Text.class.php (13030B)
1 <?php 2 // OpenRat Content Management System 3 // Copyright (C) 2002 Jan Dankert, jandankert@jandankert.de 4 // 5 // This program is free software; you can redistribute it and/or 6 // modify it under the terms of the GNU General Public License 7 // as published by the Free Software Foundation; either version 2 8 // of the License, or (at your option) any later version. 9 // 10 // This program is distributed in the hope that it will be useful, 11 // but WITHOUT ANY WARRANTY; without even the implied warranty of 12 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 // GNU General Public License for more details. 14 // 15 // You should have received a copy of the GNU General Public License 16 // along with this program; if not, write to the Free Software 17 // Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. 18 19 20 namespace util; 21 22 use cms\base\Configuration; 23 24 /** 25 * Nuetzliche Funktionen fuer das Bearbeiten von Texten/Zeichenketten 26 * @author $Author$ 27 * @version $Revision$ 28 * @package openrat.services 29 */ 30 class Text 31 { 32 const ARROW_RIGHT = "\xE2\x86\x92"; 33 const FILE_SEP = " \xE2\x86\x92 "; 34 35 36 /** 37 * 38 * @param unknown $key 39 * @param unknown $text 40 * @return string|unknown 41 */ 42 public static function accessKey($key, $text) 43 { 44 $pos = strpos(strtolower($text), strtolower($key)); 45 46 if ($pos !== false) 47 return substr($text, 0, max($pos, 0)) . '<span class="accesskey">' . substr($text, $pos, 1) . '</span>' . substr($text, $pos + 1); 48 else 49 return $text; 50 } 51 52 53 /** 54 * Einen Text auf eine bestimmte Laenge begrenzen. 55 * 56 * Ist der Text zu lang, so wird abgeschnitten und 57 * eine Zeichenkette angehaengt. 58 * 59 * @param String Text, der zu begrenzen ist 60 * @param Integer maximale Laenge des Textes (optional) 61 * @param Text, der an gekuerzten Text angehangen wird (optional) 62 */ 63 public static function maxLength($text, $laenge = 20, $append = '...', $where = STR_PAD_RIGHT) 64 { 65 if (strlen($text) > $laenge) { 66 if ($where == STR_PAD_RIGHT) 67 $text = substr($text, 0, $laenge) . $append; 68 elseif ($where == STR_PAD_BOTH) 69 $text = substr($text, 0, $laenge / 2) . $append . substr($text, strlen($text) - ($laenge / 2)); 70 } 71 72 return $text; 73 } 74 75 76 /** 77 * Umwandeln von BB-Code in Wiki-Textauszeichnungen 78 * 79 * @param text zu bearbeitender Text 80 * 81 * @return String Ausgabe 82 */ 83 public static function bbCode2Wiki($inhalt) 84 { 85 $inhalt = preg_replace('/\[b\]([^\[]*)\[\/b\]/i', '*\\1*', $inhalt); 86 $inhalt = preg_replace('/\[i\]([^\[]*)\[\/i\]/i', '_\\1_', $inhalt); 87 $inhalt = preg_replace('/\[code\]([^\[]*)\[\/code\]/i', '=\\1=', $inhalt); 88 89 $inhalt = preg_replace('/\[url\]([^\[]*)\[\/url\]/i', '"\\1"->"\\1"', $inhalt); 90 $inhalt = preg_replace('/\[url=([^\[]*)\]([^\[]*)\[\/url\]/i', '"\\2"->"\\1"', $inhalt); 91 92 return $inhalt; 93 } 94 95 96 /** 97 * Umwandeln von einfachen HTML-Befehlen in Wiki-Textauszeichnungen 98 * 99 * @param text zu bearbeitender Text 100 * 101 * @return String Ausgabe 102 */ 103 public static function Html2Wiki($inhalt) 104 { 105 $inhalt = preg_replace('/<b(.*)>(.*)<\/b>/i', '*\\2*', $inhalt); 106 $inhalt = preg_replace('/<i(.*)>(.*)<\/i>/i', '_\\2_', $inhalt); 107 $inhalt = preg_replace('/<a(.*)href="(.*)">(.