locale/euc-fbsd.c

   1 /*-
   2  * Copyright (c) 2002-2004 Tim J. Robbins. All rights reserved.
   3  * Copyright (c) 1993
   4  *      The Regents of the University of California.  All rights reserved.
   5  *
   6  * This code is derived from software contributed to Berkeley by
   7  * Paul Borman at Krystal Technologies.
   8  *
   9  * Redistribution and use in source and binary forms, with or without
  10  * modification, are permitted provided that the following conditions
  11  * are met:
  12  * 1. Redistributions of source code must retain the above copyright
  13  *    notice, this list of conditions and the following disclaimer.
  14  * 2. Redistributions in binary form must reproduce the above copyright
  15  *    notice, this list of conditions and the following disclaimer in the
  16  *    documentation and/or other materials provided with the distribution.
  17  * 3. All advertising materials mentioning features or use of this software
  18  *    must display the following acknowledgement:
  19  *      This product includes software developed by the University of
  20  *      California, Berkeley and its contributors.
  21  * 4. Neither the name of the University nor the names of its contributors
  22  *    may be used to endorse or promote products derived from this software
  23  *    without specific prior written permission.
  24  *
  25  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  26  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  27  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  28  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  29  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  30  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  31  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  32  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  33  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  34  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  35  * SUCH DAMAGE.
  36  */
  37
  38 #if defined(LIBC_SCCS) && !defined(lint)
  39 static char sccsid[] = "@(#)euc.c       8.1 (Berkeley) 6/4/93";
  40 #endif /* LIBC_SCCS and not lint */
  41 #include <sys/param.h>
  42 __FBSDID("$FreeBSD: src/lib/libc/locale/euc.c,v 1.20 2004/06/23 07:01:43 tjr Exp $");
  43
  44 #include "xlocale_private.h"
  45
  46 #include <errno.h>
  47 #include <limits.h>
  48 #include <runetype.h>
  49 #include <stdlib.h>
  50 #include <string.h>
  51 #include <wchar.h>
  52 #include "mblocal.h"
  53
  54 __private_extern__ int  _EUC_init(struct __xlocale_st_runelocale *);
  55 static size_t   _EUC_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t,
  56             mbstate_t * __restrict, locale_t);
  57 static int      _EUC_mbsinit(const mbstate_t *, locale_t);
  58 static size_t   _EUC_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict,
  59             locale_t);
  60
  61 typedef struct {
  62         int     count[4];
  63         wchar_t bits[4];
  64         wchar_t mask;
  65 } _EucInfo;
  66
  67 typedef struct {
  68         wchar_t ch;
  69         int     set;
  70         int     want;
  71 } _EucState;
  72
  73 /* This will be called by the XL_RELEASE() macro to free the extra storage */
  74 static void
  75 _EUC_free_extra(struct __xlocale_st_runelocale *xrl)
  76 {
  77         free(xrl->_CurrentRuneLocale.__variable);
  78 }
  79
  80 __private_extern__ int
  81 _EUC_init(struct __xlocale_st_runelocale *xrl)
  82 {
  83         _EucInfo *ei;
  84         int x, new__mb_cur_max;
  85         char *v, *e;
  86         _RuneLocale *rl = &xrl->_CurrentRuneLocale;
  87
  88         if (rl->__variable == NULL)
  89                 return (EFTYPE);
  90
  91         v = (char *)rl->__variable;
  92
  93         while (*v == ' ' || *v == '\t')
  94                 ++v;
  95
  96         if ((ei = malloc(sizeof(_EucInfo))) == NULL)
  97                 return (errno == 0 ? ENOMEM : errno);
  98
  99         new__mb_cur_max = 0;
 100         for (x = 0; x < 4; ++x) {
 101                 ei->count[x] = (int)strtol(v, &e, 0);
 102                 if (v == e || !(v = e)) {
 103                         free(ei);
 104                         return (EFTYPE);
 105                 }
 106                 if (new__mb_cur_max < ei->count[x])
 107                         new__mb_cur_max = ei->count[x];
 108                 while (*v == ' ' || *v == '\t')
 109                         ++v;
 110                 ei->bits[x] = (int)strtol(v, &e, 0);
 111                 if (v == e || !(v = e)) {
 112                         free(ei);
 113                         return (EFTYPE);
 114                 }
 115                 while (*v == ' ' || *v == '\t')
 116                         ++v;
 117         }
 118         ei->mask = (int)strtol(v, &e, 0);
 119         if (v == e || !(v = e)) {
 120                 free(ei);
 121                 return (EFTYPE);
 122         }
 123         rl->__variable = ei;
 124         rl->__variable_len = sizeof(_EucInfo);
 125         xrl->__mb_cur_max = new__mb_cur_max;
 126         xrl->__mbrtowc = _EUC_mbrtowc;
 127         xrl->__wcrtomb = _EUC_wcrtomb;
