Verzeichnisstruktur phpBB-3.2.0
- Veröffentlicht
- 06.01.2017
So funktioniert es
|
|
Auf das letzte Element klicken. Dies geht jeweils ein Schritt zurück |
Auf das Icon klicken, dies öffnet das Verzeichnis. Nochmal klicken schließt das Verzeichnis. |
|
|
(Beispiel Datei-Icons)
|
Auf das Icon klicken um den Quellcode anzuzeigen |
utf_tools.php
0001 <?php
0002 /**
0003 *
0004 * This file is part of the phpBB Forum Software package.
0005 *
0006 * @copyright (c) phpBB Limited <https://www.phpbb.com>
0007 * @license GNU General Public License, version 2 (GPL-2.0)
0008 *
0009 * For full copyright and license information, please see
0010 * the docs/CREDITS.txt file.
0011 *
0012 */
0013
0014 /**
0015 */
0016 if (!defined('IN_PHPBB'))
0017 {
0018 exit;
0019 }
0020
0021 // Enforce ASCII only string handling
0022 setlocale(LC_CTYPE, 'C');
0023
0024 /**
0025 * Setup the UTF-8 portability layer
0026 */
0027 Patchwork\Utf8\Bootup::initUtf8Encode();
0028 Patchwork\Utf8\Bootup::initMbstring();
0029 Patchwork\Utf8\Bootup::initIntl();
0030
0031 /**
0032 * UTF-8 tools
0033 *
0034 * Whenever possible, these functions will try to use PHP's built-in functions or
0035 * extensions, otherwise they will default to custom routines.
0036 *
0037 */
0038
0039 /**
0040 * UTF-8 aware alternative to strrpos
0041 * @ignore
0042 */
0043 function utf8_strrpos($str, $needle, $offset = null)
0044 {
0045 // Emulate behaviour of strrpos rather than raising warning
0046 if (empty($str))
0047 {
0048 return false;
0049 }
0050
0051 if (is_null($offset))
0052 {
0053 return mb_strrpos($str, $needle);
0054 }
0055 else
0056 {
0057 return mb_strrpos($str, $needle, $offset);
0058 }
0059 }
0060
0061 /**
0062 * UTF-8 aware alternative to strpos
0063 * @ignore
0064 */
0065 function utf8_strpos($str, $needle, $offset = null)
0066 {
0067 if (is_null($offset))
0068 {
0069 return mb_strpos($str, $needle);
0070 }
0071 else
0072 {
0073 return mb_strpos($str, $needle, $offset);
0074 }
0075 }
0076
0077 /**
0078 * UTF-8 aware alternative to strtolower
0079 * @ignore
0080 */
0081 function utf8_strtolower($str)
0082 {
0083 return mb_strtolower($str);
0084 }
0085
0086 /**
0087 * UTF-8 aware alternative to strtoupper
0088 * @ignore
0089 */
0090 function utf8_strtoupper($str)
0091 {
0092 return mb_strtoupper($str);
0093 }
0094
0095 /**
0096 * UTF-8 aware alternative to substr
0097 * @ignore
0098 */
0099 function utf8_substr($str, $offset, $length = null)
0100 {
0101 if (is_null($length))
0102 {
0103 return mb_substr($str, $offset);
0104 }
0105 else
0106 {
0107 return mb_substr($str, $offset, $length);
0108 }
0109 }
0110
0111 /**
0112 * Return the length (in characters) of a UTF-8 string
0113 * @ignore
0114 */
0115 function utf8_strlen($text)
0116 {
0117 return mb_strlen($text, 'utf-8');
0118 }
0119
0120 /**
0121 * UTF-8 aware alternative to str_split
0122 * Convert a string to an array
0123 *
0124 * @author Harry Fuecks
0125 * @param string $str UTF-8 encoded
0126 * @param int $split_len number to characters to split string by
0127 * @return array characters in string reverses
0128 */
0129 function utf8_str_split($str, $split_len = 1)
0130 {
0131 if (!is_int($split_len) || $split_len < 1)
0132 {
0133 return false;
0134 }
0135
0136 $len = utf8_strlen($str);
0137 if ($len <= $split_len)
0138 {
0139 return array($str);
0140 }
0141
0142 preg_match_all('/.{' . $split_len . '}|[^\x00]{1,' . $split_len . '}$/us', $str, $ar);
0143 return $ar[0];
0144 }
0145
0146 /**
0147 * UTF-8 aware alternative to strspn
0148 * Find length of initial segment matching the mask
0149 *
0150 * @author Harry Fuecks
0151 */
0152 function utf8_strspn($str, $mask, $start = null, $length = null)
0153 {
0154 if ($start !== null || $length !== null)
0155 {
0156 $str = utf8_substr($str, $start, $length);
0157 }
0158
0159 preg_match('/^[' . $mask . ']+/u', $str, $matches);
0160
0161 if (isset($matches[0]))
0162 {
0163 return utf8_strlen($matches[0]);
0164 }
0165
0166 return 0;
0167 }
0168
0169 /**
0170 * UTF-8 aware alternative to ucfirst
0171 * Make a string's first character uppercase
0172 *
0173 * @author Harry Fuecks
0174 * @param string
0175 * @return string with first character as upper case (if applicable)
0176 */
0177 function utf8_ucfirst($str)
0178 {
0179 switch (utf8_strlen($str))
0180 {
0181 case 0:
0182 return '';
0183 break;
0184
0185 case 1:
0186 return utf8_strtoupper($str);
0187 break;
0188
0189 default:
0190 preg_match('/^(.{1})(.*)$/us', $str, $matches);
0191 return utf8_strtoupper($matches[1]) . $matches[2];
0192 break;
0193 }
0194 }
0195
0196 /**
0197 * Recode a string to UTF-8
0198 *
0199 * If the encoding is not supported, the string is returned as-is
0200 *
0201 * @param string $string Original string
0202 * @param string $encoding Original encoding (lowered)
0203 * @return string The string, encoded in UTF-8
0204 */
0205 function utf8_recode($string, $encoding)
0206 {
0207 $encoding = strtolower($encoding);
0208
0209 if ($encoding == 'utf-8' || !is_string($string) || empty($string))
0210 {
0211 return $string;
0212 }
0213
0214 // we force iso-8859-1 to be cp1252
0215 if ($encoding == 'iso-8859-1')
0216 {
0217 $encoding = 'cp1252';
0218 }
0219 // convert iso-8859-8-i to iso-8859-8
0220 else if ($encoding == 'iso-8859-8-i')
0221 {
0222 $encoding = 'iso-8859-8';
0223 $string = hebrev($string);
0224 }
0225
0226 // First, try iconv()
0227 if (function_exists('iconv'))
0228 {
0229 $ret = @iconv($encoding, 'utf-8', $string);
0230
0231 if (!empty($ret))
0232 {
0233 return $ret;
0234 }
0235 }
0236
0237 // Try the mb_string extension
0238 if (function_exists('mb_convert_encoding'))
0239 {
0240 // mbstring is nasty on PHP4, we must make *sure* that we send a good encoding
0241 switch ($encoding)
0242 {
0243 case 'iso-8859-1':
0244 case 'iso-8859-2':
0245 case 'iso-8859-4':
0246 case 'iso-8859-7':
0247 case 'iso-8859-9':
0248 case 'iso-8859-15':
0249 case 'windows-1251':
0250 case 'windows-1252':
0251 case 'cp1252':
0252 case 'shift_jis':
0253 case 'euc-kr':
0254 case 'big5':
0255 case 'gb2312':
0256 $ret = @mb_convert_encoding($string, 'utf-8', $encoding);
0257
0258 if (!empty($ret))
0259 {
0260 return $ret;
0261 }
0262 }
0263 }
0264
0265 // Try the recode extension
0266 if (function_exists('recode_string'))
0267 {
0268 $ret = @recode_string($encoding . '..utf-8', $string);
0269
0270 if (!empty($ret))
0271 {
0272 return $ret;
0273 }
0274 }
0275
0276 // If nothing works, check if we have a custom transcoder available
0277 if (!preg_match('#^[a-z0-9_ \\-]+$#', $encoding))
0278 {
0279 // Make sure the encoding name is alphanumeric, we don't want it to be abused into loading arbitrary files
