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 einen 12-ziffrigen String um (yyyymmddhhmm)
38 * @return 12-ziffriger String (yyyymmdd)
41 public static final String date2webdbDateTime (GregorianCalendar theDate) {
42 StringBuffer webdbDate = new StringBuffer();
43 webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
44 webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
45 webdbDate.append(pad2(theDate.get(Calendar.DATE)));
46 webdbDate.append(pad2(theDate.get(Calendar.HOUR)));
47 webdbDate.append(pad2(theDate.get(Calendar.MINUTE)));
48 return webdbDate.toString();
52 * wandelt Calendar in dd.mm.yyyy / hh.mm um
54 * @return String mit (dd.mm.yyyy / hh.mm um)
56 public static String date2readableDateTime (GregorianCalendar theDate) {
59 readable += pad2(theDate.get(Calendar.DATE));
60 readable += "." + pad2(theDate.get(Calendar.MONTH) + 1);
61 readable += "." + String.valueOf(theDate.get(Calendar.YEAR));
62 hour = theDate.get(Calendar.HOUR);
63 if (theDate.get(Calendar.AM_PM) == Calendar.PM)
65 readable += " / " + pad2(hour);
66 readable += ":" + pad2(theDate.get(Calendar.MINUTE));
71 * wandelt eine Datum in einen 8-buchstabigen String, der durch <code>/</code>
75 * @return String mit <code>/yyyy/mm/dd</code>
77 public static final String webdbDate2path (String webdbDate) {
78 StringBuffer path = new StringBuffer();
79 path.append("/").append(webdbDate.substring(0, 4));
80 path.append("/").append(webdbDate.substring(4, 6));
83 //path.append("/").append(webdbDate.substring(6, 8));
84 return path.toString();
88 * wandelt Calendar in dd.mm.yyyy um
91 * @return String mit <code>dd.mm.yyyy</code>
93 public static final String webdbDate2readableDate (String webdbDate) {
95 date += webdbDate.substring(6, 8);
96 date += "." + webdbDate.substring(4, 6);
97 date += "." + webdbDate.substring(0, 4);
103 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
104 * to dd.mm.yyyy hh:mm
106 public static String dateToReadableDate(String date) {
107 StringBuffer returnDate = new StringBuffer();
110 returnDate.append(date.substring(8,10)).append('.');
111 returnDate.append(date.substring(5,7)).append('.');
112 returnDate.append(date.substring(0,4)).append(' ');
113 returnDate.append(date.substring(11,16));
115 return returnDate.toString();
119 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
122 public static String dateToYear (String date) {
123 StringBuffer returnDate = new StringBuffer();
126 returnDate.append(date.substring(0,4));
128 return returnDate.toString();
132 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
135 public static String dateToMonth (String date) {
136 StringBuffer returnDate = new StringBuffer();
138 if (!date.substring(5,6).equalsIgnoreCase("0")) returnDate.append(date.substring(5,7));
139 else returnDate.append(date.substring(6,7));
141 return returnDate.toString();
145 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
148 public static String dateToDayOfMonth (String date) {
149 StringBuffer returnDate = new StringBuffer();
151 if (!date.substring(8,9).equalsIgnoreCase("0")) returnDate.append(date.substring(8,10));
152 else returnDate.append(date.substring(9,10));
154 return returnDate.toString();
158 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
161 public static String dateToTime (String date) {
162 StringBuffer returnDate = new StringBuffer();
164 returnDate.append(date.substring(11,16));
166 return returnDate.toString();
171 * schließt einen String in Anführungsszeichen ein, falls er Leerzeichen o.ä. enthält
173 * @return gequoteter String
175 public static String quoteIfNecessary(String s) {
176 for (int i = 0; i < s.length(); i++)
177 if (!(Character.isLetterOrDigit(s.charAt(i)) || s.charAt(i) == '.'))
