Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
73.88% |
645 / 873 |
|
37.04% |
10 / 27 |
CRAP | n/a |
0 / 0 |
|
| utf8_strrpos | |
60.00% |
3 / 5 |
|
0.00% |
0 / 1 |
3.58 | |||
| utf8_strpos | |
0.00% |
0 / 3 |
|
0.00% |
0 / 1 |
6 | |||
| utf8_stripos | |
66.67% |
2 / 3 |
|
0.00% |
0 / 1 |
2.15 | |||
| utf8_strtolower | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_strtoupper | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_substr | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
2 | |||
| utf8_strlen | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_str_split | |
85.71% |
6 / 7 |
|
0.00% |
0 / 1 |
4.05 | |||
| utf8_strspn | |
0.00% |
0 / 6 |
|
0.00% |
0 / 1 |
20 | |||
| utf8_ucfirst | |
0.00% |
0 / 7 |
|
0.00% |
0 / 1 |
20 | |||
| utf8_recode | |
0.00% |
0 / 102 |
|
0.00% |
0 / 1 |
4290 | |||
| utf8_encode_ucr | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| utf8_encode_ncr | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| utf8_encode_ncr_callback | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| utf8_ord | |
0.00% |
0 / 10 |
|
0.00% |
0 / 1 |
42 | |||
| utf8_chr | |
0.00% |
0 / 7 |
|
0.00% |
0 / 1 |
20 | |||
| utf8_decode_ncr | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_decode_ncr_callback | |
0.00% |
0 / 2 |
|
0.00% |
0 / 1 |
6 | |||
| utf8_case_fold | |
84.62% |
11 / 13 |
|
0.00% |
0 / 1 |
7.18 | |||
| utf8_case_fold_nfkc | |
100.00% |
571 / 571 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_case_fold_nfc | |
0.00% |
0 / 70 |
|
0.00% |
0 / 1 |
2 | |||
| utf8_normalize_nfc | |
31.25% |
5 / 16 |
|
0.00% |
0 / 1 |
35.32 | |||
| utf8_clean_string | |
100.00% |
9 / 9 |
|
100.00% |
1 / 1 |
2 | |||
| utf8_htmlspecialchars | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| utf8_convert_message | |
66.67% |
2 / 3 |
|
0.00% |
0 / 1 |
2.15 | |||
| utf8_wordwrap | |
100.00% |
21 / 21 |
|
100.00% |
1 / 1 |
6 | |||
| utf8_basename | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
4 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * |
| 4 | * This file is part of the phpBB Forum Software package. |
| 5 | * |
| 6 | * @copyright (c) phpBB Limited <https://www.phpbb.com> |
| 7 | * @license GNU General Public License, version 2 (GPL-2.0) |
| 8 | * |
| 9 | * For full copyright and license information, please see |
| 10 | * the docs/CREDITS.txt file. |
| 11 | * |
| 12 | */ |
| 13 | |
| 14 | /** |
| 15 | */ |
| 16 | if (!defined('IN_PHPBB')) |
| 17 | { |
| 18 | exit; |
| 19 | } |
| 20 | |
| 21 | // Enforce ASCII only string handling |
| 22 | setlocale(LC_CTYPE, 'C'); |
| 23 | |
| 24 | /** |
| 25 | * UTF-8 portability layer is provided by |
| 26 | * symfony/polyfill-mbstring, symfony/polyfill-intl-normalizer, symfony/polyfill-php72 |
| 27 | */ |
| 28 | |
| 29 | /** |
| 30 | * UTF-8 tools |
| 31 | * |
| 32 | * Whenever possible, these functions will try to use PHP's built-in functions or |
| 33 | * extensions, otherwise they will default to custom routines. |
| 34 | * |
| 35 | */ |
| 36 | |
| 37 | /** |
| 38 | * UTF-8 aware alternative to strrpos |
| 39 | * @ignore |
| 40 | */ |
| 41 | function utf8_strrpos($str, $needle, $offset = null) |
| 42 | { |
| 43 | // Emulate behaviour of strrpos rather than raising warning |
| 44 | if (empty($str)) |
| 45 | { |
| 46 | return false; |
| 47 | } |
| 48 | |
| 49 | if (is_null($offset)) |
| 50 | { |
| 51 | return mb_strrpos($str, $needle); |
| 52 | } |
| 53 | else |
| 54 | { |
| 55 | return mb_strrpos($str, $needle, $offset); |
| 56 | } |
| 57 | } |
| 58 | |
| 59 | /** |
| 60 | * UTF-8 aware alternative to strpos |
| 61 | * @ignore |
| 62 | */ |
| 63 | function utf8_strpos($str, $needle, $offset = null) |
| 64 | { |
| 65 | if (is_null($offset)) |
| 66 | { |
| 67 | return mb_strpos($str, $needle); |
| 68 | } |
| 69 | else |
| 70 | { |
| 71 | return mb_strpos($str, $needle, $offset); |
| 72 | } |
| 73 | } |
| 74 | |
| 75 | /** |
| 76 | * UTF-8 aware alternative to stripos |
| 77 | * @ignore |
| 78 | */ |
| 79 | function utf8_stripos($str, $needle, $offset = null) |
| 80 | { |
| 81 | if (is_null($offset)) |
| 82 | { |
| 83 | return mb_stripos($str, $needle); |
| 84 | } |
| 85 | else |
| 86 | { |
| 87 | return mb_stripos($str, $needle, $offset); |
| 88 | } |
| 89 | } |
| 90 | |
| 91 | /** |
| 92 | * UTF-8 aware alternative to strtolower |
| 93 | * @ignore |
| 94 | */ |
| 95 | function utf8_strtolower($str) |
| 96 | { |
| 97 | return mb_strtolower($str); |
| 98 | } |
| 99 | |
| 100 | /** |
| 101 | * UTF-8 aware alternative to strtoupper |
| 102 | * @ignore |
| 103 | */ |
| 104 | function utf8_strtoupper($str) |
| 105 | { |
| 106 | return mb_strtoupper($str); |
| 107 | } |
| 108 | |
| 109 | /** |
| 110 | * UTF-8 aware alternative to substr |
| 111 | * @ignore |
| 112 | */ |
| 113 | function utf8_substr($str, $offset, $length = null) |
| 114 | { |
| 115 | if (is_null($length)) |
| 116 | { |
| 117 | return mb_substr($str, $offset); |
| 118 | } |
| 119 | else |
| 120 | { |
| 121 | return mb_substr($str, $offset, $length); |
| 122 | } |
| 123 | } |
| 124 | |
| 125 | /** |
| 126 | * Return the length (in characters) of a UTF-8 string |
| 127 | * @ignore |
| 128 | */ |
| 129 | function utf8_strlen($text) |
| 130 | { |
| 131 | return mb_strlen($text, 'utf-8'); |
| 132 | } |
| 133 | |
| 134 | /** |
| 135 | * UTF-8 aware alternative to str_split |
| 136 | * Convert a string to an array |
| 137 | * |
| 138 | * @author Harry Fuecks |
| 139 | * @param string $str UTF-8 encoded |
| 140 | * @param int $split_len number to characters to split string by |
| 141 | * @return array characters in string reverses |
| 142 | */ |
| 143 | function utf8_str_split($str, $split_len = 1) |
| 144 | { |
| 145 | if (!is_int($split_len) || $split_len < 1) |
| 146 | { |
| 147 | return false; |
| 148 | } |
| 149 | |
| 150 | $len = utf8_strlen($str); |
| 151 | if ($len <= $split_len) |
| 152 | { |
| 153 | return array($str); |
| 154 | } |
| 155 | |
| 156 | preg_match_all('/.{' . $split_len . '}|[^\x00]{1,' . $split_len . '}$/us', $str, $ar); |
| 157 | return $ar[0]; |
| 158 | } |
| 159 | |
| 160 | /** |
| 161 | * UTF-8 aware alternative to strspn |
| 162 | * Find length of initial segment matching the mask |
| 163 | * |
| 164 | * @author Harry Fuecks |
| 165 | */ |
| 166 | function utf8_strspn($str, $mask, $start = null, $length = null) |
| 167 | { |
| 168 | if ($start !== null || $length !== null) |
| 169 | { |
| 170 | $str = utf8_substr($str, $start, $length); |
| 171 | } |
| 172 | |
| 173 | preg_match('/^[' . $mask . ']+/u', $str, $matches); |
| 174 | |
| 175 | if (isset($matches[0])) |
| 176 | { |
| 177 | return utf8_strlen($matches[0]); |
| 178 | } |
| 179 | |
| 180 | return 0; |
| 181 | } |
| 182 | |
| 183 | /** |
| 184 | * UTF-8 aware alternative to ucfirst |
| 185 | * Make a string's first character uppercase |
| 186 | * |
| 187 | * @author Harry Fuecks |
| 188 | * @param string $str |
| 189 | * @return string with first character as upper case (if applicable) |
| 190 | */ |
| 191 | function utf8_ucfirst($str) |
| 192 | { |
| 193 | switch (utf8_strlen($str)) |
