1 /* crypto/asn1/a_utf8.c */
2 /* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
5 * This package is an SSL implementation written
6 * by Eric Young (eay@cryptsoft.com).
7 * The implementation was written so as to conform with Netscapes SSL.
9 * This library is free for commercial and non-commercial use as long as
10 * the following conditions are aheared to. The following conditions
11 * apply to all code found in this distribution, be it the RC4, RSA,
12 * lhash, DES, etc., code; not just the SSL code. The SSL documentation
13 * included with this distribution is covered by the same copyright terms
14 * except that the holder is Tim Hudson (tjh@cryptsoft.com).
16 * Copyright remains Eric Young's, and as such any Copyright notices in
17 * the code are not to be removed.
18 * If this package is used in a product, Eric Young should be given attribution
19 * as the author of the parts of the library used.
20 * This can be in the form of a textual message at program startup or
21 * in documentation (online or textual) provided with the package.
23 * Redistribution and use in source and binary forms, with or without
24 * modification, are permitted provided that the following conditions
26 * 1. Redistributions of source code must retain the copyright
27 * notice, this list of conditions and the following disclaimer.
28 * 2. Redistributions in binary form must reproduce the above copyright
29 * notice, this list of conditions and the following disclaimer in the
30 * documentation and/or other materials provided with the distribution.
31 * 3. All advertising materials mentioning features or use of this software
32 * must display the following acknowledgement:
33 * "This product includes cryptographic software written by
34 * Eric Young (eay@cryptsoft.com)"
35 * The word 'cryptographic' can be left out if the rouines from the library
36 * being used are not cryptographic related :-).
37 * 4. If you include any Windows specific code (or a derivative thereof) from
38 * the apps directory (application code) you must include an acknowledgement:
39 * "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
41 * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
42 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
43 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
44 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
45 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
46 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
47 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
48 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
49 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
50 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
53 * The licence and distribution terms for any publically available version or
54 * derivative of this code cannot be changed. i.e. this code cannot simply be
55 * copied and put under another distribution licence
56 * [including the GNU Public Licence.]
61 #include <openssl/asn1.h>
63 ASN1_UTF8STRING *ASN1_UTF8STRING_new(void)
64 { return M_ASN1_UTF8STRING_new();}
66 void ASN1_UTF8STRING_free(ASN1_UTF8STRING *x)
67 { M_ASN1_UTF8STRING_free(x);}
69 int i2d_ASN1_UTF8STRING(ASN1_UTF8STRING *a, unsigned char **pp)
71 return(i2d_ASN1_bytes((ASN1_STRING *)a,pp,
72 V_ASN1_UTF8STRING,V_ASN1_UNIVERSAL));
75 ASN1_UTF8STRING *d2i_ASN1_UTF8STRING(ASN1_UTF8STRING **a, unsigned char **pp,
78 ASN1_UTF8STRING *ret=NULL;
80 ret=(ASN1_UTF8STRING *)d2i_ASN1_bytes((ASN1_STRING **)a,
81 pp,length,V_ASN1_UTF8STRING,V_ASN1_UNIVERSAL);
84 ASN1err(ASN1_F_D2I_ASN1_UTF8STRING,ERR_R_NESTED_ASN1_ERROR);
93 /* This parses a UTF8 string one character at a time. It is passed a pointer
94 * to the string and the length of the string. It sets 'value' to the value of
95 * the current character. It returns the number of characters read or a
96 * negative error code:
97 * -1 = string too short
98 * -2 = illegal character
99 * -3 = subsequent characters not of the form 10xxxxxx
100 * -4 = character encoded incorrectly (not minimal length).
