2 * put your module comment here
14 * Statische Hilfsmethoden zur Stringbehandlung
19 public final class StringUtil {
21 private static RE re_newline2br, re_brbr2p, re_mail, re_url, re_tags;
23 private StringUtil() { } // this avoids contruction
28 re_newline2br = new RE("(\r?\n){1}");
29 re_brbr2p = new RE("(<br>\r?\n<br>){1,}");
30 re_mail = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
31 re_url = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
32 re_tags = new RE("<[^>]*>",RE.REG_ICASE);
34 catch (REException e){
35 System.err.println("FATAL: StringUtil: could not precompile REGEX: "+e.toString());
41 * Wandelt Datum in einen 8-ziffrigen String um (yyyymmdd)
43 * @return 8-ziffriger String (yyyymmdd)
46 public static final String date2webdbDate (GregorianCalendar theDate) {
47 StringBuffer webdbDate = new StringBuffer();
48 webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
49 webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
50 webdbDate.append(pad2(theDate.get(Calendar.DATE)));
51 return webdbDate.toString();
55 * Wandelt Calendar in einen 12-ziffrigen String um (yyyymmddhhmm)
57 * @return 12-ziffriger String (yyyymmdd)
60 public static final String date2webdbDateTime (GregorianCalendar theDate) {
61 StringBuffer webdbDate = new StringBuffer();
62 webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
63 webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
64 webdbDate.append(pad2(theDate.get(Calendar.DATE)));
65 webdbDate.append(pad2(theDate.get(Calendar.HOUR)));
66 webdbDate.append(pad2(theDate.get(Calendar.MINUTE)));
67 return webdbDate.toString();
71 * Return a http://www.w3.org/TR/NOTE-datetime formatted date (yyyymmddThhmmssTZ)
73 * @return w3approved datetime
76 public static final String date2w3DateTime (GregorianCalendar theDate) {
77 StringBuffer webdbDate = new StringBuffer();
78 webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
79 webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
80 webdbDate.append(pad2(theDate.get(Calendar.DATE)));
81 webdbDate.append("T");
82 webdbDate.append(pad2(theDate.get(Calendar.HOUR)));
83 webdbDate.append(pad2(theDate.get(Calendar.MINUTE)));
84 webdbDate.append(pad2(theDate.get(Calendar.SECOND)));
85 //assumes you are an hour-multiple away from UTC....
86 int offset=(theDate.get(Calendar.ZONE_OFFSET)/(60*60*1000));
88 webdbDate.append("-");
91 webdbDate.append("+");
93 webdbDate.append(pad2(Math.abs(offset)));
94 webdbDate.append("00");
95 return webdbDate.toString();
99 * wandelt Calendar in dd.mm.yyyy / hh.mm um
101 * @return String mit (dd.mm.yyyy / hh.mm um)
103 public static String date2readableDateTime (GregorianCalendar theDate) {
104 String readable = "";
106 readable += pad2(theDate.get(Calendar.DATE));
107 readable += "." + pad2(theDate.get(Calendar.MONTH) + 1);
108 readable += "." + String.valueOf(theDate.get(Calendar.YEAR));
109 hour = theDate.get(Calendar.HOUR);
110 if (theDate.get(Calendar.AM_PM) == Calendar.PM)
112 readable += " / " + pad2(hour);
113 readable += ":" + pad2(theDate.get(Calendar.MINUTE));
118 * wandelt eine Datum in einen 8-buchstabigen String, der durch <code>/</code>
122 * @return String mit <code>/yyyy/mm/dd</code>
124 public static final String webdbDate2path (String webdbDate) {
125 StringBuffer path = new StringBuffer();
126 path.append("/").append(webdbDate.substring(0, 4));
127 path.append("/").append(webdbDate.substring(4, 6));
130 //path.append("/").append(webdbDate.substring(6, 8));
131 return path.toString();
135 * wandelt Calendar in dd.mm.yyyy um
138 * @return String mit <code>dd.mm.yyyy</code>
140 public static final String webdbDate2readableDate (String webdbDate) {
142 date += webdbDate.substring(6, 8);
143 date += "." + webdbDate.substring(4, 6);
144 date += "." + webdbDate.substring(0, 4);
150 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
151 * to dd.mm.yyyy hh:mm
153 public static String dateToReadableDate(String date) {
154 StringBuffer returnDate = new StringBuffer();
157 returnDate.append(date.substring(8,10)).append('.');
158 returnDate.append(date.substring(5,7)).append('.');
159 returnDate.append(date.substring(0,4)).append(' ');
160 returnDate.append(date.substring(11,16));
162 return returnDate.toString();
166 * converts string from format: yyyy-mm-dd__hh:mm:ss.dddddd+TZ
167 * to yyyymmddThhmmss+TZ:00 (w3 format for Dublin Core)
169 public static String webdbdateToDCDate(String date) {
170 StringBuffer returnDate = new StringBuffer();
173 returnDate.append(date.substring(0,4));
174 returnDate.append(date.substring(5,7));
175 returnDate.append(date.substring(8,10));
176 returnDate.append("T");
177 returnDate.append(date.substring(11,13));