| 194 | { |
| 195 | case 0: |
| 196 | return ''; |
| 197 | break; |
| 198 | |
| 199 | case 1: |
| 200 | return utf8_strtoupper($str); |
| 201 | break; |
| 202 | |
| 203 | default: |
| 204 | preg_match('/^(.{1})(.*)$/us', $str, $matches); |
| 205 | return utf8_strtoupper($matches[1]) . $matches[2]; |
| 206 | break; |
| 207 | } |
| 208 | } |
| 209 | |
| 210 | /** |
| 211 | * Recode a string to UTF-8 |
| 212 | * |
| 213 | * If the encoding is not supported, the string is returned as-is |
| 214 | * |
| 215 | * @param string $string Original string |
| 216 | * @param string $encoding Original encoding (lowered) |
| 217 | * @return string The string, encoded in UTF-8 |
| 218 | */ |
| 219 | function utf8_recode($string, $encoding) |
| 220 | { |
| 221 | $encoding = strtolower($encoding); |
| 222 | |
| 223 | if ($encoding == 'utf-8' || !is_string($string) || empty($string)) |
| 224 | { |
| 225 | return $string; |
| 226 | } |
| 227 | |
| 228 | // we force iso-8859-1 to be cp1252 |
| 229 | if ($encoding == 'iso-8859-1') |
| 230 | { |
| 231 | $encoding = 'cp1252'; |
| 232 | } |
| 233 | // convert iso-8859-8-i to iso-8859-8 |
| 234 | else if ($encoding == 'iso-8859-8-i') |
| 235 | { |
| 236 | $encoding = 'iso-8859-8'; |
| 237 | $string = hebrev($string); |
| 238 | } |
| 239 | |
| 240 | // First, try iconv() |
| 241 | if (function_exists('iconv')) |
| 242 | { |
| 243 | $ret = @iconv($encoding, 'utf-8', $string); |
| 244 | |
| 245 | if (!empty($ret)) |
| 246 | { |
| 247 | return $ret; |
| 248 | } |
| 249 | } |
| 250 | |
| 251 | // Try the mb_string extension |
| 252 | if (function_exists('mb_convert_encoding')) |
| 253 | { |
| 254 | // mbstring is nasty on PHP4, we must make *sure* that we send a good encoding |
| 255 | switch ($encoding) |
| 256 | { |
| 257 | case 'iso-8859-1': |
| 258 | case 'iso-8859-2': |
| 259 | case 'iso-8859-4': |
| 260 | case 'iso-8859-7': |
| 261 | case 'iso-8859-9': |
| 262 | case 'iso-8859-15': |
| 263 | case 'windows-1251': |
| 264 | case 'windows-1252': |
| 265 | case 'cp1252': |
| 266 | case 'shift_jis': |
| 267 | case 'euc-kr': |
| 268 | case 'big5': |
| 269 | case 'gb2312': |
| 270 | $ret = @mb_convert_encoding($string, 'utf-8', $encoding); |
| 271 | |
| 272 | if (!empty($ret)) |
| 273 | { |
| 274 | return $ret; |
| 275 | } |
| 276 | } |
| 277 | } |
| 278 | |
| 279 | // Try the recode extension |
| 280 | if (function_exists('recode_string')) |
| 281 | { |
| 282 | $ret = @recode_string($encoding . '..utf-8', $string); |
| 283 | |
| 284 | if (!empty($ret)) |
| 285 | { |
| 286 | return $ret; |
| 287 | } |
| 288 | } |
| 289 | |
| 290 | // If nothing works, check if we have a custom transcoder available |
| 291 | if (!preg_match('#^[a-z0-9_ \\-]+$#', $encoding)) |
| 292 | { |
| 293 | // Make sure the encoding name is alphanumeric, we don't want it to be abused into loading arbitrary files |
| 294 | trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); |
| 295 | } |
| 296 | |
| 297 | global $phpbb_root_path, $phpEx; |
| 298 | |
| 299 | // iso-8859-* character encoding |
| 300 | if (preg_match('/iso[_ -]?8859[_ -]?(\\d+)/', $encoding, $array)) |
| 301 | { |
| 302 | switch ($array[1]) |
| 303 | { |
| 304 | case '1': |
| 305 | case '2': |
| 306 | case '4': |
| 307 | case '7': |
| 308 | case '8': |
| 309 | case '9': |
| 310 | case '15': |
| 311 | if (!function_exists('iso_8859_' . $array[1])) |
| 312 | { |
| 313 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) |
| 314 | { |
| 315 | trigger_error('Basic reencoder file is missing', E_USER_ERROR); |
| 316 | } |
| 317 | include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); |
| 318 | } |
| 319 | return call_user_func('iso_8859_' . $array[1], $string); |
| 320 | break; |
| 321 | |
| 322 | default: |
| 323 | trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); |
| 324 | break; |
| 325 | } |
| 326 | } |
| 327 | |
| 328 | // CP/WIN character encoding |
| 329 | if (preg_match('/(?:cp|windows)[_\- ]?(\\d+)/', $encoding, $array)) |
| 330 | { |
| 331 | switch ($array[1]) |
| 332 | { |
| 333 | case '932': |
| 334 | break; |
| 335 | case '1250': |
| 336 | case '1251': |
| 337 | case '1252': |
| 338 | case '1254': |
| 339 | case '1255': |
| 340 | case '1256': |
| 341 | case '1257': |
| 342 | case '874': |
| 343 | if (!function_exists('cp' . $array[1])) |
| 344 | { |
| 345 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) |
| 346 | { |
| 347 | trigger_error('Basic reencoder file is missing', E_USER_ERROR); |
| 348 | } |
| 349 | include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); |
| 350 | } |
| 351 | return call_user_func('cp' . $array[1], $string); |
| 352 | break; |
| 353 | |
| 354 | default: |
| 355 | trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); |
| 356 | break; |
| 357 | } |
| 358 | } |
| 359 | |
| 360 | // TIS-620 |
| 361 | if (preg_match('/tis[_ -]?620/', $encoding)) |
| 362 | { |
| 363 | if (!function_exists('tis_620')) |
| 364 | { |
| 365 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx)) |
| 366 | { |
| 367 | trigger_error('Basic reencoder file is missing', E_USER_ERROR); |
| 368 | } |
| 369 | include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx); |
| 370 | } |
| 371 | return tis_620($string); |
| 372 | } |
| 373 | |
| 374 | // SJIS |
| 375 | if (preg_match('/sjis(?:[_ -]?win)?|(?:cp|ibm)[_ -]?932|shift[_ -]?jis/', $encoding)) |
| 376 | { |
| 377 | if (!function_exists('sjis')) |
| 378 | { |
| 379 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) |
| 380 | { |
| 381 | trigger_error('CJK reencoder file is missing', E_USER_ERROR); |
| 382 | } |
| 383 | include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); |
| 384 | } |
| 385 | return sjis($string); |
| 386 | } |
| 387 | |
| 388 | // EUC_KR |
| 389 | if (preg_match('/euc[_ -]?kr/', $encoding)) |
| 390 | { |
| 391 | if (!function_exists('euc_kr')) |
| 392 | { |
| 393 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) |
| 394 | { |
| 395 | trigger_error('CJK reencoder file is missing', E_USER_ERROR); |
| 396 | } |
| 397 | include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); |
| 398 | } |
| 399 | return euc_kr($string); |
| 400 | } |
| 401 | |
| 402 | // BIG-5 |
| 403 | if (preg_match('/big[_ -]?5/', $encoding)) |
| 404 | { |
| 405 | if (!function_exists('big5')) |
| 406 | { |
| 407 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) |
| 408 | { |
| 409 | trigger_error('CJK reencoder file is missing', E_USER_ERROR); |
| 410 | } |
| 411 | include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); |
| 412 | } |
| 413 | return big5($string); |
| 414 | } |
| 415 | |
| 416 | // GB2312 |
| 417 | if (preg_match('/gb[_ -]?2312/', $encoding)) |
| 418 | { |
| 419 | if (!function_exists('gb2312')) |
| 420 | { |
| 421 | if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx)) |
| 422 | { |
| 423 | trigger_error('CJK reencoder file is missing', E_USER_ERROR); |
| 424 | } |
| 425 | include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx); |
| 426 | } |
| 427 | return gb2312($string); |
| 428 | } |
| 429 | |