103 int UTF8_getc(const unsigned char *str, int len, unsigned long *val)
105 const unsigned char *p;
108 if(len <= 0) return 0;
111 /* Check syntax and work out the encoded value (if correct) */
112 if((*p & 0x80) == 0) {
115 } else if((*p & 0xe0) == 0xc0) {
116 if(len < 2) return -1;
117 if((p[1] & 0xc0) != 0x80) return -3;
118 value = (*p++ & 0x1f) << 6;
119 value |= *p++ & 0x3f;
120 if(value < 0x80) return -4;
122 } else if((*p & 0xf0) == 0xe0) {
123 if(len < 3) return -1;
124 if( ((p[1] & 0xc0) != 0x80)
125 || ((p[2] & 0xc0) != 0x80) ) return -3;
126 value = (*p++ & 0xf) << 12;
127 value |= (*p++ & 0x3f) << 6;
128 value |= *p++ & 0x3f;
129 if(value < 0x800) return -4;
131 } else if((*p & 0xf8) == 0xf0) {
132 if(len < 4) return -1;
133 if( ((p[1] & 0xc0) != 0x80)
134 || ((p[2] & 0xc0) != 0x80)
135 || ((p[3] & 0xc0) != 0x80) ) return -3;
136 value = (*p++ & 0x7) << 18;
137 value |= (*p++ & 0x3f) << 12;
138 value |= (*p++ & 0x3f) << 6;
139 value |= *p++ & 0x3f;
140 if(value < 0x10000) return -4;
142 } else if((*p & 0xfc) == 0xf8) {
143 if(len < 5) return -1;
144 if( ((p[1] & 0xc0) != 0x80)
145 || ((p[2] & 0xc0) != 0x80)
146 || ((p[3] & 0xc0) != 0x80)
147 || ((p[4] & 0xc0) != 0x80) ) return -3;
148 value = (*p++ & 0x3) << 24;
149 value |= (*p++ & 0x3f) << 18;
150 value |= (*p++ & 0x3f) << 12;
151 value |= (*p++ & 0x3f) << 6;
152 value |= *p++ & 0x3f;
153 if(value < 0x200000) return -4;
155 } else if((*p & 0xfe) == 0xfc) {
156 if(len < 6) return -1;
157 if( ((p[1] & 0xc0) != 0x80)
158 || ((p[2] & 0xc0) != 0x80)
159 || ((p[3] & 0xc0) != 0x80)
160 || ((p[4] & 0xc0) != 0x80)
161 || ((p[5] & 0xc0) != 0x80) ) return -3;
162 value = (*p++ & 0x1) << 30;
163 value |= (*p++ & 0x3f) << 24;
164 value |= (*p++ & 0x3f) << 18;
165 value |= (*p++ & 0x3f) << 12;
166 value |= (*p++ & 0x3f) << 6;
167 value |= *p++ & 0x3f;
168 if(value < 0x4000000) return -4;
175 /* This takes a character 'value' and writes the UTF8 encoded value in
176 * 'str' where 'str' is a buffer containing 'len' characters. Returns
177 * the number of characters written or -1 if 'len' is too small. 'str' can
178 * be set to NULL in which case it just returns the number of characters.
179 * It will need at most 6 characters.
182 int UTF8_putc(unsigned char *str, int len, unsigned long value)
184 if(!str) len = 6; /* Maximum we will need */
185 else if(len <= 0) return -1;
187 if(str) *str = (unsigned char)value;
191 if(len < 2) return -1;
193 *str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
194 *str = (unsigned char)((value & 0x3f) | 0x80);
198 if(value < 0x10000) {
199 if(len < 3) return -1;
201 *str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
202 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
203 *str = (unsigned char)((value & 0x3f) | 0x80);
207 if(value < 0x200000) {
208 if(len < 4) return -1;
210 *str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
211 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
212 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
213 *str = (unsigned char)((value & 0x3f) | 0x80);
217 if(value < 0x4000000) {
218 if(len < 5) return -1;
220 *str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
221 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
222 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
223 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
224 *str = (unsigned char)((value & 0x3f) | 0x80);
228 if(len < 6) return -1;
230 *str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
231 *str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
232 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
233 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
234 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
235 *str = (unsigned char)((value & 0x3f) | 0x80);