1 /*
2 * CDDL HEADER START
3 *
4 * The contents of this file are subject to the terms of the
5 * Common Development and Distribution License (the "License").
6 * You may not use this file except in compliance with the License.
7 *
8 * You can obtain a copy of the license at src/OPENSOLARIS.LICENSE
9 * or http://www.opensolaris.org/os/licensing.
10 * See the License for the specific language governing permissions
11 * and limitations under the License.
12 *
13 * When distributing Covered Code, include this CDDL HEADER in each
14 * file and include the License file at src/OPENSOLARIS.LICENSE.
15 * If applicable, add the following below this CDDL HEADER, with the
16 * fields enclosed by brackets "[]" replaced with your own identifying
17 * information: Portions Copyright [yyyy] [name of copyright owner]
18 *
19 * CDDL HEADER END
20 */
21 /*
22 * Copyright 2004 Sun Microsystems, Inc. All rights reserved.
23 * Use is subject to license terms.
24 *
25 * This particular file is to cover conversions from UTF-8 to various single
26 * byte codesets.
27 */
28
29
30 #include <stdlib.h>
31 #include <errno.h>
32 #include <sys/types.h>
33 #include "utf8_to_sb.h"
34
35
36
37 void *
_icv_open()38 _icv_open()
39 {
40 ucs_state_t *cd = (ucs_state_t *)calloc(1, sizeof(ucs_state_t));
41 if (cd == (ucs_state_t *)NULL) {
42 errno = ENOMEM;
43 return((void *)-1);
44 }
45
46 return((void *)cd);
47 }
48
49
50 void
_icv_close(ucs_state_t * cd)51 _icv_close(ucs_state_t *cd)
52 {
53 if (! cd)
54 errno = EBADF;
55 else
56 free((void *)cd);
57 }
58
59
60 size_t
_icv_iconv(ucs_state_t * cd,char ** inbuf,size_t * inbufleft,char ** outbuf,size_t * outbufleft)61 _icv_iconv(ucs_state_t *cd, char **inbuf, size_t *inbufleft, char **outbuf,
62 size_t *outbufleft)
63 {
64 size_t ret_val = 0;
65 unsigned char *ib;
66 unsigned char *ob;
67 unsigned char *ibtail;
68 unsigned char *obtail;
69 register int i, l, h;
70 signed char sz;
71 unsigned long u8;
72
73 if (! cd) {
74 errno = EBADF;
75 return((size_t)-1);
76 }
77
78 if (!inbuf || !(*inbuf)) {
79 cd->bom_written = false;
80 return((size_t)0);
81 }
82
83 ib = (unsigned char *)*inbuf;
84 ob = (unsigned char *)*outbuf;
85 ibtail = ib + *inbufleft;
86 obtail = ob + *outbufleft;
87
88 /* We skip any first signiture of UTF-8 */
89 if (!cd->bom_written &&
90 ((ibtail - ib) >= ICV_FETCH_UTF8_BOM_SIZE)) {
91 for (u8 = 0, i = 0; i < ICV_FETCH_UTF8_BOM_SIZE; i++)
92 u8 = (u8 << 8) | ((uint_t)(*(ib + i)));
93 if (u8 == ICV_BOM_IN_BIG_ENDIAN)
94 ib += ICV_FETCH_UTF8_BOM_SIZE;
95 }
96 cd->bom_written = true;
97
98 while (ib < ibtail) {
99 sz = number_of_bytes_in_utf8_char[*ib];
100 if (sz == ICV_TYPE_ILLEGAL_CHAR) {
101 errno = EILSEQ;
102 ret_val = (size_t)-1;
103 break;
104 }
105
106 if (ob >= obtail) {
107 errno = E2BIG;
108 ret_val = (size_t)-1;
109 break;
110 }
111
112 if (sz == 1) {
113 *ob++ = *ib++;
114 } else {
115 if ((ibtail - ib) < sz) {
116 errno = EINVAL;
117 ret_val = (size_t)-1;
118 break;
119 }
120
121 u8 = 0;
122 for (i = 0; i < sz; i++) {
123 if (((unsigned int)*ib) < 0x80) {
124 errno = EILSEQ;
125 ret_val = (size_t)-1;
126 goto illegal_char_err;
127 }
128 u8 = (u8 << 8) | ((unsigned int)*ib);
129 ib++;
130 }
131 if ((u8 & ICV_UTF8_REPRESENTATION_ffff_mask) ==
132 ICV_UTF8_REPRESENTATION_fffe ||
133 (u8 & ICV_UTF8_REPRESENTATION_ffff_mask) ==
134 ICV_UTF8_REPRESENTATION_ffff ||
135 u8 > ICV_UTF8_REPRESENTATION_10fffd ||
136 (u8 >= ICV_UTF8_REPRESENTATION_d800 &&
137 u8 <= ICV_UTF8_REPRESENTATION_dfff) ||
138 (u8 >= ICV_UTF8_REPRESENTATION_fdd0 &&
139 u8 <= ICV_UTF8_REPRESENTATION_fdef)) {
140 ib -= sz;
141 errno = EILSEQ;
142 ret_val = (size_t)-1;
143 goto illegal_char_err;
144 }
145
146 i = l = 0;
147 h = (sizeof(u8_sb_tbl) /
148 sizeof(to_sb_table_component_t)) - 1;
149 while (l <= h) {
150 i = (l + h) / 2;
151 if (u8_sb_tbl[i].u8 == u8)
152 break;
153 else if (u8_sb_tbl[i].u8 < u8)
154 l = i + 1;
155 else
156 h = i - 1;
157 }
158
159 /*
160 * We just assume that either we found it or it is
161 * a non-identical character that we need to
162 * provide a replacement character.
163 */
164 if (u8_sb_tbl[i].u8 == u8) {
165 *ob++ = u8_sb_tbl[i].sb;
166 } else {
167 *ob++ = ICV_CHAR_ASCII_REPLACEMENT;
168 ret_val++;
169 }
170 }
171 }
172
173 illegal_char_err:
174 *inbuf = (char *)ib;
175 *inbufleft = ibtail - ib;
176 *outbuf = (char *)ob;
177 *outbufleft = obtail - ob;
178
179 return(ret_val);
180 }
181