0280 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
0281 }
0282
0283 global $phpbb_root_path, $phpEx;
0284
0285 // iso-8859-* character encoding
0286 if (preg_match('/iso[_ -]?8859[_ -]?(\\d+)/', $encoding, $array))
0287 {
0288 switch ($array[1])
0289 {
0290 case '1':
0291 case '2':
0292 case '4':
0293 case '7':
0294 case '8':
0295 case '9':
0296 case '15':
0297 if (!function_exists('iso_8859_' . $array[1]))
0298 {
0299 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
0300 {
0301 trigger_error('Basic reencoder file is missing', E_USER_ERROR);
0302 }
0303 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
0304 }
0305 return call_user_func('iso_8859_' . $array[1], $string);
0306 break;
0307
0308 default:
0309 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
0310 break;
0311 }
0312 }
0313
0314 // CP/WIN character encoding
0315 if (preg_match('/(?:cp|windows)[_\- ]?(\\d+)/', $encoding, $array))
0316 {
0317 switch ($array[1])
0318 {
0319 case '932':
0320 break;
0321 case '1250':
0322 case '1251':
0323 case '1252':
0324 case '1254':
0325 case '1255':
0326 case '1256':
0327 case '1257':
0328 case '874':
0329 if (!function_exists('cp' . $array[1]))
0330 {
0331 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
0332 {
0333 trigger_error('Basic reencoder file is missing', E_USER_ERROR);
0334 }
0335 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
0336 }
0337 return call_user_func('cp' . $array[1], $string);
0338 break;
0339
0340 default:
0341 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
0342 break;
0343 }
0344 }
0345
0346 // TIS-620
0347 if (preg_match('/tis[_ -]?620/', $encoding))
0348 {
0349 if (!function_exists('tis_620'))
0350 {
0351 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx))
0352 {
0353 trigger_error('Basic reencoder file is missing', E_USER_ERROR);
0354 }
0355 include($phpbb_root_path . 'includes/utf/data/recode_basic.' . $phpEx);
0356 }
0357 return tis_620($string);
0358 }
0359
0360 // SJIS
0361 if (preg_match('/sjis(?:[_ -]?win)?|(?:cp|ibm)[_ -]?932|shift[_ -]?jis/', $encoding))
0362 {
0363 if (!function_exists('sjis'))
0364 {
0365 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
0366 {
0367 trigger_error('CJK reencoder file is missing', E_USER_ERROR);
0368 }
0369 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
0370 }
0371 return sjis($string);
0372 }
0373
0374 // EUC_KR
0375 if (preg_match('/euc[_ -]?kr/', $encoding))
0376 {
0377 if (!function_exists('euc_kr'))
0378 {
0379 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
0380 {
0381 trigger_error('CJK reencoder file is missing', E_USER_ERROR);
0382 }
0383 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
0384 }
0385 return euc_kr($string);
0386 }
0387
0388 // BIG-5
0389 if (preg_match('/big[_ -]?5/', $encoding))
0390 {
0391 if (!function_exists('big5'))
0392 {
0393 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
0394 {
0395 trigger_error('CJK reencoder file is missing', E_USER_ERROR);
0396 }
0397 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
0398 }
0399 return big5($string);
0400 }
0401
0402 // GB2312
0403 if (preg_match('/gb[_ -]?2312/', $encoding))
0404 {
0405 if (!function_exists('gb2312'))
0406 {
0407 if (!file_exists($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx))
0408 {
0409 trigger_error('CJK reencoder file is missing', E_USER_ERROR);
0410 }
0411 include($phpbb_root_path . 'includes/utf/data/recode_cjk.' . $phpEx);
0412 }
0413 return gb2312($string);
0414 }
0415
0416 // Trigger an error?! Fow now just give bad data :-(
0417 trigger_error('Unknown encoding: ' . $encoding, E_USER_ERROR);
0418 }
0419
0420 /**
0421 * Replace all UTF-8 chars that are not in ASCII with their NCR
0422 *
0423 * @param string $text UTF-8 string in NFC
0424 * @return string ASCII string using NCRs for non-ASCII chars
0425 */
0426 function utf8_encode_ncr($text)
0427 {
0428 return preg_replace_callback('#[\\xC2-\\xF4][\\x80-\\xBF]{1,3}#', 'utf8_encode_ncr_callback', $text);
0429 }
0430
0431 /**
0432 * Callback used in encode_ncr()
0433 *
0434 * Takes a UTF-8 char and replaces it with its NCR. Attention, $m is an array
0435 *
0436 * @param array $m 0-based numerically indexed array passed by preg_replace_callback()
0437 * @return string A HTML NCR if the character is valid, or the original string otherwise
0438 */
0439 function utf8_encode_ncr_callback($m)
0440 {
0441 return '&#' . utf8_ord($m[0]) . ';';
0442 }
0443
0444 /**
0445 * Converts a UTF-8 char to an NCR
0446 *
0447 * @param string $chr UTF-8 char
0448 * @return integer UNICODE code point
0449 */
0450 function utf8_ord($chr)
0451 {
0452 switch (strlen($chr))
0453 {
0454 case 1:
0455 return ord($chr);
0456 break;
0457
0458 case 2:
0459 return ((ord($chr[0]) & 0x1F) << 6) | (ord($chr[1]) & 0x3F);
0460 break;
0461
0462 case 3:
0463 return ((ord($chr[0]) & 0x0F) << 12) | ((ord($chr[1]) & 0x3F) << 6) | (ord($chr[2]) & 0x3F);
0464 break;
0465
0466 case 4:
0467 return ((ord($chr[0]) & 0x07) << 18) | ((ord($chr[1]) & 0x3F) << 12) | ((ord($chr[2]) & 0x3F) << 6) | (ord($chr[3]) & 0x3F);
0468 break;
0469
0470 default:
0471 return $chr;
0472 }
0473 }
0474
0475 /**
0476 * Converts an NCR to a UTF-8 char
0477 *
0478 * @param int $cp UNICODE code point
0479 * @return string UTF-8 char
0480 */
0481 function utf8_chr($cp)
0482 {
0483 if ($cp > 0xFFFF)
0484 {
0485 return chr(0xF0 | ($cp >> 18)) . chr(0x80 | (($cp >> 12) & 0x3F)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F));
0486 }
0487 else if ($cp > 0x7FF)
0488 {
0489 return chr(0xE0 | ($cp >> 12)) . chr(0x80 | (($cp >> 6) & 0x3F)) . chr(0x80 | ($cp & 0x3F));
0490 }
0491 else if ($cp > 0x7F)
0492 {
0493 return chr(0xC0 | ($cp >> 6)) . chr(0x80 | ($cp & 0x3F));
0494 }
0495 else
0496 {
0497 return chr($cp);
0498 }
0499 }
0500
0501 /**
0502 * Convert Numeric Character References to UTF-8 chars
0503 *
0504 * Notes:
0505 * - we do not convert NCRs recursively, if you pass &#38; it will return &
0506 * - we DO NOT check for the existence of the Unicode characters, therefore an entity may be converted to an inexistent codepoint
0507 *
0508 * @param string $text String to convert, encoded in UTF-8 (no normal form required)
0509 * @return string UTF-8 string where NCRs have been replaced with the actual chars
0510 */
0511 function utf8_decode_ncr($text)
0512 {
0513 return preg_replace_callback('/&#([0-9]{1,6}|x[0-9A-F]{1,5});/i', 'utf8_decode_ncr_callback', $text);
0514 }
0515
0516 /**
0517 * Callback used in decode_ncr()
0518 *
0519 * Takes a NCR (in decimal or hexadecimal) and returns a UTF-8 char. Attention, $m is an array.
0520 * It will ignore most of invalid NCRs, but not all!