178 return quote(s, '"');
183 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
184 * "gefährliche" Zeichen innerhalb des Strings
185 * Quotes special SQL-characters in <code>s</code>
187 * @return geqoteter String
189 public static String quote(String s)
191 //String s2 = quote(s, '\'');
194 //Because of '?-Bug in Postgresql-JDBC-Driver
195 StringBuffer temp = new StringBuffer();
196 for(int i=0;i<s.length();i++){
197 if(s.charAt(i)=='\''){
198 temp.append("´");
200 temp.append(s.charAt(i));
203 String s2 = temp.toString();
206 s2 = quote(s2, '\"');
211 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
212 * "gefährliche" Zeichen innerhalb des Strings
214 * @param s String, der gequoted werden soll
215 * @param quoteChar zu quotendes Zeichen
216 * @return gequoteter String
218 public static String quote(String s, char quoteChar)
220 StringBuffer buf = new StringBuffer(s.length());
222 while (pos < s.length()) {
223 int i = s.indexOf(quoteChar, pos);
224 if (i < 0) i = s.length();
225 buf.append(s.substring(pos, i));
227 if (pos < s.length()) {
229 buf.append(quoteChar);
233 return buf.toString();
237 * replaces dangerous characters in <code>s</code>
241 public static String unquote(String s)
244 StringBuffer buf = new StringBuffer(s.length());
246 String searchString = "\\"+quoteChar;
247 while (pos < s.length()) {
248 int i = s.indexOf(searchString, pos);
249 if (i < 0) i = s.length();
250 buf.append(s.substring(pos, i));
253 return buf.toString();
257 * Wandelet String in byte[] um.
259 * @return byte[] des String
262 public static byte[] stringToBytes(String s) {
263 String crlf = System.getProperty("line.separator");
264 if (!crlf.equals("\n"))
265 s = replace(s, "\n", crlf);
266 // byte[] buf = new byte[s.length()];
267 byte[] buf = s.getBytes();
272 * Ersetzt in String <code>s</code> das <code>pattern</code> durch <code>substitute</code>
276 * @return String mit den Ersetzungen
278 public static String replace(String s, String pattern, String substitute) {
279 int i = 0, pLen = pattern.length(), sLen = substitute.length();
280 StringBuffer buf = new StringBuffer(s.length());
282 int j = s.indexOf(pattern, i);
284 buf.append(s.substring(i));
287 buf.append(s.substring(i, j));
288 buf.append(substitute);
292 return buf.toString();
296 * Ersetzt in String <code>s</code> das Regexp <code>pattern</code> durch <code>substitute</code>
300 * @return String mit den Ersetzungen
302 public static String regexpReplace(String haystack, String pattern, String substitute) {
304 RE regex = new RE(pattern);
305 return regex.substituteAll(haystack,substitute);
306 } catch(REException ex){
315 * Fügt einen Separator an den Pfad an
317 * @return Pfad mit Separator am Ende
319 public static final String addSeparator (String path) {
320 return path.length() == 0 || path.endsWith(File.separator) ? path : path
321 + File.separatorChar;
325 * Fügt ein <code>/</code> ans ende des Strings and
327 * @return Pfad mit <code>/</code> am Ende
329 public static final String addSlash (String path) {
330 return path.length() == 0 || path.endsWith("/") ? path : path + '/';
334 * Löscht <code>/</code> am Ende des Strings, falls vorhanden
336 * @return String ohne <code>/</code> am Ende
338 public static final String removeSlash (String path) {
339 return path.length() > 1 && path.endsWith("/") ? path.substring(0, path.length()
344 * Checks to see if the path is absolute by looking for a leading file
346 * @todo deal with windows drive letters.