| 430 | // Trigger an error?! Fow now just give bad data :-( |
| 431 | trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR); |
| 432 | } |
| 433 | |
| 434 | /** |
| 435 | * Replace some special UTF-8 chars that are not in ASCII with their UCR. |
| 436 | * using their Numeric Character Reference's Hexadecimal notation. |
| 437 | * |
| 438 | * Doesn't interfere with Japanese or Cyrillic etc. |
| 439 | * Unicode character visualization will depend on the character support |
| 440 | * of your web browser and the fonts installed on your system. |
| 441 | * |
| 442 | * @see https://en.wikibooks.org/wiki/Unicode/Character_reference/1F000-1FFFF |
| 443 | * |
| 444 | * @param string $text UTF-8 string in NFC |
| 445 | * @return string ASCII string using NCR for non-ASCII chars |
| 446 | */ |
| 447 | function utf8_encode_ucr($text) |
| 448 | { |
| 449 | return preg_replace_callback('/[\\xF0-\\xF4].../', 'utf8_encode_ncr_callback', $text); |
| 450 | } |
| 451 | |
| 452 | /** |
| 453 | * Replace all UTF-8 chars that are not in ASCII with their NCR |
| 454 | * using their Numeric Character Reference's Hexadecimal notation. |
| 455 | * |
| 456 | * @param string $text UTF-8 string in NFC |
| 457 | * @return string ASCII string using NCRs for non-ASCII chars |
| 458 | */ |
| 459 | function utf8_encode_ncr($text) |
| 460 | { |
| 461 | return preg_replace_callback('#[\\xC2-\\xF4][\\x80-\\xBF]{1,3}#', 'utf8_encode_ncr_callback', $text); |
| 462 | } |
| 463 | |
| 464 | /** |
| 465 | * Callback used in utf8_encode_ncr() and utf8_encode_ucr() |
| 466 | * |
| 467 | * Takes a UTF-8 char and replaces it with its NCR. Attention, $m is an array |
| 468 | * |
| 469 | * @param array $m 0-based numerically indexed array passed by preg_replace_callback() |
| 470 | * @return string A HTML NCR if the character is valid, or the original string otherwise |
| 471 | */ |
| 472 | function utf8_encode_ncr_callback($m) |
| 473 | { |
| 474 | return '&#' . utf8_ord($m[0]) . ';'; |
| 475 | } |
| 476 | |
| 477 | /** |
| 478 | * Converts a UTF-8 char to an NCR |
| 479 | * |
| 480 | * @param string $chr UTF-8 char |
| 481 | * @return integer UNICODE code point |
| 482 | */ |
| 483 | function utf8_ord($chr) |
| 484 | { |
| 485 | switch (strlen($chr)) |
| 486 | { |
| 487 | case 1: |
| 488 | return ord($chr); |
| 489 | break; |
| 490 | |
| 491 | case 2: |
| 492 | return ((ord($chr[0]) & 0x1F) << 6) | (ord($chr[1]) & 0x3F); |
| 493 | break; |
| 494 | |
| 495 | case 3: |
| 496 | return ((ord($chr[0]) & 0x0F) << 12) | ((ord($chr[1]) & 0x3F) << 6) | (ord($chr[2]) & 0x3F); |
| 497 | break; |
| 498 | |
| 499 | case 4: |
| 500 | return ((ord($chr[0]) & 0x07) << 18) | ((ord($chr[1]) & 0x3F) << 12) | ((ord($chr[2]) & 0x3F) << 6) | (ord($chr[3]) & 0x3F); |
| 501 | break; |
| 502 | |
| 503 | default: |
| 504 | return $chr; |
| 505 | } |
| 506 | } |
| 507 | |
| 508 | /** |
| 509 | * Converts an NCR to a UTF-8 char |
| 510 | * |
| 511 | * @param int $cp UNICODE code point |
| 512 | * @return string UTF-8 char |
| 513 | */ |
| 514 | function utf8_chr($cp) |
| 515 | { |
| 516 | if ($cp > 0xFFFF) |
| 517 | { |
| 518 | return chr(0xF0 | ($cp >> 18)) . chr(0x80 | (($cp >> 12) & 0x3F)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F)); |
| 519 | } |
| 520 | else if ($cp > 0x7FF) |
| 521 | { |
| 522 | return chr(0xE0 | ($cp >> 12)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F)); |
| 523 | } |
| 524 | else if ($cp > 0x7F) |
| 525 | { |
| 526 | return chr(0xC0 | ($cp >> 6)) . chr(0x80 | ($cp & 0x3F)); |
| 527 | } |
| 528 | else |
| 529 | { |
| 530 | return chr($cp); |
| 531 | } |
| 532 | } |
| 533 | |
| 534 | /** |
| 535 | * Convert Numeric Character References to UTF-8 chars |
| 536 | * |
| 537 | * Notes: |
| 538 | * - we do not convert NCRs recursively, if you pass &#38; it will return & |
| 539 | * - we DO NOT check for the existence of the Unicode characters, therefore an entity may be converted to an inexistent codepoint |
| 540 | * |
| 541 | * @param string $text String to convert, encoded in UTF-8 (no normal form required) |
| 542 | * @return string UTF-8 string where NCRs have been replaced with the actual chars |
| 543 | */ |
| 544 | function utf8_decode_ncr($text) |
| 545 | { |
| 546 | return preg_replace_callback('/&#([0-9]{1,6}|x[0-9A-F]{1,5});/i', 'utf8_decode_ncr_callback', $text); |
| 547 | } |
| 548 | |
| 549 | /** |
| 550 | * Callback used in decode_ncr() |
| 551 | * |
| 552 | * Takes a NCR (in decimal or hexadecimal) and returns a UTF-8 char. Attention, $m is an array. |
| 553 | * It will ignore most of invalid NCRs, but not all! |
| 554 | * |
| 555 | * @param array $m 0-based numerically indexed array passed by preg_replace_callback() |
| 556 | * @return string UTF-8 char |
| 557 | */ |
| 558 | function utf8_decode_ncr_callback($m) |
| 559 | { |
| 560 | $cp = (strncasecmp($m[1], 'x', 1)) ? $m[1] : hexdec(substr($m[1], 1)); |
| 561 | |
| 562 | return utf8_chr($cp); |
| 563 | } |
| 564 | |
| 565 | /** |
| 566 | * Case folds a unicode string as per Unicode 5.0, section 3.13 |
| 567 | * |
| 568 | * @param string $text text to be case folded |
| 569 | * @param string $option determines how we will fold the cases |
| 570 | * @return string case folded text |
| 571 | */ |
| 572 | function utf8_case_fold($text, $option = 'full') |
| 573 | { |
| 574 | static $uniarray = array(); |
| 575 | global $phpbb_root_path, $phpEx; |
| 576 | |
| 577 | // common is always set |
| 578 | if (!isset($uniarray['c'])) |
| 579 | { |
| 580 | $uniarray['c'] = include($phpbb_root_path . 'includes/utf/data/case_fold_c.' . $phpEx); |
| 581 | } |
| 582 | |
| 583 | // only set full if we need to |
| 584 | if ($option === 'full' && !isset($uniarray['f'])) |
| 585 | { |
| 586 | $uniarray['f'] = include($phpbb_root_path . 'includes/utf/data/case_fold_f.' . $phpEx); |
| 587 | } |
| 588 | |
| 589 | // only set simple if we need to |
| 590 | if ($option !== 'full' && !isset($uniarray['s'])) |
| 591 | { |
| 592 | $uniarray['s'] = include($phpbb_root_path . 'includes/utf/data/case_fold_s.' . $phpEx); |
| 593 | } |
| 594 | |
| 595 | // common is always replaced |
| 596 | $text = strtr($text, $uniarray['c']); |
| 597 | |
| 598 | if ($option === 'full') |
| 599 | { |
| 600 | // full replaces a character with multiple characters |
| 601 | $text = strtr($text, $uniarray['f']); |
| 602 | } |
| 603 | else |
| 604 | { |
| 605 | // simple replaces a character with another character |
| 606 | $text = strtr($text, $uniarray['s']); |
| 607 | } |
| 608 | |
| 609 | return $text; |
| 610 | } |
| 611 | |
| 612 | /** |
| 613 | * Takes the input and does a "special" case fold. It does minor normalization |
| 614 | * and returns NFKC compatable text |
| 615 | * |
| 616 | * @param string $text text to be case folded |
| 617 | * @param string $option determines how we will fold the cases |
| 618 | * @return string case folded text |
| 619 | */ |
| 620 | function utf8_case_fold_nfkc($text, $option = 'full') |
| 621 | { |
| 622 | static $fc_nfkc_closure = array( |
| 623 | "\xCD\xBA" => "\x20\xCE\xB9", |
| 624 | "\xCF\x92" => "\xCF\x85", |