0521 *
0522 * @param array $m 0-based numerically indexed array passed by preg_replace_callback()
0523 * @return string UTF-8 char
0524 */
0525 function utf8_decode_ncr_callback($m)
0526 {
0527 $cp = (strncasecmp($m[1], 'x', 1)) ? $m[1] : hexdec(substr($m[1], 1));
0528
0529 return utf8_chr($cp);
0530 }
0531
0532 /**
0533 * Case folds a unicode string as per Unicode 5.0, section 3.13
0534 *
0535 * @param string $text text to be case folded
0536 * @param string $option determines how we will fold the cases
0537 * @return string case folded text
0538 */
0539 function utf8_case_fold($text, $option = 'full')
0540 {
0541 static $uniarray = array();
0542 global $phpbb_root_path, $phpEx;
0543
0544 // common is always set
0545 if (!isset($uniarray['c']))
0546 {
0547 $uniarray['c'] = include($phpbb_root_path . 'includes/utf/data/case_fold_c.' . $phpEx);
0548 }
0549
0550 // only set full if we need to
0551 if ($option === 'full' && !isset($uniarray['f']))
0552 {
0553 $uniarray['f'] = include($phpbb_root_path . 'includes/utf/data/case_fold_f.' . $phpEx);
0554 }
0555
0556 // only set simple if we need to
0557 if ($option !== 'full' && !isset($uniarray['s']))
0558 {
0559 $uniarray['s'] = include($phpbb_root_path . 'includes/utf/data/case_fold_s.' . $phpEx);
0560 }
0561
0562 // common is always replaced
0563 $text = strtr($text, $uniarray['c']);
0564
0565 if ($option === 'full')
0566 {
0567 // full replaces a character with multiple characters
0568 $text = strtr($text, $uniarray['f']);
0569 }
0570 else
0571 {
0572 // simple replaces a character with another character
0573 $text = strtr($text, $uniarray['s']);
0574 }
0575
0576 return $text;
0577 }
0578
0579 /**
0580 * Takes the input and does a "special" case fold. It does minor normalization
0581 * and returns NFKC compatable text
0582 *
0583 * @param string $text text to be case folded
0584 * @param string $option determines how we will fold the cases
0585 * @return string case folded text
0586 */
0587 function utf8_case_fold_nfkc($text, $option = 'full')
0588 {
0589 static $fc_nfkc_closure = array(
0590 "\xCD\xBA" => "\x20\xCE\xB9",
0591 "\xCF\x92" => "\xCF\x85",
0592 "\xCF\x93" => "\xCF\x8D",
0593 "\xCF\x94" => "\xCF\x8B",
0594 "\xCF\xB2" => "\xCF\x83",
0595 "\xCF\xB9" => "\xCF\x83",
0596 "\xE1\xB4\xAC" => "\x61",
0597 "\xE1\xB4\xAD" => "\xC3\xA6",
0598 "\xE1\xB4\xAE" => "\x62",
0599 "\xE1\xB4\xB0" => "\x64",
0600 "\xE1\xB4\xB1" => "\x65",
0601 "\xE1\xB4\xB2" => "\xC7\x9D",
0602 "\xE1\xB4\xB3" => "\x67",
0603 "\xE1\xB4\xB4" => "\x68",
0604 "\xE1\xB4\xB5" => "\x69",
0605 "\xE1\xB4\xB6" => "\x6A",
0606 "\xE1\xB4\xB7" => "\x6B",
0607 "\xE1\xB4\xB8" => "\x6C",
0608 "\xE1\xB4\xB9" => "\x6D",
0609 "\xE1\xB4\xBA" => "\x6E",
0610 "\xE1\xB4\xBC" => "\x6F",
0611 "\xE1\xB4\xBD" => "\xC8\xA3",
0612 "\xE1\xB4\xBE" => "\x70",
0613 "\xE1\xB4\xBF" => "\x72",
0614 "\xE1\xB5\x80" => "\x74",
0615 "\xE1\xB5\x81" => "\x75",
0616 "\xE1\xB5\x82" => "\x77",
0617 "\xE2\x82\xA8" => "\x72\x73",
0618 "\xE2\x84\x82" => "\x63",
0619 "\xE2\x84\x83" => "\xC2\xB0\x63",
0620 "\xE2\x84\x87" => "\xC9\x9B",
0621 "\xE2\x84\x89" => "\xC2\xB0\x66",
0622 "\xE2\x84\x8B" => "\x68",
0623 "\xE2\x84\x8C" => "\x68",
0624 "\xE2\x84\x8D" => "\x68",
0625 "\xE2\x84\x90" => "\x69",
0626 "\xE2\x84\x91" => "\x69",
0627 "\xE2\x84\x92" => "\x6C",
0628 "\xE2\x84\x95" => "\x6E",
0629 "\xE2\x84\x96" => "\x6E\x6F",
0630 "\xE2\x84\x99" => "\x70",
0631 "\xE2\x84\x9A" => "\x71",
0632 "\xE2\x84\x9B" => "\x72",
0633 "\xE2\x84\x9C" => "\x72",
0634 "\xE2\x84\x9D" => "\x72",
0635 "\xE2\x84\xA0" => "\x73\x6D",
0636 "\xE2\x84\xA1" => "\x74\x65\x6C",
0637 "\xE2\x84\xA2" => "\x74\x6D",
0638 "\xE2\x84\xA4" => "\x7A",
0639 "\xE2\x84\xA8" => "\x7A",
0640 "\xE2\x84\xAC" => "\x62",
0641 "\xE2\x84\xAD" => "\x63",
0642 "\xE2\x84\xB0" => "\x65",
0643 "\xE2\x84\xB1" => "\x66",
0644 "\xE2\x84\xB3" => "\x6D",
0645 "\xE2\x84\xBB" => "\x66\x61\x78",
0646 "\xE2\x84\xBE" => "\xCE\xB3",
0647 "\xE2\x84\xBF" => "\xCF\x80",
0648 "\xE2\x85\x85" => "\x64",
0649 "\xE3\x89\x90" => "\x70\x74\x65",
0650 "\xE3\x8B\x8C" => "\x68\x67",
0651 "\xE3\x8B\x8E" => "\x65\x76",
0652 "\xE3\x8B\x8F" => "\x6C\x74\x64",
0653 "\xE3\x8D\xB1" => "\x68\x70\x61",
0654 "\xE3\x8D\xB3" => "\x61\x75",
0655 "\xE3\x8D\xB5" => "\x6F\x76",
0656 "\xE3\x8D\xBA" => "\x69\x75",
0657 "\xE3\x8E\x80" => "\x70\x61",
0658 "\xE3\x8E\x81" => "\x6E\x61",
0659 "\xE3\x8E\x82" => "\xCE\xBC\x61",
0660 "\xE3\x8E\x83" => "\x6D\x61",
0661 "\xE3\x8E\x84" => "\x6B\x61",
0662 "\xE3\x8E\x85" => "\x6B\x62",
0663 "\xE3\x8E\x86" => "\x6D\x62",
0664 "\xE3\x8E\x87" => "\x67\x62",
0665 "\xE3\x8E\x8A" => "\x70\x66",
0666 "\xE3\x8E\x8B" => "\x6E\x66",
0667 "\xE3\x8E\x8C" => "\xCE\xBC\x66",
0668 "\xE3\x8E\x90" => "\x68\x7A",
0669 "\xE3\x8E\x91" => "\x6B\x68\x7A",
0670 "\xE3\x8E\x92" => "\x6D\x68\x7A",
0671 "\xE3\x8E\x93" => "\x67\x68\x7A",
0672 "\xE3\x8E\x94" => "\x74\x68\x7A",
0673 "\xE3\x8E\xA9" => "\x70\x61",
0674 "\xE3\x8E\xAA" => "\x6B\x70\x61",
0675 "\xE3\x8E\xAB" => "\x6D\x70\x61",
0676 "\xE3\x8E\xAC" => "\x67\x70\x61",
0677 "\xE3\x8E\xB4" => "\x70\x76",
0678 "\xE3\x8E\xB5" => "\x6E\x76",
0679 "\xE3\x8E\xB6" => "\xCE\xBC\x76",
0680 "\xE3\x8E\xB7" => "\x6D\x76",
0681 "\xE3\x8E\xB8" => "\x6B\x76",
0682 "\xE3\x8E\xB9" => "\x6D\x76",
0683 "\xE3\x8E\xBA" => "\x70\x77",
0684 "\xE3\x8E\xBB" => "\x6E\x77",
0685 "\xE3\x8E\xBC" => "\xCE\xBC\x77",
