| 1 | <?php |
| 2 | /* |
| 3 | Copyright (c) 2011, Andrea Ercolino (http://noteslog.com) |
| 4 | All rights reserved. |
| 5 | |
| 6 | Redistribution and use in source and binary forms, with or without |
| 7 | modification, are permitted provided that the following conditions are met: |
| 8 | * Redistributions of source code must retain the above copyright |
| 9 | notice, this list of conditions and the following disclaimer. |
| 10 | * Redistributions in binary form must reproduce the above copyright |
| 11 | notice, this list of conditions and the following disclaimer in the |
| 12 | documentation and/or other materials provided with the distribution. |
| 13 | * Neither the name of the <organization> nor the |
| 14 | names of its contributors may be used to endorse or promote products |
| 15 | derived from this software without specific prior written permission. |
| 16 | |
| 17 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND |
| 18 | ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
| 19 | WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
| 20 | DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY |
| 21 | DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
| 22 | (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
| 23 | LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
| 24 | ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 25 | (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
| 26 | SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 27 | */ |
| 28 | |
| 29 | |
| 30 | |
| 31 | /** |
| 32 | * @package Ando_Utf8 |
| 33 | */ |
| 34 | class Ando_Utf8_Exception extends Exception |
| 35 | {} |
| 36 | |
| 37 | |
| 38 | |
| 39 | /** |
| 40 | * Basic UTF-8 support |
| 41 | * |
| 42 | * @link http://noteslog.com/ |
| 43 | * @link http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 |
| 44 | * |
| 45 | * @package Ando_Utf8 |
| 46 | */ |
| 47 | class Ando_Utf8 |
| 48 | { |
| 49 | /** |
| 50 | * Escape UTF-8 characters using the given options |
| 51 | * |
| 52 | * About the write.callback option |
| 53 | * -- it receives |
| 54 | * -- -- the given write.arguments |
| 55 | * -- -- the unicode of the current UTF-8 character |
| 56 | * -- -- the current (unescaped) UTF-8 character |
| 57 | * -- it must return the current escaped UTF-8 character |
| 58 | * |
| 59 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 60 | * |
| 61 | * @param string $value |
| 62 | * @param array $options |
| 63 | * 'escapeControlChars' => boolean (default: TRUE), |
| 64 | * 'escapePrintableASCII' => boolean (default: FALSE), |
| 65 | * 'write' => array( |
| 66 | * 'callback' => callable (default: 'sprintf'), |
| 67 | * 'arguments' => array (default: array('\u%04x')), |
| 68 | * ), |
| 69 | * 'extendedUseSurrogate' => boolean (default: true), |
| 70 | * |
| 71 | * @throws Ando_Utf8_Exception If the code point of any char in $value is |
| 72 | * not unicode |
| 73 | * @return string |
| 74 | */ |
| 75 | public static function escape($value, array $options = array()) |
| 76 | { |
| 77 | $options = array_merge(array( |
| 78 | 'escapeControlChars' => true, |
| 79 | 'escapePrintableASCII' => false, |
| 80 | 'write' => array( |
| 81 | 'callback' => 'sprintf', |
| 82 | 'arguments' => array('\u%04x'), |
| 83 | ), |
| 84 | 'extendedUseSurrogate' => true, |
