utf8.c 9.96 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
/* Synchronet UTF-8 encode/decode/translate functions */

/* $Id$ */

/****************************************************************************
 * @format.tab-size 4		(Plain Text/Source Code File Header)			*
 * @format.use-tabs true	(see http://www.synchro.net/ptsc_hdr.html)		*
 *																			*
 * Copyright Rob Swindell - http://www.synchro.net/copyright.html			*
 *																			*
 * This library is free software; you can redistribute it and/or			*
 * modify it under the terms of the GNU Lesser General Public License		*
 * as published by the Free Software Foundation; either version 2			*
 * of the License, or (at your option) any later version.					*
 * See the GNU Lesser General Public License for more details: lgpl.txt or	*
 * http://www.fsf.org/copyleft/lesser.html									*
 *																			*
 * Anonymous FTP access to the most recent released source is available at	*
 * ftp://vert.synchro.net, ftp://cvs.synchro.net and ftp://ftp.synchro.net	*
 *																			*
 * Anonymous CVS access to the development source and modification history	*
 * is available at cvs.synchro.net:/cvsroot/sbbs, example:					*
 * cvs -d :pserver:anonymous@cvs.synchro.net:/cvsroot/sbbs login			*
 *     (just hit return, no password is necessary)							*
 * cvs -d :pserver:anonymous@cvs.synchro.net:/cvsroot/sbbs checkout src		*
 *																			*
 * For Synchronet coding style and modification guidelines, see				*
 * http://www.synchro.net/source.html										*
 *																			*
 * You are encouraged to submit any modifications (preferably in Unix diff	*
 * format) via e-mail to mods@synchro.net									*
 *																			*
 * Note: If this box doesn't appear square, then you need to fix your tabs.	*
 ****************************************************************************/

#include "utf8.h"

char* utf8_normalize_str(char* str)
{
	char* dest = str;

	for(char* src = str; *src != 0; src++) {
		if(*src == '\xC2' && *(src + 1) == '\xA0') { // NO-BREAK SPACE
			src++;
			*dest++ = ' ';
			continue;
		}
		if(*src == '\xE2') {
			if(*(src + 1) == '\x80') {
				switch(*(src + 2)) {
					case '\x82': // EN SPACE
					case '\x83': // EM SPACE
						src += 2;
						*dest++ = ' ';
						continue;
					case '\x8B': // ZERO WIDTH SPACE
					case '\x8C': // ZERO WIDTH NON-JOINER
					case '\x8D': // ZERO WIDTH JOINER
						src += 2;
						continue;
					case '\x90': // HYPHEN
					case '\x91': // NON-BREAKING HYPHEN
					case '\x92': // FIGURE DASH
					case '\x93': // EN DASH
						src += 2;
						*dest++ = '-';
						continue;
					case '\x98': // LEFT SINGLE QUOTATION MARK
						src += 2;
						*dest++ = '`';
						continue;
					case '\x99': // RIGHT SINGLE QUOTATION MARK
					case '\xB2': // PRIME
						src += 2;
						*dest++ = '\'';
						continue;
					case '\x9C': // LEFT DOUBLE QUOTATION MARK
					case '\x9D': // RIGHT DOUBLE QUOTATION MARK
						src += 2;
						*dest++ = '"';
						continue;
					case '\xA6': // HORIZONTAL ELLIPSIS -> ASCII periods (3)
						src += 2;
						for(int i = 0; i < 3; i++)
							*dest++ =  '.';
						continue;
				}
			}
			else if(*(src + 1) == '\x81') {
				switch(*(src + 2)) {
					case '\x83': // HYPEN BULLET
						src += 2;
						*dest++ = '-';
						continue;
					case '\x84': // FRACTION SLASH
						src += 2;
						*dest++ = '/';
						continue;
				}
			}
			else if(*(src + 1) == '\x88') {
				switch(*(src + 2)) {
					case '\x92': // MINUS SIGN
						src += 2;
						*dest++ = '-';
						continue;
				}
			}
		}
		else if(*src == '\xEF') {
			if(*(src + 1) == '\xBB' && *(src + 2) == '\xBF') {
				// Zero Width No-Break Space (BOM, ZWNBSP)
				src += 2;
				continue;
			}
			if(*(src + 1) == '\xBC') {
				if(*(src + 2) >= '\x81' && *(src + 2) <= '\xBF') { // FULLWIDTH EXCLAMATION MARK through FULLWIDTH LOW LINE
					src += 2;
					*src -= '\x81';
					*dest++ = '!' + *src;
					continue;
				}
			}
			else if(*(src + 1) == '\xBD') {
				if(*(src + 2) >= '\x80' && *(src + 2) <= '\x9E') { // FULLWIDTH GRAVE ACCENT through FULLWIDTH TILDE
					src += 2;
					*src -= '\x80';
					*dest++ = '`' + *src;
					continue;
				}
			}
		}
		*dest++ = *src;
	}
	*dest = 0;
	return str;
}

// From openssl/crypto/asn1/a_utf8.c:
/*
 * Copyright 1995-2016 The OpenSSL Project Authors. All Rights Reserved.
 *
 * Licensed under the Apache License 2.0 (the "License").  You may not use
 * this file except in compliance with the License.  You can obtain a copy
 * in the file LICENSE in the source distribution or at
 * https://www.openssl.org/source/license.html
 */