| 625 | "\xCF\x93" => "\xCF\x8D", |
| 626 | "\xCF\x94" => "\xCF\x8B", |
| 627 | "\xCF\xB2" => "\xCF\x83", |
| 628 | "\xCF\xB9" => "\xCF\x83", |
| 629 | "\xE1\xB4\xAC" => "\x61", |
| 630 | "\xE1\xB4\xAD" => "\xC3\xA6", |
| 631 | "\xE1\xB4\xAE" => "\x62", |
| 632 | "\xE1\xB4\xB0" => "\x64", |
| 633 | "\xE1\xB4\xB1" => "\x65", |
| 634 | "\xE1\xB4\xB2" => "\xC7\x9D", |
| 635 | "\xE1\xB4\xB3" => "\x67", |
| 636 | "\xE1\xB4\xB4" => "\x68", |
| 637 | "\xE1\xB4\xB5" => "\x69", |
| 638 | "\xE1\xB4\xB6" => "\x6A", |
| 639 | "\xE1\xB4\xB7" => "\x6B", |
| 640 | "\xE1\xB4\xB8" => "\x6C", |
| 641 | "\xE1\xB4\xB9" => "\x6D", |
| 642 | "\xE1\xB4\xBA" => "\x6E", |
| 643 | "\xE1\xB4\xBC" => "\x6F", |
| 644 | "\xE1\xB4\xBD" => "\xC8\xA3", |
| 645 | "\xE1\xB4\xBE" => "\x70", |
| 646 | "\xE1\xB4\xBF" => "\x72", |
| 647 | "\xE1\xB5\x80" => "\x74", |
| 648 | "\xE1\xB5\x81" => "\x75", |
| 649 | "\xE1\xB5\x82" => "\x77", |
| 650 | "\xE2\x82\xA8" => "\x72\x73", |
| 651 | "\xE2\x84\x82" => "\x63", |
| 652 | "\xE2\x84\x83" => "\xC2\xB0\x63", |
| 653 | "\xE2\x84\x87" => "\xC9\x9B", |
| 654 | "\xE2\x84\x89" => "\xC2\xB0\x66", |
| 655 | "\xE2\x84\x8B" => "\x68", |
| 656 | "\xE2\x84\x8C" => "\x68", |
| 657 | "\xE2\x84\x8D" => "\x68", |
| 658 | "\xE2\x84\x90" => "\x69", |
| 659 | "\xE2\x84\x91" => "\x69", |
| 660 | "\xE2\x84\x92" => "\x6C", |
| 661 | "\xE2\x84\x95" => "\x6E", |
| 662 | "\xE2\x84\x96" => "\x6E\x6F", |
| 663 | "\xE2\x84\x99" => "\x70", |
| 664 | "\xE2\x84\x9A" => "\x71", |
| 665 | "\xE2\x84\x9B" => "\x72", |
| 666 | "\xE2\x84\x9C" => "\x72", |
| 667 | "\xE2\x84\x9D" => "\x72", |
| 668 | "\xE2\x84\xA0" => "\x73\x6D", |
| 669 | "\xE2\x84\xA1" => "\x74\x65\x6C", |
| 670 | "\xE2\x84\xA2" => "\x74\x6D", |
| 671 | "\xE2\x84\xA4" => "\x7A", |
| 672 | "\xE2\x84\xA8" => "\x7A", |
| 673 | "\xE2\x84\xAC" => "\x62", |
| 674 | "\xE2\x84\xAD" => "\x63", |
| 675 | "\xE2\x84\xB0" => "\x65", |
| 676 | "\xE2\x84\xB1" => "\x66", |
| 677 | "\xE2\x84\xB3" => "\x6D", |
| 678 | "\xE2\x84\xBB" => "\x66\x61\x78", |
| 679 | "\xE2\x84\xBE" => "\xCE\xB3", |
| 680 | "\xE2\x84\xBF" => "\xCF\x80", |
| 681 | "\xE2\x85\x85" => "\x64", |
| 682 | "\xE3\x89\x90" => "\x70\x74\x65", |
| 683 | "\xE3\x8B\x8C" => "\x68\x67", |
| 684 | "\xE3\x8B\x8E" => "\x65\x76", |
| 685 | "\xE3\x8B\x8F" => "\x6C\x74\x64", |
| 686 | "\xE3\x8D\xB1" => "\x68\x70\x61", |
| 687 | "\xE3\x8D\xB3" => "\x61\x75", |
| 688 | "\xE3\x8D\xB5" => "\x6F\x76", |
| 689 | "\xE3\x8D\xBA" => "\x69\x75", |
| 690 | "\xE3\x8E\x80" => "\x70\x61", |
| 691 | "\xE3\x8E\x81" => "\x6E\x61", |
| 692 | "\xE3\x8E\x82" => "\xCE\xBC\x61", |
| 693 | "\xE3\x8E\x83" => "\x6D\x61", |
| 694 | "\xE3\x8E\x84" => "\x6B\x61", |
| 695 | "\xE3\x8E\x85" => "\x6B\x62", |
| 696 | "\xE3\x8E\x86" => "\x6D\x62", |
| 697 | "\xE3\x8E\x87" => "\x67\x62", |
| 698 | "\xE3\x8E\x8A" => "\x70\x66", |
| 699 | "\xE3\x8E\x8B" => "\x6E\x66", |
| 700 | "\xE3\x8E\x8C" => "\xCE\xBC\x66", |
| 701 | "\xE3\x8E\x90" => "\x68\x7A", |
| 702 | "\xE3\x8E\x91" => "\x6B\x68\x7A", |
| 703 | "\xE3\x8E\x92" => "\x6D\x68\x7A", |
| 704 | "\xE3\x8E\x93" => "\x67\x68\x7A", |
| 705 | "\xE3\x8E\x94" => "\x74\x68\x7A", |
| 706 | "\xE3\x8E\xA9" => "\x70\x61", |
| 707 | "\xE3\x8E\xAA" => "\x6B\x70\x61", |
| 708 | "\xE3\x8E\xAB" => "\x6D\x70\x61", |
| 709 | "\xE3\x8E\xAC" => "\x67\x70\x61", |
| 710 | "\xE3\x8E\xB4" => "\x70\x76", |
| 711 | "\xE3\x8E\xB5" => "\x6E\x76", |
| 712 | "\xE3\x8E\xB6" => "\xCE\xBC\x76", |
| 713 | "\xE3\x8E\xB7" => "\x6D\x76", |
| 714 | "\xE3\x8E\xB8" => "\x6B\x76", |
| 715 | "\xE3\x8E\xB9" => "\x6D\x76", |
| 716 | "\xE3\x8E\xBA" => "\x70\x77", |
| 717 | "\xE3\x8E\xBB" => "\x6E\x77", |
| 718 | "\xE3\x8E\xBC" => "\xCE\xBC\x77", |
| 719 | "\xE3\x8E\xBD" => "\x6D\x77", |
| 720 | "\xE3\x8E\xBE" => "\x6B\x77", |
| 721 | "\xE3\x8E\xBF" => "\x6D\x77", |
| 722 | "\xE3\x8F\x80" => "\x6B\xCF\x89", |
| 723 | "\xE3\x8F\x81" => "\x6D\xCF\x89", |
| 724 | "\xE3\x8F\x83" => "\x62\x71", |
| 725 | "\xE3\x8F\x86" => "\x63\xE2\x88\x95\x6B\x67", |
| 726 | "\xE3\x8F\x87" => "\x63\x6F\x2E", |
| 727 | "\xE3\x8F\x88" => "\x64\x62", |
| 728 | "\xE3\x8F\x89" => "\x67\x79", |
| 729 | "\xE3\x8F\x8B" => "\x68\x70", |
| 730 | "\xE3\x8F\x8D" => "\x6B\x6B", |
| 731 | "\xE3\x8F\x8E" => "\x6B\x6D", |
| 732 | "\xE3\x8F\x97" => "\x70\x68", |
| 733 | "\xE3\x8F\x99" => "\x70\x70\x6D", |
| 734 | "\xE3\x8F\x9A" => "\x70\x72", |
| 735 | "\xE3\x8F\x9C" => "\x73\x76", |
| 736 | "\xE3\x8F\x9D" => "\x77\x62", |
| 737 | "\xE3\x8F\x9E" => "\x76\xE2\x88\x95\x6D", |
| 738 | "\xE3\x8F\x9F" => "\x61\xE2\x88\x95\x6D", |
| 739 | "\xF0\x9D\x90\x80" => "\x61", |
| 740 | "\xF0\x9D\x90\x81" => "\x62", |
| 741 | "\xF0\x9D\x90\x82" => "\x63", |
| 742 | "\xF0\x9D\x90\x83" => "\x64", |
| 743 | "\xF0\x9D\x90\x84" => "\x65", |
| 744 | "\xF0\x9D\x90\x85" => "\x66", |
| 745 | "\xF0\x9D\x90\x86" => "\x67", |
| 746 | "\xF0\x9D\x90\x87" => "\x68", |
| 747 | "\xF0\x9D\x90\x88" => "\x69", |
| 748 | "\xF0\x9D\x90\x89" => "\x6A", |
| 749 | "\xF0\x9D\x90\x8A" => "\x6B", |
| 750 | "\xF0\x9D\x90\x8B" => "\x6C", |
| 751 | "\xF0\x9D\x90\x8C" => "\x6D", |
| 752 | "\xF0\x9D\x90\x8D" => "\x6E", |
| 753 | "\xF0\x9D\x90\x8E" => "\x6F", |
| 754 | "\xF0\x9D\x90\x8F" => "\x70", |
| 755 | "\xF0\x9D\x90\x90" => "\x71", |
| 756 | "\xF0\x9D\x90\x91" => "\x72", |
| 757 | "\xF0\x9D\x90\x92" => "\x73", |
| 758 | "\xF0\x9D\x90\x93" => "\x74", |
| 759 | "\xF0\x9D\x90\x94" => "\x75", |
| 760 | "\xF0\x9D\x90\x95" => "\x76", |
| 761 | "\xF0\x9D\x90\x96" => "\x77", |
| 762 | "\xF0\x9D\x90\x97" => "\x78", |
| 763 | "\xF0\x9D\x90\x98" => "\x79", |
| 764 | "\xF0\x9D\x90\x99" => "\x7A", |
| 765 | "\xF0\x9D\x90\xB4" => "\x61", |
| 766 | "\xF0\x9D\x90\xB5" => "\x62", |
| 767 | "\xF0\x9D\x90\xB6" => "\x63", |
| 768 | "\xF0\x9D\x90\xB7" => "\x64", |
| 769 | "\xF0\x9D\x90\xB8" => "\x65", |
| 770 | "\xF0\x9D\x90\xB9" => "\x66", |
| 771 | "\xF0\x9D\x90\xBA" => "\x67", |
| 772 | "\xF0\x9D\x90\xBB" => "\x68", |
| 773 | "\xF0\x9D\x90\xBC" => "\x69", |
| 774 | "\xF0\x9D\x90\xBD" => "\x6A", |
| 775 | "\xF0\x9D\x90\xBE" => "\x6B", |
| 776 | "\xF0\x9D\x90\xBF" => "\x6C", |
| 777 | "\xF0\x9D\x91\x80" => "\x6D", |
| 778 | "\xF0\x9D\x91\x81" => "\x6E", |
| 779 | "\xF0\x9D\x91\x82" => "\x6F", |
| 780 | "\xF0\x9D\x91\x83" => "\x70", |
| 781 | "\xF0\x9D\x91\x84" => "\x71", |
| 782 | "\xF0\x9D\x91\x85" => "\x72", |
| 783 | "\xF0\x9D\x91\x86" => "\x73", |
| 784 | "\xF0\x9D\x91\x87" => "\x74", |
| 785 | "\xF0\x9D\x91\x88" => "\x75", |
| 786 | "\xF0\x9D\x91\x89" => "\x76", |
| 787 | "\xF0\x9D\x91\x8A" => "\x77", |
| 788 | "\xF0\x9D\x91\x8B" => "\x78", |
| 789 | "\xF0\x9D\x91\x8C" => "\x79", |
| 790 | "\xF0\x9D\x91\x8D" => "\x7A", |
| 791 | "\xF0\x9D\x91\xA8" => "\x61", |
| 792 | "\xF0\x9D\x91\xA9" => "\x62", |
| 793 | "\xF0\x9D\x91\xAA" => "\x63", |
| 794 | "\xF0\x9D\x91\xAB" => "\x64", |
| 795 | "\xF0\x9D\x91\xAC" => "\x65", |
| 796 | "\xF0\x9D\x91\xAD" => "\x66", |
| 797 | "\xF0\x9D\x91\xAE" => "\x67", |
| 798 | "\xF0\x9D\x91\xAF" => "\x68", |
| 799 | "\xF0\x9D\x91\xB0" => "\x69", |
| 800 | "\xF0\x9D\x91\xB1" => "\x6A", |
| 801 | "\xF0\x9D\x91\xB2" => "\x6B", |