 128         xrl->__mbsinit = _EUC_mbsinit;
 129         xrl->__free_extra = (__free_extra_t)_EUC_free_extra;
 130         return (0);
 131 }
 132
 133 static int
 134 _EUC_mbsinit(const mbstate_t *ps, locale_t loc)
 135 {
 136
 137         return (ps == NULL || ((const _EucState *)ps)->want == 0);
 138 }
 139
 140 #define _SS2    0x008e
 141 #define _SS3    0x008f
 142
 143 #define GR_BITS 0x80808080 /* XXX: to be fixed */
 144
 145 static __inline int
 146 _euc_set(u_int c)
 147 {
 148         c &= 0xff;
 149         return ((c & 0x80) ? c == _SS3 ? 3 : c == _SS2 ? 2 : 1 : 0);
 150 }
 151
 152 static size_t
 153 _EUC_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
 154     mbstate_t * __restrict ps, locale_t loc)
 155 {
 156         _EucState *es;
 157         int i, set, want;
 158         wchar_t wc;
 159         const char *os;
 160         struct __xlocale_st_runelocale *rl = loc->__lc_ctype;
 161         _EucInfo *CEI = (_EucInfo *)rl->_CurrentRuneLocale.__variable;
 162
 163         es = (_EucState *)ps;
 164
 165         if (es->want < 0 || es->want > rl->__mb_cur_max || es->set < 0 ||
 166             es->set > 3) {
 167                 errno = EINVAL;
 168                 return ((size_t)-1);
 169         }
 170
 171         if (s == NULL) {
 172                 s = "";
 173                 n = 1;
 174                 pwc = NULL;
 175         }
 176
 177         if (n == 0)
 178                 /* Incomplete multibyte sequence */
 179                 return ((size_t)-2);
 180
 181         os = s;
 182
 183         if (es->want == 0) {
 184                 want = CEI->count[set = _euc_set(*s)];
 185                 if (set == 2 || set == 3) {
 186                         --want;
 187                         if (--n == 0) {
 188                                 /* Incomplete multibyte sequence */
 189                                 es->set = set;
 190                                 es->want = want;
 191                                 es->ch = 0;
 192                                 return ((size_t)-2);
 193                         }
 194                         ++s;
 195                         if (*s == '\0') {
 196                                 errno = EILSEQ;
 197                                 return ((size_t)-1);
 198                         }
 199                 }
 200                 wc = (unsigned char)*s++;
 201         } else {
 202                 set = es->set;
 203                 want = es->want;
 204                 wc = es->ch;
 205         }
 206         for (i = (es->want == 0) ? 1 : 0; i < MIN(want, n); i++) {
 207                 if (*s == '\0') {
 208                         errno = EILSEQ;
 209                         return ((size_t)-1);
 210                 }
 211                 wc = (wc << 8) | (unsigned char)*s++;
 212         }
 213         if (i < want) {
 214                 /* Incomplete multibyte sequence */
 215                 es->set = set;
 216                 es->want = want - i;
 217                 es->ch = wc;
 218                 return ((size_t)-2);
 219         }
 220         wc = (wc & ~CEI->mask) | CEI->bits[set];
 221         if (pwc != NULL)
 222                 *pwc = wc;
 223         es->want = 0;
 224         return (wc == L'\0' ? 0 : s - os);
 225 }
 226
 227 static size_t
 228 _EUC_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps,
 229     locale_t loc)
 230 {
 231         _EucState *es;
 232         wchar_t m, nm;
 233         int i, len;
 234         _EucInfo *CEI = (_EucInfo *)loc->__lc_ctype->_CurrentRuneLocale.__variable;
 235
 236         es = (_EucState *)ps;
 237
 238         if (es->want != 0) {
 239                 errno = EINVAL;
 240                 return ((size_t)-1);
 241         }
 242
 243         if (s == NULL)
 244                 /* Reset to initial shift state (no-op) */
 245                 return (1);
 246
 247         m = wc & CEI->mask;
 248         nm = wc & ~m;
 249
 250         if (m == CEI->bits[1]) {
 251 CodeSet1:
 252                 /* Codeset 1: The first byte must have 0x80 in it. */
 253                 i = len = CEI->count[1];
 254                 while (i-- > 0)
 255                         *s++ = (nm >> (i << 3)) | 0x80;
 256         } else {
 257                 if (m == CEI->bits[0])
 258                         i = len = CEI->count[0];
 259                 else if (m == CEI->bits[2]) {
 260                         i = len = CEI->count[2];
 261                         *s++ = _SS2;
 262                         --i;
 263                         /* SS2 designates G2 into GR */
 264                         nm |= GR_BITS;
 265                 } else if (m == CEI->bits[3]) {
 266                         i = len = CEI->count[3];
 267                         *s++ = _SS3;
 268                         --i;
 269                         /* SS3 designates G3 into GR */
 270                         nm |= GR_BITS;
 271                 } else
 272                         goto CodeSet1;  /* Bletch */
 273                 while (i-- > 0)
 274                         *s++ = (nm >> (i << 3)) & 0xff;
 275         }
 276         return (len);
 277 }