,
  47                     const wchar_t **_RESTRICT_KYWD,
  48                     size_t, size_t, mbstate_t *_RESTRICT_KYWD);
  49 
  50 typedef struct {
  51         wchar_t ch;
  52         int     want;
  53         wchar_t lbound;
  54 } _UTF8State;
  55 
  56 int
  57 _UTF8_init(_RuneLocale *rl)
  58 {
  59         __mbrtowc = _UTF8_mbrtowc;
  60         __wcrtomb = _UTF8_wcrtomb;
  61         __mbsinit = _UTF8_mbsinit;
  62         __mbsnrtowcs = _UTF8_mbsnrtowcs;
  63         __wcsnrtombs = _UTF8_wcsnrtombs;
  64         _CurrentRuneLocale = rl;
  65 
  66         charset_is_ascii = 0;
  67 
  68         /*
  69          * In theory up to 6 bytes can be used for the encoding,
  70          * but only encodings with more than 4 bytes are illegal.
  71          */
  72         __ctype[520] = 4;
  73         /*
  74          * Note that the other CSWIDTH members are nonsensical for this
  75          * this coding.  They only are valid with EUC codings.
  76          */
  77 
  78         return (0);
  79 }
  80 
  81 static int
  82 _UTF8_mbsinit(const mbstate_t *ps)
  83 {
  84 
  85         return (ps == NULL || ((const _UTF8State *)ps)->want == 0);
  86 }
  87 
  88 static size_t
  89 _UTF8_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  90     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  91 {
  92         _UTF8State *us;
  93         int ch, i, mask, want;
  94         wchar_t lbound, wch;
  95 
  96         us = (_UTF8State *)ps;
  97 
  98         if (us->want < 0 || us->want > 6) {


   1 /*
   2  * Copyright 2013 Garrett D'Amore <garrett@damore.org>
   3  * Copyright 2011 Nexenta Systems, Inc.  All rights reserved.
   4  * Copyright (c) 2002-2004 Tim J. Robbins
   5  * All rights reserved.
   6  *
   7  * Redistribution and use in source and binary forms, with or without
   8  * modification, are permitted provided that the following conditions
   9  * are met:
  10  * 1. Redistributions of source code must retain the above copyright
  11  *    notice, this list of conditions and the following disclaimer.
  12  * 2. Redistributions in binary form must reproduce the above copyright
  13  *    notice, this list of conditions and the following disclaimer in the
  14  *    documentation and/or other materials provided with the distribution.
  15  *
  16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  19  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  20  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  21  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  22  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  23  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  24  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  26  * SUCH DAMAGE.
  27  */
  28 
  29 #include "lint.h"
  30 #include <errno.h>
  31 #include <limits.h>

  32 #include <stdlib.h>
  33 #include <string.h>
  34 #include <wchar.h>
  35 #include "mblocal.h"
  36 #include "lctype.h"
  37 
  38 static size_t   _UTF8_mbrtowc(wchar_t *_RESTRICT_KYWD,
  39                     const char *_RESTRICT_KYWD,
  40                     size_t, mbstate_t *_RESTRICT_KYWD);
  41 static int      _UTF8_mbsinit(const mbstate_t *);
  42 static size_t   _UTF8_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
  43                     const char **_RESTRICT_KYWD, size_t, size_t,
  44                     mbstate_t *_RESTRICT_KYWD);
  45 static size_t   _UTF8_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  46                     mbstate_t *_RESTRICT_KYWD);
  47 static size_t   _UTF8_wcsnrtombs(char *_RESTRICT_KYWD,
  48                     const wchar_t **_RESTRICT_KYWD,
  49                     size_t, size_t, mbstate_t *_RESTRICT_KYWD);
  50 
  51 typedef struct {
  52         wchar_t ch;
  53         int     want;
  54         wchar_t lbound;
  55 } _UTF8State;
  56 
  57 void
  58 _UTF8_init(struct lc_ctype *lct)
  59 {
  60         lct->lc_mbrtowc = _UTF8_mbrtowc;
  61         lct->lc_wcrtomb = _UTF8_wcrtomb;
  62         lct->lc_mbsinit = _UTF8_mbsinit;
  63         lct->lc_mbsnrtowcs = _UTF8_mbsnrtowcs;
  64         lct->lc_wcsnrtombs = _UTF8_wcsnrtombs;
  65         lct->lc_is_ascii = 0;
  66         lct->lc_max_mblen = 4;













  67 }
  68 
  69 static int
  70 _UTF8_mbsinit(const mbstate_t *ps)
  71 {
  72 
  73         return (ps == NULL || ((const _UTF8State *)ps)->want == 0);
  74 }
  75 
  76 static size_t
  77 _UTF8_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  78     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  79 {
  80         _UTF8State *us;
  81         int ch, i, mask, want;
  82         wchar_t lbound, wch;
  83 
  84         us = (_UTF8State *)ps;
  85 
  86         if (us->want < 0 || us->want > 6) {