/* UTF8 utilities */

/*-
 * This parses a UTF8 string one character at a time. It is passed a pointer
 * to the string and the length of the string. It sets 'value' to the value of
 * the current character. It returns the number of characters read or a
 * negative error code:
 * -1 = string too short
 * -2 = illegal character
 * -3 = subsequent characters not of the form 10xxxxxx
 * -4 = character encoded incorrectly (not minimal length).
 */

int utf8_getc(const char *str, size_t len, uint32_t* val)
{
    const unsigned char *p;
    unsigned long value;
    int ret;
    if (len <= 0)
        return 0;
rswindell's avatar
rswindell committed
169
    p = (const unsigned char*)str;
170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323

    /* Check syntax and work out the encoded value (if correct) */
    if ((*p & 0x80) == 0) {
        value = *p++ & 0x7f;
        ret = 1;
    } else if ((*p & 0xe0) == 0xc0) {
        if (len < 2)
            return -1;
        if ((p[1] & 0xc0) != 0x80)
            return -3;
        value = (*p++ & 0x1f) << 6;
        value |= *p++ & 0x3f;
        if (value < 0x80)
            return -4;
        ret = 2;
    } else if ((*p & 0xf0) == 0xe0) {
        if (len < 3)
            return -1;
        if (((p[1] & 0xc0) != 0x80)
            || ((p[2] & 0xc0) != 0x80))
            return -3;
        value = (*p++ & 0xf) << 12;
        value |= (*p++ & 0x3f) << 6;
        value |= *p++ & 0x3f;
        if (value < 0x800)
            return -4;
        ret = 3;
    } else if ((*p & 0xf8) == 0xf0) {
        if (len < 4)
            return -1;
        if (((p[1] & 0xc0) != 0x80)
            || ((p[2] & 0xc0) != 0x80)
            || ((p[3] & 0xc0) != 0x80))
            return -3;
        value = ((unsigned long)(*p++ & 0x7)) << 18;
        value |= (*p++ & 0x3f) << 12;
        value |= (*p++ & 0x3f) << 6;
        value |= *p++ & 0x3f;
        if (value < 0x10000)
            return -4;
        ret = 4;
    } else if ((*p & 0xfc) == 0xf8) {
        if (len < 5)
            return -1;
        if (((p[1] & 0xc0) != 0x80)
            || ((p[2] & 0xc0) != 0x80)
            || ((p[3] & 0xc0) != 0x80)
            || ((p[4] & 0xc0) != 0x80))
            return -3;
        value = ((unsigned long)(*p++ & 0x3)) << 24;
        value |= ((unsigned long)(*p++ & 0x3f)) << 18;
        value |= ((unsigned long)(*p++ & 0x3f)) << 12;
        value |= (*p++ & 0x3f) << 6;
        value |= *p++ & 0x3f;
        if (value < 0x200000)
            return -4;
        ret = 5;
    } else if ((*p & 0xfe) == 0xfc) {
        if (len < 6)
            return -1;
        if (((p[1] & 0xc0) != 0x80)
            || ((p[2] & 0xc0) != 0x80)
            || ((p[3] & 0xc0) != 0x80)
            || ((p[4] & 0xc0) != 0x80)
            || ((p[5] & 0xc0) != 0x80))
            return -3;
        value = ((unsigned long)(*p++ & 0x1)) << 30;
        value |= ((unsigned long)(*p++ & 0x3f)) << 24;
        value |= ((unsigned long)(*p++ & 0x3f)) << 18;
        value |= ((unsigned long)(*p++ & 0x3f)) << 12;
        value |= (*p++ & 0x3f) << 6;
        value |= *p++ & 0x3f;
        if (value < 0x4000000)
            return -4;
        ret = 6;
    } else
        return -2;
    *val = value;
    return ret;
}

/*
 * This takes a character 'value' and writes the UTF8 encoded value in 'str'
 * where 'str' is a buffer containing 'len' characters. Returns the number of
 * characters written or -1 if 'len' is too small. 'str' can be set to NULL
 * in which case it just returns the number of characters. It will need at
 * most 6 characters.
 */

int utf8_putc(char *str, size_t len, uint32_t value)
{
    if (!str)
        len = 6;                /* Maximum we will need */
    else if (len <= 0)
        return -1;
    if (value < 0x80) {
        if (str)
            *str = (unsigned char)value;
        return 1;
    }
    if (value < 0x800) {
        if (len < 2)
            return -1;
        if (str) {
            *str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
            *str = (unsigned char)((value & 0x3f) | 0x80);
        }
        return 2;
    }
    if (value < 0x10000) {
        if (len < 3)
            return -1;
        if (str) {
            *str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
            *str = (unsigned char)((value & 0x3f) | 0x80);
        }
        return 3;
    }
    if (value < 0x200000) {
        if (len < 4)
            return -1;
        if (str) {
            *str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
            *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
            *str = (unsigned char)((value & 0x3f) | 0x80);
        }
        return 4;
    }
    if (value < 0x4000000) {
        if (len < 5)
            return -1;
        if (str) {
            *str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
            *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
            *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
            *str = (unsigned char)((value & 0x3f) | 0x80);
        }
        return 5;
    }
    if (len < 6)
        return -1;
    if (str) {
        *str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
        *str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
        *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
        *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
        *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
        *str = (unsigned char)((value & 0x3f) | 0x80);
    }
    return 6;
}