locale/utf2.c

   1 /*-
   2  * Copyright (c) 1993
   3  *      The Regents of the University of California.  All rights reserved.
   4  *
   5  * This code is derived from software contributed to Berkeley by
   6  * Paul Borman at Krystal Technologies.
   7  *
   8  * Redistribution and use in source and binary forms, with or without
   9  * modification, are permitted provided that the following conditions
  10  * are met:
  11  * 1. Redistributions of source code must retain the above copyright
  12  *    notice, this list of conditions and the following disclaimer.
  13  * 2. Redistributions in binary form must reproduce the above copyright
  14  *    notice, this list of conditions and the following disclaimer in the
  15  *    documentation and/or other materials provided with the distribution.
  16  * 3. All advertising materials mentioning features or use of this software
  17  *    must display the following acknowledgement:
  18  *      This product includes software developed by the University of
  19  *      California, Berkeley and its contributors.
  20  * 4. Neither the name of the University nor the names of its contributors
  21  *    may be used to endorse or promote products derived from this software
  22  *    without specific prior written permission.
  23  *
  24  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  25  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  26  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  27  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  28  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  29  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  30  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  31  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  32  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  33  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  34  * SUCH DAMAGE.
  35  *
  36  * $FreeBSD: src/lib/libc/locale/utf2.c,v 1.3.2.2 2001/03/05 10:27:18 obrien Exp $
  37  */
  38
  39 #if defined(LIBC_SCCS) && !defined(lint)
  40 static char sccsid[] = "@(#)utf2.c      8.1 (Berkeley) 6/4/93";
  41 #endif /* LIBC_SCCS and not lint */
  42
  43 #include <rune.h>
  44 #include <stddef.h>
  45 #include <stdio.h>
  46 #include <stdlib.h>
  47
  48 rune_t  _UTF2_sgetrune __P((const char *, size_t, char const **));
  49 int     _UTF2_sputrune __P((rune_t, char *, size_t, char **));
  50
  51 static int _utf_count[16] = {
  52         1, 1, 1, 1, 1, 1, 1, 1,
  53         0, 0, 0, 0, 2, 2, 3, 0,
  54 };
  55
  56 int
  57 _UTF2_init(rl)
  58         _RuneLocale *rl;
  59 {
  60         rl->sgetrune = _UTF2_sgetrune;
  61         rl->sputrune = _UTF2_sputrune;
  62         _CurrentRuneLocale = rl;
  63         __mb_cur_max = 3;
  64         return (0);
  65 }
  66
  67 rune_t
  68 _UTF2_sgetrune(string, n, result)
  69         const char *string;
  70         size_t n;
  71         char const **result;
  72 {
  73         int c;
  74
  75         if (n < 1 || (c = _utf_count[(*string >> 4) & 0xf]) > n) {
  76                 if (result)
  77                         *result = string;
  78                 return (_INVALID_RUNE);
  79         }
  80         switch (c) {
  81         case 1:
  82                 if (result)
  83                         *result = string + 1;
  84                 return (*string & 0xff);
  85         case 2:
  86                 if ((string[1] & 0xC0) != 0x80)
  87                         goto encoding_error;
  88                 if (result)
  89                         *result = string + 2;
  90                 return (((string[0] & 0x1F) << 6) | (string[1] & 0x3F));
  91         case 3:
  92                 if ((string[1] & 0xC0) != 0x80 || (string[2] & 0xC0) != 0x80)
  93                         goto encoding_error;
  94                 if (result)
  95                         *result = string + 3;
  96                 return (((string[0] & 0x1F) << 12) | ((string[1] & 0x3F) << 6)
  97                     | (string[2] & 0x3F));
  98         default:
  99 encoding_error: if (result)
 100                         *result = string + 1;
 101                 return (_INVALID_RUNE);
 102         }
 103 }
 104
 105 int
 106 _UTF2_sputrune(c, string, n, result)
 107         rune_t c;
 108         char *string, **result;
 109         size_t n;
 110 {
 111         if (c & 0xF800) {
 112                 if (n >= 3) {
 113                         if (string) {
 114                                 string[0] = 0xE0 | ((c >> 12) & 0x0F);
 115                                 string[1] = 0x80 | ((c >> 6) & 0x3F);
 116                                 string[2] = 0x80 | ((c) & 0x3F);
 117                         }
 118                         if (result)
 119                                 *result = string + 3;
 120                 } else
 121                         if (result)
 122                                 *result = NULL;
 123
 124                 return (3);
 125         } else
 126                 if (c & 0x0780) {
 127                         if (n >= 2) {
 128                                 if (string) {
 129                                         string[0] = 0xC0 | ((c >> 6) & 0x1F);
 130                                         string[1] = 0x80 | ((c) & 0x3F);
 131                                 }
 132                                 if (result)
 133                                         *result = string + 2;
 134                         } else
 135                                 if (result)
 136                                         *result = NULL;
 137                         return (2);
 138                 } else {
 139                         if (n >= 1) {
 140                                 if (string)
 141                                         string[0] = c;
 142                                 if (result)
 143                                         *result = string + 1;
 144                         } else
 145                                 if (result)
 146                                         *result = NULL;
 147                         return (1);
 148                 }
 149 }