0686 "\xE3\x8E\xBD" => "\x6D\x77",
0687 "\xE3\x8E\xBE" => "\x6B\x77",
0688 "\xE3\x8E\xBF" => "\x6D\x77",
0689 "\xE3\x8F\x80" => "\x6B\xCF\x89",
0690 "\xE3\x8F\x81" => "\x6D\xCF\x89",
0691 "\xE3\x8F\x83" => "\x62\x71",
0692 "\xE3\x8F\x86" => "\x63\xE2\x88\x95\x6B\x67",
0693 "\xE3\x8F\x87" => "\x63\x6F\x2E",
0694 "\xE3\x8F\x88" => "\x64\x62",
0695 "\xE3\x8F\x89" => "\x67\x79",
0696 "\xE3\x8F\x8B" => "\x68\x70",
0697 "\xE3\x8F\x8D" => "\x6B\x6B",
0698 "\xE3\x8F\x8E" => "\x6B\x6D",
0699 "\xE3\x8F\x97" => "\x70\x68",
0700 "\xE3\x8F\x99" => "\x70\x70\x6D",
0701 "\xE3\x8F\x9A" => "\x70\x72",
0702 "\xE3\x8F\x9C" => "\x73\x76",
0703 "\xE3\x8F\x9D" => "\x77\x62",
0704 "\xE3\x8F\x9E" => "\x76\xE2\x88\x95\x6D",
0705 "\xE3\x8F\x9F" => "\x61\xE2\x88\x95\x6D",
0706 "\xF0\x9D\x90\x80" => "\x61",
0707 "\xF0\x9D\x90\x81" => "\x62",
0708 "\xF0\x9D\x90\x82" => "\x63",
0709 "\xF0\x9D\x90\x83" => "\x64",
0710 "\xF0\x9D\x90\x84" => "\x65",
0711 "\xF0\x9D\x90\x85" => "\x66",
0712 "\xF0\x9D\x90\x86" => "\x67",
0713 "\xF0\x9D\x90\x87" => "\x68",
0714 "\xF0\x9D\x90\x88" => "\x69",
0715 "\xF0\x9D\x90\x89" => "\x6A",
0716 "\xF0\x9D\x90\x8A" => "\x6B",
0717 "\xF0\x9D\x90\x8B" => "\x6C",
0718 "\xF0\x9D\x90\x8C" => "\x6D",
0719 "\xF0\x9D\x90\x8D" => "\x6E",
0720 "\xF0\x9D\x90\x8E" => "\x6F",
0721 "\xF0\x9D\x90\x8F" => "\x70",
0722 "\xF0\x9D\x90\x90" => "\x71",
0723 "\xF0\x9D\x90\x91" => "\x72",
0724 "\xF0\x9D\x90\x92" => "\x73",
0725 "\xF0\x9D\x90\x93" => "\x74",
0726 "\xF0\x9D\x90\x94" => "\x75",
0727 "\xF0\x9D\x90\x95" => "\x76",
0728 "\xF0\x9D\x90\x96" => "\x77",
0729 "\xF0\x9D\x90\x97" => "\x78",
0730 "\xF0\x9D\x90\x98" => "\x79",
0731 "\xF0\x9D\x90\x99" => "\x7A",
0732 "\xF0\x9D\x90\xB4" => "\x61",
0733 "\xF0\x9D\x90\xB5" => "\x62",
0734 "\xF0\x9D\x90\xB6" => "\x63",
0735 "\xF0\x9D\x90\xB7" => "\x64",
0736 "\xF0\x9D\x90\xB8" => "\x65",
0737 "\xF0\x9D\x90\xB9" => "\x66",
0738 "\xF0\x9D\x90\xBA" => "\x67",
0739 "\xF0\x9D\x90\xBB" => "\x68",
0740 "\xF0\x9D\x90\xBC" => "\x69",
0741 "\xF0\x9D\x90\xBD" => "\x6A",
0742 "\xF0\x9D\x90\xBE" => "\x6B",
0743 "\xF0\x9D\x90\xBF" => "\x6C",
0744 "\xF0\x9D\x91\x80" => "\x6D",
0745 "\xF0\x9D\x91\x81" => "\x6E",
0746 "\xF0\x9D\x91\x82" => "\x6F",
0747 "\xF0\x9D\x91\x83" => "\x70",
0748 "\xF0\x9D\x91\x84" => "\x71",
0749 "\xF0\x9D\x91\x85" => "\x72",
0750 "\xF0\x9D\x91\x86" => "\x73",
0751 "\xF0\x9D\x91\x87" => "\x74",
0752 "\xF0\x9D\x91\x88" => "\x75",
0753 "\xF0\x9D\x91\x89" => "\x76",
0754 "\xF0\x9D\x91\x8A" => "\x77",
0755 "\xF0\x9D\x91\x8B" => "\x78",
0756 "\xF0\x9D\x91\x8C" => "\x79",
0757 "\xF0\x9D\x91\x8D" => "\x7A",
0758 "\xF0\x9D\x91\xA8" => "\x61",
0759 "\xF0\x9D\x91\xA9" => "\x62",
0760 "\xF0\x9D\x91\xAA" => "\x63",
0761 "\xF0\x9D\x91\xAB" => "\x64",
0762 "\xF0\x9D\x91\xAC" => "\x65",
0763 "\xF0\x9D\x91\xAD" => "\x66",
0764 "\xF0\x9D\x91\xAE" => "\x67",
0765 "\xF0\x9D\x91\xAF" => "\x68",
0766 "\xF0\x9D\x91\xB0" => "\x69",
0767 "\xF0\x9D\x91\xB1" => "\x6A",
0768 "\xF0\x9D\x91\xB2" => "\x6B",
0769 "\xF0\x9D\x91\xB3" => "\x6C",
0770 "\xF0\x9D\x91\xB4" => "\x6D",
0771 "\xF0\x9D\x91\xB5" => "\x6E",
0772 "\xF0\x9D\x91\xB6" => "\x6F",
0773 "\xF0\x9D\x91\xB7" => "\x70",
0774 "\xF0\x9D\x91\xB8" => "\x71",
0775 "\xF0\x9D\x91\xB9" => "\x72",
0776 "\xF0\x9D\x91\xBA" => "\x73",
0777 "\xF0\x9D\x91\xBB" => "\x74",
0778 "\xF0\x9D\x91\xBC" => "\x75",
0779 "\xF0\x9D\x91\xBD" => "\x76",
0780 "\xF0\x9D\x91\xBE" => "\x77",
0781 "\xF0\x9D\x91\xBF" => "\x78",
0782 "\xF0\x9D\x92\x80" => "\x79",
0783 "\xF0\x9D\x92\x81" => "\x7A",
0784 "\xF0\x9D\x92\x9C" => "\x61",
0785 "\xF0\x9D\x92\x9E" => "\x63",
0786 "\xF0\x9D\x92\x9F" => "\x64",
0787 "\xF0\x9D\x92\xA2" => "\x67",
0788 "\xF0\x9D\x92\xA5" => "\x6A",
0789 "\xF0\x9D\x92\xA6" => "\x6B",
0790 "\xF0\x9D\x92\xA9" => "\x6E",
0791 "\xF0\x9D\x92\xAA" => "\x6F",
0792 "\xF0\x9D\x92\xAB" => "\x70",
0793 "\xF0\x9D\x92\xAC" => "\x71",
0794 "\xF0\x9D\x92\xAE" => "\x73",
0795 "\xF0\x9D\x92\xAF" => "\x74",
0796 "\xF0\x9D\x92\xB0" => "\x75",
0797 "\xF0\x9D\x92\xB1" => "\x76",
0798 "\xF0\x9D\x92\xB2" => "\x77",
0799 "\xF0\x9D\x92\xB3" => "\x78",
0800 "\xF0\x9D\x92\xB4" => "\x79",
0801 "\xF0\x9D\x92\xB5" => "\x7A",
0802 "\xF0\x9D\x93\x90" => "\x61",
0803 "\xF0\x9D\x93\x91" => "\x62",
0804 "\xF0\x9D\x93\x92" => "\x63",
0805 "\xF0\x9D\x93\x93" => "\x64",
0806 "\xF0\x9D\x93\x94" => "\x65",
0807 "\xF0\x9D\x93\x95" => "\x66",
0808 "\xF0\x9D\x93\x96" => "\x67",
0809 "\xF0\x9D\x93\x97" => "\x68",
0810 "\xF0\x9D\x93\x98" => "\x69",
0811 "\xF0\x9D\x93\x99" => "\x6A",
0812 "\xF0\x9D\x93\x9A" => "\x6B",
0813 "\xF0\x9D\x93\x9B" => "\x6C",
0814 "\xF0\x9D\x93\x9C" => "\x6D",
0815 "\xF0\x9D\x93\x9D" => "\x6E",
0816 "\xF0\x9D\x93\x9E" => "\x6F",
0817 "\xF0\x9D\x93\x9F" => "\x70",
0818 "\xF0\x9D\x93\xA0" => "\x71",
0819 "\xF0\x9D\x93\xA1" => "\x72",
0820 "\xF0\x9D\x93\xA2" => "\x73",
0821 "\xF0\x9D\x93\xA3" => "\x74",
0822 "\xF0\x9D\x93\xA4" => "\x75",
0823 "\xF0\x9D\x93\xA5" => "\x76",
0824 "\xF0\x9D\x93\xA6" => "\x77",
0825 "\xF0\x9D\x93\xA7" => "\x78",
0826 "\xF0\x9D\x93\xA8" => "\x79",
0827 "\xF0\x9D\x93\xA9" => "\x7A",
0828 "\xF0\x9D\x94\x84" => "\x61",
0829 "\xF0\x9D\x94\x85" => "\x62",
0830 "\xF0\x9D\x94\x87" => "\x64",
0831 "\xF0\x9D\x94\x88" => "\x65",
0832 "\xF0\x9D\x94\x89" => "\x66",
0833 "\xF0\x9D\x94\x8A" => "\x67",
0834 "\xF0\x9D\x94\x8D" => "\x6A",
0835 "\xF0\x9D\x94\x8E" => "\x6B",
0836 "\xF0\x9D\x94\x8F" => "\x6C",
