2 * put your module comment here
14 * Statische Hilfsmethoden zur Stringbehandlung
19 public final class StringUtil {
22 * Wandelt Datum in einen 8-ziffrigen String um (yyyymmdd)
24 * @return 8-ziffriger String (yyyymmdd)
27 public static final String date2webdbDate (GregorianCalendar theDate) {
28 StringBuffer webdbDate = new StringBuffer();
29 webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
30 webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
31 webdbDate.append(pad2(theDate.get(Calendar.DATE)));
32 return webdbDate.toString();
36 * wandelt Calendar in dd.mm.yyyy / hh.mm um
38 * @return String mit (dd.mm.yyyy / hh.mm um)
40 public static String date2readableDateTime (GregorianCalendar theDate) {
43 readable += pad2(theDate.get(Calendar.DATE));
44 readable += "." + pad2(theDate.get(Calendar.MONTH) + 1);
45 readable += "." + String.valueOf(theDate.get(Calendar.YEAR));
46 hour = theDate.get(Calendar.HOUR);
47 if (theDate.get(Calendar.AM_PM) == Calendar.PM)
49 readable += " / " + pad2(hour);
50 readable += ":" + pad2(theDate.get(Calendar.MINUTE));
55 * wandelt eine Datum in einen 8-buchstabigen String, der durch <code>/</code>
59 * @return String mit <code>/yyyy/mm/dd</code>
61 public static final String webdbDate2path (String webdbDate) {
62 StringBuffer path = new StringBuffer();
63 path.append("/").append(webdbDate.substring(0, 4));
64 path.append("/").append(webdbDate.substring(4, 6));
67 //path.append("/").append(webdbDate.substring(6, 8));
68 return path.toString();
72 * wandelt Calendar in dd.mm.yyyy um
75 * @return String mit <code>dd.mm.yyyy</code>
77 public static final String webdbDate2readableDate (String webdbDate) {
79 date += webdbDate.substring(6, 8);
80 date += "." + webdbDate.substring(4, 6);
81 date += "." + webdbDate.substring(0, 4);
87 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
90 public static String dateToReadableDate(String date) {
91 StringBuffer returnDate = new StringBuffer();
94 returnDate.append(date.substring(8,10)).append('.');
95 returnDate.append(date.substring(5,7)).append('.');
96 returnDate.append(date.substring(0,4)).append(' ');
97 returnDate.append(date.substring(11,16));
99 return returnDate.toString();
104 * schließt einen String in Anführungsszeichen ein, falls er Leerzeichen o.ä. enthält
106 * @return gequoteter String
108 public static String quoteIfNecessary(String s) {
109 for (int i = 0; i < s.length(); i++)
110 if (!(Character.isLetterOrDigit(s.charAt(i)) || s.charAt(i) == '.'))
111 return quote(s, '"');
116 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
117 * "gefährliche" Zeichen innerhalb des Strings
118 * Quotes special SQL-characters in <code>s</code>
120 * @return geqoteter String
122 public static String quote(String s)
124 //String s2 = quote(s, '\'');
127 //Because of '?-Bug in Postgresql-JDBC-Driver
128 StringBuffer temp = new StringBuffer();
129 for(int i=0;i<s.length();i++){
130 if(s.charAt(i)=='\''){
131 temp.append("´");
133 temp.append(s.charAt(i));
136 String s2 = temp.toString();
139 s2 = quote(s2, '\"');
144 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
145 * "gefährliche" Zeichen innerhalb des Strings
147 * @param s String, der gequoted werden soll
148 * @param quoteChar zu quotendes Zeichen
149 * @return gequoteter String
151 public static String quote(String s, char quoteChar)
153 StringBuffer buf = new StringBuffer(s.length());
155 while (pos < s.length()) {
156 int i = s.indexOf(quoteChar, pos);
157 if (i < 0) i = s.length();
158 buf.append(s.substring(pos, i));
160 if (pos < s.length()) {
162 buf.append(quoteChar);
166 return buf.toString();
170 * replaces dangerous characters in <code>s</code>
174 public static String unquote(String s)
177 StringBuffer buf = new StringBuffer(s.length());
179 String searchString = "\\"+quoteChar;
180 while (pos < s.length()) {
181 int i = s.indexOf(searchString, pos);
182 if (i < 0) i = s.length();
183 buf.append(s.substring(pos, i));
186 return buf.toString();
190 * Wandelet String in byte[] um.