| 85 | ), $options); |
| 86 | if (! self::isCallable($options['write'])) |
| 87 | { |
| 88 | throw new Ando_Utf8_Exception('Expected a valid write handler (callable, array).'); |
| 89 | } |
| 90 | if (self::validateFilters($options) && isset($options['filters']['before-write'])) |
| 91 | { |
| 92 | $value = self::call($options['filters']['before-write'], $value); |
| 93 | } |
| 94 | |
| 95 | $result = ""; |
| 96 | $length = strlen($value); |
| 97 | for($i = 0; $i < $length; $i++) { |
| 98 | $ord_var_c = ord($value[$i]); |
| 99 | |
| 100 | switch (true) { |
| 101 | case ($ord_var_c < 0x20): |
| 102 | // code points 0x00000000..0x0000001F, mask 0xxxxxxx |
| 103 | $utf8Char = $value[$i]; |
| 104 | $result .= $options['escapeControlChars'] |
| 105 | ? self::call($options['write'], array($ord_var_c, $utf8Char)) |
| 106 | : $value[$i]; |
| 107 | break; |
| 108 | |
| 109 | case ($ord_var_c < 0x80): |
| 110 | // code points 0x00000020..0x0000007F, mask 0xxxxxxx |
| 111 | $utf8Char = $value[$i]; |
| 112 | $result .= $options['escapePrintableASCII'] |
| 113 | ? self::call($options['write'], array($ord_var_c, $utf8Char)) |
| 114 | : $value[$i]; |
| 115 | break; |
| 116 | |
| 117 | case (($ord_var_c & 0xE0) == 0xC0): |
| 118 | // code points 0x00000080..0x000007FF, mask 110yyyyy 10xxxxxx |
| 119 | $utf8Char = substr($value, $i, 2); $i += 1; |
| 120 | $code = self::utf8CharToCodePoint($utf8Char); |
| 121 | $result .= self::call($options['write'], array($code, $utf8Char)); |
| 122 | break; |
| 123 | |
| 124 | case (($ord_var_c & 0xF0) == 0xE0): |
| 125 | // code points 0x00000800..0x0000FFFF, mask 1110zzzz 10yyyyyy 10xxxxxx |
| 126 | $utf8Char = substr($value, $i, 3); $i += 2; |
| 127 | $code = self::utf8CharToCodePoint($utf8Char); |
| 128 | $result .= self::call($options['write'], array($code, $utf8Char)); |
| 129 | break; |
| 130 | |
| 131 | case (($ord_var_c & 0xF8) == 0xF0): |
| 132 | // code points 0x00010000..0x0010FFFF, mask 11110www 10zzzzzz 10yyyyyy 10xxxxxx |
| 133 | $utf8Char = substr($value, $i, 4); $i += 3; |
| 134 | if ($options['extendedUseSurrogate']) |
| 135 | { |
| 136 | list($upper, $lower) = self::utf8CharToSurrogatePair($utf8Char); |
| 137 | $result .= self::call($options['write'], array($upper, $utf8Char)); |
| 138 | $result .= self::call($options['write'], array($lower, $utf8Char)); |
| 139 | } |
| 140 | else |
| 141 | { |
| 142 | $code = self::utf8CharToCodePoint($utf8Char); |
| 143 | $result .= self::call($options['write'], array($code, $utf8Char)); |
| 144 | } |
| 145 | break; |
| 146 | |
| 147 | default: |
| 148 | //no more cases in unicode, whose range is 0x00000000..0x0010FFFF |
| 149 | throw new Ando_Utf8_Exception('Expected a valid UTF-8 character.'); |
| 150 | break; |
| 151 | } |
| 152 | } |
| 153 | |
| 154 | return $result; |
| 155 | } |
| 156 | |
| 157 | /** |
| 158 | * Compute the code point of a given UTF-8 character |
| 159 | * |
| 160 | * If available, use the multibye string function mb_convert_encoding |
| 161 | * TODO reject overlong sequences in $utf8Char |
| 162 | * |
| 163 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 164 | * |
| 165 | * @param string $utf8Char |
| 166 | * @throws Ando_Utf8_Exception If the code point of $utf8Char is not unicode |
| 167 | * @return integer |
| 168 | */ |