350 public static boolean isAbsolutePath (String path) {
351 return path.startsWith(File.separator);
355 * Löscht Slash am Anfang des Strings
359 public static String removeFirstSlash (String path) {
360 return path.startsWith("/") ? path.substring(1) : path;
364 * formatiert eine Zahl (0-99) zweistellig (z.B. 5 -> 05)
365 * @return zwistellige Zahl
367 public static String pad2 (int number) {
368 return number < 10 ? "0" + number : String.valueOf(number);
372 * formatiert eine Zahl (0-999) dreistellig (z.B. 7 -> 007)
374 * @return 3-stellige Zahl
376 public static String pad3 (int number) {
377 return number < 10 ? "00" + number : number < 100 ? "0" + number : String.valueOf(number);
381 * Konvertiert Unix-Linefeeds in Win-Linefeeds
383 * @return Konvertierter String
385 public static String unixLineFeedsToWin(String s) {
388 i = s.indexOf('\n', i+1);
390 if ((i == 0 || s.charAt(i-1) != '\r') &&
391 (i == s.length()-1 || s.charAt(i+1) != '\r')) {
392 s = s.substring(0, i)+'\r'+s.substring(i);
401 * verwandelt einen String in eine gültige Url, konvertiert Sonderzeichen
402 * und Spaces werden zu Underscores
404 * @return gültige Url
406 public static String convert2url(String s) {
408 StringBuffer buf = new StringBuffer();
409 for(int i = 0; i < s.length(); i++ ) {
410 switch( s.charAt( i ) ) {
412 buf.append( "oe" ); break;
414 buf.append( "ae" ); break;
416 buf.append( "ue" ); break;
418 buf.append( "a" ); break;
421 buf.append( "_" ); break;
423 if( buf.charAt( buf.length() - 1 ) != '_' ) {
428 buf.append( s.charAt( i ) );
431 return buf.toString();
435 * wandelt Sonderzeichen in Quotes um
437 * @return Kovertierter String
439 public static String encodeHtml(String s) {
440 StringBuffer buf = new StringBuffer();
441 for(int i=0;i < s.length(); i++ ) {
443 /** @todo looks inefficient */
444 if (s.charAt(i)=='&') {
445 // convert html to xml-parsable representation
446 if( s.indexOf( "ö", i ) == i ) {
447 buf.append( "ö" ); i += 5;
450 if( s.indexOf( "ä", i ) == i ) {
451 buf.append( "ä" ); i += 5;
454 if( s.indexOf( "ü", i ) == i ) {
455 buf.append( "ü" ); i += 5;
458 if( s.indexOf( "Ö", i ) == i ) {
459 buf.append( "Ö" ); i += 5;
462 if( s.indexOf( "Ä", i ) == i ) {
463 buf.append( "Ä" ); i += 5;
466 if( s.indexOf( "Ü", i ) == i ) {
467 buf.append( "Ü" ); i += 5;
470 if( s.indexOf( "ß", i ) == i ) {
471 buf.append( "ß" ); i += 6;
475 /** @todo should only escape outside of tags */
477 if( s.indexOf( """, i ) == i ) {
478 buf.append( "ß" ); i += 5;
481 if( s.indexOf( "–", i ) == i ) {
482 buf.append( "–" ); i += 6;
485 if( s.indexOf( "—", i ) == i ) {
486 buf.append( "—" ); i += 6;
489 if( s.indexOf( "“", i ) == i ) {
490 buf.append( "“" ); i += 6;
493 if( s.indexOf( "”", i ) == i ) {
494 buf.append( "”" ); i += 6;
497 if( s.indexOf( "„", i ) == i ) {
498 buf.append( "„" ); i += 6;
502 //looks pretty stupid
503 if( s.indexOf( "<", i ) == i ) {
504 buf.append( "<" ); i += 3;
507 if( s.indexOf( ">", i ) == i ) {
508 buf.append( ">" ); i += 3;
511 if( s.indexOf( "´", i ) == i ) {
512 buf.append( "´" ); i += 6;
515 if( s.indexOf( " ", i ) == i ) {
516 buf.append( " " ); i += 5;
520 //if( s.indexOf( "&", i ) == i ) {
521 // buf.append( "&" ); i += 0;
525 // convert umlauts an other special charakters
526 switch( s.charAt(i) ) {
527 case 'ö': buf.append( "ö" ); break;
528 case 'ä': buf.append( "ä" ); break;
529 case 'ü': buf.append( "ü" ); break;