0837 "\xF0\x9D\x94\x90" => "\x6D",
0838 "\xF0\x9D\x94\x91" => "\x6E",
0839 "\xF0\x9D\x94\x92" => "\x6F",
0840 "\xF0\x9D\x94\x93" => "\x70",
0841 "\xF0\x9D\x94\x94" => "\x71",
0842 "\xF0\x9D\x94\x96" => "\x73",
0843 "\xF0\x9D\x94\x97" => "\x74",
0844 "\xF0\x9D\x94\x98" => "\x75",
0845 "\xF0\x9D\x94\x99" => "\x76",
0846 "\xF0\x9D\x94\x9A" => "\x77",
0847 "\xF0\x9D\x94\x9B" => "\x78",
0848 "\xF0\x9D\x94\x9C" => "\x79",
0849 "\xF0\x9D\x94\xB8" => "\x61",
0850 "\xF0\x9D\x94\xB9" => "\x62",
0851 "\xF0\x9D\x94\xBB" => "\x64",
0852 "\xF0\x9D\x94\xBC" => "\x65",
0853 "\xF0\x9D\x94\xBD" => "\x66",
0854 "\xF0\x9D\x94\xBE" => "\x67",
0855 "\xF0\x9D\x95\x80" => "\x69",
0856 "\xF0\x9D\x95\x81" => "\x6A",
0857 "\xF0\x9D\x95\x82" => "\x6B",
0858 "\xF0\x9D\x95\x83" => "\x6C",
0859 "\xF0\x9D\x95\x84" => "\x6D",
0860 "\xF0\x9D\x95\x86" => "\x6F",
0861 "\xF0\x9D\x95\x8A" => "\x73",
0862 "\xF0\x9D\x95\x8B" => "\x74",
0863 "\xF0\x9D\x95\x8C" => "\x75",
0864 "\xF0\x9D\x95\x8D" => "\x76",
0865 "\xF0\x9D\x95\x8E" => "\x77",
0866 "\xF0\x9D\x95\x8F" => "\x78",
0867 "\xF0\x9D\x95\x90" => "\x79",
0868 "\xF0\x9D\x95\xAC" => "\x61",
0869 "\xF0\x9D\x95\xAD" => "\x62",
0870 "\xF0\x9D\x95\xAE" => "\x63",
0871 "\xF0\x9D\x95\xAF" => "\x64",
0872 "\xF0\x9D\x95\xB0" => "\x65",
0873 "\xF0\x9D\x95\xB1" => "\x66",
0874 "\xF0\x9D\x95\xB2" => "\x67",
0875 "\xF0\x9D\x95\xB3" => "\x68",
0876 "\xF0\x9D\x95\xB4" => "\x69",
0877 "\xF0\x9D\x95\xB5" => "\x6A",
0878 "\xF0\x9D\x95\xB6" => "\x6B",
0879 "\xF0\x9D\x95\xB7" => "\x6C",
0880 "\xF0\x9D\x95\xB8" => "\x6D",
0881 "\xF0\x9D\x95\xB9" => "\x6E",
0882 "\xF0\x9D\x95\xBA" => "\x6F",
0883 "\xF0\x9D\x95\xBB" => "\x70",
0884 "\xF0\x9D\x95\xBC" => "\x71",
0885 "\xF0\x9D\x95\xBD" => "\x72",
0886 "\xF0\x9D\x95\xBE" => "\x73",
0887 "\xF0\x9D\x95\xBF" => "\x74",
0888 "\xF0\x9D\x96\x80" => "\x75",
0889 "\xF0\x9D\x96\x81" => "\x76",
0890 "\xF0\x9D\x96\x82" => "\x77",
0891 "\xF0\x9D\x96\x83" => "\x78",
0892 "\xF0\x9D\x96\x84" => "\x79",
0893 "\xF0\x9D\x96\x85" => "\x7A",
0894 "\xF0\x9D\x96\xA0" => "\x61",
0895 "\xF0\x9D\x96\xA1" => "\x62",
0896 "\xF0\x9D\x96\xA2" => "\x63",
0897 "\xF0\x9D\x96\xA3" => "\x64",
0898 "\xF0\x9D\x96\xA4" => "\x65",
0899 "\xF0\x9D\x96\xA5" => "\x66",
0900 "\xF0\x9D\x96\xA6" => "\x67",
0901 "\xF0\x9D\x96\xA7" => "\x68",
0902 "\xF0\x9D\x96\xA8" => "\x69",
0903 "\xF0\x9D\x96\xA9" => "\x6A",
0904 "\xF0\x9D\x96\xAA" => "\x6B",
0905 "\xF0\x9D\x96\xAB" => "\x6C",
0906 "\xF0\x9D\x96\xAC" => "\x6D",
0907 "\xF0\x9D\x96\xAD" => "\x6E",
0908 "\xF0\x9D\x96\xAE" => "\x6F",
0909 "\xF0\x9D\x96\xAF" => "\x70",
0910 "\xF0\x9D\x96\xB0" => "\x71",
0911 "\xF0\x9D\x96\xB1" => "\x72",
0912 "\xF0\x9D\x96\xB2" => "\x73",
0913 "\xF0\x9D\x96\xB3" => "\x74",
0914 "\xF0\x9D\x96\xB4" => "\x75",
0915 "\xF0\x9D\x96\xB5" => "\x76",
0916 "\xF0\x9D\x96\xB6" => "\x77",
0917 "\xF0\x9D\x96\xB7" => "\x78",
0918 "\xF0\x9D\x96\xB8" => "\x79",
0919 "\xF0\x9D\x96\xB9" => "\x7A",
0920 "\xF0\x9D\x97\x94" => "\x61",
0921 "\xF0\x9D\x97\x95" => "\x62",
0922 "\xF0\x9D\x97\x96" => "\x63",
0923 "\xF0\x9D\x97\x97" => "\x64",
0924 "\xF0\x9D\x97\x98" => "\x65",
0925 "\xF0\x9D\x97\x99" => "\x66",
0926 "\xF0\x9D\x97\x9A" => "\x67",
0927 "\xF0\x9D\x97\x9B" => "\x68",
0928 "\xF0\x9D\x97\x9C" => "\x69",
0929 "\xF0\x9D\x97\x9D" => "\x6A",
0930 "\xF0\x9D\x97\x9E" => "\x6B",
0931 "\xF0\x9D\x97\x9F" => "\x6C",
0932 "\xF0\x9D\x97\xA0" => "\x6D",
0933 "\xF0\x9D\x97\xA1" => "\x6E",
0934 "\xF0\x9D\x97\xA2" => "\x6F",
0935 "\xF0\x9D\x97\xA3" => "\x70",
0936 "\xF0\x9D\x97\xA4" => "\x71",
0937 "\xF0\x9D\x97\xA5" => "\x72",
0938 "\xF0\x9D\x97\xA6" => "\x73",
0939 "\xF0\x9D\x97\xA7" => "\x74",
0940 "\xF0\x9D\x97\xA8" => "\x75",
0941 "\xF0\x9D\x97\xA9" => "\x76",
0942 "\xF0\x9D\x97\xAA" => "\x77",
0943 "\xF0\x9D\x97\xAB" => "\x78",
0944 "\xF0\x9D\x97\xAC" => "\x79",
0945 "\xF0\x9D\x97\xAD" => "\x7A",
0946 "\xF0\x9D\x98\x88" => "\x61",
0947 "\xF0\x9D\x98\x89" => "\x62",
0948 "\xF0\x9D\x98\x8A" => "\x63",
0949 "\xF0\x9D\x98\x8B" => "\x64",
0950 "\xF0\x9D\x98\x8C" => "\x65",
0951 "\xF0\x9D\x98\x8D" => "\x66",
0952 "\xF0\x9D\x98\x8E" => "\x67",
0953 "\xF0\x9D\x98\x8F" => "\x68",
0954 "\xF0\x9D\x98\x90" => "\x69",
0955 "\xF0\x9D\x98\x91" => "\x6A",
0956 "\xF0\x9D\x98\x92" => "\x6B",
0957 "\xF0\x9D\x98\x93" => "\x6C",
0958 "\xF0\x9D\x98\x94" => "\x6D",
0959 "\xF0\x9D\x98\x95" => "\x6E",
0960 "\xF0\x9D\x98\x96" => "\x6F",
0961 "\xF0\x9D\x98\x97" => "\x70",
0962 "\xF0\x9D\x98\x98" => "\x71",
0963 "\xF0\x9D\x98\x99" => "\x72",
0964 "\xF0\x9D\x98\x9A" => "\x73",
0965 "\xF0\x9D\x98\x9B" => "\x74",
0966 "\xF0\x9D\x98\x9C" => "\x75",
0967 "\xF0\x9D\x98\x9D" => "\x76",
0968 "\xF0\x9D\x98\x9E" => "\x77",
0969 "\xF0\x9D\x98\x9F" => "\x78",
0970 "\xF0\x9D\x98\xA0" => "\x79",
0971 "\xF0\x9D\x98\xA1" => "\x7A",
0972 "\xF0\x9D\x98\xBC" => "\x61",
0973 "\xF0\x9D\x98\xBD" => "\x62",
0974 "\xF0\x9D\x98\xBE" => "\x63",
0975 "\xF0\x9D\x98\xBF" => "\x64",
0976 "\xF0\x9D\x99\x80" => "\x65",
0977 "\xF0\x9D\x99\x81" => "\x66",
0978 "\xF0\x9D\x99\x82" => "\x67",
0979 "\xF0\x9D\x99\x83" => "\x68",
0980 "\xF0\x9D\x99\x84" => "\x69",
0981 "\xF0\x9D\x99\x85" => "\x6A",
0982 "\xF0\x9D\x99\x86" => "\x6B",
0983 "\xF0\x9D\x99\x87" => "\x6C",
0984 "\xF0\x9D\x99\x88" => "\x6D",
0985 "\xF0\x9D\x99\x89" => "\x6E",
0986 "\xF0\x9D\x99\x8A" => "\x6F",
0987 "\xF0\x9D\x99\x8B" => "\x70",
0988 "\xF0\x9D\x99\x8C" => "\x71",
0989 "\xF0\x9D\x99\x8D" => "\x72",