| 169 | public static function utf8CharToCodePoint($utf8Char) |
| 170 | { |
| 171 | if (function_exists('mb_convert_encoding')) |
| 172 | { |
| 173 | $utf32Char = mb_convert_encoding($utf8Char, 'UTF-32', 'UTF-8'); |
| 174 | } |
| 175 | else |
| 176 | { |
| 177 | $bytes = array('C*'); |
| 178 | list(, $utf8Int) = unpack('N', str_repeat(chr(0), 4 - strlen($utf8Char)) . $utf8Char); |
| 179 | switch (strlen($utf8Char)) |
| 180 | { |
| 181 | case 1: |
| 182 | //Code points U+0000..U+007F |
| 183 | //mask 0xxxxxxx (7 bits) |
| 184 | //map to 00000000 00000000 00000000 0xxxxxxx |
| 185 | $bytes[] = 0; |
| 186 | $bytes[] = 0; |
| 187 | $bytes[] = 0; |
| 188 | $bytes[] = $utf8Int; |
| 189 | break; |
| 190 | |
| 191 | case 2: |
| 192 | //Code points U+0080..U+07FF |
| 193 | //mask 110yyyyy 10xxxxxx (5 + 6 = 11 bits) |
| 194 | //map to 00000000 00000000 00000yyy yyxxxxxx |
| 195 | $bytes[] = 0; |
| 196 | $bytes[] = 0; |
| 197 | $bytes[] = $utf8Int >> 10 & 0x07; |
| 198 | $bytes[] = $utf8Int >> 2 & 0xC0 | $utf8Int & 0x3F; |
| 199 | break; |
| 200 | |
| 201 | case 3: |
| 202 | //Code points U+0800..U+D7FF and U+E000..U+FFFF |
| 203 | //mask 1110zzzz 10yyyyyy 10xxxxxx (4 + 6 + 6 = 16 bits) |
| 204 | //map to 00000000 00000000 zzzzyyyy yyxxxxxx |
| 205 | $bytes[] = 0; |
| 206 | $bytes[] = 0; |
| 207 | $bytes[] = $utf8Int >> 12 & 0xF0 | $utf8Int >> 10 & 0x0F; |
| 208 | $bytes[] = $utf8Int >> 2 & 0xC0 | $utf8Int & 0x3F; |
| 209 | break; |
| 210 | |
| 211 | case 4: |
| 212 | //Code points U+10000..U+10FFFF |
| 213 | //mask 11110www 10zzzzzz 10yyyyyy 10xxxxxx (3 + 6 + 6 + 6 = 21 bits) |
| 214 | //map to 00000000 000wwwzz zzzzyyyy yyxxxxxx |
| 215 | $bytes[] = 0; |
| 216 | $bytes[] = $utf8Int >> 22 & 0x1C | $utf8Int >> 20 & 0x03; |
| 217 | $bytes[] = $utf8Int >> 12 & 0xF0 | $utf8Int >> 10 & 0x0F; |
| 218 | $bytes[] = $utf8Int >> 2 & 0xC0 | $utf8Int & 0x3F; |
| 219 | break; |
| 220 | |
| 221 | default: |
| 222 | //no more cases in unicode, whose range is 0x00000000 - 0x0010FFFF |
| 223 | throw new Ando_Utf8_Exception('Expected a valid UTF-8 character.'); |
| 224 | break; |
| 225 | } |
| 226 | $utf32Char = call_user_func_array('pack', $bytes); |
| 227 | } |
| 228 | list(, $result) = unpack('N', $utf32Char); //unpack returns an array with base 1 |
| 229 | if (0xD800 <= $result && $result <= 0xDFFF) |
| 230 | { |
| 231 | //reserved for UTF-16 surrogates |
| 232 | throw new Ando_Utf8_Exception('Expected a valid UTF-8 character.'); |
| 233 | } |
| 234 | if (0xFFFE == $result || 0xFFFF == $result) |
| 235 | { |
| 236 | //reserved |
| 237 | throw new Ando_Utf8_Exception('Expected a valid UTF-8 character.'); |
| 238 | } |
| 239 | |
| 240 | return $result; |
| 241 | } |
| 242 | |
| 243 | /** |
| 244 | * Compute the surrogate pair of a given extended UTF-8 character |
| 245 | * |
| 246 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 247 | * @link http://en.wikipedia.org/wiki/UTF-16/UCS-2 |
| 248 | * |
| 249 | * @param string $utf8Char |
| 250 | * @throws Ando_Utf8_Exception If the code point of $utf8Char is not extended unicode |
| 251 | * @return array |
| 252 | */ |
| 253 | public static function utf8CharToSurrogatePair($utf8Char) |
| 254 | { |
| 255 | $codePoint = self::utf8CharToCodePoint($utf8Char); |
| 256 | if ($codePoint < 0x10000) |
| 257 | { |