530 case 'Ö': buf.append( "Ö" ); break;
531 case 'Ä': buf.append( "Ä" ); break;
532 case 'Ü': buf.append( "Ü" ); break;
533 case 'ß': buf.append( "ß" ); break;
534 case 'é': buf.append( "é" ); break;
535 case 'è': buf.append( "è" ); break;
536 case 'á': buf.append( "á" ); break;
537 case 'à': buf.append( "à" ); break;
538 case 'â': buf.append( "â" ); break;
539 case 'ã': buf.append( "ã" ); break;
540 case '¬': buf.append( "¬" ); break;
541 case '¹': buf.append( "¹" ); break;
542 case '²': buf.append( "²" ); break;
543 case '³': buf.append( "³" ); break;
544 case '¼': buf.append( "¼" ); break;
545 case '½': buf.append( "½" ); break;
546 case '¾': buf.append( "¾" ); break;
547 case '¶': buf.append( "¶" ); break;
548 case 'æ': buf.append( "æ" ); break;
549 case 'ð': buf.append( "ð" ); break;
550 case '|': buf.append( "¦" ); break;
551 case '·': buf.append( "·" ); break;
552 case '°': buf.append( "°" ); break;
553 case '§': buf.append( "§" ); break;
554 case 'ø': buf.append( "ø" ); break;
555 case 'ç': buf.append( "ç" ); break;
556 case '¤': buf.append( "¤" ); break;
557 case 'ª': buf.append( "ª" ); break;
558 case 'Ç': buf.append( "Ç" ); break;
559 case 'Ã': buf.append( "Ã" ); break;
560 case 'Â': buf.append( "Â" ); break;
561 case 'Æ': buf.append( "Æ" ); break;
562 case '©': buf.append( "©" ); break;
563 case '®': buf.append( "®" ); break;
564 case '¥': buf.append( "¥" ); break;
565 case 'Þ': buf.append( "þ" ); break;
566 case '¯': buf.append( "¯" ); break;
567 case 'Ð': buf.append( "Ð" ); break;
568 case 'º': buf.append( "º" ); break;
569 case '¡': buf.append( "¡" ); break;
570 case '£': buf.append( "£" ); break;
571 case '±': buf.append( "±" ); break;
572 case '¿': buf.append( "¿" ); break;
573 case 'Ø': buf.append( "Ø" ); break;
574 case 'Á': buf.append( "À" ); break;
575 case 'À': buf.append( "Á" ); break;
576 case 'É': buf.append( "È" ); break;
577 case 'È': buf.append( "É" ); break;
578 case 'ù': buf.append( "ú" ); break;
579 case 'ñ': buf.append( "ñ" ); break;
580 case 'Ñ': buf.append( "Ñ" ); break;
581 case 'µ': buf.append( "µ" ); break;
582 case 'Í': buf.append( "Ì" ); break;
583 case 'Ì': buf.append( "Í" ); break;
584 case 'í': buf.append( "ì" ); break;
585 case 'ì': buf.append( "í" ); break;
586 case 'î': buf.append( "î" ); break;
587 case 'Î': buf.append( "Î" ); break;
588 case 'ó': buf.append( "ó" ); break;
589 case 'Ó': buf.append( "Ò" ); break;
590 case 'ò': buf.append( "Î" ); break;
591 case 'Ò': buf.append( "Ó" ); break;
592 case 'ô': buf.append( "ô" ); break;
593 case 'Ô': buf.append( "Ô" ); break;
594 case 'õ': buf.append( "õ" ); break;
595 case 'Õ': buf.append( "Õ" ); break;
596 case 'ý': buf.append( "ý" ); break;
597 case 'Ý': buf.append( "Ý" ); break;
598 case 'û': buf.append( "û" ); break;
599 case 'Û': buf.append( "Û" ); break;
600 case 'ú': buf.append( "ù" ); break;
601 case 'Ú': buf.append( "Ù" ); break;
602 case 'Ù': buf.append( "Ú" ); break;
603 case 'Ê': buf.append( "Ê" ); break;
604 case 'ê': buf.append( "ê" ); break;
605 case 'å': buf.append( "å" ); break;
606 case 'Å': buf.append( "Å" ); break;
607 case 'ë': buf.append( "ë" ); break;
608 case 'Ë': buf.append( "Ë" ); break;
609 case 'ÿ': buf.append( "ÿ" ); break;
610 case 'ï': buf.append( "ï" ); break;
611 case 'Ï': buf.append( "Ï" ); break;
612 case '«': buf.append( "«" ); break;
613 case '»': buf.append( "»" ); break;
614 case '\'': buf.append( "´" ); break;