| 802 | "\xF0\x9D\x91\xB3" => "\x6C", |
| 803 | "\xF0\x9D\x91\xB4" => "\x6D", |
| 804 | "\xF0\x9D\x91\xB5" => "\x6E", |
| 805 | "\xF0\x9D\x91\xB6" => "\x6F", |
| 806 | "\xF0\x9D\x91\xB7" => "\x70", |
| 807 | "\xF0\x9D\x91\xB8" => "\x71", |
| 808 | "\xF0\x9D\x91\xB9" => "\x72", |
| 809 | "\xF0\x9D\x91\xBA" => "\x73", |
| 810 | "\xF0\x9D\x91\xBB" => "\x74", |
| 811 | "\xF0\x9D\x91\xBC" => "\x75", |
| 812 | "\xF0\x9D\x91\xBD" => "\x76", |
| 813 | "\xF0\x9D\x91\xBE" => "\x77", |
| 814 | "\xF0\x9D\x91\xBF" => "\x78", |
| 815 | "\xF0\x9D\x92\x80" => "\x79", |
| 816 | "\xF0\x9D\x92\x81" => "\x7A", |
| 817 | "\xF0\x9D\x92\x9C" => "\x61", |
| 818 | "\xF0\x9D\x92\x9E" => "\x63", |
| 819 | "\xF0\x9D\x92\x9F" => "\x64", |
| 820 | "\xF0\x9D\x92\xA2" => "\x67", |
| 821 | "\xF0\x9D\x92\xA5" => "\x6A", |
| 822 | "\xF0\x9D\x92\xA6" => "\x6B", |
| 823 | "\xF0\x9D\x92\xA9" => "\x6E", |
| 824 | "\xF0\x9D\x92\xAA" => "\x6F", |
| 825 | "\xF0\x9D\x92\xAB" => "\x70", |
| 826 | "\xF0\x9D\x92\xAC" => "\x71", |
| 827 | "\xF0\x9D\x92\xAE" => "\x73", |
| 828 | "\xF0\x9D\x92\xAF" => "\x74", |
| 829 | "\xF0\x9D\x92\xB0" => "\x75", |
| 830 | "\xF0\x9D\x92\xB1" => "\x76", |
| 831 | "\xF0\x9D\x92\xB2" => "\x77", |
| 832 | "\xF0\x9D\x92\xB3" => "\x78", |
| 833 | "\xF0\x9D\x92\xB4" => "\x79", |
| 834 | "\xF0\x9D\x92\xB5" => "\x7A", |
| 835 | "\xF0\x9D\x93\x90" => "\x61", |
| 836 | "\xF0\x9D\x93\x91" => "\x62", |
| 837 | "\xF0\x9D\x93\x92" => "\x63", |
| 838 | "\xF0\x9D\x93\x93" => "\x64", |
| 839 | "\xF0\x9D\x93\x94" => "\x65", |
| 840 | "\xF0\x9D\x93\x95" => "\x66", |
| 841 | "\xF0\x9D\x93\x96" => "\x67", |
| 842 | "\xF0\x9D\x93\x97" => "\x68", |
| 843 | "\xF0\x9D\x93\x98" => "\x69", |
| 844 | "\xF0\x9D\x93\x99" => "\x6A", |
| 845 | "\xF0\x9D\x93\x9A" => "\x6B", |
| 846 | "\xF0\x9D\x93\x9B" => "\x6C", |
| 847 | "\xF0\x9D\x93\x9C" => "\x6D", |
| 848 | "\xF0\x9D\x93\x9D" => "\x6E", |
| 849 | "\xF0\x9D\x93\x9E" => "\x6F", |
| 850 | "\xF0\x9D\x93\x9F" => "\x70", |
| 851 | "\xF0\x9D\x93\xA0" => "\x71", |
| 852 | "\xF0\x9D\x93\xA1" => "\x72", |
| 853 | "\xF0\x9D\x93\xA2" => "\x73", |
| 854 | "\xF0\x9D\x93\xA3" => "\x74", |
| 855 | "\xF0\x9D\x93\xA4" => "\x75", |
| 856 | "\xF0\x9D\x93\xA5" => "\x76", |
| 857 | "\xF0\x9D\x93\xA6" => "\x77", |
| 858 | "\xF0\x9D\x93\xA7" => "\x78", |
| 859 | "\xF0\x9D\x93\xA8" => "\x79", |
| 860 | "\xF0\x9D\x93\xA9" => "\x7A", |
| 861 | "\xF0\x9D\x94\x84" => "\x61", |
| 862 | "\xF0\x9D\x94\x85" => "\x62", |
| 863 | "\xF0\x9D\x94\x87" => "\x64", |
| 864 | "\xF0\x9D\x94\x88" => "\x65", |
| 865 | "\xF0\x9D\x94\x89" => "\x66", |
| 866 | "\xF0\x9D\x94\x8A" => "\x67", |
| 867 | "\xF0\x9D\x94\x8D" => "\x6A", |
| 868 | "\xF0\x9D\x94\x8E" => "\x6B", |
| 869 | "\xF0\x9D\x94\x8F" => "\x6C", |
| 870 | "\xF0\x9D\x94\x90" => "\x6D", |
| 871 | "\xF0\x9D\x94\x91" => "\x6E", |
| 872 | "\xF0\x9D\x94\x92" => "\x6F", |
| 873 | "\xF0\x9D\x94\x93" => "\x70", |
| 874 | "\xF0\x9D\x94\x94" => "\x71", |
| 875 | "\xF0\x9D\x94\x96" => "\x73", |
| 876 | "\xF0\x9D\x94\x97" => "\x74", |
| 877 | "\xF0\x9D\x94\x98" => "\x75", |
| 878 | "\xF0\x9D\x94\x99" => "\x76", |
| 879 | "\xF0\x9D\x94\x9A" => "\x77", |
| 880 | "\xF0\x9D\x94\x9B" => "\x78", |
| 881 | "\xF0\x9D\x94\x9C" => "\x79", |
| 882 | "\xF0\x9D\x94\xB8" => "\x61", |
| 883 | "\xF0\x9D\x94\xB9" => "\x62", |
| 884 | "\xF0\x9D\x94\xBB" => "\x64", |
| 885 | "\xF0\x9D\x94\xBC" => "\x65", |
| 886 | "\xF0\x9D\x94\xBD" => "\x66", |
| 887 | "\xF0\x9D\x94\xBE" => "\x67", |
| 888 | "\xF0\x9D\x95\x80" => "\x69", |
| 889 | "\xF0\x9D\x95\x81" => "\x6A", |
| 890 | "\xF0\x9D\x95\x82" => "\x6B", |
| 891 | "\xF0\x9D\x95\x83" => "\x6C", |
| 892 | "\xF0\x9D\x95\x84" => "\x6D", |
| 893 | "\xF0\x9D\x95\x86" => "\x6F", |
| 894 | "\xF0\x9D\x95\x8A" => "\x73", |
| 895 | "\xF0\x9D\x95\x8B" => "\x74", |
| 896 | "\xF0\x9D\x95\x8C" => "\x75", |
| 897 | "\xF0\x9D\x95\x8D" => "\x76", |
| 898 | "\xF0\x9D\x95\x8E" => "\x77", |
| 899 | "\xF0\x9D\x95\x8F" => "\x78", |
| 900 | "\xF0\x9D\x95\x90" => "\x79", |
| 901 | "\xF0\x9D\x95\xAC" => "\x61", |
| 902 | "\xF0\x9D\x95\xAD" => "\x62", |
| 903 | "\xF0\x9D\x95\xAE" => "\x63", |
| 904 | "\xF0\x9D\x95\xAF" => "\x64", |
| 905 | "\xF0\x9D\x95\xB0" => "\x65", |
| 906 | "\xF0\x9D\x95\xB1" => "\x66", |
| 907 | "\xF0\x9D\x95\xB2" => "\x67", |
| 908 | "\xF0\x9D\x95\xB3" => "\x68", |
| 909 | "\xF0\x9D\x95\xB4" => "\x69", |
| 910 | "\xF0\x9D\x95\xB5" => "\x6A", |
| 911 | "\xF0\x9D\x95\xB6" => "\x6B", |
| 912 | "\xF0\x9D\x95\xB7" => "\x6C", |
| 913 | "\xF0\x9D\x95\xB8" => "\x6D", |
| 914 | "\xF0\x9D\x95\xB9" => "\x6E", |
| 915 | "\xF0\x9D\x95\xBA" => "\x6F", |
| 916 | "\xF0\x9D\x95\xBB" => "\x70", |
| 917 | "\xF0\x9D\x95\xBC" => "\x71", |
| 918 | "\xF0\x9D\x95\xBD" => "\x72", |
| 919 | "\xF0\x9D\x95\xBE" => "\x73", |
| 920 | "\xF0\x9D\x95\xBF" => "\x74", |
| 921 | "\xF0\x9D\x96\x80" => "\x75", |
| 922 | "\xF0\x9D\x96\x81" => "\x76", |
| 923 | "\xF0\x9D\x96\x82" => "\x77", |
| 924 | "\xF0\x9D\x96\x83" => "\x78", |
| 925 | "\xF0\x9D\x96\x84" => "\x79", |
| 926 | "\xF0\x9D\x96\x85" => "\x7A", |
| 927 | "\xF0\x9D\x96\xA0" => "\x61", |
| 928 | "\xF0\x9D\x96\xA1" => "\x62", |
| 929 | "\xF0\x9D\x96\xA2" => "\x63", |
| 930 | "\xF0\x9D\x96\xA3" => "\x64", |
| 931 | "\xF0\x9D\x96\xA4" => "\x65", |
| 932 | "\xF0\x9D\x96\xA5" => "\x66", |
| 933 | "\xF0\x9D\x96\xA6" => "\x67", |
| 934 | "\xF0\x9D\x96\xA7" => "\x68", |
| 935 | "\xF0\x9D\x96\xA8" => "\x69", |
| 936 | "\xF0\x9D\x96\xA9" => "\x6A", |
| 937 | "\xF0\x9D\x96\xAA" => "\x6B", |
| 938 | "\xF0\x9D\x96\xAB" => "\x6C", |
| 939 | "\xF0\x9D\x96\xAC" => "\x6D", |
| 940 | "\xF0\x9D\x96\xAD" => "\x6E", |
| 941 | "\xF0\x9D\x96\xAE" => "\x6F", |
| 942 | "\xF0\x9D\x96\xAF" => "\x70", |
| 943 | "\xF0\x9D\x96\xB0" => "\x71", |
| 944 | "\xF0\x9D\x96\xB1" => "\x72", |
| 945 | "\xF0\x9D\x96\xB2" => "\x73", |
| 946 | "\xF0\x9D\x96\xB3" => "\x74", |
| 947 | "\xF0\x9D\x96\xB4" => "\x75", |
| 948 | "\xF0\x9D\x96\xB5" => "\x76", |
| 949 | "\xF0\x9D\x96\xB6" => "\x77", |
| 950 | "\xF0\x9D\x96\xB7" => "\x78", |
| 951 | "\xF0\x9D\x96\xB8" => "\x79", |
| 952 | "\xF0\x9D\x96\xB9" => "\x7A", |
| 953 | "\xF0\x9D\x97\x94" => "\x61", |
| 954 | "\xF0\x9D\x97\x95" => "\x62", |
| 955 | "\xF0\x9D\x97\x96" => "\x63", |
| 956 | "\xF0\x9D\x97\x97" => "\x64", |
| 957 | "\xF0\x9D\x97\x98" => "\x65", |
| 958 | "\xF0\x9D\x97\x99" => "\x66", |
| 959 | "\xF0\x9D\x97\x9A" => "\x67", |
| 960 | "\xF0\x9D\x97\x9B" => "\x68", |
| 961 | "\xF0\x9D\x97\x9C" => "\x69", |
| 962 | "\xF0\x9D\x97\x9D" => "\x6A", |
| 963 | "\xF0\x9D\x97\x9E" => "\x6B", |
| 964 | "\xF0\x9D\x97\x9F" => "\x6C", |
| 965 | "\xF0\x9D\x97\xA0" => "\x6D", |
| 966 | "\xF0\x9D\x97\xA1" => "\x6E", |
| 967 | "\xF0\x9D\x97\xA2" => "\x6F", |
| 968 | "\xF0\x9D\x97\xA3" => "\x70", |
| 969 | "\xF0\x9D\x97\xA4" => "\x71", |
| 970 | "\xF0\x9D\x97\xA5" => "\x72", |
| 971 | "\xF0\x9D\x97\xA6" => "\x73", |
| 972 | "\xF0\x9D\x97\xA7" => "\x74", |
| 973 | "\xF0\x9D\x97\xA8" => "\x75", |
| 974 | "\xF0\x9D\x97\xA9" => "\x76", |
| 975 | "\xF0\x9D\x97\xAA" => "\x77", |
| 976 | "\xF0\x9D\x97\xAB" => "\x78", |
| 977 | "\xF0\x9D\x97\xAC" => "\x79", |