192 * @return byte[] des String
195 public static byte[] stringToBytes(String s) {
196 String crlf = System.getProperty("line.separator");
197 if (!crlf.equals("\n"))
198 s = replace(s, "\n", crlf);
199 // byte[] buf = new byte[s.length()];
200 byte[] buf = s.getBytes();
205 * Ersetzt in String <code>s</code> das <code>pattern</code> durch <code>substitute</code>
209 * @return String mit den Ersetzungen
211 public static String replace(String s, String pattern, String substitute) {
212 int i = 0, pLen = pattern.length(), sLen = substitute.length();
213 StringBuffer buf = new StringBuffer(s.length());
215 int j = s.indexOf(pattern, i);
217 buf.append(s.substring(i));
220 buf.append(s.substring(i, j));
221 buf.append(substitute);
225 return buf.toString();
229 * Ersetzt in String <code>s</code> das Regexp <code>pattern</code> durch <code>substitute</code>
233 * @return String mit den Ersetzungen
235 public static String regexpReplace(String haystack, String pattern, String substitute) {
237 RE regex = new RE(pattern);
238 return regex.substituteAll(haystack,substitute);
239 } catch(REException ex){
248 * Fügt einen Separator an den Pfad an
250 * @return Pfad mit Separator am Ende
252 public static final String addSeparator (String path) {
253 return path.length() == 0 || path.endsWith(File.separator) ? path : path
254 + File.separatorChar;
258 * Fügt ein <code>/</code> ans ende des Strings and
260 * @return Pfad mit <code>/</code> am Ende
262 public static final String addSlash (String path) {
263 return path.length() == 0 || path.endsWith("/") ? path : path + '/';
267 * Löscht <code>/</code> am Ende des Strings, falls vorhanden
269 * @return String ohne <code>/</code> am Ende
271 public static final String removeSlash (String path) {
272 return path.length() > 1 && path.endsWith("/") ? path.substring(0, path.length()
277 * Checks to see if the path is absolute by looking for a leading file
279 * @todo deal with windows drive letters.
283 public static boolean isAbsolutePath (String path) {
284 return path.startsWith(File.separator);
288 * Löscht Slash am Anfang des Strings
292 public static String removeFirstSlash (String path) {
293 return path.startsWith("/") ? path.substring(1) : path;
297 * formatiert eine Zahl (0-99) zweistellig (z.B. 5 -> 05)
298 * @return zwistellige Zahl
300 public static String pad2 (int number) {
301 return number < 10 ? "0" + number : String.valueOf(number);
305 * formatiert eine Zahl (0-999) dreistellig (z.B. 7 -> 007)
307 * @return 3-stellige Zahl
309 public static String pad3 (int number) {
310 return number < 10 ? "00" + number : number < 100 ? "0" + number : String.valueOf(number);
314 * Konvertiert Unix-Linefeeds in Win-Linefeeds
316 * @return Konvertierter String
318 public static String unixLineFeedsToWin(String s) {
321 i = s.indexOf('\n', i+1);
323 if ((i == 0 || s.charAt(i-1) != '\r') &&
324 (i == s.length()-1 || s.charAt(i+1) != '\r')) {
325 s = s.substring(0, i)+'\r'+s.substring(i);
334 * verwandelt einen String in eine gültige Url, konvertiert Sonderzeichen
