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 (c) 1996 by Sun Microsystems, Inc.
23 */
24
25
26 #include <errno.h>
27 #include <widec.h>
28 #include "common_def.h"
29 #include "common_han.h"
30 #include "utf_euc_api.h"
31 #include "common_defs.h"
32
33 /**** _ I C V _ O P E N ****/
34
_icv_open()35 void* _icv_open()
36 {
37 return((void*)MAGIC_NUMBER);
38 } /* end of int _icv_open(). */
39
40
41 /**** _ I C V _ C L O S E ****/
42
_icv_close(int * cd)43 void _icv_close(int* cd)
44 {
45 if (!cd || cd != (int*)MAGIC_NUMBER)
46 errno = EBADF;
47 } /* end of void _icv_close(int*). */
48
49
50 /**** _ I C V _ I C O N V ****/
51
_icv_iconv(int * cd,char ** inbuf,size_t * inbufleft,char ** outbuf,size_t * outbufleft)52 size_t _icv_iconv(int* cd, char** inbuf, size_t* inbufleft,
53 char** outbuf, size_t* outbufleft)
54 {
55 size_t ret_val = 0;
56 unsigned char* ib;
57 unsigned char* ob;
58 unsigned char* ibtail;
59 unsigned char* obtail;
60
61 if (!cd || cd != (int*)MAGIC_NUMBER)
62 {
63 errno = EBADF;
64 return((size_t)-1);
65 }
66
67 if (!inbuf || !(*inbuf))
68 return((size_t)0);
69
70 ib = (unsigned char*)*inbuf;
71 ob = (unsigned char*)*outbuf;
72 ibtail = ib + *inbufleft;
73 obtail = ob + *outbufleft;
74
75 while (ib < ibtail)
76 {
77 if (!(*ib & 0x80)) /* 1-byte sequence */
78 {
79 if (ob >= obtail)
80 {
81 errno = E2BIG;
82 ret_val = (size_t)-1;
83 break;
84 }
85 *ob++ = *ib++;
86 }
87 else if((*ib & 0xF0) == 0xE0) /* 3-byte sequence */
88 {
89 hcode_type utf8_code, euc_code;
90
91 if ((ibtail - ib) < 3)
92 {
93 errno = EINVAL;
94 ret_val = (size_t)-1;
95 break;
96 }
97
98 if (!is_valid_utf8_string(ib, 3))
99 {
100 errno = EILSEQ;
101 ret_val = (size_t)-1;
102 break;
103 }
104
105 utf8_code.byte.byte1 = 0;
106 utf8_code.byte.byte2 = *ib;
107 utf8_code.byte.byte3 = *(ib + 1);
108 utf8_code.byte.byte4 = *(ib + 2);
109
110 euc_code = _utf8_to_wansung(utf8_code);
111
112 if ((obtail - ob) < 2)
113 {
114 errno = E2BIG;
115 ret_val = (size_t)-1;
116 break;
117 }
118
119 if (euc_code.code != 0) {
120 /* If find something -> EUC code */
121 *ob++ = euc_code.byte.byte3;
122 *ob++ = euc_code.byte.byte4;
123 }
124 else
125 {
126 /* Let's assume the code is non-identical. */
127 *ob++ = NON_IDENTICAL;
128 ret_val += 1;
129 }
130 ib += 3;
131 }
132 else if((*ib & 0xE0) == 0xC0) /* 2-byte sequence */
133 {
134 hcode_type utf8_code, euc_code;
135
136 if ((ibtail - ib) < 2)
137 {
138 errno = EINVAL;
139 ret_val = (size_t)-1;
140 break;
141 }
142
143 if (!is_valid_utf8_string(ib, 2))
144 {
145 errno = EILSEQ;
146 ret_val = (size_t)-1;
147 break;
148 }
149
150 utf8_code.byte.byte1 = 0;
151 utf8_code.byte.byte2 = 0;
152 utf8_code.byte.byte3 = *ib;
153 utf8_code.byte.byte4 = *(ib + 1);
154
155 euc_code = _utf8_to_wansung(utf8_code);
156
157 if ((obtail - ob) < 2)
158 {
159 errno = E2BIG;
160 ret_val = (size_t)-1;
161 break;
162 }
163
164 if (euc_code.code != 0) {
165 *ob++ = euc_code.byte.byte3;
166 *ob++ = euc_code.byte.byte4;
167 }
168 else
169 {
170 *ob++ = NON_IDENTICAL;
171 ret_val += 1;
172 }
173 ib += 2;
174 }
175 else /* 11, 21, 26 & 31 bits codes won't be able to convert. */
176 {
177 short int offset, offset2;
178
179 if ((*ib & 0xE0) == 0xC0) /* 11 */
180 offset = 2;
181 else if ((*ib & 0xF0) == 0xE0) /* 16 */
182 offset = 3;
183 else if ((*ib & 0xF8) == 0xF0) /* 21 */
184 offset = 4;
185 else if ((*ib & 0xFC) == 0xF8) /* 26 */
186 offset = 5;
187 else if ((*ib & 0xFE) == 0xFC) /* 31 */
188 offset = 6;
189 else /* Illegal sequence. */
190 offset = 1;
191
192 if ((ibtail - ib) < offset)
193 {
194 errno = EINVAL;
195 ret_val = (size_t)-1;
196 break;
197 }
198
199 if (!is_valid_utf8_string(ib, offset))
200 {
201 errno = EILSEQ;
202 ret_val = (size_t)-1;
203 break;
204 }
205
206 /* Let's assume the code is non-identical. */
207 offset2 = (offset > 2) ? 2 : 1;
208 if ((obtail - ob) < offset2)
209 {
210 errno = E2BIG;
211 ret_val = (size_t)-1;
212 break;
213 }
214
215 *ob++ = NON_IDENTICAL;
216 if (offset2 > 1)
217 *ob++ = NON_IDENTICAL;
218
219 ib += offset;
220
221 ret_val += offset2;
222 }
223 }
224
225 *inbuf = (char*)ib;
226 *inbufleft = ibtail - ib;
227 *outbuf = (char*)ob;
228 *outbufleft = obtail - ob;
229
230 return(ret_val);
231 } /* end of size_t _icv_iconv(int*, char**, size_t*, char**, size_t*).*/
232