| 978 | "\xF0\x9D\x97\xAD" => "\x7A", |
| 979 | "\xF0\x9D\x98\x88" => "\x61", |
| 980 | "\xF0\x9D\x98\x89" => "\x62", |
| 981 | "\xF0\x9D\x98\x8A" => "\x63", |
| 982 | "\xF0\x9D\x98\x8B" => "\x64", |
| 983 | "\xF0\x9D\x98\x8C" => "\x65", |
| 984 | "\xF0\x9D\x98\x8D" => "\x66", |
| 985 | "\xF0\x9D\x98\x8E" => "\x67", |
| 986 | "\xF0\x9D\x98\x8F" => "\x68", |
| 987 | "\xF0\x9D\x98\x90" => "\x69", |
| 988 | "\xF0\x9D\x98\x91" => "\x6A", |
| 989 | "\xF0\x9D\x98\x92" => "\x6B", |
| 990 | "\xF0\x9D\x98\x93" => "\x6C", |
| 991 | "\xF0\x9D\x98\x94" => "\x6D", |
| 992 | "\xF0\x9D\x98\x95" => "\x6E", |
| 993 | "\xF0\x9D\x98\x96" => "\x6F", |
| 994 | "\xF0\x9D\x98\x97" => "\x70", |
| 995 | "\xF0\x9D\x98\x98" => "\x71", |
| 996 | "\xF0\x9D\x98\x99" => "\x72", |
| 997 | "\xF0\x9D\x98\x9A" => "\x73", |
| 998 | "\xF0\x9D\x98\x9B" => "\x74", |
| 999 | "\xF0\x9D\x98\x9C" => "\x75", |
| 1000 | "\xF0\x9D\x98\x9D" => "\x76", |
| 1001 | "\xF0\x9D\x98\x9E" => "\x77", |
| 1002 | "\xF0\x9D\x98\x9F" => "\x78", |
| 1003 | "\xF0\x9D\x98\xA0" => "\x79", |
| 1004 | "\xF0\x9D\x98\xA1" => "\x7A", |
| 1005 | "\xF0\x9D\x98\xBC" => "\x61", |
| 1006 | "\xF0\x9D\x98\xBD" => "\x62", |
| 1007 | "\xF0\x9D\x98\xBE" => "\x63", |
| 1008 | "\xF0\x9D\x98\xBF" => "\x64", |
| 1009 | "\xF0\x9D\x99\x80" => "\x65", |
| 1010 | "\xF0\x9D\x99\x81" => "\x66", |
| 1011 | "\xF0\x9D\x99\x82" => "\x67", |
| 1012 | "\xF0\x9D\x99\x83" => "\x68", |
| 1013 | "\xF0\x9D\x99\x84" => "\x69", |
| 1014 | "\xF0\x9D\x99\x85" => "\x6A", |
| 1015 | "\xF0\x9D\x99\x86" => "\x6B", |
| 1016 | "\xF0\x9D\x99\x87" => "\x6C", |
| 1017 | "\xF0\x9D\x99\x88" => "\x6D", |
| 1018 | "\xF0\x9D\x99\x89" => "\x6E", |
| 1019 | "\xF0\x9D\x99\x8A" => "\x6F", |
| 1020 | "\xF0\x9D\x99\x8B" => "\x70", |
| 1021 | "\xF0\x9D\x99\x8C" => "\x71", |
| 1022 | "\xF0\x9D\x99\x8D" => "\x72", |
| 1023 | "\xF0\x9D\x99\x8E" => "\x73", |
| 1024 | "\xF0\x9D\x99\x8F" => "\x74", |
| 1025 | "\xF0\x9D\x99\x90" => "\x75", |
| 1026 | "\xF0\x9D\x99\x91" => "\x76", |
| 1027 | "\xF0\x9D\x99\x92" => "\x77", |
| 1028 | "\xF0\x9D\x99\x93" => "\x78", |
| 1029 | "\xF0\x9D\x99\x94" => "\x79", |
| 1030 | "\xF0\x9D\x99\x95" => "\x7A", |
| 1031 | "\xF0\x9D\x99\xB0" => "\x61", |
| 1032 | "\xF0\x9D\x99\xB1" => "\x62", |
| 1033 | "\xF0\x9D\x99\xB2" => "\x63", |
| 1034 | "\xF0\x9D\x99\xB3" => "\x64", |
| 1035 | "\xF0\x9D\x99\xB4" => "\x65", |
| 1036 | "\xF0\x9D\x99\xB5" => "\x66", |
| 1037 | "\xF0\x9D\x99\xB6" => "\x67", |
| 1038 | "\xF0\x9D\x99\xB7" => "\x68", |
| 1039 | "\xF0\x9D\x99\xB8" => "\x69", |
| 1040 | "\xF0\x9D\x99\xB9" => "\x6A", |
| 1041 | "\xF0\x9D\x99\xBA" => "\x6B", |
| 1042 | "\xF0\x9D\x99\xBB" => "\x6C", |
| 1043 | "\xF0\x9D\x99\xBC" => "\x6D", |
| 1044 | "\xF0\x9D\x99\xBD" => "\x6E", |
| 1045 | "\xF0\x9D\x99\xBE" => "\x6F", |
| 1046 | "\xF0\x9D\x99\xBF" => "\x70", |
| 1047 | "\xF0\x9D\x9A\x80" => "\x71", |
| 1048 | "\xF0\x9D\x9A\x81" => "\x72", |
| 1049 | "\xF0\x9D\x9A\x82" => "\x73", |
| 1050 | "\xF0\x9D\x9A\x83" => "\x74", |
| 1051 | "\xF0\x9D\x9A\x84" => "\x75", |
| 1052 | "\xF0\x9D\x9A\x85" => "\x76", |
| 1053 | "\xF0\x9D\x9A\x86" => "\x77", |
| 1054 | "\xF0\x9D\x9A\x87" => "\x78", |
| 1055 | "\xF0\x9D\x9A\x88" => "\x79", |
| 1056 | "\xF0\x9D\x9A\x89" => "\x7A", |
| 1057 | "\xF0\x9D\x9A\xA8" => "\xCE\xB1", |
| 1058 | "\xF0\x9D\x9A\xA9" => "\xCE\xB2", |
| 1059 | "\xF0\x9D\x9A\xAA" => "\xCE\xB3", |
| 1060 | "\xF0\x9D\x9A\xAB" => "\xCE\xB4", |
| 1061 | "\xF0\x9D\x9A\xAC" => "\xCE\xB5", |
| 1062 | "\xF0\x9D\x9A\xAD" => "\xCE\xB6", |
| 1063 | "\xF0\x9D\x9A\xAE" => "\xCE\xB7", |
| 1064 | "\xF0\x9D\x9A\xAF" => "\xCE\xB8", |
| 1065 | "\xF0\x9D\x9A\xB0" => "\xCE\xB9", |
| 1066 | "\xF0\x9D\x9A\xB1" => "\xCE\xBA", |
| 1067 | "\xF0\x9D\x9A\xB2" => "\xCE\xBB", |
| 1068 | "\xF0\x9D\x9A\xB3" => "\xCE\xBC", |
| 1069 | "\xF0\x9D\x9A\xB4" => "\xCE\xBD", |
| 1070 | "\xF0\x9D\x9A\xB5" => "\xCE\xBE", |
| 1071 | "\xF0\x9D\x9A\xB6" => "\xCE\xBF", |
| 1072 | "\xF0\x9D\x9A\xB7" => "\xCF\x80", |
| 1073 | "\xF0\x9D\x9A\xB8" => "\xCF\x81", |
| 1074 | "\xF0\x9D\x9A\xB9" => "\xCE\xB8", |
| 1075 | "\xF0\x9D\x9A\xBA" => "\xCF\x83", |
| 1076 | "\xF0\x9D\x9A\xBB" => "\xCF\x84", |
| 1077 | "\xF0\x9D\x9A\xBC" => "\xCF\x85", |
| 1078 | "\xF0\x9D\x9A\xBD" => "\xCF\x86", |
| 1079 | "\xF0\x9D\x9A\xBE" => "\xCF\x87", |
| 1080 | "\xF0\x9D\x9A\xBF" => "\xCF\x88", |
| 1081 | "\xF0\x9D\x9B\x80" => "\xCF\x89", |
| 1082 | "\xF0\x9D\x9B\x93" => "\xCF\x83", |
| 1083 | "\xF0\x9D\x9B\xA2" => "\xCE\xB1", |
| 1084 | "\xF0\x9D\x9B\xA3" => "\xCE\xB2", |
| 1085 | "\xF0\x9D\x9B\xA4" => "\xCE\xB3", |
| 1086 | "\xF0\x9D\x9B\xA5" => "\xCE\xB4", |
| 1087 | "\xF0\x9D\x9B\xA6" => "\xCE\xB5", |
| 1088 | "\xF0\x9D\x9B\xA7" => "\xCE\xB6", |
| 1089 | "\xF0\x9D\x9B\xA8" => "\xCE\xB7", |
| 1090 | "\xF0\x9D\x9B\xA9" => "\xCE\xB8", |
| 1091 | "\xF0\x9D\x9B\xAA" => "\xCE\xB9", |
| 1092 | "\xF0\x9D\x9B\xAB" => "\xCE\xBA", |
| 1093 | "\xF0\x9D\x9B\xAC" => "\xCE\xBB", |
| 1094 | "\xF0\x9D\x9B\xAD" => "\xCE\xBC", |
| 1095 | "\xF0\x9D\x9B\xAE" => "\xCE\xBD", |
| 1096 | "\xF0\x9D\x9B\xAF" => "\xCE\xBE", |
| 1097 | "\xF0\x9D\x9B\xB0" => "\xCE\xBF", |
| 1098 | "\xF0\x9D\x9B\xB1" => "\xCF\x80", |
| 1099 | "\xF0\x9D\x9B\xB2" => "\xCF\x81", |
| 1100 | "\xF0\x9D\x9B\xB3" => "\xCE\xB8", |
| 1101 | "\xF0\x9D\x9B\xB4" => "\xCF\x83", |
| 1102 | "\xF0\x9D\x9B\xB5" => "\xCF\x84", |
| 1103 | "\xF0\x9D\x9B\xB6" => "\xCF\x85", |
| 1104 | "\xF0\x9D\x9B\xB7" => "\xCF\x86", |
| 1105 | "\xF0\x9D\x9B\xB8" => "\xCF\x87", |
| 1106 | "\xF0\x9D\x9B\xB9" => "\xCF\x88", |
| 1107 | "\xF0\x9D\x9B\xBA" => "\xCF\x89", |
| 1108 | "\xF0\x9D\x9C\x8D" => "\xCF\x83", |
| 1109 | "\xF0\x9D\x9C\x9C" => "\xCE\xB1", |
| 1110 | "\xF0\x9D\x9C\x9D" => "\xCE\xB2", |
| 1111 | "\xF0\x9D\x9C\x9E" => "\xCE\xB3", |
| 1112 | "\xF0\x9D\x9C\x9F" => "\xCE\xB4", |
| 1113 | "\xF0\x9D\x9C\xA0" => "\xCE\xB5", |
| 1114 | "\xF0\x9D\x9C\xA1" => "\xCE\xB6", |
| 1115 | "\xF0\x9D\x9C\xA2" => "\xCE\xB7", |
| 1116 | "\xF0\x9D\x9C\xA3" => "\xCE\xB8", |
| 1117 | "\xF0\x9D\x9C\xA4" => "\xCE\xB9", |
| 1118 | "\xF0\x9D\x9C\xA5" => "\xCE\xBA", |
| 1119 | "\xF0\x9D\x9C\xA6" => "\xCE\xBB", |
| 1120 | "\xF0\x9D\x9C\xA7" => "\xCE\xBC", |
| 1121 | "\xF0\x9D\x9C\xA8" => "\xCE\xBD", |
| 1122 | "\xF0\x9D\x9C\xA9" => "\xCE\xBE", |
| 1123 | "\xF0\x9D\x9C\xAA" => "\xCE\xBF", |
| 1124 | "\xF0\x9D\x9C\xAB" => "\xCF\x80", |
| 1125 | "\xF0\x9D\x9C\xAC" => "\xCF\x81", |
| 1126 | "\xF0\x9D\x9C\xAD" => "\xCE\xB8", |
| 1127 | "\xF0\x9D\x9C\xAE" => "\xCF\x83", |
| 1128 | "\xF0\x9D\x9C\xAF" => "\xCF\x84", |
| 1129 | "\xF0\x9D\x9C\xB0" => "\xCF\x85", |
| 1130 | "\xF0\x9D\x9C\xB1" => "\xCF\x86", |
| 1131 | "\xF0\x9D\x9C\xB2" => "\xCF\x87", |
| 1132 | "\xF0\x9D\x9C\xB3" => "\xCF\x88", |
| 1133 | "\xF0\x9D\x9C\xB4" => "\xCF\x89", |
| 1134 | "\xF0\x9D\x9D\x87" => "\xCF\x83", |
| 1135 | "\xF0\x9D\x9D\x96" => "\xCE\xB1", |
| 1136 | "\xF0\x9D\x9D\x97" => "\xCE\xB2", |
| 1137 | "\xF0\x9D\x9D\x98" => "\xCE\xB3", |
| 1138 | "\xF0\x9D\x9D\x99" => "\xCE\xB4", |
| 1139 | "\xF0\x9D\x9D\x9A" => "\xCE\xB5", |
| 1140 | "\xF0\x9D\x9D\x9B" => "\xCE\xB6", |
| 1141 | "\xF0\x9D\x9D\x9C" => "\xCE\xB7", |
| 1142 | "\xF0\x9D\x9D\x9D" => "\xCE\xB8", |