| 258 | throw new Ando_Utf8_Exception('Expected an extended UTF-8 character.'); |
| 259 | } |
| 260 | $codePoint -= 0x10000; |
| 261 | $upperSurrogate = 0xD800 + ($codePoint >> 10); |
| 262 | $lowerSurrogate = 0xDC00 + ($codePoint & 0x03FF); |
| 263 | $result = array($upperSurrogate, $lowerSurrogate); |
| 264 | |
| 265 | return $result; |
| 266 | } |
| 267 | |
| 268 | /** |
| 269 | * Unescape UTF-8 characters from a given escape format |
| 270 | * |
| 271 | * About the read.callback option |
| 272 | * -- it receives |
| 273 | * -- -- the given read.arguments |
| 274 | * -- -- the current match of the pattern with all submatches |
| 275 | * -- it must return the current unicode integer |
| 276 | * |
| 277 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 278 | * |
| 279 | * @param string $value |
| 280 | * @param array $options |
| 281 | * 'read' => array( |
| 282 | * 'pattern' => preg (default: '@\\\\u([0-9A-Fa-f]{4})@'), |
| 283 | * 'callback' => callable (default: create_function('$all, $code', 'return hexdec($code);')), |
| 284 | * 'arguments' => array (deafult: array()), |
| 285 | * ), |
| 286 | * 'extendedUseSurrogate' => boolean (default: TRUE), |
| 287 | * |
| 288 | * @throws Ando_Utf8_Exception If the code point of any char in $value is |
| 289 | * not unicode |
| 290 | * |
| 291 | * @return string |
| 292 | */ |
| 293 | public static function unescape($value, array $options = array()) |
| 294 | { |
| 295 | $options = array_merge(array( |
| 296 | 'read' => array( |
| 297 | 'pattern' => '@\\\\u([0-9A-Fa-f]{4})@', |
| 298 | 'callback' => create_function('$all, $code', 'return hexdec($code);'), |
| 299 | 'arguments' => array(), |
| 300 | ), |
| 301 | 'extendedUseSurrogate' => true, |
| 302 | ), $options); |
| 303 | |
| 304 | if (! self::isCallable($options['read'])) |
| 305 | { |
| 306 | throw new Ando_Utf8_Exception('Expected a valid read handler (callable, array).'); |
| 307 | } |
| 308 | $thereAreFilters = self::validateFilters($options); |
| 309 | |
| 310 | $result = ""; |
| 311 | while (preg_match($options['read']['pattern'], $value, $matches, PREG_OFFSET_CAPTURE)) |
| 312 | { |
| 313 | $unicode = self::eatUpMatches($result, $value, $matches, $options['read']); |
| 314 | if ($options['extendedUseSurrogate'] && (0xD800 <= $unicode && $unicode < 0xDC00)) |
| 315 | { |
| 316 | $upperSurrogate = $unicode; |
| 317 | if (! preg_match($options['read']['pattern'], $value, $matches, PREG_OFFSET_CAPTURE)) |
| 318 | { |
| 319 | throw new Ando_Utf8_Exception('Expected an extended UTF-8 character.'); |
| 320 | } |
| 321 | $unicode = self::eatUpMatches($result, $value, $matches, $options['read']); |
| 322 | $utf8Char = self::utf8CharFromSurrogatePair(array($upperSurrogate, $unicode)); |
| 323 | } |
| 324 | else |
| 325 | { |
| 326 | $utf8Char = self::utf8CharFromCodePoint($unicode); |
| 327 | } |
| 328 | $result .= $utf8Char; |
| 329 | } |
| 330 | $result .= $value; |
| 331 | |
| 332 | if ($thereAreFilters && isset($options['filters']['after-read'])) |
| 333 | { |
| 334 | $result = self::call($options['filters']['after-read'], $result); |
| 335 | } |
| 336 | |
| 337 | return $result; |
| 338 | } |
| 339 | |
| 340 | /** |
| 341 | * Compute the UTF-8 character of a given code point |
| 342 | * |
| 343 | * If available, use the multibye string function mb_convert_encoding |