615 case '\"': buf.append( """ ); break;
616 //case '\u8211': buf.append( "–" ); break;
617 //case '\u8212': buf.append( "—" ); break;
618 //case '\u8220': buf.append( "“" ); break;
619 //case '\u8221': buf.append( "”" ); break;
620 //case '\u8222': buf.append( "„" ); break;
621 //case '\"': buf.append( """ ); break;
622 default: buf.append( s.charAt(i) );
626 return buf.toString();
630 public static String decodeHTMLinTags(String s){
631 StringBuffer buffer = new StringBuffer();
632 boolean start = false;
633 boolean stop = false;
638 for(int i=0;i<s.length();i++){
639 if(s.charAt(i)=='<'){
642 } else if(s.charAt(i)=='>'){
647 buffer.append(s.substring(temp,startIndex));
648 buffer.append(replaceQuot(s.substring(startIndex,stopIndex+1)));
649 i= temp= stopIndex+1;
655 buffer.append(s.substring(stopIndex+1));
656 return buffer.toString();
662 public static String replaceQuot(String s) {
663 StringBuffer buffer = new StringBuffer();
664 for(int j = 0; j < s.length();j++){
665 if(s.charAt(j)=='&'){
666 if(s.indexOf( """,j) == j) {
667 buffer.append( "\"" );
671 buffer.append(s.charAt(j));
674 return buffer.toString();
677 /** wandelt Quotes in Sonderzeichen um
680 public static String decodeHtml(String s) {
681 StringBuffer buf = new StringBuffer();
682 for(int i=0;i < s.length(); i++ ) {
683 if( s.indexOf( "ö", i ) == i ) {
684 buf.append( "ö" ); i += 5;
687 if( s.indexOf( "ä", i ) == i ) {
688 buf.append( "ä" ); i += 5;
691 if( s.indexOf( "ü", i ) == i ) {
692 buf.append( "ü" ); i += 5;
695 if( s.indexOf( "Ö", i ) == i ) {
696 buf.append( "Ö" ); i += 5;
699 if( s.indexOf( "Ä", i ) == i ) {
700 buf.append( "Ä" ); i += 5;
703 if( s.indexOf( "Ü", i ) == i ) {
704 buf.append( "Ü" ); i += 5;
707 if( s.indexOf( "ß", i ) == i ) {
708 buf.append( "ß" ); i += 6;
711 if( s.indexOf( """, i ) == i ) {
712 buf.append( "\"" ); i += 5;
715 buf.append( s.charAt(i) );
717 return buf.toString();
722 * schnellere Variante der String.toLowerCase()-Routine
724 * @return String in Kleinbuchsten
726 public static String toLowerCase(String s) {
728 char[] a = new char[l];
729 for (int i = 0; i < l; i++)
730 a[i] = Character.toLowerCase(s.charAt(i));
731 return new String(a);
735 * Findet <code>element</code> im String-Array <code>array</code>
738 * @return Fundstelle als int oder -1
740 public static int indexOf(String[] array, String element) {
742 for (int i = 0; i < array.length; i++)
743 if (array[i].equals(element))
749 * Testet auf Vorkommen von <code>element</code> in <code>array</code>
750 * @param array String-Array
752 * @return true wenn <code>element</code> vorkommt, sonst false
754 public static boolean contains(String[] array, String element) {
755 return indexOf(array, element) >= 0;
759 * Ermittelt CRC-Prüfsumme von String <code>s</code>
761 * @return CRC-Prüfsumme
763 public static int getCRC(String s) {
765 char val[] = s.toCharArray();
766 int len = val.length;
768 for (int i = 0 ; i < len; i++) {
770 h = (((h >> 30) | (h << 1)) ^ (val[i]+i));
773 return (h << 8) | (len & 0xff);
777 * Liefert Default-Wert def zurück, wenn String <code>s</code>
782 * @return geparster int aus s oder def
784 public static int parseInt(String s, int def) {
785 if (s == null) return def;
787 return Integer.parseInt(s);
788 } catch (NumberFormatException e) {
794 * Liefert Defaultwert def zurück, wenn s nicht zu einem float geparsed werden kann.