| 1143 | "\xF0\x9D\x9D\x9E" => "\xCE\xB9", |
| 1144 | "\xF0\x9D\x9D\x9F" => "\xCE\xBA", |
| 1145 | "\xF0\x9D\x9D\xA0" => "\xCE\xBB", |
| 1146 | "\xF0\x9D\x9D\xA1" => "\xCE\xBC", |
| 1147 | "\xF0\x9D\x9D\xA2" => "\xCE\xBD", |
| 1148 | "\xF0\x9D\x9D\xA3" => "\xCE\xBE", |
| 1149 | "\xF0\x9D\x9D\xA4" => "\xCE\xBF", |
| 1150 | "\xF0\x9D\x9D\xA5" => "\xCF\x80", |
| 1151 | "\xF0\x9D\x9D\xA6" => "\xCF\x81", |
| 1152 | "\xF0\x9D\x9D\xA7" => "\xCE\xB8", |
| 1153 | "\xF0\x9D\x9D\xA8" => "\xCF\x83", |
| 1154 | "\xF0\x9D\x9D\xA9" => "\xCF\x84", |
| 1155 | "\xF0\x9D\x9D\xAA" => "\xCF\x85", |
| 1156 | "\xF0\x9D\x9D\xAB" => "\xCF\x86", |
| 1157 | "\xF0\x9D\x9D\xAC" => "\xCF\x87", |
| 1158 | "\xF0\x9D\x9D\xAD" => "\xCF\x88", |
| 1159 | "\xF0\x9D\x9D\xAE" => "\xCF\x89", |
| 1160 | "\xF0\x9D\x9E\x81" => "\xCF\x83", |
| 1161 | "\xF0\x9D\x9E\x90" => "\xCE\xB1", |
| 1162 | "\xF0\x9D\x9E\x91" => "\xCE\xB2", |
| 1163 | "\xF0\x9D\x9E\x92" => "\xCE\xB3", |
| 1164 | "\xF0\x9D\x9E\x93" => "\xCE\xB4", |
| 1165 | "\xF0\x9D\x9E\x94" => "\xCE\xB5", |
| 1166 | "\xF0\x9D\x9E\x95" => "\xCE\xB6", |
| 1167 | "\xF0\x9D\x9E\x96" => "\xCE\xB7", |
| 1168 | "\xF0\x9D\x9E\x97" => "\xCE\xB8", |
| 1169 | "\xF0\x9D\x9E\x98" => "\xCE\xB9", |
| 1170 | "\xF0\x9D\x9E\x99" => "\xCE\xBA", |
| 1171 | "\xF0\x9D\x9E\x9A" => "\xCE\xBB", |
| 1172 | "\xF0\x9D\x9E\x9B" => "\xCE\xBC", |
| 1173 | "\xF0\x9D\x9E\x9C" => "\xCE\xBD", |
| 1174 | "\xF0\x9D\x9E\x9D" => "\xCE\xBE", |
| 1175 | "\xF0\x9D\x9E\x9E" => "\xCE\xBF", |
| 1176 | "\xF0\x9D\x9E\x9F" => "\xCF\x80", |
| 1177 | "\xF0\x9D\x9E\xA0" => "\xCF\x81", |
| 1178 | "\xF0\x9D\x9E\xA1" => "\xCE\xB8", |
| 1179 | "\xF0\x9D\x9E\xA2" => "\xCF\x83", |
| 1180 | "\xF0\x9D\x9E\xA3" => "\xCF\x84", |
| 1181 | "\xF0\x9D\x9E\xA4" => "\xCF\x85", |
| 1182 | "\xF0\x9D\x9E\xA5" => "\xCF\x86", |
| 1183 | "\xF0\x9D\x9E\xA6" => "\xCF\x87", |
| 1184 | "\xF0\x9D\x9E\xA7" => "\xCF\x88", |
| 1185 | "\xF0\x9D\x9E\xA8" => "\xCF\x89", |
| 1186 | "\xF0\x9D\x9E\xBB" => "\xCF\x83", |
| 1187 | "\xF0\x9D\x9F\x8A" => "\xCF\x9D", |
| 1188 | ); |
| 1189 | |
| 1190 | // do the case fold |
| 1191 | $text = utf8_case_fold($text, $option); |
| 1192 | |
| 1193 | // convert to NFKC |
| 1194 | Normalizer::normalize($text, Normalizer::NFKC); |
| 1195 | |
| 1196 | // FC_NFKC_Closure, http://www.unicode.org/Public/5.0.0/ucd/DerivedNormalizationProps.txt |
| 1197 | $text = strtr($text, $fc_nfkc_closure); |
| 1198 | |
| 1199 | return $text; |
| 1200 | } |
| 1201 | |
| 1202 | /** |
| 1203 | * Assume the input is NFC: |
| 1204 | * Takes the input and does a "special" case fold. It does minor normalization as well. |
| 1205 | * |
| 1206 | * @param string $text text to be case folded |
| 1207 | * @param string $option determines how we will fold the cases |
| 1208 | * @return string case folded text |
| 1209 | */ |
| 1210 | function utf8_case_fold_nfc($text, $option = 'full') |
| 1211 | { |
| 1212 | static $uniarray = array(); |
| 1213 | static $ypogegrammeni = array( |
| 1214 | "\xCD\xBA" => "\x20\xCD\x85", |
| 1215 | "\xE1\xBE\x80" => "\xE1\xBC\x80\xCD\x85", |
| 1216 | "\xE1\xBE\x81" => "\xE1\xBC\x81\xCD\x85", |
| 1217 | "\xE1\xBE\x82" => "\xE1\xBC\x82\xCD\x85", |
| 1218 | "\xE1\xBE\x83" => "\xE1\xBC\x83\xCD\x85", |
| 1219 | "\xE1\xBE\x84" => "\xE1\xBC\x84\xCD\x85", |
| 1220 | "\xE1\xBE\x85" => "\xE1\xBC\x85\xCD\x85", |
| 1221 | "\xE1\xBE\x86" => "\xE1\xBC\x86\xCD\x85", |
| 1222 | "\xE1\xBE\x87" => "\xE1\xBC\x87\xCD\x85", |
| 1223 | "\xE1\xBE\x88" => "\xE1\xBC\x88\xCD\x85", |
| 1224 | "\xE1\xBE\x89" => "\xE1\xBC\x89\xCD\x85", |
| 1225 | "\xE1\xBE\x8A" => "\xE1\xBC\x8A\xCD\x85", |
| 1226 | "\xE1\xBE\x8B" => "\xE1\xBC\x8B\xCD\x85", |
| 1227 | "\xE1\xBE\x8C" => "\xE1\xBC\x8C\xCD\x85", |
| 1228 | "\xE1\xBE\x8D" => "\xE1\xBC\x8D\xCD\x85", |
| 1229 | "\xE1\xBE\x8E" => "\xE1\xBC\x8E\xCD\x85", |
| 1230 | "\xE1\xBE\x8F" => "\xE1\xBC\x8F\xCD\x85", |
| 1231 | "\xE1\xBE\x90" => "\xE1\xBC\xA0\xCD\x85", |
| 1232 | "\xE1\xBE\x91" => "\xE1\xBC\xA1\xCD\x85", |
| 1233 | "\xE1\xBE\x92" => "\xE1\xBC\xA2\xCD\x85", |
| 1234 | "\xE1\xBE\x93" => "\xE1\xBC\xA3\xCD\x85", |
| 1235 | "\xE1\xBE\x94" => "\xE1\xBC\xA4\xCD\x85", |
| 1236 | "\xE1\xBE\x95" => "\xE1\xBC\xA5\xCD\x85", |
| 1237 | "\xE1\xBE\x96" => "\xE1\xBC\xA6\xCD\x85", |
| 1238 | "\xE1\xBE\x97" => "\xE1\xBC\xA7\xCD\x85", |
| 1239 | "\xE1\xBE\x98" => "\xE1\xBC\xA8\xCD\x85", |
| 1240 | "\xE1\xBE\x99" => "\xE1\xBC\xA9\xCD\x85", |
| 1241 | "\xE1\xBE\x9A" => "\xE1\xBC\xAA\xCD\x85", |
| 1242 | "\xE1\xBE\x9B" => "\xE1\xBC\xAB\xCD\x85", |
| 1243 | "\xE1\xBE\x9C" => "\xE1\xBC\xAC\xCD\x85", |
| 1244 | "\xE1\xBE\x9D" => "\xE1\xBC\xAD\xCD\x85", |
| 1245 | "\xE1\xBE\x9E" => "\xE1\xBC\xAE\xCD\x85", |
| 1246 | "\xE1\xBE\x9F" => "\xE1\xBC\xAF\xCD\x85", |
| 1247 | "\xE1\xBE\xA0" => "\xE1\xBD\xA0\xCD\x85", |
| 1248 | "\xE1\xBE\xA1" => "\xE1\xBD\xA1\xCD\x85", |
| 1249 | "\xE1\xBE\xA2" => "\xE1\xBD\xA2\xCD\x85", |
| 1250 | "\xE1\xBE\xA3" => "\xE1\xBD\xA3\xCD\x85", |
| 1251 | "\xE1\xBE\xA4" => "\xE1\xBD\xA4\xCD\x85", |
| 1252 | "\xE1\xBE\xA5" => "\xE1\xBD\xA5\xCD\x85", |
| 1253 | "\xE1\xBE\xA6" => "\xE1\xBD\xA6\xCD\x85", |
| 1254 | "\xE1\xBE\xA7" => "\xE1\xBD\xA7\xCD\x85", |
| 1255 | "\xE1\xBE\xA8" => "\xE1\xBD\xA8\xCD\x85", |
| 1256 | "\xE1\xBE\xA9" => "\xE1\xBD\xA9\xCD\x85", |
| 1257 | "\xE1\xBE\xAA" => "\xE1\xBD\xAA\xCD\x85", |
| 1258 | "\xE1\xBE\xAB" => "\xE1\xBD\xAB\xCD\x85", |
| 1259 | "\xE1\xBE\xAC" => "\xE1\xBD\xAC\xCD\x85", |
| 1260 | "\xE1\xBE\xAD" => "\xE1\xBD\xAD\xCD\x85", |
| 1261 | "\xE1\xBE\xAE" => "\xE1\xBD\xAE\xCD\x85", |
| 1262 | "\xE1\xBE\xAF" => "\xE1\xBD\xAF\xCD\x85", |
| 1263 | "\xE1\xBE\xB2" => "\xE1\xBD\xB0\xCD\x85", |
| 1264 | "\xE1\xBE\xB3" => "\xCE\xB1\xCD\x85", |
| 1265 | "\xE1\xBE\xB4" => "\xCE\xAC\xCD\x85", |
| 1266 | "\xE1\xBE\xB7" => "\xE1\xBE\xB6\xCD\x85", |
| 1267 | "\xE1\xBE\xBC" => "\xCE\x91\xCD\x85", |
| 1268 | "\xE1\xBF\x82" => "\xE1\xBD\xB4\xCD\x85", |
| 1269 | "\xE1\xBF\x83" => "\xCE\xB7\xCD\x85", |
| 1270 | "\xE1\xBF\x84" => "\xCE\xAE\xCD\x85", |
| 1271 | "\xE1\xBF\x87" => "\xE1\xBF\x86\xCD\x85", |
| 1272 | "\xE1\xBF\x8C" => "\xCE\x97\xCD\x85", |
| 1273 | "\xE1\xBF\xB2" => "\xE1\xBD\xBC\xCD\x85", |
| 1274 | "\xE1\xBF\xB3" => "\xCF\x89\xCD\x85", |
| 1275 | "\xE1\xBF\xB4" => "\xCF\x8E\xCD\x85", |
| 1276 | "\xE1\xBF\xB7" => "\xE1\xBF\xB6\xCD\x85", |
| 1277 | "\xE1\xBF\xBC" => "\xCE\xA9\xCD\x85", |
| 1278 | ); |
| 1279 | |
| 1280 | // perform a small trick, avoid further normalization on composed points that contain U+0345 in their decomposition |
| 1281 | $text = strtr($text, $ypogegrammeni); |
| 1282 | |
| 1283 | // do the case fold |
| 1284 | $text = utf8_case_fold($text, $option); |
| 1285 | |
| 1286 | return $text; |
| 1287 | } |
| 1288 | |
| 1289 | /** |
| 1290 | * wrapper around PHP's native normalizer from intl |
| 1291 | * previously a PECL extension, included in the core since PHP 5.3.0 |
| 1292 | * http://php.net/manual/en/normalizer.normalize.php |
| 1293 | * |
| 1294 | * @param mixed $strings a string or an array of strings to normalize |
| 1295 | * @return mixed the normalized content, preserving array keys if array given. |