335 * und Spaces werden zu Underscores
337 * @return gültige Url
339 public static String convert2url(String s) {
341 StringBuffer buf = new StringBuffer();
342 for(int i = 0; i < s.length(); i++ ) {
343 switch( s.charAt( i ) ) {
345 buf.append( "oe" ); break;
347 buf.append( "ae" ); break;
349 buf.append( "ue" ); break;
351 buf.append( "a" ); break;
354 buf.append( "_" ); break;
356 if( buf.charAt( buf.length() - 1 ) != '_' ) {
361 buf.append( s.charAt( i ) );
364 return buf.toString();
368 * wandelt Sonderzeichen in Quotes um
370 * @return Kovertierter String
372 public static String encodeHtml(String s) {
373 StringBuffer buf = new StringBuffer();
374 for(int i=0;i < s.length(); i++ ) {
376 /** @todo looks inefficient */
377 if (s.charAt(i)=='&') {
378 // convert html to xml-parsable representation
379 if( s.indexOf( "ö", i ) == i ) {
380 buf.append( "ö" ); i += 5;
383 if( s.indexOf( "ä", i ) == i ) {
384 buf.append( "ä" ); i += 5;
387 if( s.indexOf( "ü", i ) == i ) {
388 buf.append( "ü" ); i += 5;
391 if( s.indexOf( "Ö", i ) == i ) {
392 buf.append( "Ö" ); i += 5;
395 if( s.indexOf( "Ä", i ) == i ) {
396 buf.append( "Ä" ); i += 5;
399 if( s.indexOf( "Ü", i ) == i ) {
400 buf.append( "Ü" ); i += 5;
403 if( s.indexOf( "ß", i ) == i ) {
404 buf.append( "ß" ); i += 6;
408 /** @todo should only escape outside of tags */
410 if( s.indexOf( """, i ) == i ) {
411 buf.append( "ß" ); i += 5;
414 if( s.indexOf( "–", i ) == i ) {
415 buf.append( "–" ); i += 6;
418 if( s.indexOf( "—", i ) == i ) {
419 buf.append( "—" ); i += 6;
422 if( s.indexOf( "“", i ) == i ) {
423 buf.append( "“" ); i += 6;
426 if( s.indexOf( "”", i ) == i ) {
427 buf.append( "”" ); i += 6;
430 if( s.indexOf( "„", i ) == i ) {
431 buf.append( "„" ); i += 6;
435 //looks pretty stupid
436 if( s.indexOf( "<", i ) == i ) {
437 buf.append( "<" ); i += 3;
440 if( s.indexOf( ">", i ) == i ) {
441 buf.append( ">" ); i += 3;
444 if( s.indexOf( "´", i ) == i ) {
445 buf.append( "´" ); i += 6;
448 if( s.indexOf( " ", i ) == i ) {
449 buf.append( " " ); i += 5;
453 //if( s.indexOf( "&", i ) == i ) {
454 // buf.append( "&" ); i += 0;
458 // convert umlauts an other special charakters
459 switch( s.charAt(i) ) {
460 case 'ö': buf.append( "ö" ); break;
461 case 'ä': buf.append( "ä" ); break;
462 case 'ü': buf.append( "ü" ); break;
463 case 'Ö': buf.append( "Ö" ); break;
464 case 'Ä': buf.append( "Ä" ); break;
465 case 'Ü': buf.append( "Ü" ); break;
466 case 'ß': buf.append( "ß" ); break;
467 case 'é': buf.append( "é" ); break;
468 case 'è': buf.append( "è" ); break;
469 case 'á': buf.append( "á" ); break;
470 case 'à': buf.append( "à" ); break;
471 case 'â': buf.append( "â" ); break;
472 case 'ã': buf.append( "ã" ); break;
473 case '¬': buf.append( "¬" ); break;
474 case '¹': buf.append( "¹" ); break;
475 case '²': buf.append( "²" ); break;
476 case '³': buf.append( "³" ); break;
477 case '¼': buf.append( "¼" ); break;
478 case '½': buf.append( "½" ); break;
479 case '¾': buf.append( "¾" ); break;
480 case '¶': buf.append( "¶" ); break;