797 * @return geparster float oder def
799 public static float parseFloat(String s, float def) {
800 if (s == null) return def;
802 return new Float(s).floatValue();
803 } catch (NumberFormatException e) {
809 * Findet Ende eines Satzes in String <code>text</code>
812 * @return index des Satzendes, oder -1
814 public static int findEndOfSentence(String text, int startIndex) {
816 int i = text.indexOf('.', startIndex);
817 if (i < 0) return -1;
818 if (i > 0 && !Character.isDigit(text.charAt(i-1)) &&
819 (i+1 >= text.length()
820 || text.charAt(i+1) == ' '
821 || text.charAt(i+1) == '\n'
822 || text.charAt(i+1) == '\t'))
829 * Findet Wortende in String <code>text</code> ab <code>startIndex</code>
832 * @return Index des Wortendes, oder -1
834 public static int findEndOfWord(String text, int startIndex) {
835 int i = text.indexOf(' ', startIndex),
836 j = text.indexOf('\n', startIndex);
837 if (i < 0) i = text.length();
838 if (j < 0) j = text.length();
839 return Math.min(i, j);
843 * This routine makes html links (href) out of text browseable urls
845 * @return Konvertierter String
847 public static String makeLinks(String text) {
849 StringBuffer buf = new StringBuffer(text.length());
851 int j = text.indexOf("http://", i);
853 buf.append(text.substring(i));
856 buf.append(text.substring(i, j));
857 int k = findEndOfWord(text,j+7);
859 if (k<0) url = text.substring(j);
860 else url = text.substring(j,k);
862 buf.append("<a href=\042"+url+"\042>"+url+"</a>");
863 //System.out.println("url mark: " + url);
867 return buf.toString();
873 * convertNewline2P ist eine regex-routine zum umwandeln von 2 oder mehr newlines (\n)
874 * in den html-tag <p>
875 * nur sinnvoll, wenn text nicht im html-format eingegeben
877 public static String convertNewline2P(String haystack) {
879 RE regex = new RE("(<br>\r?\n<br>){1,}");
880 return regex.substituteAll(haystack,"\n</p><p>");
881 } catch(REException ex){
887 * convertNewline2Break ist eine regex-routine zum umwandeln von 1 newline (\n)
888 * in den html-tag <br>
889 * nur sinnvoll, wenn text nicht im html-format eingegeben
891 public static String convertNewline2Break(String haystack) {
893 RE regex = new RE("(\r?\n){1}");
894 return regex.substituteAll(haystack,"$0<br>");
895 } catch(REException ex){
901 * createMailLinks wandelt text im email-adressenformat
902 * in einen klickbaren link um
903 * nur sinnvoll, wenn text nicht im html-format eingegeben
905 public static String createMailLinks(String haystack) {
907 RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
908 return regex.substituteAll(haystack,"<a href=\"mailto:$0\">$0</a>");
909 } catch(REException ex){
916 * createMailLinks wandelt text im email-adressenformat
917 * in einen klickbaren link um
918 * nur sinnvoll, wenn text nicht im html-format eingegeben
920 public static String createMailLinks(String haystack, String imageRoot, String mailImage) {
922 RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
923 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+mailImage+"\" border=\"0\"/> <a href=\"mailto:$0\">$0</a>");
924 } catch(REException ex){
931 * createURLLinks wandelt text im url-format
932 * in einen klickbaren link um
933 * nur sinnvoll, wenn text nicht im html-format eingegeben
935 public static String createURLLinks(String haystack) {
938 //dieser Ausdruck brauch dringend fachliche Beratung
939 //RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_:-]+)/([^ \t\r\n<>)]+[^ \t\r\n,<>])");
940 RE regex = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
941 return regex.substituteAll(haystack,"<a href=\"$0\">$0</a>");
942 } catch(REException ex){
948 * this routine takes text in url format and makes
949 * a clickaeble "<href>" link removing any "illegal" html tags
950 * @param haystack, the url
951 * @param title, the href link text
952 * @param imagRoot, the place to find icons
953 * @param extImage, the url of the icon to show next to the link
954 * @return a String containing the url
956 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage) {
958 //dieser Ausdruck brauch dringend fachliche Beratung
959 RE regex = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
962 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">$0</a>");
964 title = removeHTMLTags(title);
965 return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">"+title+"</a>");
