/forum/includes/utf/utf_tools.php
PHP | 2018 lines | 1492 code | 134 blank | 392 comment | 129 complexity | ca564dde6899cb748cdf8fb1943ee1c7 MD5 | raw file
1<?php 2/** 3* 4* @package utf 5* @version $Id$ 6* @copyright (c) 2006 phpBB Group 7* @license http://opensource.org/licenses/gpl-license.php GNU Public License 8* 9*/ 10 11/** 12*/ 13if (!defined('IN_PHPBB')) 14{ 15 exit; 16} 17 18// Enforce ASCII only string handling 19setlocale(LC_CTYPE, 'C'); 20 21/** 22* UTF-8 tools 23* 24* Whenever possible, these functions will try to use PHP's built-in functions or 25* extensions, otherwise they will default to custom routines. 26* 27* @package utf 28*/ 29 30if (!extension_loaded('xml')) 31{ 32 /** 33 * Implementation of PHP's native utf8_encode for people without XML support 34 * This function exploits some nice things that ISO-8859-1 and UTF-8 have in common 35 * 36 * @param string $str ISO-8859-1 encoded data 37 * @return string UTF-8 encoded data 38 */ 39 function utf8_encode($str) 40 { 41 $out = ''; 42 for ($i = 0, $len = strlen($str); $i < $len; $i++) 43 { 44 $letter = $str[$i]; 45 $num = ord($letter); 46 if ($num < 0x80) 47 { 48 $out .= $letter; 49 } 50 else if ($num < 0xC0) 51 { 52 $out .= "\xC2" . $letter; 53 } 54 else 55 { 56 $out .= "\xC3" . chr($num - 64); 57 } 58 } 59 return $out; 60 } 61 62 /** 63 * Implementation of PHP's native utf8_decode for people without XML support 64 * 65 * @param string $str UTF-8 encoded data 66 * @return string ISO-8859-1 encoded data 67 */ 68 function utf8_decode($str) 69 { 70 $pos = 0; 71 $len = strlen($str); 72 $ret = ''; 73 74 while ($pos < $len) 75 { 76 $ord = ord($str[$pos]) & 0xF0; 77 if ($ord === 0xC0 || $ord === 0xD0) 78 { 79 $charval = ((ord($str[$pos]) & 0x1F) << 6) | (ord($str[$pos + 1]) & 0x3F); 80 $pos += 2; 81 $ret .= (($charval < 256) ? chr($charval) : '?'); 82 } 83 else if ($ord === 0xE0) 84 { 85 $ret .= '?'; 86 $pos += 3; 87 } 88 else if ($ord === 0xF0) 89 { 90 $ret .= '?'; 91 $pos += 4; 92 } 93 else 94 { 95 $ret .= $str[$pos]; 96 ++$pos; 97 } 98 } 99 return $ret; 100 } 101} 102 103// mbstring is old and has it's functions around for older versions of PHP. 104// if mbstring is not loaded, we go into native mode. 105if (extension_loaded('mbstring')) 106{ 107 mb_internal_encoding('UTF-8'); 108 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 109 // ini_set is only used to try to make things better for mods using mbstring directly 110 // I know they're not supposed to, but you know they still could and the fix is costless 111 @ini_set("mbstring.internal_encoding", 'UTF-8'); 112 113 /** 114 * UTF-8 aware alternative to strrpos 115 * Find position of last occurrence of a char in a string 116 * 117 * Notes: 118 * - offset for mb_strrpos was added in 5.2.0, we emulate if it is lower 119 */ 120 if (version_compare(PHP_VERSION, '5.2.0', '>=')) 121 { 122 /** 123 * UTF-8 aware alternative to strrpos 124 * @ignore 125 */ 126 function utf8_strrpos($str, $needle, $offset = null) 127 { 128 // Emulate behaviour of strrpos rather than raising warning 129 if (empty($str)) 130 { 131 return false; 132 } 133 134 if (is_null($offset)) 135 { 136 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 137 // Explicit encoding 138 return mb_strrpos($str, $needle, 0, 'UTF-8'); 139 } 140 else 141 { 142 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 143 // Explicit encoding 144 return mb_strrpos($str, $needle, $offset, 'UTF-8'); 145 } 146 } 147 } 148 else 149 { 150 /** 151 * UTF-8 aware alternative to strrpos 152 * @ignore 153 */ 154 function utf8_strrpos($str, $needle, $offset = null) 155 { 156 // offset for mb_strrpos was added in 5.2.0 157 if (is_null($offset)) 158 { 159 // Emulate behaviour of strrpos rather than raising warning 160 if (empty($str)) 161 { 162 return false; 163 } 164 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 165 // Explicit encoding 166 return mb_strrpos($str, $needle, 'UTF-8'); 167 } 168 else 169 { 170 if (!is_int($offset)) 171 { 172 trigger_error('utf8_strrpos expects parameter 3 to be long', E_USER_ERROR); 173 return false; 174 } 175 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 176 // Explicit encoding 177 $str = mb_substr($str, $offset, mb_strlen($str, 'UTF-8'), 'UTF-8'); 178 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 179 // Explicit encoding 180 if (false !== ($pos = mb_strrpos($str, $needle, 'UTF-8'))) 181 { 182 return $pos + $offset; 183 } 184 185 return false; 186 } 187 } 188 } 189 190 /** 191 * UTF-8 aware alternative to strpos 192 * @ignore 193 */ 194 function utf8_strpos($str, $needle, $offset = null) 195 { 196 if (is_null($offset)) 197 { 198 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 199 // Explicit encoding 200 return mb_strpos($str, $needle, 0, 'UTF-8'); 201 } 202 else 203 { 204 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 205 // Explicit encoding 206 return mb_strpos($str, $needle, $offset, 'UTF-8'); 207 } 208 } 209 210 /** 211 * UTF-8 aware alternative to strtolower 212 * @ignore 213 */ 214 function utf8_strtolower($str) 215 { 216 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 217 // Explicit encoding 218 return mb_strtolower($str, 'UTF-8'); 219 } 220 221 /** 222 * UTF-8 aware alternative to strtoupper 223 * @ignore 224 */ 225 function utf8_strtoupper($str) 226 { 227 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 228 // Explicit encoding 229 return mb_strtoupper($str, 'UTF-8'); 230 } 231 232 /** 233 * UTF-8 aware alternative to substr 234 * @ignore 235 */ 236 function utf8_substr($str, $offset, $length = null) 237 { 238 if (is_null($length)) 239 { 240 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 241 // Explicit encoding 242 return mb_substr($str, $offset, mb_strlen($str, 'UTF-8'), 'UTF-8'); 243 } 244 else 245 { 246 // Fix for http://www.phpbb.com/bugs/phpbb3/52315 247 // Explicit encoding 248 return mb_substr($str, $offset, $length, 'UTF-8'); 249 } 250 } 251 252 /** 253 * Return the length (in characters) of a UTF-8 string 254 * @ignore 255 */ 256 function utf8_strlen($text) 257 { 258 return mb_strlen($text, 'utf-8'); 259 } 260} 261else 262{ 263 /** 264 * UTF-8 aware alternative to strrpos 265 * Find position of last occurrence of a char in a string 266 * 267 * @author Harry Fuecks 268 * @param string $str haystack 269 * @param string $needle needle 270 * @param integer $offset (optional) offset (from left) 271 * @return mixed integer position or FALSE on failure 272 */ 273 function utf8_strrpos($str, $needle, $offset = null) 274 { 275 if (is_null($offset)) 276 { 277 $ar = explode($needle, $str); 278 279 if (sizeof($ar) > 1) 280 { 281 // Pop off the end of the string where the last match was made 282 array_pop($ar); 283 $str = join($needle, $ar); 284 285 return utf8_strlen($str); 286 } 287 return false; 288 } 289 else 290 { 291 if (!is_int($offset)) 292 { 293 trigger_error('utf8_strrpos expects parameter 3 to be long', E_USER_ERROR); 294 return false; 295 } 296 297 $str = utf8_substr($str, $offset); 298 299 if (false !== ($pos = utf8_strrpos($str, $needle))) 300 { 301 return $pos + $offset; 302 } 303 304 return false; 305 } 306 } 307 308 /** 309 * UTF-8 aware alternative to strpos 310 * Find position of first occurrence of a string 311 * 312 * @author Harry Fuecks 313 * @param string $str haystack 314 * @param string $needle needle 315 * @param integer $offset offset in characters (from left) 316 * @return mixed integer position or FALSE on failure 317 */ 318 function utf8_strpos($str, $needle, $offset = null) 319 { 320 if (is_null($offset)) 321 { 322 $ar = explode($needle, $str); 323 if (sizeof($ar) > 1) 324 { 325 return utf8_strlen($ar[0]); 326 } 327 return false; 328 } 329 else 330 { 331 if (!is_int($offset)) 332 { 333 trigger_error('utf8_strpos: Offset must be an integer', E_USER_ERROR); 334 return false; 335 } 336 337 $str = utf8_substr($str, $offset); 338 339 if (false !