*)<\/a>/i', '"\\3"->"\\2"', $inhalt); 108 109 return $inhalt; 110 } 111 112 113 /** 114 * HTML-Entitaeten fuer HTML-Tags verwenden 115 * 116 * @param String Text, in dem HTML-Tags umgewandelt werden sollen 117 * @return String Ausgabe 118 */ 119 public static function encodeHtml($inhalt) 120 { 121 //$inhalt = str_replace('&','&',$inhalt); 122 $inhalt = str_replace('"', '"', $inhalt); 123 $inhalt = str_replace('<', '<', $inhalt); 124 $inhalt = str_replace('>', '>', $inhalt); 125 126 return $inhalt; 127 } 128 129 130 /** 131 * Ersetzt Sonderzeichen durch HTML-�quivalente.<br> 132 * Z.B. Ersetzt "(c)" durch "©". 133 */ 134 public static function replaceHtmlChars($text) 135 { 136 $htmlConfig = Configuration::subset(['editor','html']); 137 138 foreach ( $htmlConfig->get('replace',[]) as $repl) { 139 list($ersetze, $mit) = explode(':', $repl . ':'); 140 $text = str_replace($ersetze, $mit, $text); 141 } 142 143 return $text; 144 } 145 146 147 /** 148 * HTML-Entitaeten fuer HTML-Tags verwenden 149 * 150 * @param String Text, in dem HTML-Tags umgewandelt werden sollen 151 * @return String Ausgabe 152 */ 153 public static function encodeHtmlSpecialChars($inhalt) 154 { 155 return Text::replaceHtmlChars($inhalt); 156 } 157 158 159 const DIFF_NEW = 'new'; 160 const DIFF_OLD = 'old'; 161 const DIFF_EQUAL = 'equal'; 162 const DIFF_CHANGED = 'notequal'; 163 const DIFF_EMPTY = 'empty'; 164 165 /** 166 * Vergleicht 2 Text-Arrays und ermittelt eine Darstellung der Unterschiede 167 * @param $from_text array text lines 168 * @param $to_text array text lines 169 * @return array[] an array containing 2 arrays with the same length 170 */ 171 public static function diff($from_text, $to_text) 172 { 173 /** 174 * Creating a diff entry 175 * @param $text 176 * @param $line 177 * @param $type 178 * @return array 179 */ 180 $createEntry = function($text, $line, $type) { 181 return [ 182 'text' => $text, 183 'line' => $line, 184 'type' => $type, 185 ]; 186 }; 187 $emptyEntry = $createEntry(null,null,self::DIFF_EMPTY); 188 189 // Zaehler pro Textarray 190 $pos_from = -1; 191 $pos_to = -1; 192 193 // Ergebnis-Arrays 194 $from_out = []; 195 $to_out = []; 196 197 while (true) { 198 $pos_from++; 199 $pos_to++; 200 201 if (!isset($from_text[$pos_from]) && 202 !isset($to_text [$pos_to])) { 203 // Text in ist 'neu' und 'alt' zuende. Ende der Schleife. 204 break; 205 } elseif 206 (isset($from_text[$pos_from]) && 207 !isset($to_text [$pos_to])) { 208 // Text in 'neu' ist zuende, die Restzeilen von 'alt' werden ausgegeben 209 while (isset($from_text[$pos_from])) { 210 $from_out[] = $createEntry( $from_text[$pos_from],$pos_from + 1, self::DIFF_OLD); 211 $to_out [] = $emptyEntry; 212 $pos_from++; 213 } 214 break; 215 } elseif 216 (!isset($from_text[$pos_from]) && 217 isset($to_text [$pos_to])) { 218 // Umgekehrter Fall: Text in 'alt' ist zuende, Restzeilen aus 'neu' werden ausgegeben 219 while (isset($to_text[$pos_to])) { 220 $from_out[] = $emptyEntry; 221 $to_out [] = $createEntry($to_text[$pos_to], $pos_to + 1, self::DIFF_NEW); 222 $pos_to++; 223 } 224 break; 225 } elseif( rtrim($from_text[$pos_from]) != rtrim($to_text[$pos_to]) ) { 226 // Zeilen sind vorhanden, aber ungleich 227 // Wir suchen jetzt die naechsten beiden Zeilen, die gleich sind. 228 $max_entf = min(count($from_text) - $pos_from - 1, count($to_text) - $pos_to - 1); 229 230 for ($a = 0; $a <= $max_entf; $a++) { 231 for ($b = 0; $b <= $max_entf; $b++) { 232 if (trim($from_text[$pos_from + $b]) != '' && 233 $from_text[$pos_from + $b] == $to_text[$pos_to + $a]) { 234 $pos_gef_from = $pos_from + $b; 235 $pos_gef_to = $pos_to + $a; 236 break; 237 } 238 239 if (trim($from_text[$pos_from + $a]) != '' && 240 $from_text[$pos_from + $a] == $to_text[$pos_to + $b]) { 241 $pos_gef_from = $pos_from + $a; 242 $pos_gef_to = $pos_to + $b; 243 break; 244 } 245 } 246 247 if ($b <= $max_entf) { 248 break; 249 } 250 } 251 252 if ($a <= $max_entf) { 253 // Gleiche Zeile gefunden 254 255 if ($pos_gef_from - $pos_from == 0) 256 $type = self::DIFF_NEW; 257 elseif 258 ($pos_gef_to - $pos_to == 0) 259 $type = self::DIFF_OLD; 260 else 261 $type = self::DIFF_CHANGED; 262 263 while ($pos_gef_from - $pos_from > 0 && 264 $pos_gef_to - $pos_to > 0) { 265 $from_out[] = $createEntry($from_text[$pos_from], $pos_from + 1, $type); 266 $to_out [] = $createEntry($to_text [$pos_to ], $pos_to + 1, $type); 267 268 $pos_from++; 269 $pos_to++; 270 } 271 272 while ($pos_gef_from - $pos_from > 0) { 273 $from_out[] = $createEntry($from_text[$pos_from], $pos_from + 1, $type); 274 $to_out [] = $emptyEntry; 275 $pos_from++; 276 } 277 278 while ($pos_gef_to - $pos_to > 0) { 279 $from_out[] = $emptyEntry; 280 $to_out [] = $createEntry($to_text [$pos_to], $pos_to + 1, $type); 281 $pos_to++; 282 } 283 $pos_from--; 284 $pos_to--; 285 } else { 286 // Keine gleichen Zeilen gefunden 287 288 while (true) { 289 if (!isset($from_text[$pos_from]) && 290 !isset($to_text [$pos_to ])) { 291 break; 292 } elseif 293 (isset($from_text[$pos_from]) && 294 !isset($to_text [$pos_to])) { 295 $from_out[] = array($from_text[$pos_from], $pos_from + 1, self::DIFF_CHANGED); 296 $to_out [] = $emptyEntry; 297 } elseif 298 (!isset($from_text[$pos_from]) && 299 isset($to_text [$pos_to])) { 300 $from_out[] = $emptyEntry; 301 $to_out [] = $createEntry($to_text [$pos_to] , $pos_to + 1, self::DIFF_CHANGED); 302 } else { 303 $from_out[] = $createEntry($from_text[$pos_from], $pos_from + 1, self::DIFF_CHANGED); 304 $to_out [] = $createEntry($to_text [$pos_to] , $pos_to + 1, self::DIFF_CHANGED); 305 } 306 $pos_from++; 307 $pos_to++; 308 } 309 } 310 } else { 311 // Zeilen sind gleich 312 $from_out[] = $createEntry($from_text[$pos_from], $pos_from + 1, self::DIFF_EQUAL); 313 $to_out [] = $createEntry($to_text [$pos_to] , $pos_to + 1, self::DIFF_EQUAL); 314 } 315 } 316 317 return ( [$from_out, $to_out] ); 318 } 319 320 321 /** 322 * Saeubert eine Zeichenkette. 323 * 324 * Es werden ungueltige Zeichen aus einer Zeichenkette entfernt. Es wird mit einer Whitelist 325 * gearbeitet, d.h. die erlaubten Zeichen werden angegeben. 326 * 327 * @param $eingabe Die Eingabe-Zeichenkette, aus der ungueltige Zeichen entfernt werden sollen. 328 * @param $erlaubt Die erlaubten Zeichen (eine "White-List") 329 * @return String die aufgeräumte Zeichenkette 330 */ 331 public static function clean($eingabe, $erlaubt) 332 { 333 $first = strtr($eingabe, $erlaubt, str_repeat("\x01", strlen($erlaubt))); 334 $second = strtr($eingabe, $first, str_repeat("\x00", strlen($first))); 335 return str_replace("\x00", '', $second); 336 } 337 338 339 /** 340 * Searches for Object-Ids in a text. 341 * Searches in the provided text for URLs with "__OID__nnn__", where nnn is an object id. 342 * @param $text 343 * @return array 344 */ 345 public static function parseOID($text) 346 { 347 $oids = array(); 348 $treffer = array(); 349 350 // This are all chars which are used in our URLs. 351 // Sure, there are more, but not used by this system. 