967 } catch(REException ex){
973 * this routine takes text in url format and makes
974 * a clickaeble "<href>" link removing any "illegal" html tags
975 * @param haystack, the url
976 * @param imageRoot, the place to find icons
977 * @param extImage, the url of the icon to show next to the link
978 * @param intImage, unused
979 * @return a String containing the url
981 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage,String intImage) {
982 return createURLLinks(haystack, title, imageRoot, extImage);
986 * this routine takes text in url format and makes
987 * an image link removing any "illegal" html tags
988 * @param haystack, the url
989 * @param title, the image alt text, can be null
990 * @param height, height of the image
991 * @param width, width of the image
992 * @return a String containing the url
994 public static String createIMGLinks(String haystack, String title, String height,String width) {
996 //dieser Ausdruck brauch dringend fachliche Beratung
997 RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>]+[^ \t\r\n.,<>])");
999 title = removeHTMLTags(title);
1000 return regex.substituteAll(haystack,"<img hspace=\"10\" vspace=\"6\" align=\"left\" src=\"$0\" width=\""+width+"\" height=\""+height+"\" alt=\""+title+"\"/> <br><i>"+title+"</i>");
1002 return regex.substituteAll(haystack,"<img hspace=\"10\" vspace=\"6\" align=\"left\" src=\"$0\" width=\""+width+"\" height=\""+height+"\" alt=\"\"/> ");
1004 } catch(REException ex){
1012 * deleteForbiddenTags
1013 * this method deletes all <script>, <body> and <head>-tags
1015 public static String deleteForbiddenTags(String haystack) {
1017 RE regex = new RE("<[ \t\r\n](.*?)script(.*?)/script(.*?)>",RE.REG_ICASE);
1018 haystack = regex.substituteAll(haystack,"");
1019 regex = new RE("<head>(.*?)</head>");
1020 haystack = regex.substituteAll(haystack,"");
1021 regex = new RE("<[ \t\r\n/]*body(.*?)>");
1022 haystack = regex.substituteAll(haystack,"");
1024 } catch(REException ex){
1030 * this method deletes all html tags
1034 public static String removeHTMLTags(String haystack){
1036 RE regex = new RE("<[^>]*>",RE.REG_ICASE);
1037 haystack = regex.substituteAll(haystack,"");
1040 } catch(REException ex){
1048 * this method deletes all but the approved tags html tags
1049 * it also deletes approved tags which contain malicious-looking attributes and doesn't work at all
1053 public static String approveHTMLTags(String haystack){
1055 String approvedTags="a|img|h1|h2|h3|h4|h5|h6|br|b|i|strong|p";
1056 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";
1057 String approvedProtocols="rtsp|http|ftp|https|freenet|mailto";
1059 // kill all the bad tags that have attributes
1060 String s = "<\\s*/?\\s*(?!(("+approvedTags+")\\s))\\w+\\s[^>]*>";
1061 RE regex = new RE(s,RE.REG_ICASE);
1062 haystack = regex.substituteAll(haystack,"");
1064 // kill all the bad tags that are attributeless
1065 regex = new RE("<\\s*/?\\s*(?!(("+approvedTags+")\\s*>))\\w+\\s*>",RE.REG_ICASE);
1066 haystack = regex.substituteAll(haystack,"");
1068 // kill all the tags which have a javascript attribute like onLoad
1069 regex = new RE("<[^>]*("+badAttributes+")[^>]*>",RE.REG_ICASE);
1070 haystack = regex.substituteAll(haystack,"");
1072 // kill all the tags which include a url to an unacceptable protocol
1073 regex = new RE("<\\s*a\\s+[^>]*href=(?!(\'|\")?("+approvedProtocols+"))[^>]*>",RE.REG_ICASE);
1074 haystack = regex.substituteAll(haystack,"");
1077 } catch(REException ex){
1078 ex.printStackTrace();
1087 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1088 * htmlcodierten string auf und returnt einen htmlcodierten String
1090 public static String createHTML(String content){
1091 content=convertNewline2Break(content);
1092 content=convertNewline2P(content);
1093 content=createMailLinks(content);
1094 content=createURLLinks(content);
1099 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1100 * htmlcodierten string auf und returnt einen htmlcodierten String
1102 public static String createHTML(String content,String producerDocRoot,String mailImage,String extImage,String intImage){
1103 content=convertNewline2Break(content);
1104 content=convertNewline2P(content);
1105 content=createMailLinks(content,producerDocRoot,mailImage);
1106 content=createURLLinks(content,null,producerDocRoot,extImage,intImage);