481 case 'æ': buf.append( "æ" ); break;
482 case 'ð': buf.append( "ð" ); break;
483 case '|': buf.append( "¦" ); break;
484 case '·': buf.append( "·" ); break;
485 case '°': buf.append( "°" ); break;
486 case '§': buf.append( "§" ); break;
487 case 'ø': buf.append( "ø" ); break;
488 case 'ç': buf.append( "ç" ); break;
489 case '¤': buf.append( "¤" ); break;
490 case 'ª': buf.append( "ª" ); break;
491 case 'Ç': buf.append( "Ç" ); break;
492 case 'Ã': buf.append( "Ã" ); break;
493 case 'Â': buf.append( "Â" ); break;
494 case 'Æ': buf.append( "Æ" ); break;
495 case '©': buf.append( "©" ); break;
496 case '®': buf.append( "®" ); break;
497 case '¥': buf.append( "¥" ); break;
498 case 'Þ': buf.append( "þ" ); break;
499 case '¯': buf.append( "¯" ); break;
500 case 'Ð': buf.append( "Ð" ); break;
501 case 'º': buf.append( "º" ); break;
502 case '¡': buf.append( "¡" ); break;
503 case '£': buf.append( "£" ); break;
504 case '±': buf.append( "±" ); break;
505 case '¿': buf.append( "¿" ); break;
506 case 'Ø': buf.append( "Ø" ); break;
507 case 'Á': buf.append( "À" ); break;
508 case 'À': buf.append( "Á" ); break;
509 case 'É': buf.append( "È" ); break;
510 case 'È': buf.append( "É" ); break;
511 case 'ù': buf.append( "ú" ); break;
512 case 'ñ': buf.append( "ñ" ); break;
513 case 'Ñ': buf.append( "Ñ" ); break;
514 case 'µ': buf.append( "µ" ); break;
515 case 'Í': buf.append( "Ì" ); break;
516 case 'Ì': buf.append( "Í" ); break;
517 case 'í': buf.append( "ì" ); break;
518 case 'ì': buf.append( "í" ); break;
519 case 'î': buf.append( "î" ); break;
520 case 'Î': buf.append( "Î" ); break;
521 case 'ó': buf.append( "ó" ); break;
522 case 'Ó': buf.append( "Ò" ); break;
523 case 'ò': buf.append( "Î" ); break;
524 case 'Ò': buf.append( "Ó" ); break;
525 case 'ô': buf.append( "ô" ); break;
526 case 'Ô': buf.append( "Ô" ); break;
527 case 'õ': buf.append( "õ" ); break;
528 case 'Õ': buf.append( "Õ" ); break;
529 case 'ý': buf.append( "ý" ); break;
530 case 'Ý': buf.append( "Ý" ); break;
531 case 'û': buf.append( "û" ); break;
532 case 'Û': buf.append( "Û" ); break;
533 case 'ú': buf.append( "ù" ); break;
534 case 'Ú': buf.append( "Ù" ); break;
535 case 'Ù': buf.append( "Ú" ); break;
536 case 'Ê': buf.append( "Ê" ); break;
537 case 'ê': buf.append( "ê" ); break;
538 case 'å': buf.append( "å" ); break;
539 case 'Å': buf.append( "Å" ); break;
540 case 'ë': buf.append( "ë" ); break;
541 case 'Ë': buf.append( "Ë" ); break;
542 case 'ÿ': buf.append( "ÿ" ); break;
543 case 'ï': buf.append( "ï" ); break;
544 case 'Ï': buf.append( "Ï" ); break;
545 case '«': buf.append( "«" ); break;
546 case '»': buf.append( "»" ); break;
547 case '\'': buf.append( "´" ); break;
548 case '\"': buf.append( """ ); break;
549 //case '\u8211': buf.append( "–" ); break;
550 //case '\u8212': buf.append( "—" ); break;
551 //case '\u8220': buf.append( "“" ); break;
552 //case '\u8221': buf.append( "”" ); break;
553 //case '\u8222': buf.append( "„" ); break;
554 //case '\"': buf.append( """ ); break;
555 default: buf.append( s.charAt(i) );
