gb18030.c revision 118146 
1/*
2 * Copyright (c) 2003
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * This code is contributed to Robin Hu <huxw@knight.6test.edu.cn>
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 * 3. All advertising materials mentioning features or use of this software
16 *    must display the following acknowledgement:
17 *	This product includes software developed by the University of
18 *	California, Berkeley and its contributors.
19 * 4. Neither the name of the University nor the names of its contributors
20 *    may be used to endorse or promote products derived from this software
21 *    without specific prior written permission.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * SUCH DAMAGE.
34 */
35
36#include <sys/cdefs.h>
37__FBSDID("$FreeBSD: head/lib/libc/locale/gb18030.c 118146 2003-07-29 07:52:44Z ache $");
38
39#include <rune.h>
40#include <stddef.h>
41#include <stdio.h>
42#include <stdlib.h>
43#include <sys/types.h>
44
45rune_t	_GB18030_sgetrune(const char *, size_t, char const **);
46int	_GB18030_sputrune(rune_t, char *, size_t, char **);
47
48int
49_GB18030_init(rl)
50	_RuneLocale *rl;
51{
52	rl->sgetrune = _GB18030_sgetrune;
53	rl->sputrune = _GB18030_sputrune;
54	_CurrentRuneLocale = rl;
55	__mb_cur_max = 4;
56	return (0);
57}
58
59static inline int
60_gb18030_check_string(s_, n)
61     const char* s_;
62     int n;
63{
64  const unsigned char* s = s_;
65  if ((s[0]>=0x81&&s[0]<=0xfe)) {
66    if (n<2) goto bad_string;
67    if ((s[1]>=0x40&&s[1]<=0x7e)||(s[1]>=0x80&&s[1]<=0xfe))
68      return 2;
69    if ((s[1]>=0x30&&s[1]<=0x39)) {
70      if (n<4) goto bad_string;
71      if ((s[2]>=0x81&&s[2]<=0xfe) && (s[3]>=0x30&&s[3]<=0x39))
72        return 4;
73      else
74        goto bad_string;
75    }
76  } else {
77    return 1;
78  }
79 bad_string:
80  return -1;
81}
82
83static inline int
84_gb18030_check_rune(r)
85     rune_t r;
86{
87  if (r&0xff000000) {
88      return 4;
89  }
90  if (r&0xff00) {
91      return 2;
92  }
93  return 1;
94}
95
96rune_t
97_GB18030_sgetrune(string, n, result)
98	const char *string;
99	size_t n;
100	char const **result;
101{
102  rune_t rune = 0;
103  int len;
104
105  len = _gb18030_check_string(string, n);
106
107  if (len == -1) {
108    if (result)
109      *result = string;
110    return (_INVALID_RUNE);
111  }
112
113  while (--len >= 0)
114    rune = (rune << 8) | ((u_int)(*string++) & 0xff);
115
116  rune &= 0x7fffffff;
117  if (result)
118    *result = string;
119  return rune;
120}
121
122int
123_GB18030_sputrune(c, string, n, result)
124	rune_t c;
125	char *string, **result;
126	size_t n;
127{
128  int len;
129  len = _gb18030_check_rune(c);
130
131  switch (len) {
132  case 1:
133    if (n >= 1) {
134      *string = c & 0xff;
135      if (result)
136        *result = string + 1;
137      return (1);
138    }
139    break;
140  case 2:
141    if (n >= 2) {
142      string[0] = (c >> 8) & 0xff;
143      string[1] = c & 0xff;
144      if (result)
145        *result = string + 2;
146      return (2);
147    }
148    break;
149  case 4:
150    if (n >= 4) {
151      string[0] = ((c >>24) & 0xff) | 0x80;
152      string[1] = (c >>16) & 0xff;
153      string[2] = (c >>8)  & 0xff;
154      string[3] = c & 0xff;
155      if (result)
156        *result = string + 4;
157      return (4);
158    }
159    break;
160  default:
161    break;
162  }
163  if (result)
164    *result = string;
165  return (0);
166}
167