0990 "\xF0\x9D\x99\x8E" => "\x73",
0991 "\xF0\x9D\x99\x8F" => "\x74",
0992 "\xF0\x9D\x99\x90" => "\x75",
0993 "\xF0\x9D\x99\x91" => "\x76",
0994 "\xF0\x9D\x99\x92" => "\x77",
0995 "\xF0\x9D\x99\x93" => "\x78",
0996 "\xF0\x9D\x99\x94" => "\x79",
0997 "\xF0\x9D\x99\x95" => "\x7A",
0998 "\xF0\x9D\x99\xB0" => "\x61",
0999 "\xF0\x9D\x99\xB1" => "\x62",
1000 "\xF0\x9D\x99\xB2" => "\x63",
1001 "\xF0\x9D\x99\xB3" => "\x64",
1002 "\xF0\x9D\x99\xB4" => "\x65",
1003 "\xF0\x9D\x99\xB5" => "\x66",
1004 "\xF0\x9D\x99\xB6" => "\x67",
1005 "\xF0\x9D\x99\xB7" => "\x68",
1006 "\xF0\x9D\x99\xB8" => "\x69",
1007 "\xF0\x9D\x99\xB9" => "\x6A",
1008 "\xF0\x9D\x99\xBA" => "\x6B",
1009 "\xF0\x9D\x99\xBB" => "\x6C",
1010 "\xF0\x9D\x99\xBC" => "\x6D",
1011 "\xF0\x9D\x99\xBD" => "\x6E",
1012 "\xF0\x9D\x99\xBE" => "\x6F",
1013 "\xF0\x9D\x99\xBF" => "\x70",
1014 "\xF0\x9D\x9A\x80" => "\x71",
1015 "\xF0\x9D\x9A\x81" => "\x72",
1016 "\xF0\x9D\x9A\x82" => "\x73",
1017 "\xF0\x9D\x9A\x83" => "\x74",
1018 "\xF0\x9D\x9A\x84" => "\x75",
1019 "\xF0\x9D\x9A\x85" => "\x76",
1020 "\xF0\x9D\x9A\x86" => "\x77",
1021 "\xF0\x9D\x9A\x87" => "\x78",
1022 "\xF0\x9D\x9A\x88" => "\x79",
1023 "\xF0\x9D\x9A\x89" => "\x7A",
1024 "\xF0\x9D\x9A\xA8" => "\xCE\xB1",
1025 "\xF0\x9D\x9A\xA9" => "\xCE\xB2",
1026 "\xF0\x9D\x9A\xAA" => "\xCE\xB3",
1027 "\xF0\x9D\x9A\xAB" => "\xCE\xB4",
1028 "\xF0\x9D\x9A\xAC" => "\xCE\xB5",
1029 "\xF0\x9D\x9A\xAD" => "\xCE\xB6",
1030 "\xF0\x9D\x9A\xAE" => "\xCE\xB7",
1031 "\xF0\x9D\x9A\xAF" => "\xCE\xB8",
1032 "\xF0\x9D\x9A\xB0" => "\xCE\xB9",
1033 "\xF0\x9D\x9A\xB1" => "\xCE\xBA",
1034 "\xF0\x9D\x9A\xB2" => "\xCE\xBB",
1035 "\xF0\x9D\x9A\xB3" => "\xCE\xBC",
1036 "\xF0\x9D\x9A\xB4" => "\xCE\xBD",
1037 "\xF0\x9D\x9A\xB5" => "\xCE\xBE",
1038 "\xF0\x9D\x9A\xB6" => "\xCE\xBF",
1039 "\xF0\x9D\x9A\xB7" => "\xCF\x80",
1040 "\xF0\x9D\x9A\xB8" => "\xCF\x81",
1041 "\xF0\x9D\x9A\xB9" => "\xCE\xB8",
1042 "\xF0\x9D\x9A\xBA" => "\xCF\x83",
1043 "\xF0\x9D\x9A\xBB" => "\xCF\x84",
1044 "\xF0\x9D\x9A\xBC" => "\xCF\x85",
1045 "\xF0\x9D\x9A\xBD" => "\xCF\x86",
1046 "\xF0\x9D\x9A\xBE" => "\xCF\x87",
1047 "\xF0\x9D\x9A\xBF" => "\xCF\x88",
1048 "\xF0\x9D\x9B\x80" => "\xCF\x89",
1049 "\xF0\x9D\x9B\x93" => "\xCF\x83",
1050 "\xF0\x9D\x9B\xA2" => "\xCE\xB1",
1051 "\xF0\x9D\x9B\xA3" => "\xCE\xB2",
1052 "\xF0\x9D\x9B\xA4" => "\xCE\xB3",
1053 "\xF0\x9D\x9B\xA5" => "\xCE\xB4",
1054 "\xF0\x9D\x9B\xA6" => "\xCE\xB5",
1055 "\xF0\x9D\x9B\xA7" => "\xCE\xB6",
1056 "\xF0\x9D\x9B\xA8" => "\xCE\xB7",
1057 "\xF0\x9D\x9B\xA9" => "\xCE\xB8",
1058 "\xF0\x9D\x9B\xAA" => "\xCE\xB9",
1059 "\xF0\x9D\x9B\xAB" => "\xCE\xBA",
1060 "\xF0\x9D\x9B\xAC" => "\xCE\xBB",
1061 "\xF0\x9D\x9B\xAD" => "\xCE\xBC",
1062 "\xF0\x9D\x9B\xAE" => "\xCE\xBD",
1063 "\xF0\x9D\x9B\xAF" => "\xCE\xBE",
1064 "\xF0\x9D\x9B\xB0" => "\xCE\xBF",
1065 "\xF0\x9D\x9B\xB1" => "\xCF\x80",
1066 "\xF0\x9D\x9B\xB2" => "\xCF\x81",
1067 "\xF0\x9D\x9B\xB3" => "\xCE\xB8",
1068 "\xF0\x9D\x9B\xB4" => "\xCF\x83",
1069 "\xF0\x9D\x9B\xB5" => "\xCF\x84",
1070 "\xF0\x9D\x9B\xB6" => "\xCF\x85",
1071 "\xF0\x9D\x9B\xB7" => "\xCF\x86",
1072 "\xF0\x9D\x9B\xB8" => "\xCF\x87",
1073 "\xF0\x9D\x9B\xB9" => "\xCF\x88",
1074 "\xF0\x9D\x9B\xBA" => "\xCF\x89",
1075 "\xF0\x9D\x9C\x8D" => "\xCF\x83",
1076 "\xF0\x9D\x9C\x9C" => "\xCE\xB1",
1077 "\xF0\x9D\x9C\x9D" => "\xCE\xB2",
1078 "\xF0\x9D\x9C\x9E" => "\xCE\xB3",
1079 "\xF0\x9D\x9C\x9F" => "\xCE\xB4",
1080 "\xF0\x9D\x9C\xA0" => "\xCE\xB5",
1081 "\xF0\x9D\x9C\xA1" => "\xCE\xB6",
1082 "\xF0\x9D\x9C\xA2" => "\xCE\xB7",
1083 "\xF0\x9D\x9C\xA3" => "\xCE\xB8",
1084 "\xF0\x9D\x9C\xA4" => "\xCE\xB9",
1085 "\xF0\x9D\x9C\xA5" => "\xCE\xBA",
1086 "\xF0\x9D\x9C\xA6" => "\xCE\xBB",
1087 "\xF0\x9D\x9C\xA7" => "\xCE\xBC",
1088 "\xF0\x9D\x9C\xA8" => "\xCE\xBD",
1089 "\xF0\x9D\x9C\xA9" => "\xCE\xBE",
1090 "\xF0\x9D\x9C\xAA" => "\xCE\xBF",
1091 "\xF0\x9D\x9C\xAB" => "\xCF\x80",
1092 "\xF0\x9D\x9C\xAC" => "\xCF\x81",
1093 "\xF0\x9D\x9C\xAD" => "\xCE\xB8",
1094 "\xF0\x9D\x9C\xAE" => "\xCF\x83",
1095 "\xF0\x9D\x9C\xAF" => "\xCF\x84",
1096 "\xF0\x9D\x9C\xB0" => "\xCF\x85",
1097 "\xF0\x9D\x9C\xB1" => "\xCF\x86",
1098 "\xF0\x9D\x9C\xB2" => "\xCF\x87",
1099 "\xF0\x9D\x9C\xB3" => "\xCF\x88",
1100 "\xF0\x9D\x9C\xB4" => "\xCF\x89",
1101 "\xF0\x9D\x9D\x87" => "\xCF\x83",
1102 "\xF0\x9D\x9D\x96" => "\xCE\xB1",
1103 "\xF0\x9D\x9D\x97" => "\xCE\xB2",
1104 "\xF0\x9D\x9D\x98" => "\xCE\xB3",
1105 "\xF0\x9D\x9D\x99" => "\xCE\xB4",
1106 "\xF0\x9D\x9D\x9A" => "\xCE\xB5",
1107 "\xF0\x9D\x9D\x9B" => "\xCE\xB6",
1108 "\xF0\x9D\x9D\x9C" => "\xCE\xB7",
1109 "\xF0\x9D\x9D\x9D" => "\xCE\xB8",
1110 "\xF0\x9D\x9D\x9E" => "\xCE\xB9",
1111 "\xF0\x9D\x9D\x9F" => "\xCE\xBA",
1112 "\xF0\x9D\x9D\xA0" => "\xCE\xBB",
1113 "\xF0\x9D\x9D\xA1" => "\xCE\xBC",
1114 "\xF0\x9D\x9D\xA2" => "\xCE\xBD",
1115 "\xF0\x9D\x9D\xA3" => "\xCE\xBE",
1116 "\xF0\x9D\x9D\xA4" => "\xCE\xBF",
1117 "\xF0\x9D\x9D\xA5" => "\xCF\x80",
1118 "\xF0\x9D\x9D\xA6" => "\xCF\x81",
1119 "\xF0\x9D\x9D\xA7" => "\xCE\xB8",
1120 "\xF0\x9D\x9D\xA8" => "\xCF\x83",
1121 "\xF0\x9D\x9D\xA9" => "\xCF\x84",
1122 "\xF0\x9D\x9D\xAA" => "\xCF\x85",
1123 "\xF0\x9D\x9D\xAB" => "\xCF\x86",
1124 "\xF0\x9D\x9D\xAC" => "\xCF\x87",
1125 "\xF0\x9D\x9D\xAD" => "\xCF\x88",
1126 "\xF0\x9D\x9D\xAE" => "\xCF\x89",
1127 "\xF0\x9D\x9E\x81" => "\xCF\x83",
1128 "\xF0\x9D\x9E\x90" => "\xCE\xB1",
1129 "\xF0\x9D\x9E\x91" => "\xCE\xB2",
1130 "\xF0\x9D\x9E\x92" => "\xCE\xB3",