559 return buf.toString();
563 public static String decodeHTMLinTags(String s){
564 StringBuffer buffer = new StringBuffer();
565 boolean start = false;
566 boolean stop = false;
571 for(int i=0;i<s.length();i++){
572 if(s.charAt(i)=='<'){
575 } else if(s.charAt(i)=='>'){
580 buffer.append(s.substring(temp,startIndex));
581 buffer.append(replaceQuot(s.substring(startIndex,stopIndex+1)));
582 i= temp= stopIndex+1;
588 buffer.append(s.substring(stopIndex+1));
589 return buffer.toString();
595 public static String replaceQuot(String s) {
596 StringBuffer buffer = new StringBuffer();
597 for(int j = 0; j < s.length();j++){
598 if(s.charAt(j)=='&'){
599 if(s.indexOf( """,j) == j) {
600 buffer.append( "\"" );
604 buffer.append(s.charAt(j));
607 return buffer.toString();
610 /** wandelt Quotes in Sonderzeichen um
613 public static String decodeHtml(String s) {
614 StringBuffer buf = new StringBuffer();
615 for(int i=0;i < s.length(); i++ ) {
616 if( s.indexOf( "ö", i ) == i ) {
617 buf.append( "ö" ); i += 5;
620 if( s.indexOf( "ä", i ) == i ) {
621 buf.append( "ä" ); i += 5;
624 if( s.indexOf( "ü", i ) == i ) {
625 buf.append( "ü" ); i += 5;
628 if( s.indexOf( "Ö", i ) == i ) {
629 buf.append( "Ö" ); i += 5;
632 if( s.indexOf( "Ä", i ) == i ) {
633 buf.append( "Ä" ); i += 5;
636 if( s.indexOf( "Ü", i ) == i ) {
637 buf.append( "Ü" ); i += 5;
640 if( s.indexOf( "ß", i ) == i ) {
641 buf.append( "ß" ); i += 6;
644 if( s.indexOf( """, i ) == i ) {
645 buf.append( "\"" ); i += 5;
648 buf.append( s.charAt(i) );
650 return buf.toString();
655 * schnellere Variante der String.toLowerCase()-Routine
657 * @return String in Kleinbuchsten
659 public static String toLowerCase(String s) {
661 char[] a = new char[l];
662 for (int i = 0; i < l; i++)
663 a[i] = Character.toLowerCase(s.charAt(i));
664 return new String(a);
668 * Findet <code>element</code> im String-Array <code>array</code>
671 * @return Fundstelle als int oder -1
673 public static int indexOf(String[] array, String element) {
675 for (int i = 0; i < array.length; i++)
676 if (array[i].equals(element))
682 * Testet auf Vorkommen von <code>element</code> in <code>array</code>
683 * @param array String-Array
685 * @return true wenn <code>element</code> vorkommt, sonst false
687 public static boolean contains(String[] array, String element) {
688 return indexOf(array, element) >= 0;
692 * Ermittelt CRC-Prüfsumme von String <code>s</code>
694 * @return CRC-Prüfsumme
696 public static int getCRC(String s) {
698 char val[] = s.toCharArray();
699 int len = val.length;
701 for (int i = 0 ; i < len; i++) {
703 h = (((h >> 30) | (h << 1)) ^ (val[i]+i));
706 return (h << 8) | (len & 0xff);
710 * Liefert Default-Wert def zurück, wenn String <code>s</code>
715 * @return geparster int aus s oder def
717 public static int parseInt(String s, int def) {
718 if (s == null) return def;
720 return Integer.parseInt(s);
721 } catch (NumberFormatException e) {
727 * Liefert Defaultwert def zurück, wenn s nicht zu einem float geparsed werden kann.