| 344 | * |
| 345 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 346 | * |
| 347 | * @param integer $codePoint |
| 348 | * @throws Ando_Utf8_Exception if the code point is not unicode |
| 349 | * @return string |
| 350 | */ |
| 351 | public static function utf8CharFromCodePoint($codePoint) |
| 352 | { |
| 353 | if (0xD800 <= $codePoint && $codePoint <= 0xDFFF) |
| 354 | { |
| 355 | //reserved for UTF-16 surrogates |
| 356 | throw new Ando_Utf8_Exception('Expected a valid code point.'); |
| 357 | } |
| 358 | if (0xFFFE == $codePoint || 0xFFFF == $codePoint) |
| 359 | { |
| 360 | //reserved |
| 361 | throw new Ando_Utf8_Exception('Expected a valid code point.'); |
| 362 | } |
| 363 | |
| 364 | if (function_exists('mb_convert_encoding')) |
| 365 | { |
| 366 | $utf32Char = pack('N', $codePoint); |
| 367 | $result = mb_convert_encoding($utf32Char, 'UTF-8', 'UTF-32'); |
| 368 | } |
| 369 | else |
| 370 | { |
| 371 | $bytes = array('C*'); |
| 372 | switch (true) |
| 373 | { |
| 374 | case ($codePoint < 0x80): |
| 375 | //Code points U+0000..U+007F |
| 376 | //mask 0xxxxxxx (7 bits) |
| 377 | //map from xxxxxxx |
| 378 | $bytes[] = $codePoint; |
| 379 | break; |
| 380 | |
| 381 | case ($codePoint < 0x800): |
| 382 | //Code points U+0080..U+07FF |
| 383 | //mask 110yyyyy 10xxxxxx (5 + 6 = 11 bits) |
| 384 | //map from yyy yyxxxxxx |
| 385 | $bytes[] = 0xC0 | $codePoint >> 6; |
| 386 | $bytes[] = 0x80 | $codePoint & 0x3F; |
| 387 | break; |
| 388 | |
| 389 | case ($codePoint < 0x10000): |
| 390 | //Code points U+0800..U+D7FF and U+E000..U+FFFF |
| 391 | //mask 1110zzzz 10yyyyyy 10xxxxxx (4 + 6 + 6 = 16 bits) |
| 392 | //map from zzzzyyyy yyxxxxxx |
| 393 | $bytes[] = 0xE0 | $codePoint >> 12; |
| 394 | $bytes[] = 0x80 | $codePoint >> 6 & 0x3F; |
| 395 | $bytes[] = 0x80 | $codePoint & 0x3F; |
| 396 | break; |
| 397 | |
| 398 | case ($codePoint < 0x110000): |
| 399 | //Code points U+10000..U+10FFFF |
| 400 | //mask 11110www 10zzzzzz 10yyyyyy 10xxxxxx (3 + 6 + 6 + 6 = 21 bits) |
| 401 | //map from wwwzz zzzzyyyy yyxxxxxx |
| 402 | $bytes[] = 0xF0 | $codePoint >> 18; |
| 403 | $bytes[] = 0x80 | $codePoint >> 12 & 0x3F; |
| 404 | $bytes[] = 0x80 | $codePoint >> 6 & 0x3F; |
| 405 | $bytes[] = 0x80 | $codePoint & 0x3F; |
| 406 | break; |
| 407 | |
| 408 | default: |
| 409 | throw new Ando_Utf8_Exception('Expected a valid code point.'); |
| 410 | break; |
| 411 | } |
| 412 | $result = call_user_func_array('pack', $bytes); |
| 413 | } |
| 414 | return $result; |
| 415 | } |
| 416 | |
| 417 | /** |
| 418 | * Compute the extended UTF-8 character of a given surrogate pair |
| 419 | * |
| 420 | * @link http://noteslog.com/post/escaping-and-unescaping-utf-8-characters-in-php/ |
| 421 | * @link http://en.wikipedia.org/wiki/UTF-16/UCS-2 |
| 422 | * |
| 423 | * @param array $surrogatePair |
| 424 | * @throws Ando_Utf8_Exception If the surrogate pair is not extended unicode |
| 425 | * @return string |
| 426 | */ |
| 427 | public static function utf8CharFromSurrogatePair($surrogatePair) |
| 428 | { |
| 429 | list($upperSurrogate, $lowerSurrogate) = $surrogatePair; |
| 430 | if (! (0xD800 <= $upperSurrogate && $upperSurrogate < 0xDC00)) |
| 431 | { |
| 432 | throw new Ando_Utf8_Exception('Expected an extended UTF-8 character.'); |
| 433 | } |