1131 "\xF0\x9D\x9E\x93" => "\xCE\xB4",
1132 "\xF0\x9D\x9E\x94" => "\xCE\xB5",
1133 "\xF0\x9D\x9E\x95" => "\xCE\xB6",
1134 "\xF0\x9D\x9E\x96" => "\xCE\xB7",
1135 "\xF0\x9D\x9E\x97" => "\xCE\xB8",
1136 "\xF0\x9D\x9E\x98" => "\xCE\xB9",
1137 "\xF0\x9D\x9E\x99" => "\xCE\xBA",
1138 "\xF0\x9D\x9E\x9A" => "\xCE\xBB",
1139 "\xF0\x9D\x9E\x9B" => "\xCE\xBC",
1140 "\xF0\x9D\x9E\x9C" => "\xCE\xBD",
1141 "\xF0\x9D\x9E\x9D" => "\xCE\xBE",
1142 "\xF0\x9D\x9E\x9E" => "\xCE\xBF",
1143 "\xF0\x9D\x9E\x9F" => "\xCF\x80",
1144 "\xF0\x9D\x9E\xA0" => "\xCF\x81",
1145 "\xF0\x9D\x9E\xA1" => "\xCE\xB8",
1146 "\xF0\x9D\x9E\xA2" => "\xCF\x83",
1147 "\xF0\x9D\x9E\xA3" => "\xCF\x84",
1148 "\xF0\x9D\x9E\xA4" => "\xCF\x85",
1149 "\xF0\x9D\x9E\xA5" => "\xCF\x86",
1150 "\xF0\x9D\x9E\xA6" => "\xCF\x87",
1151 "\xF0\x9D\x9E\xA7" => "\xCF\x88",
1152 "\xF0\x9D\x9E\xA8" => "\xCF\x89",
1153 "\xF0\x9D\x9E\xBB" => "\xCF\x83",
1154 "\xF0\x9D\x9F\x8A" => "\xCF\x9D",
1155 );
1156
1157 // do the case fold
1158 $text = utf8_case_fold($text, $option);
1159
1160 // convert to NFKC
1161 Normalizer::normalize($text, Normalizer::NFKC);
1162
1163 // FC_NFKC_Closure, http://www.unicode.org/Public/5.0.0/ucd/DerivedNormalizationProps.txt
1164 $text = strtr($text, $fc_nfkc_closure);
1165
1166 return $text;
1167 }
1168
1169 /**
1170 * Assume the input is NFC:
1171 * Takes the input and does a "special" case fold. It does minor normalization as well.
1172 *
1173 * @param string $text text to be case folded
1174 * @param string $option determines how we will fold the cases
1175 * @return string case folded text
1176 */
1177 function utf8_case_fold_nfc($text, $option = 'full')
1178 {
1179 static $uniarray = array();
1180 static $ypogegrammeni = array(
1181 "\xCD\xBA" => "\x20\xCD\x85",
1182 "\xE1\xBE\x80" => "\xE1\xBC\x80\xCD\x85",
1183 "\xE1\xBE\x81" => "\xE1\xBC\x81\xCD\x85",
1184 "\xE1\xBE\x82" => "\xE1\xBC\x82\xCD\x85",
1185 "\xE1\xBE\x83" => "\xE1\xBC\x83\xCD\x85",
1186 "\xE1\xBE\x84" => "\xE1\xBC\x84\xCD\x85",
1187 "\xE1\xBE\x85" => "\xE1\xBC\x85\xCD\x85",
1188 "\xE1\xBE\x86" => "\xE1\xBC\x86\xCD\x85",
1189 "\xE1\xBE\x87" => "\xE1\xBC\x87\xCD\x85",
1190 "\xE1\xBE\x88" => "\xE1\xBC\x88\xCD\x85",
1191 "\xE1\xBE\x89" => "\xE1\xBC\x89\xCD\x85",
1192 "\xE1\xBE\x8A" => "\xE1\xBC\x8A\xCD\x85",
1193 "\xE1\xBE\x8B" => "\xE1\xBC\x8B\xCD\x85",
1194 "\xE1\xBE\x8C" => "\xE1\xBC\x8C\xCD\x85",
1195 "\xE1\xBE\x8D" => "\xE1\xBC\x8D\xCD\x85",
1196 "\xE1\xBE\x8E" => "\xE1\xBC\x8E\xCD\x85",
1197 "\xE1\xBE\x8F" => "\xE1\xBC\x8F\xCD\x85",
1198 "\xE1\xBE\x90" => "\xE1\xBC\xA0\xCD\x85",
1199 "\xE1\xBE\x91" => "\xE1\xBC\xA1\xCD\x85",
1200 "\xE1\xBE\x92" => "\xE1\xBC\xA2\xCD\x85",
1201 "\xE1\xBE\x93" => "\xE1\xBC\xA3\xCD\x85",
1202 "\xE1\xBE\x94" => "\xE1\xBC\xA4\xCD\x85",
1203 "\xE1\xBE\x95" => "\xE1\xBC\xA5\xCD\x85",
1204 "\xE1\xBE\x96" => "\xE1\xBC\xA6\xCD\x85",
1205 "\xE1\xBE\x97" => "\xE1\xBC\xA7\xCD\x85",
1206 "\xE1\xBE\x98" => "\xE1\xBC\xA8\xCD\x85",
1207 "\xE1\xBE\x99" => "\xE1\xBC\xA9\xCD\x85",
1208 "\xE1\xBE\x9A" => "\xE1\xBC\xAA\xCD\x85",
1209 "\xE1\xBE\x9B" => "\xE1\xBC\xAB\xCD\x85",
1210 "\xE1\xBE\x9C" => "\xE1\xBC\xAC\xCD\x85",
1211 "\xE1\xBE\x9D" => "\xE1\xBC\xAD\xCD\x85",
1212 "\xE1\xBE\x9E" => "\xE1\xBC\xAE\xCD\x85",
1213 "\xE1\xBE\x9F" => "\xE1\xBC\xAF\xCD\x85",
1214 "\xE1\xBE\xA0" => "\xE1\xBD\xA0\xCD\x85",
1215 "\xE1\xBE\xA1" => "\xE1\xBD\xA1\xCD\x85",
1216 "\xE1\xBE\xA2" => "\xE1\xBD\xA2\xCD\x85",
1217 "\xE1\xBE\xA3" => "\xE1\xBD\xA3\xCD\x85",
1218 "\xE1\xBE\xA4" => "\xE1\xBD\xA4\xCD\x85",
1219 "\xE1\xBE\xA5" => "\xE1\xBD\xA5\xCD\x85",
1220 "\xE1\xBE\xA6" => "\xE1\xBD\xA6\xCD\x85",
1221 "\xE1\xBE\xA7" => "\xE1\xBD\xA7\xCD\x85",
1222 "\xE1\xBE\xA8" => "\xE1\xBD\xA8\xCD\x85",
1223 "\xE1\xBE\xA9" => "\xE1\xBD\xA9\xCD\x85",
1224 "\xE1\xBE\xAA" => "\xE1\xBD\xAA\xCD\x85",
1225 "\xE1\xBE\xAB" => "\xE1\xBD\xAB\xCD\x85",
1226 "\xE1\xBE\xAC" => "\xE1\xBD\xAC\xCD\x85",
1227 "\xE1\xBE\xAD" => "\xE1\xBD\xAD\xCD\x85",
1228 "\xE1\xBE\xAE" => "\xE1\xBD\xAE\xCD\x85",
1229 "\xE1\xBE\xAF" => "\xE1\xBD\xAF\xCD\x85",
1230 "\xE1\xBE\xB2" => "\xE1\xBD\xB0\xCD\x85",
1231 "\xE1\xBE\xB3" => "\xCE\xB1\xCD\x85",
1232 "\xE1\xBE\xB4" => "\xCE\xAC\xCD\x85",
1233 "\xE1\xBE\xB7" => "\xE1\xBE\xB6\xCD\x85",
1234 "\xE1\xBE\xBC" => "\xCE\x91\xCD\x85",
1235 "\xE1\xBF\x82" => "\xE1\xBD\xB4\xCD\x85",
1236 "\xE1\xBF\x83" => "\xCE\xB7\xCD\x85",
1237 "\xE1\xBF\x84" => "\xCE\xAE\xCD\x85",
1238 "\xE1\xBF\x87" => "\xE1\xBF\x86\xCD\x85",
1239 "\xE1\xBF\x8C" => "\xCE\x97\xCD\x85",
1240 "\xE1\xBF\xB2" => "\xE1\xBD\xBC\xCD\x85",
1241 "\xE1\xBF\xB3" => "\xCF\x89\xCD\x85",
1242 "\xE1\xBF\xB4" => "\xCF\x8E\xCD\x85",
1243 "\xE1\xBF\xB7" => "\xE1\xBF\xB6\xCD\x85",
1244 "\xE1\xBF\xBC" => "\xCE\xA9\xCD\x85",
1245 );
1246
1247 // perform a small trick, avoid further normalization on composed points that contain U+0345 in their decomposition
1248 $text = strtr($text, $ypogegrammeni);
1249
1250 // do the case fold
1251 $text = utf8_case_fold($text, $option);
1252
1253 return $text;
1254 }
1255
1256 /**
1257 * wrapper around PHP's native normalizer from intl
1258 * previously a PECL extension, included in the core since PHP 5.3.0
1259 * http://php.net/manual/en/normalizer.normalize.php
1260 *
1261 * @param mixed $strings a string or an array of strings to normalize
1262 * @return mixed the normalized content, preserving array keys if array given.