730 * @return geparster float oder def
732 public static float parseFloat(String s, float def) {
733 if (s == null) return def;
735 return new Float(s).floatValue();
736 } catch (NumberFormatException e) {
742 * Findet Ende eines Satzes in String <code>text</code>
745 * @return index des Satzendes, oder -1
747 public static int findEndOfSentence(String text, int startIndex) {
749 int i = text.indexOf('.', startIndex);
750 if (i < 0) return -1;
751 if (i > 0 && !Character.isDigit(text.charAt(i-1)) &&
752 (i+1 >= text.length()
753 || text.charAt(i+1) == ' '
754 || text.charAt(i+1) == '\n'
755 || text.charAt(i+1) == '\t'))
762 * Findet Wortende in String <code>text</code> ab <code>startIndex</code>
765 * @return Index des Wortendes, oder -1
767 public static int findEndOfWord(String text, int startIndex) {
768 int i = text.indexOf(' ', startIndex),
769 j = text.indexOf('\n', startIndex);
770 if (i < 0) i = text.length();
771 if (j < 0) j = text.length();
772 return Math.min(i, j);
776 * This routine makes html links (href) out of text browseable urls
778 * @return Konvertierter String
780 public static String makeLinks(String text) {
782 StringBuffer buf = new StringBuffer(text.length());
784 int j = text.indexOf("http://", i);
786 buf.append(text.substring(i));
789 buf.append(text.substring(i, j));
790 int k = findEndOfWord(text,j+7);
792 if (k<0) url = text.substring(j);
793 else url = text.substring(j,k);
795 buf.append("<a href=\042"+url+"\042>"+url+"</a>");
796 //System.out.println("url mark: " + url);
800 return buf.toString();
806 * convertNewline2P ist eine regex-routine zum umwandeln von 2 oder mehr newlines (\n)
807 * in den html-tag <p>
808 * nur sinnvoll, wenn text nicht im html-format eingegeben
810 public static String convertNewline2P(String haystack) {
812 RE regex = new RE("(<br>\r?\n<br>){1,}");
813 return regex.substituteAll(haystack,"\n</p><p>");
814 } catch(REException ex){
820 * convertNewline2Break ist eine regex-routine zum umwandeln von 1 newline (\n)
821 * in den html-tag <br>
822 * nur sinnvoll, wenn text nicht im html-format eingegeben
824 public static String convertNewline2Break(String haystack) {
826 RE regex = new RE("(\r?\n){1}");
827 return regex.substituteAll(haystack,"$0<br>");
828 } catch(REException ex){
834 * createMailLinks wandelt text im email-adressenformat
835 * in einen klickbaren link um
836 * nur sinnvoll, wenn text nicht im html-format eingegeben
838 public static String createMailLinks(String haystack) {
840 RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
841 return regex.substituteAll(haystack,"<a href=\"mailto:$0\">$0</a>");
842 } catch(REException ex){
849 * createMailLinks wandelt text im email-adressenformat
850 * in einen klickbaren link um
851 * nur sinnvoll, wenn text nicht im html-format eingegeben
853 public static String createMailLinks(String haystack, String imageRoot, String mailImage) {
855 RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
856 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+mailImage+"\" border=\"0\"/> <a href=\"mailto:$0\">$0</a>");
857 } catch(REException ex){
864 * createURLLinks wandelt text im url-format
865 * in einen klickbaren link um
866 * nur sinnvoll, wenn text nicht im html-format eingegeben
868 public static String createURLLinks(String haystack) {
871 //dieser Ausdruck brauch dringend fachliche Beratung
872 //RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_:-]+)/([^ \t\r\n<>)]+[^ \t\r\n,<>])");
873 RE regex = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
874 return regex.substituteAll(haystack,"<a href=\"$0\">$0</a>");
875 } catch(REException ex){
881 * this routine takes text in url format and makes
882 * a clickaeble "<href>" link removing any "illegal" html tags
883 * @param haystack, the url
884 * @param title, the href link text
885 * @param imagRoot, the place to find icons
886 * @param extImage, the url of the icon to show next to the link
887 * @return a String containing the url
889 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage) {
891 //dieser Ausdruck brauch dringend fachliche Beratung
892 RE regex = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
895 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">$0</a>");
897 title = removeHTMLTags(title);
898 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">"+title+"</a>");
900 } catch(REException ex){
906 * this routine takes text in url format and makes