== ($pos = utf8_strpos($str, $needle))) 340 { 341 return $pos + $offset; 342 } 343 344 return false; 345 } 346 } 347 348 /** 349 * UTF-8 aware alternative to strtolower 350 * Make a string lowercase 351 * Note: The concept of a characters "case" only exists is some alphabets 352 * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does 353 * not exist in the Chinese alphabet, for example. See Unicode Standard 354 * Annex #21: Case Mappings 355 * 356 * @param string 357 * @return string string in lowercase 358 */ 359 function utf8_strtolower($string) 360 { 361 static $utf8_upper_to_lower = array( 362 "\xC3\x80" => "\xC3\xA0", "\xC3\x81" => "\xC3\xA1", 363 "\xC3\x82" => "\xC3\xA2", "\xC3\x83" => "\xC3\xA3", "\xC3\x84" => "\xC3\xA4", "\xC3\x85" => "\xC3\xA5", 364 "\xC3\x86" => "\xC3\xA6", "\xC3\x87" => "\xC3\xA7", "\xC3\x88" => "\xC3\xA8", "\xC3\x89" => "\xC3\xA9", 365 "\xC3\x8A" => "\xC3\xAA", "\xC3\x8B" => "\xC3\xAB", "\xC3\x8C" => "\xC3\xAC", "\xC3\x8D" => "\xC3\xAD", 366 "\xC3\x8E" => "\xC3\xAE", "\xC3\x8F" => "\xC3\xAF", "\xC3\x90" => "\xC3\xB0", "\xC3\x91" => "\xC3\xB1", 367 "\xC3\x92" => "\xC3\xB2", "\xC3\x93" => "\xC3\xB3", "\xC3\x94" => "\xC3\xB4", "\xC3\x95" => "\xC3\xB5", 368 "\xC3\x96" => "\xC3\xB6", "\xC3\x98" => "\xC3\xB8", "\xC3\x99" => "\xC3\xB9", "\xC3\x9A" => "\xC3\xBA", 369 "\xC3\x9B" => "\xC3\xBB", "\xC3\x9C" => "\xC3\xBC", "\xC3\x9D" => "\xC3\xBD", "\xC3\x9E" => "\xC3\xBE", 370 "\xC4\x80" => "\xC4\x81", "\xC4\x82" => "\xC4\x83", "\xC4\x84" => "\xC4\x85", "\xC4\x86" => "\xC4\x87", 371 "\xC4\x88" => "\xC4\x89", "\xC4\x8A" => "\xC4\x8B", "\xC4\x8C" => "\xC4\x8D", "\xC4\x8E" => "\xC4\x8F", 372 "\xC4\x90" => "\xC4\x91", "\xC4\x92" => "\xC4\x93", "\xC4\x96" => "\xC4\x97", "\xC4\x98" => "\xC4\x99", 373 "\xC4\x9A" => "\xC4\x9B", "\xC4\x9C" => "\xC4\x9D", "\xC4\x9E" => "\xC4\x9F", "\xC4\xA0" => "\xC4\xA1", 374 "\xC4\xA2" => "\xC4\xA3", "\xC4\xA4" => "\xC4\xA5", "\xC4\xA6" => "\xC4\xA7", "\xC4\xA8" => "\xC4\xA9", 375 "\xC4\xAA" => "\xC4\xAB", "\xC4\xAE" => "\xC4\xAF", "\xC4\xB4" => "\xC4\xB5", "\xC4\xB6" => "\xC4\xB7", 376 "\xC4\xB9" => "\xC4\xBA", "\xC4\xBB" => "\xC4\xBC", "\xC4\xBD" => "\xC4\xBE", "\xC5\x81" => "\xC5\x82", 377 "\xC5\x83" => "\xC5\x84", "\xC5\x85" => "\xC5\x86", "\xC5\x87" => "\xC5\x88", "\xC5\x8A" => "\xC5\x8B", 378 "\xC5\x8C" => "\xC5\x8D", "\xC5\x90" => "\xC5\x91", "\xC5\x94" => "\xC5\x95", "\xC5\x96" => "\xC5\x97", 379 "\xC5\x98" => "\xC5\x99", "\xC5\x9A" => "\xC5\x9B", "\xC5\x9C" => "\xC5\x9D", "\xC5\x9E" => "\xC5\x9F", 380 "\xC5\xA0" => "\xC5\xA1", "\xC5\xA2" => "\xC5\xA3", "\xC5\xA4" => "\xC5\xA5", "\xC5\xA6" => "\xC5\xA7", 381 "\xC5\xA8" => "\xC5\xA9", "\xC5\xAA" => "\xC5\xAB", "\xC5\xAC" => "\xC5\xAD", "\xC5\xAE" => "\xC5\xAF", 382 "\xC5\xB0" => "\xC5\xB1", "\xC5\xB2" => "\xC5\xB3", "\xC5\xB4" => "\xC5\xB5", "\xC5\xB6" => "\xC5\xB7", 383 "\xC5\xB8" => "\xC3\xBF", "\xC5\xB9" => "\xC5\xBA", "\xC5\xBB" => "\xC5\xBC", "\xC5\xBD" => "\xC5\xBE", 384 "\xC6\xA0" => "\xC6\xA1", "\xC6\xAF" => "\xC6\xB0", "\xC8\x98" => "\xC8\x99", "\xC8\x9A" => "\xC8\x9B", 385 "\xCE\x86" => "\xCE\xAC", "\xCE\x88" => "\xCE\xAD", "\xCE\x89" => "\xCE\xAE", "\xCE\x8A" => "\xCE\xAF", 386 "\xCE\x8C" => "\xCF\x8C", "\xCE\x8E" => "\xCF\x8D", "\xCE\x8F" => "\xCF\x8E", "\xCE\x91" => "\xCE\xB1", 387 "\xCE\x92" => "\xCE\xB2", "\xCE\x93" => "\xCE\xB3", "\xCE\x94" => "\xCE\xB4", "\xCE\x95" => "\xCE\xB5", 388 "\xCE\x96" => "\xCE\xB6", "\xCE\x97" => "\xCE\xB7", "\xCE\x98" => "\xCE\xB8", "\xCE\x99" => "\xCE\xB9", 389 "\xCE\x9A" => "\xCE\xBA", "\xCE\x9B" => "\xCE\xBB", "\xCE\x9C" => "\xCE\xBC", "\xCE\x9D" => "\xCE\xBD", 390 "\xCE\x9E" => "\xCE\xBE", "\xCE\x9F" => "\xCE\xBF", "\xCE\xA0" => "\xCF\x80", "\xCE\xA1" => "\xCF\x81", 391 "\xCE\xA3" => "\xCF\x83", "\xCE\xA4" => "\xCF\x84", "\xCE\xA5" => "\xCF\x85", "\xCE\xA6" => "\xCF\x86", 392 "\xCE\xA7" => "\xCF\x87", "\xCE\xA8" => "\xCF\x88", "\xCE\xA9" => "\xCF\x89", "\xCE\xAA" => "\xCF\x8A", 393 "\xCE\xAB" => "\xCF\x8B", "\xD0\x81" => "\xD1\x91", "\xD0\x82" => "\xD1\x92", "\xD0\x83" => "\xD1\x93", 394 "\xD0\x84" => "\xD1\x94", "\xD0\x85" => "\xD1\x95", "\xD0\x86" => "\xD1\x96", "\xD0\x87" => "\xD1\x97", 395 "\xD0\x88" => "\xD1\x98", "\xD0\x89" => "\xD1\x99", "\xD0\x8A" => "\xD1\x9A", "\xD0\x8B" => "\xD1\x9B", 396 "\xD0\x8C" => "\xD1\x9C", "\xD0\x8E" => "\xD1\x9E", "\xD0\x8F" => "\xD1\x9F", "\xD0\x90" => "\xD0\xB0", 397 "\xD0\x91" => "\xD0\xB1", "\xD0\x92" => "\xD0\xB2", "\xD0\x93" => "\xD0\xB3", "\xD0\x94" => "\xD0\xB4", 398 "\xD0\x95" => "\xD0\xB5", "\xD0\x96" => "\xD0\xB6", "\xD0\x97" => "\xD0\xB7", "\xD0\x98" => "\xD0\xB8", 399 "\xD0\x99" => "\xD0\xB9", "\xD0\x9A" => "\xD0\xBA", "\xD0\x9B" => "\xD0\xBB", "\xD0\x9C" => "\xD0\xBC", 400 "\xD0\x9D" => "\xD0\xBD", "\xD0\x9E" => "\xD0\xBE", "\xD0\x9F" => "\xD0\xBF", "\xD0\xA0" => "\xD1\x80", 401 "\xD0\xA1" => "\xD1\x81", "\xD0\xA2" => "\xD1\x82", "\xD0\xA3" => "\xD1\x83", "\xD0\xA4" => "\xD1\x84", 402 "\xD0\xA5" => "\xD1\x85", "\xD0\xA6" => "\xD1\x86", "\xD0\xA7" => "\xD1\x87", "\xD0\xA8" => "\xD1\x88", 403 "\xD0\xA9" => "\xD1\x89", "\xD0\xAA" => "\xD1\x8A", "\xD0\xAB" => "\xD1\x8B", "\xD0\xAC" => "\xD1\x8C", 404 "\xD0\xAD" => "\xD1\x8D", "\xD0\xAE" => "\xD1\x8E", "\xD0\xAF" => "\xD1\x8F", "\xD2\x90" => "\xD2\x91", 405 "\xE1\xB8\x82" => "\xE1\xB8\x83", "\xE1\xB8\x8A" => "\xE1\xB8\x8B", "\xE1\xB8\x9E" => "\xE1\xB8\x9F", "\xE1\xB9\x80" => "\xE1\xB9\x81", 406 "\xE1\xB9\x96" => "\xE1\xB9\x97", "\xE1\xB9\xA0" => "\xE1\xB9\xA1", "\xE1\xB9\xAA" => "\xE1\xB9\xAB", "\xE1\xBA\x80" => "\xE1\xBA\x81", 407 "\xE1\xBA\x82" => "\xE1\xBA\x83", "\xE1\xBA\x84" => "\xE1\xBA\x85", "\xE1\xBB\xB2" => "\xE1\xBB\xB3" 408 ); 409 410 return strtr(strtolower($string), $utf8_upper_to_lower); 411 } 412 413 /** 414 * UTF-8 aware alternative to strtoupper 415 * Make a string uppercase 416 * Note: The concept of a characters "case" only exists is some alphabets 417 * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does 418 * not exist in the Chinese alphabet, for example. See Unicode Standard 419 * Annex #21: Case Mappings 420 * 421 * @param string 422 * @return string string in uppercase 423 */ 424 function utf8_strtoupper($string) 425 { 426 static $utf8_lower_to_upper = array( 427 "\xC3\xA0" => "\xC3\x80", "\xC3\xA1" => "\xC3\x81", 428 "\xC3\xA2" => "\xC3\x82", "\xC3\xA3" => "\xC3\x83", "\xC3\xA4" => "\xC3\x84", "\xC3\xA5" => "\xC3\x85", 429 "\xC3\xA6" => "\xC3\x86", "\xC3\xA7" => "\xC3\x87", "\xC3\xA8" => "\xC3\x88", "\xC3\xA9" => "\xC3\x89", 430 "\xC3\xAA" => "\xC3\x8A", "\xC3\xAB" => "\xC3\x8B", "\xC3\xAC" => "\xC3\x8C", "\xC3\xAD" => "\xC3\x8D", 431 "\xC3\xAE" => "\xC3\x8E", "\xC3\xAF" => "\xC3\x8F", "\xC3\xB0" => "\xC3\x90", "\xC3\xB1" => "\xC3\x91", 432 "\xC3\xB2" => "\xC3\x92", "\xC3\xB3" => "\xC3\x93", "\xC3\xB4" => "\xC3\x94", "\xC3\xB5" => "\xC3\x95", 433 "\xC3\xB6" => "\xC3\x96", "\xC3\xB8" => "\xC3\x98", "\xC3\xB9" => "\xC3\x99", "\xC3\xBA" => "\xC3\x9A", 434 "\xC3\xBB" => "\xC3\x9B", "\xC3\xBC" => "\xC3\x9C", "\xC3\xBD" => "\xC3\x9D", "\xC3\xBE" => "\xC3\x9E", 435 "\xC3\xBF" => "\xC5\xB8", "\xC4\x81" => "\xC4\x80", "\xC4\x83" => "\xC4\x82", "\xC4\x85" => "\xC4\x84", 436 "\xC4\x87" => "\xC4\x86", "\xC4\x89" => "\xC4\x88", "\xC4\x8B" => "\xC4\x8A", "\xC4\x8D" => "\xC4\x8C", 437 "\xC4\x8F" => "\xC4\x8E", "\xC4\x91" => "\xC4\x90", "\xC4\x93" => "\xC4\x92", "\xC4\x97" => "\xC4\x96", 438 "\xC4\x99" => "\xC4\x98", "\xC4\x9B" => "\xC4\x9A", "\xC4\x9D" => "\xC4\x9C", "\xC4\x9F" => "\xC4\x9E", 439 "\xC4\xA1" => "\xC4\xA0", "\xC4\xA3" => "\xC4\xA2", "\xC4\xA5" => "\xC4\xA4", "\xC4\xA7" => "\xC4\xA6", 440 "\xC4\xA9" => "\xC4\xA8", "\xC4\xAB" => "\xC4\xAA", "\xC4\xAF" => "\xC4\xAE", "\xC4\xB5" => "\xC4\xB4", 441 "\xC4\xB7" => "\xC4\xB6", "\xC4\xBA" => "\xC4\xB9", "\xC4\xBC" => "\xC4\xBB", "\xC4\xBE" => "\xC4\xBD", 442 "\xC5\x82" => "\xC5\x81", "\xC5\x84" => "\xC5\x83", "\xC5\x86" => "\xC5\x85", "\xC5\x88" => "\xC5\x87", 443 "\xC5\x8B" => "\xC5\x8A", "\xC5\x8D" => "\xC5\x8C", "\xC5\x91" => "\xC5\x90", "\xC5\x95" => "\xC5\x94", 444 "\xC5\x97" => "\xC5\x96", "\xC5\x99" => "\xC5\x98", "\xC5\x9B" => "\xC5\x9A", "\xC5\x9D" => "\xC5\x9C", 445 "\xC5\x9F" => "\xC5\x9E", "\xC5\xA1" => "\xC5\xA0", "\xC5\xA3" => "\xC5\xA2", "\xC5\xA5" => "\xC5\xA4", 446 "\xC5\xA7" => "\xC5\xA6", "\xC5\xA9" => "\xC5\xA8", "\xC5\xAB" => "\xC5\xAA", "\xC5\xAD" => "\xC5\xAC", 447 "\xC5\xAF" => "\xC5\xAE", "\xC5\xB1" => "\xC5\xB0", "\xC5\xB3" => "\xC5\xB2", "\xC5\xB5" => "\xC5\xB4", 448 "\xC5\xB7" => "\xC5\xB6", "\xC5\xBA" => "\xC5\xB9", "\xC5\xBC" => "\xC5\xBB", "\xC5\xBE" => "\xC5\xBD", 449 "\xC6\xA1" => "\xC6\xA0", "\xC6\xB0" => "\xC6\xAF", "\xC8\x99" => "\xC8\x98", "\xC8\x9B" => "\xC8\x9A", 450 "\xCE\xAC" => "\xCE\x86", "\xCE\xAD" => "\xCE\x88", "\xCE\xAE" => "\xCE\x89", "\xCE\xAF" => "\xCE\x8A", 451 "\xCE\xB1" => "\xCE\x91", "\xCE\xB2" => "\xCE\x92", "\xCE\xB3" => "\xCE\x93", "\xCE\xB4" => "\xCE\x94", 452 "\xCE\xB5" => "\xCE\x95", "\xCE\xB6" => "\xCE\x96", "\xCE\xB7" => "\xCE\x97", "\xCE\xB8" => "\xCE\x98", 453 "\xCE\xB9" => "\xCE\x99", "\xCE\xBA" => "\xCE\x9A", "\xCE\xBB" => "\xCE\x9B", "\xCE\xBC" => "\xCE\x9C", 454 "\xCE\xBD" => "\xCE\x9D", "\xCE\xBE" => "\xCE\x9E", "\xCE\xBF" => "\xCE\x9F", "\xCF\x80" => "\xCE\xA0", 455 "\xCF\x81" => "\xCE\xA1", "\xCF\x83" => "\xCE\xA3", "\xCF\x84" => "\xCE\xA4", "\xCF\x85" => "\xCE\xA5", 456 "\xCF\x86" => "\xCE\xA6", "\xCF\x87" => "\xCE\xA7", "\xCF\x88" => "\xCE\xA8", "\xCF\x89" => "\xCE\xA9", 457 "\xCF\x8A" => "\xCE\xAA", "\xCF\x8B" => "\xCE\xAB", "\xCF\x8C" => "\xCE\x8C", "\xCF\x8D" => "\xCE\x8E", 458 "\xCF\x8E" => "\xCE\x8F", "\xD0\xB0" => "\xD0\x90", "\xD0\xB1" => "\xD0\x91", "\xD0\xB2" => "\xD0\x92", 459 "\xD0\xB3" => "\xD0\x93", "\xD0\xB4" => "\xD0\x94", "\xD0\xB5" => "\xD0\x95", "\xD0\xB6" => "\xD0\x96", 460 "\xD0\xB7" => "\xD0\x97", "\xD0\xB8" => "\xD0\x98", "\xD0\xB9" => "\xD0\x99", "\xD0\xBA" => "\xD0\x9A", 461 "\xD0\xBB" => "\xD0\x9B", "\xD0\xBC" => "\xD0\x9C", "\xD0\xBD" => "\xD0\x9D", "\xD0\xBE" => "\xD0\x9E", 462 "\xD0\xBF" => "\xD0\x9F", "\xD1\x80" => "\xD0\xA0", "\xD1\x81" => "\xD0\xA1", "\xD1\x82" => "\xD0\xA2", 463 "\xD1\x83" => "\xD0\xA3", "\xD1\x84" => "\xD0\xA4", "\xD1\x85" => "\xD0\xA5", "\xD1\x86" => "\xD0\xA6", 464 "\xD1\x87" => "\xD0\xA7", "\xD1\x88" => "\xD0\xA8", "\xD1\x89" => "\xD0\xA9", "\xD1\x8A" => "\xD0\xAA", 465 "\xD1\x8B" => "\xD0\xAB", "\xD1\x8C" => "\xD0\xAC", "\xD1\x8D" => "\xD0\xAD", "\xD1\x8E" => "\xD0\xAE", 466 "\xD1\x8F" => "\xD0\xAF", "\xD1\x91" => "\xD0\x81", "\xD1\x92" => "\xD0\x82", "\xD1\x93" => "\xD0\x83", 467 "\xD1\x94" => "\xD0\x84", "\xD1\x95" => "\xD0\x85", "\xD1\x96" => "\xD0\x86", "\xD1\x97" => "\xD0\x87", 468 "\xD1\x98" => "\xD0\x88", "\xD1\x99" => "\xD0\x89", "\xD1\x9A" => "\xD0\x8A", "\xD1\x9B" => "\xD0\x8B", 469 "\xD1\x9C" => "\xD0\x8C", "\xD1\x9E" => "\xD0\x8E", "\xD1\x9F" => "\xD0\x8F", "\xD2\x91" => "\xD2\x90", 470 "\xE1\xB8\x83" => "\xE1\xB8\x82", "\xE1\xB8\x8B" => "\xE1\xB8\x8A", "\xE1\xB8\x9F" => "\xE1\xB8\x9E", "\xE1\xB9\x81" => "\xE1\xB9\x80", 471 "\xE1\xB9\x97" => "\xE1\xB9\x96", "\xE1\xB9\xA1" => "\xE1\xB9\xA0", "\xE1\xB9\xAB" => "\xE1\xB9\xAA", "\xE1\xBA\x81" => "\xE1\xBA\x80", 472 "\xE1\xBA\x83" => "\xE1\xBA\x82", "\xE1\xBA\x85" => "\xE1\xBA\x84", "\xE1\xBB\xB3" => "\xE1\xBB\xB2" 473 ); 474 475 return strtr(strtoupper($string), $utf8_lower_to_upper); 476 } 477 478 /** 479 * UTF-8 aware alternative to substr 480 * Return part of a string given character offset (and optionally length) 481 * 482 * Note arguments: comparied to substr - if offset or length are 483 * not integers, this version will not complain but rather massages them 484 * into an integer. 485 * 486 * Note on returned values: substr documentation states false can be 487 * returned in some cases (e.g. offset > string length) 488 * mb_substr never returns false, it will return an empty string instead. 489 * This adopts the mb_substr approach 490 * 491 * Note on implementation: PCRE only supports repetitions of less than 492 * 65536, in order to accept up to MAXINT values for offset and length, 493 * we'll repeat a group of 65535 characters when needed. 494 * 495 * Note on implementation: calculating the number of characters in the 496 * string is a relatively expensive operation, so we only carry it out when 497 * necessary. It isn't necessary for +ve offsets and no specified length 498 * 499 * @author Chris Smith<chris@jalakai.co.uk> 500 * @param string $str 501 * @param integer $offset number of UTF-8 characters offset (from left) 502 * @param integer $length (optional) length in UTF-8 characters from offset 503 * @return mixed string or FALSE if failure 504 */ 505 function utf8_substr($str, $offset, $length = NULL) 506 { 507 // generates E_NOTICE 508 // for PHP4 objects, but not PHP5 objects 509 $str = (string) $str; 510 $offset = (int) $offset; 511 if (!is_null($length)) 512 { 513 $length = (int) $length; 514 } 515 516 // handle trivial cases 517 if ($length === 0 || ($offset < 0 && $length < 0 && $length < $offset)) 518 { 519 return ''; 520 } 521 522 // normalise negative offsets (we could use a tail 523 // anchored pattern, but they are horribly slow!) 524 if ($offset < 0) 525 { 526 // see notes 527 $strlen = utf8_strlen($str); 528 $offset = $strlen + $offset; 529 if ($offset < 0) 530 { 531 $offset = 0; 532 } 533 } 534 535 $op = ''; 536 $lp = ''; 537 538 // establish a pattern for offset, a 539 // non-captured group equal in length to offset 540 if ($offset > 0) 541 { 542 $ox = (int) ($offset / 65535); 543 $oy = $offset % 65535; 544 545 if ($ox) 546 { 547 $op = '(?:.{65535}){' . $ox . '}'; 548 } 549 550 $op = '^(?:' . $op . '.{' . $oy . '})'; 551 } 552 else 553 { 554 // offset == 0; just anchor the pattern 555 $op = '^'; 556 } 557 558 // establish a pattern for length 559 if (is_null($length)) 560 { 561 // the rest of the string 562 $lp = '(.*)$'; 563 } 564 else 565 { 566 if (!isset($strlen)) 567 { 568 // see notes 569 $strlen = utf8_strlen($str); 570 } 571 572 // another trivial case 573 if ($offset > $strlen) 574 { 575 return ''; 576 } 577 578 if ($length > 0) 579 { 580 // reduce any length that would 581 // go passed the end of the string 582 $length = min($strlen - $offset, $length); 583 584 $lx = (int) ($length / 65535); 585 $ly = $length % 65535; 586 587 // negative length requires a captured group 588 // of length characters 589 if ($lx) 590 { 591 $lp = '(?:.{65535}){' . $lx . '}'; 592 } 593 $lp = '(' . $lp . '.{'. $ly . '})'; 594 } 595 else if ($length < 0) 596 { 597 if ($length < ($offset - $strlen)) 598 { 599 return ''; 600 } 601 602 $lx = (int)((-$length) / 65535); 603 $ly = (-$length) % 65535; 604 605 // negative length requires ... capture everything 606 // except a group of -length characters 607 // anchored at the tail-end of the string 608 if ($lx) 609 { 610 $lp = '(?:.{65535}){' . $lx . '}'; 611 } 612 $lp = '(.*)(?:' . $lp . '.{' . $ly . '})$'; 613 } 614 } 615 616 if (!preg_match('#' . $op . $lp . '#us', $str, $match)) 617 { 618 return ''; 619 } 620 621 return $match[1]; 622 } 623 624 /** 625 * Return the length (in characters) of a UTF-8 string 626 * 627 * @param string $text UTF-8 string 628 * @return integer Length (in chars) of given string 629 */ 630 function utf8_strlen($text) 631 { 632 // Since utf8_decode is replacing multibyte characters to ? strlen works fine 633 return strlen(utf8_decode($text)); 634 } 635} 636 637/** 638* UTF-8 aware alternative to str_split 639* Convert a string to an array 640* 641* @author Harry Fuecks 642* @param string $str UTF-8 encoded 643* @param int $split_len number to characters to split string by 644* @return array characters in string reverses 645*/ 646function utf8_str_split($str, $split_len = 1) 647{ 648 if (!is_int($split_len) || $split_len < 1) 649 { 650 return false; 651 } 652 653 $len = utf8_strlen($str); 654 if ($len <= $split_len) 655 { 656 return array($str); 657 } 658 659 preg_match_all('/.{' . $split_len . '}|[^\x00]{1,' . $split_len . '}$/us', $str, $ar); 660 return $ar[0]; 661} 662 663/** 664* UTF-8 aware alternative to strspn 665* Find length of initial segment matching the mask 666* 667* @author Harry Fuecks 668*/ 669function utf8_strspn($str, $mask, $start = null, $length = null) 670{ 671 if ($start !== null || $length !== null) 672 { 673 $str = utf8_substr($str, $start, $length); 674 } 675 676 preg_match('/^[' . $mask . ']+/u', $str, $matches); 677 678 if (isset($matches[0])) 679 { 680 return utf8_strlen($matches[0]); 681 } 682 683 return 0; 684} 685 686/** 687* UTF-8 aware alternative to ucfirst 688* Make a string's first character uppercase 689* 690* @author Harry Fuecks 691* @param string 692* @return string with first character as upper case (if applicable) 693*/ 694function utf8_ucfirst($str) 695{ 696 switch (utf8_strlen($str)) 697 { 698 case 0: 699 return ''; 700 break; 701 702 case 1: 703 return utf8_strtoupper($str); 704 break; 705 706 default: 707 preg_match('/^(.{1})(.