locale/FreeBSD/euc.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 1.22 2007/10/13 16:28:21 ache 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 static size_t   _EUC_mbrtowc(wchar_t * __restrict, const char * __restrict,
  55                     size_t, mbstate_t * __restrict, locale_t);
  56 static int      _EUC_mbsinit(const mbstate_t *, locale_t);
  57 static size_t   _EUC_wcrtomb(char * __restrict, wchar_t,
  58                     mbstate_t * __restrict, locale_t);
  59
  60 typedef struct {
  61         int     count[4];
  62         wchar_t bits[4];
  63         wchar_t mask;
  64 } _EucInfo;
  65
  66 typedef struct {
  67         wchar_t ch;
  68         int     set;
  69         int     want;
  70 } _EucState;
  71
  72 /* This will be called by the XL_RELEASE() macro to free the extra storage */
  73 static void
  74 _EUC_free_extra(struct __xlocale_st_runelocale *xrl)
  75 {
  76         free(xrl->_CurrentRuneLocale.__variable);
  77 }
  78
  79 __private_extern__ int
  80 _EUC_init(struct __xlocale_st_runelocale *xrl)
  81 {
  82         _EucInfo *ei;
  83         int x, new__mb_cur_max;
  84         char *v, *e;
  85         _RuneLocale *rl = &xrl->_CurrentRuneLocale;
  86
  87         if (rl->__variable == NULL)
  88                 return (EFTYPE);
  89
  90         v = (char *)rl->__variable;
  91
  92         while (*v == ' ' || *v == '\t')
  93                 ++v;
  94
  95         if ((ei = malloc(sizeof(_EucInfo))) == NULL)
  96                 return (errno == 0 ? ENOMEM : errno);
  97
  98         new__mb_cur_max = 0;
  99         for (x = 0; x < 4; ++x) {
 100                 ei->count[x] = (int)strtol(v, &e, 0);
 101                 if (v == e || !(v = e)) {
 102                         free(ei);
 103                         return (EFTYPE);
 104                 }
 105                 if (new__mb_cur_max < ei->count[x])
 106                         new__mb_cur_max = ei->count[x];
 107                 while (*v == ' ' || *v == '\t')
 108                         ++v;
 109                 ei->bits[x] = (int)strtol(v, &e, 0);
 110                 if (v == e || !(v = e)) {
 111                         free(ei);
 112                         return (EFTYPE);
 113                 }
 114                 while (*v == ' ' || *v == '\t')
 115                         ++v;
 116         }
 117         ei->mask = (int)strtol(v, &e, 0);
 118         if (v == e || !(v = e)) {
 119                 free(ei);
 120                 return (EFTYPE);
 121         }
 122         rl->__variable = ei;
 123         rl->__variable_len = sizeof(_EucInfo);
 124         xrl->__mb_cur_max = new__mb_cur_max;
 125         xrl->__mbrtowc = _EUC_mbrtowc;
 126         xrl->__wcrtomb = _EUC_wcrtomb;
 127         xrl->__mbsinit = _EUC_mbsinit;
 128         xrl->__mb_sb_limit = 256;
 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 __unused)
 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
 149         c &= 0xff;
 150         return ((c & 0x80) ? c == _SS3 ? 3 : c == _SS2 ? 2 : 1 : 0);
 151 }
 152
 153 static size_t
 154 _EUC_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
 155     mbstate_t * __restrict ps, locale_t loc)
 156 {
 157         _EucState *es;
 158         int i, set, want;
 159         wchar_t wc;
 160         const char *os;
 161         struct __xlocale_st_runelocale *rl = loc->__lc_ctype;
 162         _EucInfo *CEI = (_EucInfo *)rl->_CurrentRuneLocale.__variable;
 163
 164         es = (_EucState *)ps;
 165
 166         if (es->want < 0 || es->want > rl->__mb_cur_max || es->set < 0 ||
 167             es->set > 3) {
 168                 errno = EINVAL;
 169                 return ((size_t)-1);
 170         }
 171
 172         if (s == NULL) {
 173                 s = "";
 174                 n = 1;
 175                 pwc = NULL;
 176         }
 177
 178         if (n == 0)
 179                 /* Incomplete multibyte sequence */
 180                 return ((size_t)-2);
 181
 182         os = s;
 183
 184         if (es->want == 0) {
 185                 want = CEI->count[set = _euc_set(*s)];
 186                 if (set == 2 || set == 3) {
 187                         --want;
 188                         if (--n == 0) {
 189                                 /* Incomplete multibyte sequence */
 190                                 es->set = set;
 191                                 es->want = want;
 192                                 es->ch = 0;
 193                                 return ((size_t)-2);
 194                         }
 195                         ++s;
 196                         if (*s == '\0') {
 197                                 errno = EILSEQ;
 198                                 return ((size_t)-1);
 199                         }
 200                 }
 201                 wc = (unsigned char)*s++;
 202         } else {
 203                 set = es->set;
 204                 want = es->want;
 205                 wc = es->ch;
 206         }
 207         for (i = (es->want == 0) ? 1 : 0; i < MIN(want, n); i++) {
 208                 if (*s == '\0') {
 209                         errno = EILSEQ;
 210                         return ((size_t)-1);
 211                 }
 212                 wc = (wc << 8) | (unsigned char)*s++;
 213         }
 214         if (i < want) {
 215                 /* Incomplete multibyte sequence */
 216                 es->set = set;
 217                 es->want = want - i;
 218                 es->ch = wc;
 219                 return ((size_t)-2);
 220         }
 221         wc = (wc & ~CEI->mask) | CEI->bits[set];
 222         if (pwc != NULL)
 223                 *pwc = wc;
 224         es->want = 0;
 225         return (wc == L'\0' ? 0 : s - os);
 226 }
 227
 228 static size_t
 229 _EUC_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps, 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 }