| 434 | if (! (0xDC00 <= $lowerSurrogate && $lowerSurrogate < 0xE000)) |
| 435 | { |
| 436 | throw new Ando_Utf8_Exception('Expected an extended UTF-8 character.'); |
| 437 | } |
| 438 | $codePoint = ($upperSurrogate & 0x03FF) << 10 | ($lowerSurrogate & 0x03FF); |
| 439 | $codePoint += 0x10000; |
| 440 | $result = self::utf8CharFromCodePoint($codePoint); |
| 441 | |
| 442 | return $result; |
| 443 | } |
| 444 | |
| 445 | /** |
| 446 | * Validate filters. If there are filters return true, else false |
| 447 | * |
| 448 | * @param array $options |
| 449 | * @throws Ando_Utf8_Exception If there are malformed filters |
| 450 | * @return boolean |
| 451 | */ |
| 452 | protected static function validateFilters($options) |
| 453 | { |
| 454 | if (isset($options['filters'])) |
| 455 | { |
| 456 | if (! is_array($options['filters'])) |
| 457 | { |
| 458 | throw new Ando_Utf8_Exception('Expected valid filters.'); |
| 459 | } |
| 460 | foreach ($options['filters'] as $key => $value) |
| 461 | { |
| 462 | if (! self::isCallable($value)) |
| 463 | { |
| 464 | throw new Ando_Utf8_Exception("Expected a valid $key handler."); |
| 465 | } |
| 466 | } |
| 467 | return true; |
| 468 | } |
| 469 | return false; |
| 470 | } |
| 471 | |
| 472 | /** |
| 473 | * A little calling interface: validation |
| 474 | * |
| 475 | * @param array $handler |
| 476 | * @return boolean |
| 477 | */ |
| 478 | private static function isCallable($handler) |
| 479 | { |
| 480 | $result = is_callable($handler['callback']) && is_array($handler['arguments']); |
| 481 | return $result; |
| 482 | } |
| 483 | |
| 484 | /** |
| 485 | * A little calling interface: call |
| 486 | * |
| 487 | * @param array $handler |
| 488 | * @param mixed $args |
| 489 | * @return mixed |
| 490 | */ |
| 491 | private static function call($handler, $args) |
| 492 | { |
| 493 | $args = array_merge($handler['arguments'], is_array($args) ? $args : array($args)); |
| 494 | $result = call_user_func_array($handler['callback'], $args); |
| 495 | return $result; |
| 496 | } |
| 497 | |
| 498 | /** |
| 499 | * Return the transposition of the given array |
| 500 | * |
| 501 | * @param array $rows |
| 502 | * @return array |
| 503 | */ |
| 504 | private static function transpose($rows) |
| 505 | { |
| 506 | $result = call_user_func_array('array_map', array_merge(array(null), $rows)); |
| 507 | return $result; |
| 508 | } |
| 509 | |
| 510 | /** |
| 511 | * 1: update $processed with the unmatched substring before $matches |
| 512 | * 2: update $value with the rest of the substring after $matches |
| 513 | * 3: return unicode read from the matched substring in $matches |
| 514 | * |
| 515 | * @param string $processed |
| 516 | * @param string $value |
| 517 | * @param array $matches |
| 518 | * @param array $handler |
| 519 | * @return integer |
| 520 | */ |
| 521 | private static function eatUpMatches(&$processed, &$value, $matches, $handler) |
| 522 | { |
| 523 | $match = $matches[0][0]; |
| 524 | $offset = $matches[0][1]; |
| 525 | $processed .= substr($value, 0, $offset); |
| 526 | $value = substr($value, $offset + strlen($match)); |
| 527 | |
| 528 | $matches = self::transpose($matches); |
| 529 | $args = $matches[0]; |
| 530 | $result = self::call($handler, $args); |
| 531 | |
| 532 | return $result; |
| 533 | } |
| 534 | |
| 535 | } |