*)$/us', $str, $matches); 708 return utf8_strtoupper($matches[1]) . $matches[2]; 709 break; 710 } 711} 712 713/** 714* Recode a string to UTF-8 715* 716* If the encoding is not supported, the string is returned as-is 717* 718* @param string $string Original string 719* @param string $encoding Original encoding (lowered) 720* @return string The string, encoded in UTF-8 721*/ 722function utf8_recode($string, $encoding) 723{ 724 $encoding = strtolower($encoding); 725 726 if ($encoding == 'utf-8' || !is_string($string) || empty($string)) 727 { 728 return $string; 729 } 730 731 // we force iso-8859-1 to be cp1252 732 if ($encoding == 'iso-8859-1') 733 { 734 $encoding = 'cp1252'; 735 } 736 // convert iso-8859-8-i to iso-8859-8 737 else if ($encoding == 'iso-8859-8-i') 738 { 739 $encoding = 'iso-8859-8'; 740 $string = hebrev($string); 741 } 742 743 // First, try iconv() 744 if (function_exists('iconv')) 745 { 746 $ret = @iconv($encoding, 'utf-8', $string); 747 748 if (!empty($ret)) 749 { 750 return $ret; 751 } 752 } 753 754 // Try the mb_string extension 755 if (function_exists('mb_convert_encoding')) 756 { 757 // mbstring is nasty on PHP4, we must make *sure* that we send a good encoding 758 switch ($encoding) 759 { 760 case 'iso-8859-1': 761 case 'iso-8859-2': 762 case 'iso-8859-4': 763 case 'iso-8859-7': 764 case 'iso-8859-9': 765 case 'iso-8859-15': 766 case 'windows-1251': 767 case 'windows-1252': 768 case 'cp1252': 769 case 'shift_jis': 770 case 'euc-kr': 771 case 'big5': 772 case 'gb2312': 773 $ret = @mb_convert_encoding($string, 'utf-8', $encoding); 774 775 if (!empty($ret)) 776 { 777 return $ret; 778 } 779 } 780 } 781 782 // Try the recode extension 783 if (function_exists('recode_string')) 784 { 785 $ret = @recode_string($encoding . '..utf-8', $string); 786 787 if (!empty($ret)) 788 { 789 return $ret; 790 } 791 } 792 793 // If nothing works, check if we have a custom transcoder available 794 if (!preg_match('#^[a-z0-9_ \\-]+$#', $encoding)) 795 { 796 // Make sure the encoding name is alphanumeric, we don't want it to be abused into loading arbitrary files 797 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); 798 } 799 800 global $phpbb_root_path, $phpEx; 801 802 // iso-8859-* character encoding 803 if (preg_match('/iso[_ -]?8859[_ -]?(\\d+)/', $encoding, $array)) 804 { 805 switch ($array[1]) 806 { 807 case '1': 808 case '2': 809 case '4': 810 case '7': 811 case '8': 812 case '9': 813 case '15': 814 if (!function_exists('iso_8859_' . $array[1])) 815 { 816 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) 817 { 818 trigger_error('Basic reencoder file is missing', E_USER_ERROR); 819 } 820 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); 821 } 822 return call_user_func('iso_8859_' . $array[1], $string); 823 break; 824 825 default: 826 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); 827 break; 828 } 829 } 830 831 // CP/WIN character encoding 832 if (preg_match('/(?:cp|windows)[_\- ]?(\\d+)/', $encoding, $array)) 833 { 834 switch ($array[1]) 835 { 836 case '932': 837 break; 838 case '1250': 839 case '1251': 840 case '1252': 841 case '1254': 842 case '1255': 843 case '1256': 844 case '1257': 845 case '874': 846 if (!function_exists('cp' . $array[1])) 847 { 848 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) 849 { 850 trigger_error('Basic reencoder file is missing', E_USER_ERROR); 851 } 852 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); 853 } 854 return call_user_func('cp' . $array[1], $string); 855 break; 856 857 default: 858 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); 859 break; 860 } 861 } 862 863 // TIS-620 864 if (preg_match('/tis[_ -]?620/', $encoding)) 865 { 866 if (!function_exists('tis_620')) 867 { 868 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) 869 { 870 trigger_error('Basic reencoder file is missing', E_USER_ERROR); 871 } 872 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); 873 } 874 return tis_620($string); 875 } 876 877 // SJIS 878 if (preg_match('/sjis(?:[_ -]?win)?|(?:cp|ibm)[_ -]?932|shift[_ -]?jis/', $encoding)) 879 { 880 if (!function_exists('sjis')) 881 { 882 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) 883 { 884 trigger_error('CJK reencoder file is missing', E_USER_ERROR); 885 } 886 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); 887 } 888 return sjis($string); 889 } 890 891 // EUC_KR 892 if (preg_match('/euc[_ -]?kr/', $encoding)) 893 { 894 if (!function_exists('euc_kr')) 895 { 896 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) 897 { 898 trigger_error('CJK reencoder file is missing', E_USER_ERROR); 899 } 900 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); 901 } 902 return euc_kr($string); 903 } 904 905 // BIG-5 906 if (preg_match('/big[_ -]?5/', $encoding)) 907 { 908 if (!function_exists('big5')) 909 { 910 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) 911 { 912 trigger_error('CJK reencoder file is missing', E_USER_ERROR); 913 } 914 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); 915 } 916 return big5($string); 917 } 918 919 // GB2312 920 if (preg_match('/gb[_ -]?2312/', $encoding)) 921 { 922 if (!function_exists('gb2312')) 923 { 924 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) 925 { 926 trigger_error('CJK reencoder file is missing', E_USER_ERROR); 927 } 928 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); 929 } 930 return gb2312($string); 931 } 932 933 // Trigger an error?! Fow now just give bad data :-( 934 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); 935 //return $string; // use utf_normalizer::cleanup() ? 936} 937 938/** 939* Replace all UTF-8 chars that are not in ASCII with their NCR 940* 941* @param string $text UTF-8 string in NFC 942* @return string ASCII string using NCRs for non-ASCII chars 943*/ 944function utf8_encode_ncr($text) 945{ 946 return preg_replace_callback('#[\\xC2-\\xF4][\\x80-\\xBF]{1,3}#', 'utf8_encode_ncr_callback', $text); 947} 948 949/** 950* Callback used in encode_ncr() 951* 952* Takes a UTF-8 char and replaces it with its NCR. Attention, $m is an array 953* 954* @param array $m 0-based numerically indexed array passed by preg_replace_callback() 955* @return string A HTML NCR if the character is valid, or the original string otherwise 956*/ 957function utf8_encode_ncr_callback($m) 958{ 959 return '&#' . utf8_ord($m[0]) . ';'; 960} 961 962/** 963* Converts a UTF-8 char to an NCR 964* 965* @param string $chr UTF-8 char 966* @return integer UNICODE code point 967*/ 968function utf8_ord($chr) 969{ 970 switch (strlen($chr)) 971 { 972 case 1: 973 return ord($chr); 974 break; 975 976 case 2: 977 return ((ord($chr[0]) & 0x1F) << 6) | (ord($chr[1]) & 0x3F); 978 break; 979 980 case 3: 981 return ((ord($chr[0]) & 0x0F) << 12) | ((ord($chr[1]) & 0x3F) << 6) | (ord($chr[2]) & 0x3F); 982 break; 983 984 case 4: 985 return ((ord($chr[0]) & 0x07) << 18) | ((ord($chr[1]) & 0x3F) << 12) | ((ord($chr[2]) & 0x3F) << 6) | (ord($chr[3]) & 0x3F); 986 break; 987 988 default: 989 return $chr; 990 } 991} 992 993/** 994* Converts an NCR to a UTF-8 char 995* 996* @param int $cp UNICODE code point 997* @return string UTF-8 char 998*/ 999function utf8_chr($cp) 1000{ 1001 if ($cp > 0xFFFF) 1002 { 1003 return chr(0xF0 | ($cp >> 18)) . chr(0x80 | (($cp >> 12) & 0x3F)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F)); 1004 } 1005 else if ($cp > 0x7FF) 1006 { 1007 return chr(0xE0 | ($cp >> 12)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F)); 1008 } 1009 else if ($cp > 0x7F) 1010 { 1011 return chr(0xC0 | ($cp >> 6)) . chr(0x80 | ($cp & 0x3F)); 1012 } 1013 else 1014 { 1015 return chr($cp); 1016 } 1017} 1018 1019/** 1020* Convert Numeric Character References to UTF-8 chars 1021* 1022* Notes: 1023* - we do not convert NCRs recursively, if you pass &#38; it will return & 1024* - we DO NOT check for the existence of the Unicode characters, therefore an entity may be converted to an inexistent codepoint 1025* 1026* @param string $text String to convert, encoded in UTF-8 (no normal form required) 1027* @return string UTF-8 string where NCRs have been replaced with the actual chars 1028*/ 1029function utf8_decode_ncr($text) 1030{ 1031 return preg_replace_callback('/&#([0-9]{1,6}|x[0-9A-F]{1,5});/i', 'utf8_decode_ncr_callback', $text); 1032} 1033 1034/** 1035* Callback used in decode_ncr() 1036* 1037* Takes a NCR (in decimal or hexadecimal) and returns a UTF-8 char. Attention, $m is an array. 