1263 */
1264 function utf8_normalize_nfc($strings)
1265 {
1266 if (empty($strings))
1267 {
1268 return $strings;
1269 }
1270
1271 if (!is_array($strings))
1272 {
1273 if (Normalizer::isNormalized($strings))
1274 {
1275 return $strings;
1276 }
1277 return (string) Normalizer::normalize($strings);
1278 }
1279 else
1280 {
1281 foreach ($strings as $key => $string)
1282 {
1283 if (is_array($string))
1284 {
1285 foreach ($string as $_key => $_string)
1286 {
1287 if (Normalizer::isNormalized($strings[$key][$_key]))
1288 {
1289 continue;
1290 }
1291 $strings[$key][$_key] = (string) Normalizer::normalize($strings[$key][$_key]);
1292 }
1293 }
1294 else
1295 {
1296 if (Normalizer::isNormalized($strings[$key]))
1297 {
1298 continue;
1299 }
1300 $strings[$key] = (string) Normalizer::normalize($strings[$key]);
1301 }
1302 }
1303 }
1304
1305 return $strings;
1306 }
1307
1308 /**
1309 * This function is used to generate a "clean" version of a string.
1310 * Clean means that it is a case insensitive form (case folding) and that it is normalized (NFC).
1311 * Additionally a homographs of one character are transformed into one specific character (preferably ASCII
1312 * if it is an ASCII character).
1313 *
1314 * Please be aware that if you change something within this function or within
1315 * functions used here you need to rebuild/update the username_clean column in the users table. And all other
1316 * columns that store a clean string otherwise you will break this functionality.
1317 *
1318 * @param string $text An unclean string, mabye user input (has to be valid UTF-8!)
1319 * @return string Cleaned up version of the input string
1320 */
1321 function utf8_clean_string($text)
1322 {
1323 global $phpbb_root_path, $phpEx;
1324
1325 static $homographs = array();
1326 if (empty($homographs))
1327 {
1328 $homographs = include($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx);
1329 }
1330
1331 $text = utf8_case_fold_nfkc($text);
1332 $text = strtr($text, $homographs);
1333 // Other control characters
1334 $text = preg_replace('#(?:[\x00-\x1F\x7F]+|(?:\xC2[\x80-\x9F])+)#', '', $text);
1335
1336 // we need to reduce multiple spaces to a single one
1337 $text = preg_replace('# {2,}#', ' ', $text);
1338
1339 // we can use trim here as all the other space characters should have been turned
1340 // into normal ASCII spaces by now
1341 return trim($text);
1342 }
1343
1344 /**
1345 * A wrapper for htmlspecialchars($value, ENT_COMPAT, 'UTF-8')
1346 */
1347 function utf8_htmlspecialchars($value)
1348 {
1349 return htmlspecialchars($value, ENT_COMPAT, 'UTF-8');
1350 }
1351
1352 /**
1353 * Trying to convert returned system message to utf8
1354 *
1355 * PHP assumes such messages are ISO-8859-1 so we'll do that too
1356 * and if it breaks messages we'll blame it on them ;-)
1357 */
1358 function utf8_convert_message($message)
1359 {
1360 // First of all check if conversion is neded at all, as there is no point
1361 // in converting ASCII messages from ISO-8859-1 to UTF-8
1362 if (!preg_match('/[\x80-\xFF]/', $message))
1363 {
1364 return utf8_htmlspecialchars($message);
1365 }
1366
1367 // else we need to convert some part of the message
1368 return utf8_htmlspecialchars(utf8_recode($message, 'ISO-8859-1'));
1369 }
1370
1371 /**
1372 * UTF8-compatible wordwrap replacement
1373 *
1374 * @param string $string The input string
1375 * @param int $width The column width. Defaults to 75.
1376 * @param string $break The line is broken using the optional break parameter. Defaults to '\n'.
1377 * @param bool $cut If the cut is set to TRUE, the string is always wrapped at the specified width. So if you have a word that is larger than the given width, it is broken apart.
1378 *
1379 * @return string the given string wrapped at the specified column.
1380 *
1381 */
1382 function utf8_wordwrap($string, $width = 75, $break = "\n", $cut = false)
1383 {
1384 // We first need to explode on $break, not destroying existing (intended) breaks
1385 $lines = explode($break, $string);
1386 $new_lines = array(0 => '');
1387 $index = 0;
1388
1389 foreach ($lines as $line)
1390 {
1391 $words = explode(' ', $line);
1392
1393 for ($i = 0, $size = sizeof($words); $i < $size; $i++)
1394 {
1395 $word = $words[$i];
1396
1397 // If cut is true we need to cut the word if it is > width chars
1398 if ($cut && utf8_strlen($word) > $width)
1399 {
1400 $words[$i] = utf8_substr($word, $width);
1401 $word = utf8_substr($word, 0, $width);
1402 $i--;
1403 }
1404
1405 if (utf8_strlen($new_lines[$index] . $word) > $width)
1406 {
1407 $new_lines[$index] = substr($new_lines[$index], 0, -1);
1408 $index++;
1409 $new_lines[$index] = '';
1410 }
1411
1412 $new_lines[$index] .= $word . ' ';
1413 }
1414
1415 $new_lines[$index] = substr($new_lines[$index], 0, -1);
1416 $index++;
1417 $new_lines[$index] = '';
1418 }
1419
1420 unset($new_lines[$index]);
1421 return implode($break, $new_lines);
1422 }
1423
1424 /**
1425 * UTF8-safe basename() function
1426 *
1427 * basename() has some limitations and is dependent on the locale setting
1428 * according to the PHP manual. Therefore we provide our own locale independent
1429 * basename function.
1430 *
1431 * @param string $filename The filename basename() should be applied to
1432 * @return string The basenamed filename
1433 */
1434 function utf8_basename($filename)
1435 {
1436 // We always check for forward slash AND backward slash
1437 // because they could be mixed or "sneaked" in. ;)
1438 // You know, never trust user input...
1439 if (strpos($filename, '/') !== false)
1440 {
1441 $filename = utf8_substr($filename, utf8_strrpos($filename, '/') + 1);
1442 }
1443
1444 if (strpos($filename, '\\') !== false)
1445 {
1446 $filename = utf8_substr($filename, utf8_strrpos($filename, '\\') + 1);
1447 }
1448
1449 return $filename;
1450 }
1451