352 $urlChars = '[A-Za-z0-9_.:,\/=+&?-]'; 353 354 preg_match_all('/(' . $urlChars . '*)__OID__([0-9]+)__(' . $urlChars . '*)/', $text, $treffer, PREG_SET_ORDER); 355 356 foreach ($treffer as $t) { 357 358 $id = $t[2]; 359 $match = $t[0]; 360 361 if (!isset($oids[$id])) 362 $oids[$id] = array(); 363 364 $oids[$id][] = $match; 365 } 366 367 return $oids; 368 } 369 370 371 372 373 // Source: http://de.php.net/manual/de/function.htmlentities.php#96648 374 // Thx to silverbeat! 375 // When using UTF-8 as a charset, htmlentities will only convert 1-byte and 2-byte characters. 376 // Use this function if you also want to convert 3-byte and 4-byte characters: 377 // converts a UTF8-string into HTML entities 378 public static function translateutf8tohtml($txt) 379 { 380 //$txt = html_entity_decode($txt); 381 $txt2 = ''; 382 for ($i = 0; $i < strlen($txt); $i++) { 383 $o = ord($txt[$i]); 384 if ($o < 128) { 385 // 0..127: raw 386 $txt2 .= $txt[$i]; 387 } else { 388 $o1 = 0; 389 $o2 = 0; 390 $o3 = 0; 391 if ($i < strlen($txt) - 1) $o1 = ord($txt[$i + 1]); 392 if ($i < strlen($txt) - 2) $o2 = ord($txt[$i + 2]); 393 if ($i < strlen($txt) - 3) $o3 = ord($txt[$i + 3]); 394 $hexval = 0; 395 if ($o >= 0xc0 && $o < 0xc2) { 396 // INVALID --- should never occur: 2-byte UTF-8 although value < 128 397 $hexval = $o1; 398 $i++; 399 } elseif ($o >= 0xc2 && $o < 0xe0 && $o1 >= 0x80) { 400 // 194..223: 2-byte UTF-8 401 $hexval |= ($o & 0x1f) << 6; // 1. byte: five bits of 1. char 402 $hexval |= ($o1 & 0x3f); // 2. byte: six bits of 2. char 403 $i++; 404 } elseif ($o >= 0xe0 && $o < 0xf0 && $o1 >= 0x80 && $o2 >= 0x80) { 405 // 224..239: 3-byte UTF-8 406 $hexval |= ($o & 0x0f) << 12; // 1. byte: four bits of 1. char 407 $hexval |= ($o1 & 0x3f) << 6; // 2.+3. byte: six bits of 2.+3. char 408 $hexval |= ($o2 & 0x3f); 409 $i += 2; 410 } elseif ($o >= 0xf0 && $o < 0xf4 && $o1 >= 0x80) { 411 // 240..244: 4-byte UTF-8 412 $hexval |= ($o & 0x07) << 18; // 1. byte: three bits of 1. char 413 $hexval |= ($o1 & 0x3f) << 12; // 2.-4. byte: six bits of 2.-4. char 414 $hexval |= ($o2 & 0x3f) << 6; 415 $hexval |= ($o3 & 0x3f); 416 $i += 3; 417 } else { 418 // don't know ... just encode 419 $hexval = $o; 420 } 421 $hexstring = dechex($hexval); 422 if (strlen($hexstring) % 2) $hexstring = '0' . $hexstring; 423 $txt2 .= '&#x' . $hexstring . ';'; 424 } 425 } 426 $result = $txt2; 427 428 return $result; 429 } 430 431 432 public static function hexDump( $data, $newline="\n") 433 { 434 $width = 16; # number of bytes per line 435 $pad = '.'; # padding for non-visible characters 436 437 $from = ''; 438 $to = ''; 439 $output = ''; 440 441 for ($i=0; $i<=0xFF; $i++) 442 { 443 $from .= chr($i); 444 $to .= ($i >= 0x20 && $i <= 0x7E) ? chr($i) : $pad; 445 } 446 447 $hex = str_split(bin2hex($data), $width*2); 448 $chars = str_split(strtr($data, $from, $to), $width); 449 450 foreach ($hex as $i=>$line) 451 $output .= 452 implode(' ',array_pad(str_split($chars[$i]),16,' ') ) . ' ['.str_pad($chars[$i],16).']' . $newline . 453 implode(' ' ,array_pad(str_split($line ,2),16,' ') ) . $newline; 454 return $output; 455 } 456 457 458 459 } 460