1038* It will ignore most of invalid NCRs, but not all! 1039* 1040* @param array $m 0-based numerically indexed array passed by preg_replace_callback() 1041* @return string UTF-8 char 1042*/ 1043function utf8_decode_ncr_callback($m) 1044{ 1045 $cp = (strncasecmp($m[1], 'x', 1)) ? $m[1] : hexdec(substr($m[1], 1)); 1046 1047 return utf8_chr($cp); 1048} 1049 1050/** 1051* Case folds a unicode string as per Unicode 5.0, section 3.13 1052* 1053* @param string $text text to be case folded 1054* @param string $option determines how we will fold the cases 1055* @return string case folded text 1056*/ 1057function utf8_case_fold($text, $option = 'full') 1058{ 1059 static $uniarray = array(); 1060 global $phpbb_root_path, $phpEx; 1061 1062 // common is always set 1063 if (!isset($uniarray['c'])) 1064 { 1065 $uniarray['c'] = include($phpbb_root_path . 'includes/utf/data/case_fold_c.' . $phpEx); 1066 } 1067 1068 // only set full if we need to 1069 if ($option === 'full' && !isset($uniarray['f'])) 1070 { 1071 $uniarray['f'] = include($phpbb_root_path . 'includes/utf/data/case_fold_f.' . $phpEx); 1072 } 1073 1074 // only set simple if we need to 1075 if ($option !== 'full' && !isset($uniarray['s'])) 1076 { 1077 $uniarray['s'] = include($phpbb_root_path . 'includes/utf/data/case_fold_s.' . $phpEx); 1078 } 1079 1080 // common is always replaced 1081 $text = strtr($text, $uniarray['c']); 1082 1083 if ($option === 'full') 1084 { 1085 // full replaces a character with multiple characters 1086 $text = strtr($text, $uniarray['f']); 1087 } 1088 else 1089 { 1090 // simple replaces a character with another character 1091 $text = strtr($text, $uniarray['s']); 1092 } 1093 1094 return $text; 1095} 1096 1097/** 1098* Takes the input and does a "special" case fold. It does minor normalization 1099* and returns NFKC compatable text 1100* 1101* @param string $text text to be case folded 1102* @param string $option determines how we will fold the cases 1103* @return string case folded text 1104*/ 1105function utf8_case_fold_nfkc($text, $option = 'full') 1106{ 1107 static $fc_nfkc_closure = array( 1108 "\xCD\xBA" => "\x20\xCE\xB9", 1109 "\xCF\x92" => "\xCF\x85", 1110 "\xCF\x93" => "\xCF\x8D", 1111 "\xCF\x94" => "\xCF\x8B", 1112 "\xCF\xB2" => "\xCF\x83", 1113 "\xCF\xB9" => "\xCF\x83", 1114 "\xE1\xB4\xAC" => "\x61", 1115 "\xE1\xB4\xAD" => "\xC3\xA6", 1116 "\xE1\xB4\xAE" => "\x62", 1117 "\xE1\xB4\xB0" => "\x64", 1118 "\xE1\xB4\xB1" => "\x65", 1119 "\xE1\xB4\xB2" => "\xC7\x9D", 1120 "\xE1\xB4\xB3" => "\x67", 1121 "\xE1\xB4\xB4" => "\x68", 1122 "\xE1\xB4\xB5" => "\x69", 1123 "\xE1\xB4\xB6" => "\x6A", 1124 "\xE1\xB4\xB7" => "\x6B", 1125 "\xE1\xB4\xB8" => "\x6C", 1126 "\xE1\xB4\xB9" => "\x6D", 1127 "\xE1\xB4\xBA" => "\x6E", 1128 "\xE1\xB4\xBC" => "\x6F", 1129 "\xE1\xB4\xBD" => "\xC8\xA3", 1130 "\xE1\xB4\xBE" => "\x70", 1131 "\xE1\xB4\xBF" => "\x72", 1132 "\xE1\xB5\x80" => "\x74", 1133 "\xE1\xB5\x81" => "\x75", 1134 "\xE1\xB5\x82" => "\x77", 1135 "\xE2\x82\xA8" => "\x72\x73", 1136 "\xE2\x84\x82" => "\x63", 1137 "\xE2\x84\x83" => "\xC2\xB0\x63", 1138 "\xE2\x84\x87" => "\xC9\x9B", 1139 "\xE2\x84\x89" => "\xC2\xB0\x66", 1140 "\xE2\x84\x8B" => "\x68", 1141 "\xE2\x84\x8C" => "\x68", 1142 "\xE2\x84\x8D" => "\x68", 1143 "\xE2\x84\x90" => "\x69", 1144 "\xE2\x84\x91" => "\x69", 1145 "\xE2\x84\x92" => "\x6C", 1146 "\xE2\x84\x95" => "\x6E", 1147 "\xE2\x84\x96" => "\x6E\x6F", 1148 "\xE2\x84\x99" => "\x70", 1149 "\xE2\x84\x9A" => "\x71", 1150 "\xE2\x84\x9B" => "\x72", 1151 "\xE2\x84\x9C" => "\x72", 1152 "\xE2\x84\x9D" => "\x72", 1153 "\xE2\x84\xA0" => "\x73\x6D", 1154 "\xE2\x84\xA1" => "\x74\x65\x6C", 1155 "\xE2\x84\xA2" => "\x74\x6D", 1156 "\xE2\x84\xA4" => "\x7A", 1157 "\xE2\x84\xA8" => "\x7A", 1158 "\xE2\x84\xAC" => "\x62", 1159 "\xE2\x84\xAD" => "\x63", 1160 "\xE2\x84\xB0" => "\x65", 1161 "\xE2\x84\xB1" => "\x66", 1162 "\xE2\x84\xB3" => "\x6D", 1163 "\xE2\x84\xBB" => "\x66\x61\x78", 1164 "\xE2\x84\xBE" => "\xCE\xB3", 1165 "\xE2\x84\xBF" => "\xCF\x80", 1166 "\xE2\x85\x85" => "\x64", 1167 "\xE3\x89\x90" => "\x70\x74\x65", 1168 "\xE3\x8B\x8C" => "\x68\x67", 1169 "\xE3\x8B\x8E" => "\x65\x76", 1170 "\xE3\x8B\x8F" => "\x6C\x74\x64", 1171 "\xE3\x8D\xB1" => "\x68\x70\x61", 1172 "\xE3\x8D\xB3" => "\x61\x75", 1173 "\xE3\x8D\xB5" => "\x6F\x76", 1174 "\xE3\x8D\xBA" => "\x69\x75", 1175 "\xE3\x8E\x80" => "\x70\x61", 1176 "\xE3\x8E\x81" => "\x6E\x61", 1177 "\xE3\x8E\x82" => "\xCE\xBC\x61", 1178 "\xE3\x8E\x83" => "\x6D\x61", 1179 "\xE3\x8E\x84" => "\x6B\x61", 1180 "\xE3\x8E\x85" => "\x6B\x62", 1181 "\xE3\x8E\x86" => "\x6D\x62", 1182 "\xE3\x8E\x87" => "\x67\x62", 1183 "\xE3\x8E\x8A" => "\x70\x66", 1184 "\xE3\x8E\x8B" => "\x6E\x66", 1185 "\xE3\x8E\x8C" => "\xCE\xBC\x66", 1186 "\xE3\x8E\x90" => "\x68\x7A", 1187 "\xE3\x8E\x91" => "\x6B\x68\x7A", 1188 "\xE3\x8E\x92" => "\x6D\x68\x7A", 1189 "\xE3\x8E\x93" => "\x67\x68\x7A", 1190 "\xE3\x8E\x94" => "\x74\x68\x7A", 1191 "\xE3\x8E\xA9" => "\x70\x61", 1192 "\xE3\x8E\xAA" => "\x6B\x70\x61", 1193 "\xE3\x8E\xAB" => "\x6D\x70\x61", 1194 "\xE3\x8E\xAC" => "\x67\x70\x61", 1195 "\xE3\x8E\xB4" => "\x70\x76", 1196 "\xE3\x8E\xB5" => "\x6E\x76", 1197 "\xE3\x8E\xB6" => "\xCE\xBC\x76", 1198 "\xE3\x8E\xB7" => "\x6D\x76", 1199 "\xE3\x8E\xB8" => "\x6B\x76", 1200 "\xE3\x8E\xB9" => "\x6D\x76", 1201 "\xE3\x8E\xBA" => "\x70\x77", 1202 "\xE3\x8E\xBB" => "\x6E\x77", 1203 "\xE3\x8E\xBC" => "\xCE\xBC\x77", 1204 "\xE3\x8E\xBD" => "\x6D\x77", 1205 "\xE3\x8E\xBE" => "\x6B\x77", 1206 "\xE3\x8E\xBF" => "\x6D\x77", 1207 "\xE3\x8F\x80" => "\x6B\xCF\x89", 1208 "\xE3\x8F\x81" => "\x6D\xCF\x89", 1209 "\xE3\x8F\x83" => "\x62\x71", 1210 "\xE3\x8F\x86" => "\x63\xE2\x88\x95\x6B\x67", 1211 "\xE3\x8F\x87" => "\x63\x6F\x2E", 1212 "\xE3\x8F\x88" => "\x64\x62", 1213 "\xE3\x8F\x89" => "\x67\x79", 1214 "\xE3\x8F\x8B" => "\x68\x70", 1215 "\xE3\x8F\x8D" => "\x6B\x6B", 1216 "\xE3\x8F\x8E" => "\x6B\x6D", 1217 "\xE3\x8F\x97" => "\x70\x68", 1218 "\xE3\x8F\x99" => "\x70\x70\x6D", 1219 "\xE3\x8F\x9A" => "\x70\x72", 1220 "\xE3\x8F\x9C" => "\x73\x76", 1221 "\xE3\x8F\x9D" => "\x77\x62", 1222 "\xE3\x8F\x9E" => "\x76\xE2\x88\x95\x6D", 1223 "\xE3\x8F\x9F" => "\x61\xE2\x88\x95\x6D", 1224 "\xF0\x9D\x90\x80" => "\x61", 1225 "\xF0\x9D\x90\x81" => "\x62", 1226 "\xF0\x9D\x90\x82" => "\x63", 1227 "\xF0\x9D\x90\x83" => "\x64", 1228 "\xF0\x9D\x90\x84" => "\x65", 1229 "\xF0\x9D\x90\x85" => "\x66", 1230 "\xF0\x9D\x90\x86" => "\x67", 1231 "\xF0\x9D\x90\x87" => "\x68", 1232 "\xF0\x9D\x90\x88" => "\x69", 1233 "\xF0\x9D\x90\x89" => "\x6A", 1234 "\xF0\x9D\x90\x8A" => "\x6B", 1235 "\xF0\x9D\x90\x8B" => "\x6C", 1236 "\xF0\x9D\x90\x8C" => "\x6D", 1237 "\xF0\x9D\x90\x8D" => "\x6E", 1238 "\xF0\x9D\x90\x8E" => "\x6F", 1239 "\xF0\x9D\x90\x8F" => "\x70", 1240 "\xF0\x9D\x90\x90" => "\x71", 1241 "\xF0\x9D\x90\x91" => "\x72", 1242 "\xF0\x9D\x90\x92" => "\x73", 1243 "\xF0\x9D\x90\x93" => "\x74", 1244 "\xF0\x9D\x90\x94" => "\x75", 1245 "\xF0\x9D\x90\x95" => "\x76", 1246 "\xF0\x9D\x90\x96" => "\x77", 1247 "\xF0\x9D\x90\x97" => "\x78", 1248 "\xF0\x9D\x90\x98" => "\x79", 1249 "\xF0\x9D\x90\x99" => "\x7A", 1250 "\xF0\x9D\x90\xB4" => "\x61", 1251 "\xF0\x9D\x90\xB5" => "\x62", 1252 "\xF0\x9D\x90\xB6" => "\x63", 1253 "\xF0\x9D\x90\xB7" => "\x64", 1254 "\xF0\x9D\x90\xB8" => "\x65", 1255 "\xF0\x9D\x90\xB9" => "\x66", 1256 "\xF0\x9D\x90\xBA" => "\x67", 1257 "\xF0\x9D\x90\xBB" => "\x68", 1258 "\xF0\x9D\x90\xBC" => "\x69", 1259 "\xF0\x9D\x90\xBD" => "\x6A", 1260 "\xF0\x9D\x90\xBE" => "\x6B", 1261 "\xF0\x9D\x90\xBF" => "\x6C", 1262 "\xF0\x9D\x91\x80" => "\x6D", 1263 "\xF0\x9D\x91\x81" => "\x6E", 1264 "\xF0\x9D\x91\x82" => "\x6F", 1265 "\xF0\x9D\x91\x83" => "\x70", 1266 "\xF0\x9D\x91\x84" => "\x71", 1267 "\xF0\x9D\x91\x85" => "\x72", 1268 "\xF0\x9D\x91\x86" => "\x73", 1269 "\xF0\x9D\x91\x87" => "\x74", 1270 "\xF0\x9D\x91\x88" => "\x75", 1271 "\xF0\x9D\x91\x89" => "\x76", 1272 "\xF0\x9D\x91\x8A" => "\x77", 1273 "\xF0\x9D\x91\x8B" => "\x78", 1274 "\xF0\x9D\x91\x8C" => "\x79", 1275 "\xF0\x9D\x91\x8D" => "\x7A", 1276 "\xF0\x9D\x91\xA8" => "\x61", 1277 "\xF0\x9D\x91\xA9" => "\x62", 1278 "\xF0\x9D\x91\xAA" => "\x63", 1279 "\xF0\x9D\x91\xAB" => "\x64", 1280 "\xF0\x9D\x91\xAC" => "\x65", 1281 "\xF0\x9D\x91\xAD" => "\x66", 1282 "\xF0\x9D\x91\xAE" => "\x67", 1283 "\xF0\x9D\x91\xAF" => "\x68", 1284 "\xF0\x9D\x91\xB0" => "\x69", 1285 "\xF0\x9D\x91\xB1" => "\x6A", 1286 "\xF0\x9D\x91\xB2" => "\x6B", 1287 "\xF0\x9D\x91\xB3" => "\x6C", 1288 "\xF0\x9D\x91\xB4" => "\x6D", 1289 "\xF0\x9D\x91\xB5" => "\x6E", 1290 "\xF0\x9D\x91\xB6" => "\x6F", 1291 "\xF0\x9D\x91\xB7" => "\x70", 1292 "\xF0\x9D\x91\xB8" => "\x71", 1293 "\xF0\x9D\x91\xB9" => "\x72", 1294 "\xF0\x9D\x91\xBA" => "\x73", 1295 "\xF0\x9D\x91\xBB" => "\x74", 1296 "\xF0\x9D\x91\xBC" => "\x75", 1297 "\xF0\x9D\x91\xBD" => "\x76", 1298 "\xF0\x9D\x91\xBE" => "\x77", 1299 "\xF0\x9D\x91\xBF" => "\x78", 1300 "\xF0\x9D\x92\x80" => "\x79", 1301 "\xF0\x9D\x92\x81" => "\x7A", 1302 "\xF0\x9D\x92\x9C" => "\x61", 1303 "\xF0\x9D\x92\x9E" => "\x63", 1304 "\xF0\x9D\x92\x9F" => "\x64", 1305 "\xF0\x9D\x92\xA2" => "\x67", 1306 "\xF0\x9D\x92\xA5" => "\x6A", 1307 "\xF0\x9D\x92\xA6" => "\x6B", 1308 "\xF0\x9D\x92\xA9" => "\x6E", 1309 "\xF0\x9D\x92\xAA" => "\x6F", 1310 "\xF0\x9D\x92\xAB" => "\x70", 1311 "\xF0\x9D\x92\xAC" => "\x71", 1312 "\xF0\x9D\x92\xAE" => "\x73", 1313 "\xF0\x9D\x92\xAF" => "\x74", 1314 "\xF0\x9D\x92\xB0" => "\x75", 1315 "\xF0\x9D\x92\xB1" => "\x76", 1316 "\xF0\x9D\x92\xB2" => "\x77", 1317 "\xF0\x9D\x92\xB3" => "\x78", 1318 "\xF0\x9D\x92\xB4" => "\x79", 1319 "\xF0\x9D\x92\xB5" => "\x7A", 1320 "\xF0\x9D\x93\x90" => "\x61", 1321 "\xF0\x9D\x93\x91" => "\x62", 1322 "\xF0\x9D\x93\x92" => "\x63", 1323 "\xF0\x9D\x93\x93" => "\x64", 1324 "\xF0\x9D\x93\x94" => "\x65", 1325 "\xF0\x9D\x93\x95" => "\x66", 1326 "\xF0\x9D\x93\x96" => "\x67", 1327 "\xF0\x9D\x93\x97" => "\x68", 1328 "\xF0\x9D\x93\x98" => "\x69", 1329 "\xF0\x9D\x93\x99" => "\x6A", 1330 "\xF0\x9D\x93\x9A" => "\x6B", 1331 "\xF0\x9D\x93\x9B" => "\x6C", 1332 "\xF0\x9D\x93\x9C" => "\x6D", 1333 "\xF0\x9D\x93\x9D" => "\x6E", 1334 "\xF0\x9D\x93\x9E" => "\x6F", 1335 "\xF0\x9D\x93\x9F" => "\x70", 1336 "\xF0\x9D\x93\xA0" => "\x71", 1337 "\xF0\x9D\x93\xA1" => "\x72", 1338 "\xF0\x9D\x93\xA2" => "\x73", 1339 "\xF0\x9D\x93\xA3" => "\x74", 1340 "\xF0\x9D\x93\xA4" => "\x75", 1341 "\xF0\x9D\x93\xA5" => "\x76", 1342 "\xF0\x9D\x93\xA6" => "\x77", 1343 "\xF0\x9D\x93\xA7" => "\x78", 1344 "\xF0\x9D\x93\xA8" => "\x79", 1345 "\xF0\x9D\x93\xA9" => "\x7A", 1346 "\xF0\x9D\x94\x84" => "\x61", 1347 "\xF0\x9D\x94\x85" => "\x62", 1348 "\xF0\x9D\x94\x87" => "\x64", 1349 "\xF0\x9D\x94\x88" => "\x65", 1350 "\xF0\x9D\x94\x89" => "\x66", 1351 "\xF0\x9D\x94\x8A" => "\x67", 1352 "\xF0\x9D\x94\x8D" => "\x6A", 1353 "\xF0\x9D\x94\x8E" => "\x6B", 1354 "\xF0\x9D\x94\x8F" => "\x6C", 1355 "\xF0\x9D\x94\x90" => "\x6D", 1356 "\xF0\x9D\x94\x91" => "\x6E", 1357 "\xF0\x9D\x94\x92" => "\x6F", 1358 "\xF0\x9D\x94\x93" => "\x70", 1359 "\xF0\x9D\x94\x94" => "\x71", 1360 "\xF0\x9D\x94\x96" => "\x73", 1361 "\xF0\x9D\x94\x97" => "\x74", 1362 "\xF0\x9D\x94\x98" => "\x75", 1363 "\xF0\x9D\x94\x99" => "\x76", 1364 "\xF0\x9D\x94\x9A" => "\x77", 1365 "\xF0\x9D\x94\x9B" => "\x78", 1366 "\xF0\x9D\x94\x9C" => "\x79", 1367 "\xF0\x9D\x94\xB8" => "\x61", 1368 "\xF0\x9D\x94\xB9" => "\x62", 1369 "\xF0\x9D\x94\xBB" => "\x64", 1370 "\xF0\x9D\x94\xBC" => "\x65", 1371 "\xF0\x9D\x94\xBD" => "\x66", 1372 "\xF0\x9D\x94\xBE" => "\x67", 1373 "\xF0\x9D\x95\x80" => "\x69", 1374 "\xF0\x9D\x95\x81" => "\x6A", 1375 "\xF0\x9D\x95\x82" => "\x6B", 1376 "\xF0\x9D\x95\x83" => "\x6C", 1377 "\xF0\x9D\x95\x84" => "\x6D", 1378 "\xF0\x9D\x95\x86" => "\x6F", 1379 "\xF0\x9D\x95\x8A" => "\x73", 1380 "\xF0\x9D\x95\x8B" => "\x74", 1381 "\xF0\x9D\x95\x8C" => "\x75", 1382 "\xF0\x9D\x95\x8D" => "\x76", 1383 "\xF0\x9D\x95\x8E" => "\x77", 1384 "\xF0\x9D\x95\x8F" => "\x78", 1385 "\xF0\x9D\x95\x90" => "\x79", 1386 "\xF0\x9D\x95\xAC" => "\x61", 1387 "\xF0\x9D\x95\xAD" => "\x62", 1388 "\xF0\x9D\x95\xAE" => "\x63", 1389 "\xF0\x9D\x95\xAF" => "\x64", 1390 "\xF0\x9D\x95\xB0" => "\x65", 1391 "\xF0\x9D\x95\xB1" => "\x66", 1392 "\xF0\x9D\x95\xB2" => "\x67", 1393 "\xF0\x9D\x95\xB3" => "\x68", 1394 "\xF0\x9D\x95\xB4" => "\x69", 1395 "\xF0\x9D\x95\xB5" => "\x6A", 1396 "\xF0\x9D\x95\xB6" => "\x6B", 1397 "\xF0\x9D\x95\xB7" => "\x6C", 1398 "\xF0\x9D\x95\xB8" => "\x6D", 1399 "\xF0\x9D\x95\xB9" => "\x6E", 1400 "\xF0\x9D\x95\xBA" => "\x6F", 1401 "\xF0\x9D\x95\xBB" => "\x70", 1402 "\xF0\x9D\x95\xBC" => "\x71", 1403 "\xF0\x9D\x95\xBD" => "\x72", 1404 "\xF0\x9D\x95\xBE" => "\x73", 1405 "\xF0\x9D\x95\xBF" => "\x74", 1406 "\xF0\x9D\x96\x80" => "\x75", 1407 "\xF0\x9D\x96\x81" => "\x76", 1408 "\xF0\x9D\x96\x82" => "\x77", 1409 "\xF0\x9D\x96\x83" => "\x78", 1410 "\xF0\x9D\x96\x84" => "\x79", 1411 "\xF0\x9D\x96\x85" => "\x7A", 1412 "\xF0\x9D\x96\xA0" => "\x61", 1413 "\xF0\x9D\x96\xA1" => "\x62", 1414 "\xF0\x9D\x96\xA2" => "\x63", 1415 "\xF0\x9D\x96\xA3" => "\x64", 1416 "\xF0\x9D\x96\xA4" => "\x65", 1417 "\xF0\x9D\x96\xA5" => "\x66", 1418 "\xF0\x9D\x96\xA6" => "\x67", 1419 "\xF0\x9D\x96\xA7" => "\x68", 1420 "\xF0\x9D\x96\xA8" => "\x69", 1421 "\xF0\x9D\x96\xA9" => "\x6A", 1422 "\xF0\x9D\x96\xAA" => "\x6B", 1423 "\xF0\x9D\x96\xAB" => "\x6C", 1424 "\xF0\x9D\x96\xAC" => "\x6D", 1425 "\xF0\x9D\x96\xAD" => "\x6E", 1426 "\xF0\x9D\x96\xAE" => "\x6F", 1427 "\xF0\x9D\x96\xAF" => "\x70", 1428 "\xF0\x9D\x96\xB0" => "\x71", 1429 "\xF0\x9D\x96\xB1" => "\x72", 1430 "\xF0\x9D\x96\xB2" => "\x73", 1431 "\xF0\x9D\x96\xB3" => "\x74", 1432 "\xF0\x9D\x96\xB4" => "\x75", 1433 "\xF0\x9D\x96\xB5" => "\x76", 1434 "\xF0\x9D\x96\xB6" => "\x77", 1435 "\xF0\x9D\x96\xB7" => "\x78", 1436 "\xF0\x9D\x96\xB8" => "\x79", 1437 "\xF0\x9D\x96\xB9" => "\x7A", 1438 "\xF0\x9D\x97\x94" => "\x61", 1439 "\xF0\x9D\x97\x95" => "\x62", 1440 "\xF0\x9D\x97\x96" => "\x63", 1441 "\xF0\x9D\x97\x97" => "\x64", 1442 "\xF0\x9D\x97\x98" => "\x65", 1443 "\xF0\x9D\x97\x99" => "\x66", 1444 "\xF0\x9D\x97\x9A" => "\x67", 1445 "\xF0\x9D\x97\x9B" => "\x68", 1446 "\xF0\x9D\x97\x9C" => "\x69", 1447 "\xF0\x9D\x97\x9D" => "\x6A", 1448 "\xF0\x9D\x97\x9E" => "\x6B", 1449 "\xF0\x9D\x97\x9F" => "\x6C", 1450 "\xF0\x9D\x97\xA0" => "\x6D", 1451 "\xF0\x9D\x97\xA1" => "\x6E", 1452 "\xF0\x9D\x97\xA2" => "\x6F", 1453 "\xF0\x9D\x97\xA3" => "\x70", 1454 "\xF0\x9D\x97\xA4" => "\x71", 1455 "\xF0\x9D\x97\xA5" => "\x72", 1456 "\xF0\x9D\x97\xA6" => "\x73", 1457 "\xF0\x9D\x97\xA7" => "\x74", 1458 "\xF0\x9D\x97\xA8" => "\x75", 1459 "\xF0\x9D\x97\xA9" => "\x76", 1460 "\xF0\x9D\x97\xAA" => "\x77", 1461 "\xF0\x9D\x97\xAB" => "\x78", 1462 "\xF0\x9D\x97\xAC" => "\x79", 1463 "\xF0\x9D\x97\xAD" => "\x7A", 1464 "\xF0\x9D\x98\x88" => "\x61", 1465 "\xF0\x9D\x98\x89" => "\x62", 1466 "\xF0\x9D\x98\x8A" => "\x63", 1467 "\xF0\x9D\x98\x8B" => "\x64", 1468 "\xF0\x9D\x98\x8C" => "\x65", 1469 "\xF0\x9D\x98\x8D" => "\x66", 1470 "\xF0\x9D\x98\x8E" => "\x67", 1471 "\xF0\x9D\x98\x8F" => "\x68", 1472 "\xF0\x9D\x98\x90" => "\x69", 1473 "\xF0\x9D\x98\x91" => "\x6A", 1474 "\xF0\x9D\x98\x92" => "\x6B", 1475 "\xF0\x9D\x98\x93" => "\x6C", 1476 "\xF0\x9D\x98\x94" => "\x6D", 1477 "\xF0\x9D\x98\x95" => "\x6E", 1478 "\xF0\x9D\x98\x96" => "\x6F", 1479 "\xF0\x9D\x98\x97" => "\x70", 1480 "\xF0\x9D\x98\x98" => "\x71", 1481 "\xF0\x9D\x98\x99" => "\x72", 1482 "\xF0\x9D\x98\x9A" => "\x73", 1483 "\xF0\x9D\x98\x9B" => "\x74", 1484 "\xF0\x9D\x98\x9C" => "\x75", 1485 "\xF0\x9D\x98\x9D" => "\x76", 1486 "\xF0\x9D\x98\x9E" => "\x77", 1487 "\xF0\x9D\x98\x9F" => "\x78", 1488 "\xF0\x9D\x98\xA0" => "\x79", 1489 "\xF0\x9D\x98\xA1" => "\x7A", 1490 "\xF0\x9D\x98\xBC" => "\x61", 1491 "\xF0\x9D\x98\xBD" => "\x62", 1492 "\xF0\x9D\x98\xBE" => "\x63", 1493 "\xF0\x9D\x98\xBF" => "\x64", 1494 "\xF0\x9D\x99\x80" => "\x65", 1495 "\xF0\x9D\x99\x81" => "\x66", 1496 "\xF0\x9D\x99\x82" => "\x67", 1497 "\xF0\x9D\x99\x83" => "\x68", 1498 "\xF0\x9D\x99\x84" => "\x69", 1499 "\xF0\x9D\x99\x85" => "\x6A", 1500 "\xF0\x9D\x99\x86" => "\x6B", 1501 "\xF0\x9D\x99\x87" => "\x6C", 1502 "\xF0\x9D\x99\x88" => "\x6D", 1503 "\xF0\x9D\x99\x89" => "\x6E", 1504 "\xF0\x9D\x99\x8A" => "\x6F", 1505 "\xF0\x9D\x99\x8B" => "\x70", 1506 "\xF0\x9D\x99\x8C" => "\x71", 1507 "\xF0\x9D\x99\x8D" => "\x72", 1508 "\xF0\x9D\x99\x8E" => "\x73", 1509 "\xF0\x9D\x99\x8F" => "\x74", 1510 "\xF0\x9D\x99\x90" => "\x75", 1511 "\xF0\x9D\x99\x91" => "\x76", 1512 "\xF0\x9D\x99\x92" => "\x77", 1513 "\xF0\x9D\x99\x93" => "\x78", 1514 "\xF0\x9D\x99\x94" => "\x79", 1515 "\xF0\x9D\x99\x95" => "\x7A", 1516 "\xF0\x9D\x99\xB0" => "\x61", 1517 "\xF0\x9D\x99\xB1" => "\x62", 1518 "\xF0\x9D\x99\xB2" => "\x63", 1519 "\xF0\x9D\x99\xB3" => "\x64", 1520 "\xF0\x9D\x99\xB4" => "\x65", 1521 "\xF0\x9D\x99\xB5" => "\x66", 1522 "\xF0\x9D\x99\xB6" => "\x67", 1523 "\xF0\x9D\x99\xB7" => "\x68", 1524 "\xF0\x9D\x99\xB8" => "\x69", 1525 "\xF0\x9D\x99\xB9" => "\x6A", 1526 "\xF0\x9D\x99\xBA" => "\x6B", 1527 "\xF0\x9D\x99\xBB" => "\x6C", 1528 "\xF0\x9D\x99\xBC" => "\x6D", 1529 "\xF0\x9D\x99\xBD" => "\x6E", 1530 "\xF0\x9D\x99\xBE" => "\x6F", 1531 "\xF0\x9D\x99\xBF" => "\x70", 1532 "\xF0\x9D\x9A\x80" => "\x71", 1533 "\xF0\x9D\x9A\x81" => "\x72", 1534 "\xF0\x9D\x9A\x82" => "\x73", 1535 "\xF0\x9D\x9A\x83" => "\x74", 1536 "\xF0\x9D\x9A\x84" => "\x75", 