| 1296 | */ |
| 1297 | function utf8_normalize_nfc($strings) |
| 1298 | { |
| 1299 | if (empty($strings)) |
| 1300 | { |
| 1301 | return $strings; |
| 1302 | } |
| 1303 | |
| 1304 | if (!is_array($strings)) |
| 1305 | { |
| 1306 | if (Normalizer::isNormalized($strings)) |
| 1307 | { |
| 1308 | return $strings; |
| 1309 | } |
| 1310 | return (string) Normalizer::normalize($strings); |
| 1311 | } |
| 1312 | else |
| 1313 | { |
| 1314 | foreach ($strings as $key => $string) |
| 1315 | { |
| 1316 | if (is_array($string)) |
| 1317 | { |
| 1318 | foreach ($string as $_key => $_string) |
| 1319 | { |
| 1320 | if (Normalizer::isNormalized($strings[$key][$_key])) |
| 1321 | { |
| 1322 | continue; |
| 1323 | } |
| 1324 | $strings[$key][$_key] = (string) Normalizer::normalize($strings[$key][$_key]); |
| 1325 | } |
| 1326 | } |
| 1327 | else |
| 1328 | { |
| 1329 | if (Normalizer::isNormalized($strings[$key])) |
| 1330 | { |
| 1331 | continue; |
| 1332 | } |
| 1333 | $strings[$key] = (string) Normalizer::normalize($strings[$key]); |
| 1334 | } |
| 1335 | } |
| 1336 | } |
| 1337 | |
| 1338 | return $strings; |
| 1339 | } |
| 1340 | |
| 1341 | /** |
| 1342 | * This function is used to generate a "clean" version of a string. |
| 1343 | * Clean means that it is a case insensitive form (case folding) and that it is normalized (NFC). |
| 1344 | * Additionally a homographs of one character are transformed into one specific character (preferably ASCII |
| 1345 | * if it is an ASCII character). |
| 1346 | * |
| 1347 | * Please be aware that if you change something within this function or within |
| 1348 | * functions used here you need to rebuild/update the username_clean column in the users table. And all other |
| 1349 | * columns that store a clean string otherwise you will break this functionality. |
| 1350 | * |
| 1351 | * @param string $text An unclean string, mabye user input (has to be valid UTF-8!) |
| 1352 | * @return string Cleaned up version of the input string |
| 1353 | */ |
| 1354 | function utf8_clean_string($text) |
| 1355 | { |
| 1356 | global $phpbb_root_path, $phpEx; |
| 1357 | |
| 1358 | static $homographs = array(); |
| 1359 | if (empty($homographs)) |
| 1360 | { |
| 1361 | $homographs = include($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx); |
| 1362 | } |
| 1363 | |
| 1364 | $text = utf8_case_fold_nfkc($text); |
| 1365 | $text = strtr($text, $homographs); |
| 1366 | // Other control characters |
| 1367 | $text = preg_replace('#(?:[\x00-\x1F\x7F]+|(?:\xC2[\x80-\x9F])+)#', '', $text); |
| 1368 | |
| 1369 | // we need to reduce multiple spaces to a single one |
| 1370 | $text = preg_replace('# {2,}#', ' ', $text); |
| 1371 | |
| 1372 | // we can use trim here as all the other space characters should have been turned |
| 1373 | // into normal ASCII spaces by now |
| 1374 | return trim($text); |
| 1375 | } |
| 1376 | |
| 1377 | /** |
| 1378 | * A wrapper for htmlspecialchars($value, ENT_COMPAT, 'UTF-8') |
| 1379 | */ |
| 1380 | function utf8_htmlspecialchars($value) |
| 1381 | { |
| 1382 | return htmlspecialchars($value, ENT_COMPAT, 'UTF-8'); |
| 1383 | } |
| 1384 | |
| 1385 | /** |
| 1386 | * Trying to convert returned system message to utf8 |
| 1387 | * |
| 1388 | * PHP assumes such messages are ISO-8859-1 so we'll do that too |
| 1389 | * and if it breaks messages we'll blame it on them ;-) |
| 1390 | */ |
| 1391 | function utf8_convert_message($message) |
| 1392 | { |
| 1393 | // First of all check if conversion is neded at all, as there is no point |
| 1394 | // in converting ASCII messages from ISO-8859-1 to UTF-8 |
| 1395 | if (!preg_match('/[\x80-\xFF]/', $message)) |
| 1396 | { |
| 1397 | return utf8_htmlspecialchars($message); |
| 1398 | } |
| 1399 | |
| 1400 | // else we need to convert some part of the message |
| 1401 | return utf8_htmlspecialchars(utf8_recode($message, 'ISO-8859-1')); |
| 1402 | } |
| 1403 | |
| 1404 | /** |
| 1405 | * UTF8-compatible wordwrap replacement |
| 1406 | * |
| 1407 | * @param string $string The input string |
| 1408 | * @param int $width The column width. Defaults to 75. |
| 1409 | * @param string $break The line is broken using the optional break parameter. Defaults to '\n'. |
| 1410 | * @param bool $cut If the cut is set to TRUE, the string is always wrapped at the specified width. So if you have a word that is larger than the given width, it is broken apart. |
| 1411 | * |
| 1412 | * @return string the given string wrapped at the specified column. |
| 1413 | * |
| 1414 | */ |
| 1415 | function utf8_wordwrap($string, $width = 75, $break = "\n", $cut = false) |
| 1416 | { |
| 1417 | // We first need to explode on $break, not destroying existing (intended) breaks |
| 1418 | $lines = explode($break, $string); |
| 1419 | $new_lines = array(0 => ''); |
| 1420 | $index = 0; |
| 1421 | |
| 1422 | foreach ($lines as $line) |
| 1423 | { |
| 1424 | $words = explode(' ', $line); |
| 1425 | |
| 1426 | for ($i = 0, $size = count($words); $i < $size; $i++) |
| 1427 | { |
| 1428 | $word = $words[$i]; |
| 1429 | |
| 1430 | // If cut is true we need to cut the word if it is > width chars |
| 1431 | if ($cut && utf8_strlen($word) > $width) |
| 1432 | { |
| 1433 | $words[$i] = utf8_substr($word, $width); |
| 1434 | $word = utf8_substr($word, 0, $width); |
| 1435 | $i--; |
| 1436 | } |
| 1437 | |
| 1438 | if (utf8_strlen($new_lines[$index] . $word) > $width) |
| 1439 | { |
| 1440 | $new_lines[$index] = substr($new_lines[$index], 0, -1); |
| 1441 | $index++; |
| 1442 | $new_lines[$index] = ''; |
| 1443 | } |
| 1444 | |
| 1445 | $new_lines[$index] .= $word . ' '; |
| 1446 | } |
| 1447 | |
| 1448 | $new_lines[$index] = substr($new_lines[$index], 0, -1); |
| 1449 | $index++; |
| 1450 | $new_lines[$index] = ''; |
| 1451 | } |
| 1452 | |
| 1453 | unset($new_lines[$index]); |
| 1454 | return implode($break, $new_lines); |
| 1455 | } |
| 1456 | |
| 1457 | /** |
| 1458 | * UTF8-safe basename() function |
| 1459 | * |
| 1460 | * basename() has some limitations and is dependent on the locale setting |
| 1461 | * according to the PHP manual. Therefore we provide our own locale independent |
| 1462 | * basename function. |
| 1463 | * |
| 1464 | * @param string $filename The filename basename() should be applied to |
| 1465 | * @return string The basenamed filename |
| 1466 | */ |
| 1467 | function utf8_basename($filename): string |
| 1468 | { |
| 1469 | if (!$filename) |
| 1470 | { |
| 1471 | return ''; |
| 1472 | } |
| 1473 | |
| 1474 | // We always check for forward slash AND backward slash |
| 1475 | // because they could be mixed or "sneaked" in. ;) |
| 1476 | // You know, never trust user input... |
| 1477 | if (str_contains($filename, '/')) |
| 1478 | { |
| 1479 | $filename = utf8_substr($filename, utf8_strrpos($filename, '/') + 1); |
| 1480 | } |
| 1481 | |
| 1482 | if (str_contains($filename, '\\')) |
| 1483 | { |
| 1484 | $filename = utf8_substr($filename, utf8_strrpos($filename, '\\') + 1); |
| 1485 | } |
| 1486 | |
| 1487 | return $filename; |
| 1488 | } |