907 * a clickaeble "<href>" link removing any "illegal" html tags
908 * @param haystack, the url
909 * @param imageRoot, the place to find icons
910 * @param extImage, the url of the icon to show next to the link
911 * @param intImage, unused
912 * @return a String containing the url
914 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage,String intImage) {
915 return createURLLinks(haystack, title, imageRoot, extImage);
919 * this routine takes text in url format and makes
920 * an image link removing any "illegal" html tags
921 * @param haystack, the url
922 * @param title, the image alt text, can be null
923 * @param height, height of the image
924 * @param width, width of the image
925 * @return a String containing the url
927 public static String createIMGLinks(String haystack, String title, String height,String width) {
929 //dieser Ausdruck brauch dringend fachliche Beratung
930 RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>]+[^ \t\r\n.,<>])");
932 title = removeHTMLTags(title);
933 return regex.substituteAll(haystack,"<img hspace=\"10\" vspace=\"6\" align=\"left\" src=\"$0\" width=\""+width+"\" height=\""+height+"\" alt=\""+title+"\"/> <br><i>"+title+"</i>");
935 return regex.substituteAll(haystack,"<img hspace=\"10\" vspace=\"6\" align=\"left\" src=\"$0\" width=\""+width+"\" height=\""+height+"\" alt=\"\"/> ");
937 } catch(REException ex){
945 * deleteForbiddenTags
946 * this method deletes all <script>, <body> and <head>-tags
948 public static String deleteForbiddenTags(String haystack) {
950 RE regex = new RE("<[ \t\r\n](.*?)script(.*?)/script(.*?)>",RE.REG_ICASE);
951 haystack = regex.substituteAll(haystack,"");
952 regex = new RE("<head>(.*?)</head>");
953 haystack = regex.substituteAll(haystack,"");
954 regex = new RE("<[ \t\r\n/]*body(.*?)>");
955 haystack = regex.substituteAll(haystack,"");
957 } catch(REException ex){
963 * this method deletes all html tags
967 public static String removeHTMLTags(String haystack){
969 RE regex = new RE("<[^>]*>",RE.REG_ICASE);
970 haystack = regex.substituteAll(haystack,"");
973 } catch(REException ex){
981 * this method deletes all but the approved tags html tags
982 * it also deletes approved tags which contain malicious-looking attributes and doesn't work at all
986 public static String approveHTMLTags(String haystack){
988 String approvedTags="a|img|h1|h2|h3|h4|h5|h6|br|b|i|strong|p";
989 String badAttributes="onAbort|onBlur|onChange|onClick|onDblClick|onDragDrop|onError|onFocus|onKeyDown|onKeyPress|onKeyUp|onLoad|onMouseDown|onMouseMove|onMouseOut|onMouseOver|onMouseUp|onMove|onReset|onResize|onSelect|onSubmit|onUnload";
990 String approvedProtocols="rtsp|http|ftp|https|freenet|mailto";
992 // kill all the bad tags that have attributes
993 String s = "<\\s*/?\\s*(?!(("+approvedTags+")\\s))\\w+\\s[^>]*>";
994 RE regex = new RE(s,RE.REG_ICASE);
995 haystack = regex.substituteAll(haystack,"");
997 // kill all the bad tags that are attributeless
998 regex = new RE("<\\s*/?\\s*(?!(("+approvedTags+")\\s*>))\\w+\\s*>",RE.REG_ICASE);
999 haystack = regex.substituteAll(haystack,"");
1001 // kill all the tags which have a javascript attribute like onLoad
1002 regex = new RE("<[^>]*("+badAttributes+")[^>]*>",RE.REG_ICASE);
1003 haystack = regex.substituteAll(haystack,"");
1005 // kill all the tags which include a url to an unacceptable protocol
1006 regex = new RE("<\\s*a\\s+[^>]*href=(?!(\'|\")?("+approvedProtocols+"))[^>]*>",RE.REG_ICASE);
1007 haystack = regex.substituteAll(haystack,"");
1010 } catch(REException ex){
1011 ex.printStackTrace();
1020 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1021 * htmlcodierten string auf und returnt einen htmlcodierten String
1023 public static String createHTML(String content){
1024 content=convertNewline2Break(content);
1025 content=convertNewline2P(content);
1026 content=createMailLinks(content);
1027 content=createURLLinks(content);
1032 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1033 * htmlcodierten string auf und returnt einen htmlcodierten String
1035 public static String createHTML(String content,String producerDocRoot,String mailImage,String extImage,String intImage){
1036 content=convertNewline2Break(content);
1037 content=convertNewline2P(content);
1038 content=createMailLinks(content,producerDocRoot,mailImage);
1039 content=createURLLinks(content,null,producerDocRoot,extImage,intImage);