1537 "\xF0\x9D\x9A\x85" => "\x76", 1538 "\xF0\x9D\x9A\x86" => "\x77", 1539 "\xF0\x9D\x9A\x87" => "\x78", 1540 "\xF0\x9D\x9A\x88" => "\x79", 1541 "\xF0\x9D\x9A\x89" => "\x7A", 1542 "\xF0\x9D\x9A\xA8" => "\xCE\xB1", 1543 "\xF0\x9D\x9A\xA9" => "\xCE\xB2", 1544 "\xF0\x9D\x9A\xAA" => "\xCE\xB3", 1545 "\xF0\x9D\x9A\xAB" => "\xCE\xB4", 1546 "\xF0\x9D\x9A\xAC" => "\xCE\xB5", 1547 "\xF0\x9D\x9A\xAD" => "\xCE\xB6", 1548 "\xF0\x9D\x9A\xAE" => "\xCE\xB7", 1549 "\xF0\x9D\x9A\xAF" => "\xCE\xB8", 1550 "\xF0\x9D\x9A\xB0" => "\xCE\xB9", 1551 "\xF0\x9D\x9A\xB1" => "\xCE\xBA", 1552 "\xF0\x9D\x9A\xB2" => "\xCE\xBB", 1553 "\xF0\x9D\x9A\xB3" => "\xCE\xBC", 1554 "\xF0\x9D\x9A\xB4" => "\xCE\xBD", 1555 "\xF0\x9D\x9A\xB5" => "\xCE\xBE", 1556 "\xF0\x9D\x9A\xB6" => "\xCE\xBF", 1557 "\xF0\x9D\x9A\xB7" => "\xCF\x80", 1558 "\xF0\x9D\x9A\xB8" => "\xCF\x81", 1559 "\xF0\x9D\x9A\xB9" => "\xCE\xB8", 1560 "\xF0\x9D\x9A\xBA" => "\xCF\x83", 1561 "\xF0\x9D\x9A\xBB" => "\xCF\x84", 1562 "\xF0\x9D\x9A\xBC" => "\xCF\x85", 1563 "\xF0\x9D\x9A\xBD" => "\xCF\x86", 1564 "\xF0\x9D\x9A\xBE" => "\xCF\x87", 1565 "\xF0\x9D\x9A\xBF" => "\xCF\x88", 1566 "\xF0\x9D\x9B\x80" => "\xCF\x89", 1567 "\xF0\x9D\x9B\x93" => "\xCF\x83", 1568 "\xF0\x9D\x9B\xA2" => "\xCE\xB1", 1569 "\xF0\x9D\x9B\xA3" => "\xCE\xB2", 1570 "\xF0\x9D\x9B\xA4" => "\xCE\xB3", 1571 "\xF0\x9D\x9B\xA5" => "\xCE\xB4", 1572 "\xF0\x9D\x9B\xA6" => "\xCE\xB5", 1573 "\xF0\x9D\x9B\xA7" => "\xCE\xB6", 1574 "\xF0\x9D\x9B\xA8" => "\xCE\xB7", 1575 "\xF0\x9D\x9B\xA9" => "\xCE\xB8", 1576 "\xF0\x9D\x9B\xAA" => "\xCE\xB9", 1577 "\xF0\x9D\x9B\xAB" => "\xCE\xBA", 1578 "\xF0\x9D\x9B\xAC" => "\xCE\xBB", 1579 "\xF0\x9D\x9B\xAD" => "\xCE\xBC", 1580 "\xF0\x9D\x9B\xAE" => "\xCE\xBD", 1581 "\xF0\x9D\x9B\xAF" => "\xCE\xBE", 1582 "\xF0\x9D\x9B\xB0" => "\xCE\xBF", 1583 "\xF0\x9D\x9B\xB1" => "\xCF\x80", 1584 "\xF0\x9D\x9B\xB2" => "\xCF\x81", 1585 "\xF0\x9D\x9B\xB3" => "\xCE\xB8", 1586 "\xF0\x9D\x9B\xB4" => "\xCF\x83", 1587 "\xF0\x9D\x9B\xB5" => "\xCF\x84", 1588 "\xF0\x9D\x9B\xB6" => "\xCF\x85", 1589 "\xF0\x9D\x9B\xB7" => "\xCF\x86", 1590 "\xF0\x9D\x9B\xB8" => "\xCF\x87", 1591 "\xF0\x9D\x9B\xB9" => "\xCF\x88", 1592 "\xF0\x9D\x9B\xBA" => "\xCF\x89", 1593 "\xF0\x9D\x9C\x8D" => "\xCF\x83", 1594 "\xF0\x9D\x9C\x9C" => "\xCE\xB1", 1595 "\xF0\x9D\x9C\x9D" => "\xCE\xB2", 1596 "\xF0\x9D\x9C\x9E" => "\xCE\xB3", 1597 "\xF0\x9D\x9C\x9F" => "\xCE\xB4", 1598 "\xF0\x9D\x9C\xA0" => "\xCE\xB5", 1599 "\xF0\x9D\x9C\xA1" => "\xCE\xB6", 1600 "\xF0\x9D\x9C\xA2" => "\xCE\xB7", 1601 "\xF0\x9D\x9C\xA3" => "\xCE\xB8", 1602 "\xF0\x9D\x9C\xA4" => "\xCE\xB9", 1603 "\xF0\x9D\x9C\xA5" => "\xCE\xBA", 1604 "\xF0\x9D\x9C\xA6" => "\xCE\xBB", 1605 "\xF0\x9D\x9C\xA7" => "\xCE\xBC", 1606 "\xF0\x9D\x9C\xA8" => "\xCE\xBD", 1607 "\xF0\x9D\x9C\xA9" => "\xCE\xBE", 1608 "\xF0\x9D\x9C\xAA" => "\xCE\xBF", 1609 "\xF0\x9D\x9C\xAB" => "\xCF\x80", 1610 "\xF0\x9D\x9C\xAC" => "\xCF\x81", 1611 "\xF0\x9D\x9C\xAD" => "\xCE\xB8", 1612 "\xF0\x9D\x9C\xAE" => "\xCF\x83", 1613 "\xF0\x9D\x9C\xAF" => "\xCF\x84", 1614 "\xF0\x9D\x9C\xB0" => "\xCF\x85", 1615 "\xF0\x9D\x9C\xB1" => "\xCF\x86", 1616 "\xF0\x9D\x9C\xB2" => "\xCF\x87", 1617 "\xF0\x9D\x9C\xB3" => "\xCF\x88", 1618 "\xF0\x9D\x9C\xB4" => "\xCF\x89", 1619 "\xF0\x9D\x9D\x87" => "\xCF\x83", 1620 "\xF0\x9D\x9D\x96" => "\xCE\xB1", 1621 "\xF0\x9D\x9D\x97" => "\xCE\xB2", 1622 "\xF0\x9D\x9D\x98" => "\xCE\xB3", 1623 "\xF0\x9D\x9D\x99" => "\xCE\xB4", 1624 "\xF0\x9D\x9D\x9A" => "\xCE\xB5", 1625 "\xF0\x9D\x9D\x9B" => "\xCE\xB6", 1626 "\xF0\x9D\x9D\x9C" => "\xCE\xB7", 1627 "\xF0\x9D\x9D\x9D" => "\xCE\xB8", 1628 "\xF0\x9D\x9D\x9E" => "\xCE\xB9", 1629 "\xF0\x9D\x9D\x9F" => "\xCE\xBA", 1630 "\xF0\x9D\x9D\xA0" => "\xCE\xBB", 1631 "\xF0\x9D\x9D\xA1" => "\xCE\xBC", 1632 "\xF0\x9D\x9D\xA2" => "\xCE\xBD", 1633 "\xF0\x9D\x9D\xA3" => "\xCE\xBE", 1634 "\xF0\x9D\x9D\xA4" => "\xCE\xBF", 1635 "\xF0\x9D\x9D\xA5" => "\xCF\x80", 1636 "\xF0\x9D\x9D\xA6" => "\xCF\x81", 1637 "\xF0\x9D\x9D\xA7" => "\xCE\xB8", 1638 "\xF0\x9D\x9D\xA8" => "\xCF\x83", 1639 "\xF0\x9D\x9D\xA9" => "\xCF\x84", 1640 "\xF0\x9D\x9D\xAA" => "\xCF\x85", 1641 "\xF0\x9D\x9D\xAB" => "\xCF\x86", 1642 "\xF0\x9D\x9D\xAC" => "\xCF\x87", 1643 "\xF0\x9D\x9D\xAD" => "\xCF\x88", 1644 "\xF0\x9D\x9D\xAE" => "\xCF\x89", 1645 "\xF0\x9D\x9E\x81" => "\xCF\x83", 1646 "\xF0\x9D\x9E\x90" => "\xCE\xB1", 1647 "\xF0\x9D\x9E\x91" => "\xCE\xB2", 1648 "\xF0\x9D\x9E\x92" => "\xCE\xB3", 1649 "\xF0\x9D\x9E\x93" => "\xCE\xB4", 1650 "\xF0\x9D\x9E\x94" => "\xCE\xB5", 1651 "\xF0\x9D\x9E\x95" => "\xCE\xB6", 1652 "\xF0\x9D\x9E\x96" => "\xCE\xB7", 1653 "\xF0\x9D\x9E\x97" => "\xCE\xB8", 1654 "\xF0\x9D\x9E\x98" => "\xCE\xB9", 1655 "\xF0\x9D\x9E\x99" => "\xCE\xBA", 1656 "\xF0\x9D\x9E\x9A" => "\xCE\xBB", 1657 "\xF0\x9D\x9E\x9B" => "\xCE\xBC", 1658 "\xF0\x9D\x9E\x9C" => "\xCE\xBD", 1659 "\xF0\x9D\x9E\x9D" => "\xCE\xBE", 1660 "\xF0\x9D\x9E\x9E" => "\xCE\xBF", 1661 "\xF0\x9D\x9E\x9F" => "\xCF\x80", 1662 "\xF0\x9D\x9E\xA0" => "\xCF\x81", 1663 "\xF0\x9D\x9E\xA1" => "\xCE\xB8", 1664 "\xF0\x9D\x9E\xA2" => "\xCF\x83", 1665 "\xF0\x9D\x9E\xA3" => "\xCF\x84", 1666 "\xF0\x9D\x9E\xA4" => "\xCF\x85", 1667 "\xF0\x9D\x9E\xA5" => "\xCF\x86", 1668 "\xF0\x9D\x9E\xA6" => "\xCF\x87", 1669 "\xF0\x9D\x9E\xA7" => "\xCF\x88", 1670 "\xF0\x9D\x9E\xA8" => "\xCF\x89", 1671 "\xF0\x9D\x9E\xBB" => "\xCF\x83", 1672 "\xF0\x9D\x9F\x8A" => "\xCF\x9D", 1673 ); 1674 global $phpbb_root_path, $phpEx; 1675 1676 // do the case fold 1677 $text = utf8_case_fold($text, $option); 1678 1679 if (!class_exists('utf_normalizer')) 1680 { 1681 global $phpbb_root_path, $phpEx; 1682 include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx); 1683 } 1684 1685 // convert to NFKC 1686 utf_normalizer::nfkc($text); 1687 1688 // FC_NFKC_Closure, http://www.unicode.org/Public/5.0.0/ucd/DerivedNormalizationProps.txt 1689 $text = strtr($text, $fc_nfkc_closure); 1690 1691 return $text; 1692} 1693 1694/** 1695* Assume the input is NFC: 1696* Takes the input and does a "special" case fold. It does minor normalization as well. 1697* 1698* @param string $text text to be case folded 1699* @param string $option determines how we will fold the cases 1700* @return string case folded text 1701*/ 1702function utf8_case_fold_nfc($text, $option = 'full') 1703{ 1704 static $uniarray = array(); 1705 static $ypogegrammeni = array( 1706 "\xCD\xBA" => "\x20\xCD\x85", 1707 "\xE1\xBE\x80" => "\xE1\xBC\x80\xCD\x85", 1708 "\xE1\xBE\x81" => "\xE1\xBC\x81\xCD\x85", 1709 "\xE1\xBE\x82" => "\xE1\xBC\x82\xCD\x85", 1710 "\xE1\xBE\x83" => "\xE1\xBC\x83\xCD\x85", 1711 "\xE1\xBE\x84" => "\xE1\xBC\x84\xCD\x85", 1712 "\xE1\xBE\x85" => "\xE1\xBC\x85\xCD\x85", 1713 "\xE1\xBE\x86" => "\xE1\xBC\x86\xCD\x85", 1714 "\xE1\xBE\x87" => "\xE1\xBC\x87\xCD\x85", 1715 "\xE1\xBE\x88" => "\xE1\xBC\x88\xCD\x85", 1716 "\xE1\xBE\x89" => "\xE1\xBC\x89\xCD\x85", 1717 "\xE1\xBE\x8A" => "\xE1\xBC\x8A\xCD\x85", 1718 "\xE1\xBE\x8B" => "\xE1\xBC\x8B\xCD\x85", 1719 "\xE1\xBE\x8C" => "\xE1\xBC\x8C\xCD\x85", 1720 "\xE1\xBE\x8D" => "\xE1\xBC\x8D\xCD\x85", 1721 "\xE1\xBE\x8E" => "\xE1\xBC\x8E\xCD\x85", 1722 "\xE1\xBE\x8F" => "\xE1\xBC\x8F\xCD\x85", 1723 "\xE1\xBE\x90" => "\xE1\xBC\xA0\xCD\x85", 1724 "\xE1\xBE\x91" => "\xE1\xBC\xA1\xCD\x85", 1725 "\xE1\xBE\x92" => "\xE1\xBC\xA2\xCD\x85", 1726 "\xE1\xBE\x93" => "\xE1\xBC\xA3\xCD\x85", 1727 "\xE1\xBE\x94" => "\xE1\xBC\xA4\xCD\x85", 1728 "\xE1\xBE\x95" => "\xE1\xBC\xA5\xCD\x85", 1729 "\xE1\xBE\x96" => "\xE1\xBC\xA6\xCD\x85", 1730 "\xE1\xBE\x97" => "\xE1\xBC\xA7\xCD\x85", 1731 "\xE1\xBE\x98" => "\xE1\xBC\xA8\xCD\x85", 1732 "\xE1\xBE\x99" => "\xE1\xBC\xA9\xCD\x85", 1733 "\xE1\xBE\x9A" => "\xE1\xBC\xAA\xCD\x85", 1734 "\xE1\xBE\x9B" => "\xE1\xBC\xAB\xCD\x85", 1735 "\xE1\xBE\x9C" => "\xE1\xBC\xAC\xCD\x85", 1736 "\xE1\xBE\x9D" => "\xE1\xBC\xAD\xCD\x85", 1737 "\xE1\xBE\x9E" => "\xE1\xBC\xAE\xCD\x85", 1738 "\xE1\xBE\x9F" => "\xE1\xBC\xAF\xCD\x85", 1739 "\xE1\xBE\xA0" => "\xE1\xBD\xA0\xCD\x85", 1740 "\xE1\xBE\xA1" => "\xE1\xBD\xA1\xCD\x85", 1741 "\xE1\xBE\xA2" => "\xE1\xBD\xA2\xCD\x85", 1742 "\xE1\xBE\xA3" => "\xE1\xBD\xA3\xCD\x85", 1743 "\xE1\xBE\xA4" => "\xE1\xBD\xA4\xCD\x85", 1744 "\xE1\xBE\xA5" => "\xE1\xBD\xA5\xCD\x85", 1745 "\xE1\xBE\xA6" => "\xE1\xBD\xA6\xCD\x85", 1746 "\xE1\xBE\xA7" => "\xE1\xBD\xA7\xCD\x85", 1747 "\xE1\xBE\xA8" => "\xE1\xBD\xA8\xCD\x85", 1748 "\xE1\xBE\xA9" => "\xE1\xBD\xA9\xCD\x85", 1749 "\xE1\xBE\xAA" => "\xE1\xBD\xAA\xCD\x85", 1750 "\xE1\xBE\xAB" => "\xE1\xBD\xAB\xCD\x85", 1751 "\xE1\xBE\xAC" => "\xE1\xBD\xAC\xCD\x85", 1752 "\xE1\xBE\xAD" => "\xE1\xBD\xAD\xCD\x85", 1753 "\xE1\xBE\xAE" => "\xE1\xBD\xAE\xCD\x85", 1754 "\xE1\xBE\xAF" => "\xE1\xBD\xAF\xCD\x85", 1755 "\xE1\xBE\xB2" => "\xE1\xBD\xB0\xCD\x85", 1756 "\xE1\xBE\xB3" => "\xCE\xB1\xCD\x85", 1757 "\xE1\xBE\xB4" => "\xCE\xAC\xCD\x85", 1758 "\xE1\xBE\xB7" => "\xE1\xBE\xB6\xCD\x85", 1759 "\xE1\xBE\xBC" => "\xCE\x91\xCD\x85", 1760 "\xE1\xBF\x82" => "\xE1\xBD\xB4\xCD\x85", 1761 "\xE1\xBF\x83" => "\xCE\xB7\xCD\x85", 1762 "\xE1\xBF\x84" => "\xCE\xAE\xCD\x85", 1763 "\xE1\xBF\x87" => "\xE1\xBF\x86\xCD\x85", 1764 "\xE1\xBF\x8C" => "\xCE\x97\xCD\x85", 1765 "\xE1\xBF\xB2" => "\xE1\xBD\xBC\xCD\x85", 1766 "\xE1\xBF\xB3" => "\xCF\x89\xCD\x85", 1767 "\xE1\xBF\xB4" => "\xCF\x8E\xCD\x85", 1768 "\xE1\xBF\xB7" => "\xE1\xBF\xB6\xCD\x85", 1769 "\xE1\xBF\xBC" => "\xCE\xA9\xCD\x85", 1770 ); 1771 global $phpbb_root_path, $phpEx; 1772 1773 // perform a small trick, avoid further normalization on composed points that contain U+0345 in their decomposition 1774 $text = strtr($text, $ypogegrammeni); 1775 1776 // do the case fold 1777 $text = utf8_case_fold($text, $option); 1778 1779 return $text; 1780} 1781 1782/** 1783* A wrapper function for the normalizer which takes care of including the class if required and modifies the passed strings 1784* to be in NFC (Normalization Form Composition). 1785* 1786* @param mixed $strings a string or an array of strings to normalize 1787* @return mixed the normalized content, preserving array keys if array given. 1788*/ 1789function utf8_normalize_nfc($strings) 1790{ 1791 if (empty($strings)) 1792 { 1793 return $strings; 1794 } 1795 1796 if (!class_exists('utf_normalizer')) 1797 { 1798 global $phpbb_root_path, $phpEx; 1799 include($phpbb_root_path . 'includes/utf/utf_normalizer.' . $phpEx); 1800 } 1801 1802 if (!is_array($strings)) 1803 { 1804 utf_normalizer::nfc($strings); 1805 } 1806 else if (is_array($strings)) 1807 { 1808 foreach ($strings as $key => $string) 1809 { 1810 if (is_array($string)) 1811 { 1812 foreach ($string as $_key => $_string) 1813 { 1814 utf_normalizer::nfc($strings[$key][$_key]); 1815 } 1816 } 1817 else 1818 { 1819 utf_normalizer::nfc($strings[$key]); 1820 } 1821 } 1822 } 1823 1824 return $strings; 1825} 1826 1827/** 1828* This function is used to generate a "clean" version of a string. 1829* Clean means that it is a case insensitive form (case folding) and that it is normalized (NFC). 1830* Additionally a homographs of one character are transformed into one specific character (preferably ASCII 1831* if it is an ASCII character). 1832* 1833* Please be aware that if you change something within this function or within 1834* functions used here you need to rebuild/update the username_clean column in the users table. And all other 1835* columns that store a clean string otherwise you will break this functionality. 1836* 1837* @param string $text An unclean string, mabye user input (has to be valid UTF-8!) 1838* @return string Cleaned up version of the input string 1839*/ 1840function utf8_clean_string($text) 1841{ 1842 global $phpbb_root_path, $phpEx; 1843 1844 static $homographs = array(); 1845 if (empty($homographs)) 1846 { 1847 $homographs = include($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx); 1848 } 1849 1850 $text = utf8_case_fold_nfkc($text); 1851 $text = strtr($text, $homographs); 1852 // Other control characters 1853 $text = preg_replace('#(?:[\x00-\x1F\x7F]+|(?:\xC2[\x80-\x9F])+)#', '', $text); 1854 1855 // we need to reduce multiple spaces to a single one 1856 $text = preg_replace('# {2,}#', ' ', $text); 1857 1858 // we can use trim here as all the other space characters should have been turned 1859 // into normal ASCII spaces by now 1860 return trim($text); 1861} 1862 1863/** 1864* A wrapper for htmlspecialchars($value, ENT_COMPAT, 'UTF-8') 1865*/ 1866function utf8_htmlspecialchars($value) 1867{ 1868 return htmlspecialchars($value, ENT_COMPAT, 'UTF-8'); 1869} 1870 1871/** 1872* Trying to convert returned system message to utf8 1873* 1874* PHP assumes such messages are ISO-8859-1 so we'll do that too 1875* and if it breaks messages we'll blame it on them ;-) 1876*/ 1877function utf8_convert_message($message) 1878{ 1879 // First of all check if conversion is neded at all, as there is no point 1880 // in converting ASCII messages from ISO-8859-1 to UTF-8 1881 if (!preg_match('/[\x80-\xFF]/', $message)) 1882 { 1883 return utf8_htmlspecialchars($message); 1884 } 1885 1886 // else we need to convert some part of the message 1887 return utf8_htmlspecialchars(utf8_recode($message, 'ISO-8859-1')); 1888} 1889 1890/** 1891* UTF8-compatible wordwrap replacement 1892* 1893* @param string $string The input string 1894* @param int $width The column width. Defaults to 75. 1895* @param string $break The line is broken using the optional break parameter. Defaults to '\n'. 1896* @param bool $cut If the cut is set to TRUE, the string is always wrapped at the specified width. So if you have a word that is larger than the given width, it is broken apart. 1897* 1898* @return string the given string wrapped at the specified column. 1899* 1900*/ 1901function utf8_wordwrap($string, $width = 75, $break = "\n", $cut = false) 1902{ 1903 // We first need to explode on $break, not destroying existing (intended) breaks 1904 $lines = explode($break, $string); 1905 $new_lines = array(0 => ''); 1906 $index = 0; 1907 1908 foreach ($lines as $line) 1909 { 1910 $words = explode(' ', $line); 1911 1912 for ($i = 0, $size = sizeof($words); $i < $size; $i++) 1913 { 1914 $word = $words[$i]; 1915 1916 // If cut is true we need to cut the word if it is > width chars 1917 if ($cut && utf8_strlen($word) > $width) 1918 { 1919 $words[$i] = utf8_substr($word, $width); 1920 $word = utf8_substr($word, 0, $width); 1921 $i--; 1922 } 1923 1924 if (utf8_strlen($new_lines[$index] . $word) > $width) 1925 { 1926 $new_lines[$index] = substr($new_lines[$index], 0, -1); 1927 $index++; 1928 $new_lines[$index] = ''; 1929 } 1930 1931 $new_lines[$index] .= $word . ' '; 1932 } 1933 1934 $new_lines[$index] = substr($new_lines[$index], 0, -1); 1935 $index++; 1936 $new_lines[$index] = ''; 1937 } 1938 1939 unset($new_lines[$index]); 1940 return implode($break, $new_lines); 1941} 1942 1943/** 1944* UTF8-safe basename() function 1945* 1946* basename() has some limitations and is dependent on the locale setting 1947* according to the PHP manual. Therefore we provide our own locale independant 1948* basename function. 1949* 1950* @param string $filename The filename basename() should be applied to 1951* @return string The basenamed filename 1952*/ 1953function utf8_basename($filename) 1954{ 1955 // We always check for forward slash AND backward slash 1956 // because they could be mixed or "sneaked" in. ;) 1957 // You know, never trust user input... 1958 if (strpos($filename, '/') !== false) 1959 { 1960 $filename = utf8_substr($filename, utf8_strrpos($filename, '/') + 1); 1961 } 1962 1963 if (strpos($filename, '\\') !== false) 1964 { 1965 $filename = utf8_substr($filename, utf8_strrpos($filename, '\\') + 1); 1966 } 1967 1968 return $filename; 1969} 1970 1971/** 1972* UTF8-safe str_replace() function 1973* 1974* @param string $search The value to search for 1975* @param string $replace The replacement string 1976* @param string $subject The target string 1977* @return string The resultant string 1978*/ 1979function utf8_str_replace($search, $replace, $subject) 1980{ 1981 if (!is_array($search)) 1982 { 1983 $search = array($search); 1984 if (is_array($replace)) 1985 { 1986 $replace = (string) $replace; 1987 trigger_error('Array to string conversion', E_USER_NOTICE); 1988 } 1989 } 1990 1991 $length = sizeof($search); 1992 1993 if (!is_array($replace)) 1994 { 1995 $replace = array_fill(0, $length, $replace); 1996 } 1997 else 1998 { 1999 $replace = array_pad($replace, $length, ''); 2000 } 2001 2002 for ($i = 0; $i < $length; $i++) 2003 { 2004 $search_length = utf8_strlen($search[$i]); 2005 $replace_length = utf8_strlen($replace[$i]); 2006 2007 $offset = 0; 2008 while (($start = utf8_strpos($subject, $search[$i], $offset)) !== false) 2009 { 2010 $subject = utf8_substr($subject, 0, $start) . $replace[$i] . utf8_substr($subject, $start + $search_length); 2011 $offset = $start + $replace_length; 2012 } 2013 } 2014 2015 return $subject; 2016} 2017 2018?>