compiler/clib/locale/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 <errno.h>
  45 #include <limits.h>
  46 #include <runetype.h>
  47 #include <stdlib.h>
  48 #include <string.h>
  49 #include <wchar.h>
  50 #include "mblocal.h"
  51
  52 extern int __mb_sb_limit;
  53
  54 static size_t   _EUC_mbrtowc(wchar_t * __restrict, const char * __restrict,
  55                     size_t, mbstate_t * __restrict);
  56 static int      _EUC_mbsinit(const mbstate_t *);
  57 static size_t   _EUC_wcrtomb(char * __restrict, wchar_t,
  58                     mbstate_t * __restrict);
  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 int
  73 _EUC_init(_RuneLocale *rl)
  74 {
  75         _EucInfo *ei;
  76         int x, new__mb_cur_max;
  77         char *v, *e;
  78
  79         if (rl->__variable == NULL)
  80                 return (EFTYPE);
  81
  82         v = (char *)rl->__variable;
  83
  84         while (*v == ' ' || *v == '\t')
  85                 ++v;
  86
  87         if ((ei = malloc(sizeof(_EucInfo))) == NULL)
  88                 return (errno == 0 ? ENOMEM : errno);
  89
  90         new__mb_cur_max = 0;
  91         for (x = 0; x < 4; ++x) {
  92                 ei->count[x] = (int)strtol(v, &e, 0);
  93                 if (v == e || !(v = e)) {
  94                         free(ei);
  95                         return (EFTYPE);
  96                 }
  97                 if (new__mb_cur_max < ei->count[x])
  98                         new__mb_cur_max = ei->count[x];
  99                 while (*v == ' ' || *v == '\t')
 100                         ++v;
 101                 ei->bits[x] = (int)strtol(v, &e, 0);
 102                 if (v == e || !(v = e)) {
 103                         free(ei);
 104                         return (EFTYPE);
 105                 }
 106                 while (*v == ' ' || *v == '\t')
 107                         ++v;
 108         }
 109         ei->mask = (int)strtol(v, &e, 0);
 110         if (v == e || !(v = e)) {
 111                 free(ei);
 112                 return (EFTYPE);
 113         }
 114         rl->__variable = ei;
 115         rl->__variable_len = sizeof(_EucInfo);
 116         _CurrentRuneLocale = rl;
 117         __mb_cur_max = new__mb_cur_max;
 118         __mbrtowc = _EUC_mbrtowc;
 119         __wcrtomb = _EUC_wcrtomb;
 120         __mbsinit = _EUC_mbsinit;
 121         __mb_sb_limit = 256;
 122         return (0);
 123 }
 124
 125 static int
 126 _EUC_mbsinit(const mbstate_t *ps)
 127 {
 128
 129         return (ps == NULL || ((const _EucState *)ps)->want == 0);
 130 }
 131
 132 #define CEI     ((_EucInfo *)(_CurrentRuneLocale->__variable))
 133
 134 #define _SS2    0x008e
 135 #define _SS3    0x008f
 136
 137 #define GR_BITS 0x80808080 /* XXX: to be fixed */
 138
 139 static __inline int
 140 _euc_set(u_int c)
 141 {
 142
 143         c &= 0xff;
 144         return ((c & 0x80) ? c == _SS3 ? 3 : c == _SS2 ? 2 : 1 : 0);
 145 }
 146
 147 static size_t
 148 _EUC_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
 149     mbstate_t * __restrict ps)
 150 {
 151         _EucState *es;
 152         int i, set, want;
 153         wchar_t wc;
 154         const char *os;
 155
 156         es = (_EucState *)ps;
 157
 158         if (es->want < 0 || es->want > MB_CUR_MAX || es->set < 0 ||
 159             es->set > 3) {
 160                 errno = EINVAL;
 161                 return ((size_t)-1);
 162         }
 163
 164         if (s == NULL) {
 165                 s = "";
 166                 n = 1;
 167                 pwc = NULL;
 168         }
 169
 170         if (n == 0)
 171                 /* Incomplete multibyte sequence */
 172                 return ((size_t)-2);
 173
 174         os = s;
 175
 176         if (es->want == 0) {
 177                 want = CEI->count[set = _euc_set(*s)];
 178                 if (set == 2 || set == 3) {
 179                         --want;
 180                         if (--n == 0) {
 181                                 /* Incomplete multibyte sequence */
 182                                 es->set = set;
 183                                 es->want = want;
 184                                 es->ch = 0;
 185                                 return ((size_t)-2);
 186                         }
 187                         ++s;
 188                         if (*s == '\0') {
 189                                 errno = EILSEQ;
 190                                 return ((size_t)-1);
 191                         }
 192                 }
 193                 wc = (unsigned char)*s++;
 194         } else {
 195                 set = es->set;
 196                 want = es->want;
 197                 wc = es->ch;
 198         }
 199         for (i = (es->want == 0) ? 1 : 0; i < MIN(want, n); i++) {
 200                 if (*s == '\0') {
 201                         errno = EILSEQ;
 202                         return ((size_t)-1);
 203                 }
 204                 wc = (wc << 8) | (unsigned char)*s++;
 205         }
 206         if (i < want) {
 207                 /* Incomplete multibyte sequence */
 208                 es->set = set;
 209                 es->want = want - i;
 210                 es->ch = wc;
 211                 return ((size_t)-2);
 212         }
 213         wc = (wc & ~CEI->mask) | CEI->bits[set];
 214         if (pwc != NULL)
 215                 *pwc = wc;
 216         es->want = 0;
 217         return (wc == L'\0' ? 0 : s - os);
 218 }
 219
 220 static size_t
 221 _EUC_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
 222 {
 223         _EucState *es;
 224         wchar_t m, nm;
 225         int i, len;
 226
 227         es = (_EucState *)ps;
 228
 229         if (es->want != 0) {
 230                 errno = EINVAL;
 231                 return ((size_t)-1);
 232         }
 233
 234         if (s == NULL)
 235                 /* Reset to initial shift state (no-op) */
 236                 return (1);
 237
 238         m = wc & CEI->mask;
 239         nm = wc & ~m;
 240
 241         if (m == CEI->bits[1]) {
 242 CodeSet1:
 243                 /* Codeset 1: The first byte must have 0x80 in it. */
 244                 i = len = CEI->count[1];
 245                 while (i-- > 0)
 246                         *s++ = (nm >> (i << 3)) | 0x80;
 247         } else {
 248                 if (m == CEI->bits[0])
 249                         i = len = CEI->count[0];
 250                 else if (m == CEI->bits[2]) {
 251                         i = len = CEI->count[2];
 252                         *s++ = _SS2;
 253                         --i;
 254                         /* SS2 designates G2 into GR */
 255                         nm |= GR_BITS;
 256                 } else if (m == CEI->bits[3]) {
 257                         i = len = CEI->count[3];
 258                         *s++ = _SS3;
 259                         --i;
 260                         /* SS3 designates G3 into GR */
 261                         nm |= GR_BITS;
 262                 } else
 263                         goto CodeSet1;  /* Bletch */
 264                 while (i-- > 0)
 265                         *s++ = (nm >> (i << 3)) & 0xff;
 266         }
 267         return (len);
 268 }