178 returnDate.append(date.substring(14,16));
179 returnDate.append(date.substring(17,19));
180 returnDate.append(date.substring(20,22));
181 returnDate.append(":00");
183 return returnDate.toString();
188 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
191 public static String dateToYear (String date) {
192 StringBuffer returnDate = new StringBuffer();
195 returnDate.append(date.substring(0,4));
197 return returnDate.toString();
201 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
204 public static String dateToMonth (String date) {
205 StringBuffer returnDate = new StringBuffer();
207 if (!date.substring(5,6).equalsIgnoreCase("0")) returnDate.append(date.substring(5,7));
208 else returnDate.append(date.substring(6,7));
210 return returnDate.toString();
214 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
217 public static String dateToDayOfMonth (String date) {
218 StringBuffer returnDate = new StringBuffer();
220 if (!date.substring(8,9).equalsIgnoreCase("0")) returnDate.append(date.substring(8,10));
221 else returnDate.append(date.substring(9,10));
223 return returnDate.toString();
227 * converts string from format: yyyy-mm-dd__hh:mm:ss.d
230 public static String dateToTime (String date) {
231 StringBuffer returnDate = new StringBuffer();
233 returnDate.append(date.substring(11,16));
235 return returnDate.toString();
239 * Splits the provided CSV text into a list. stolen wholesale from
240 * from Jakarta Turbine StrinUtils.java -mh
242 * @param text The CSV list of values to split apart.
243 * @param separator The separator character.
244 * @return The list of values.
246 public static String[] split(String text, String separator)
248 StringTokenizer st = new StringTokenizer(text, separator);
249 String[] values = new String[st.countTokens()];
251 while (st.hasMoreTokens())
253 values[pos++] = st.nextToken();
259 * Joins the elements of the provided array into a single string
260 * containing a list of CSV elements. Stolen wholesale from Jakarta
261 * Turbine StringUtils.java. -mh
263 * @param list The list of values to join together.
264 * @param separator The separator character.
265 * @return The CSV text.
267 public static String join(String[] list, String separator)
269 StringBuffer csv = new StringBuffer();
270 for (int i = 0; i < list.length; i++)
274 csv.append(separator);
278 return csv.toString();
283 * schließt einen String in Anführungsszeichen ein, falls er Leerzeichen o.ä. enthält
285 * @return gequoteter String
287 public static String quoteIfNecessary(String s) {
288 for (int i = 0; i < s.length(); i++)
289 if (!(Character.isLetterOrDigit(s.charAt(i)) || s.charAt(i) == '.'))
290 return quote(s, '"');
295 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
296 * "gefährliche" Zeichen innerhalb des Strings
297 * Quotes special SQL-characters in <code>s</code>
299 * @return geqoteter String
301 public static String quote(String s)
303 String s2 = quote(s, '\'');
304 s2 = quote(s2, '\"');
309 * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
310 * "gefährliche" Zeichen innerhalb des Strings
312 * @param s String, der gequoted werden soll
313 * @param quoteChar zu quotendes Zeichen
314 * @return gequoteter String
316 public static String quote(String s, char quoteChar)
318 StringBuffer buf = new StringBuffer(s.length());
320 while (pos < s.length()) {
321 int i = s.indexOf(quoteChar, pos);
322 if (i < 0) i = s.length();
323 buf.append(s.substring(pos, i));
325 if (pos < s.length()) {
327 buf.append(quoteChar);
331 return buf.toString();
335 * replaces dangerous characters in <code>s</code>
339 public static String unquote(String s)
342 StringBuffer buf = new StringBuffer(s.length());
344 String searchString = "\\"+quoteChar;
345 while (pos < s.length()) {
346 int i = s.indexOf(searchString, pos);
347 if (i < 0) i = s.length();
348 buf.append(s.substring(pos, i));
351 return buf.toString();
355 * Wandelet String in byte[] um.
357 * @return byte[] des String
360 public static byte[] stringToBytes(String s) {
361 String crlf = System.getProperty("line.separator");
362 if (!crlf.equals("\n"))
363 s = replace(s, "\n", crlf);
364 // byte[] buf = new byte[s.length()];
365 byte[] buf = s.getBytes();
370 * Ersetzt in String <code>s</code> das <code>pattern</code> durch <code>substitute</code>
374 * @return String mit den Ersetzungen
376 public static String replace(String s, String pattern, String substitute) {
377 int i = 0, pLen = pattern.length(), sLen = substitute.length();
378 StringBuffer buf = new StringBuffer(s.length());
380 int j = s.indexOf(pattern, i);
382 buf.append(s.substring(i));
385 buf.append(s.substring(i, j));
386 buf.append(substitute);
390 return buf.toString();
394 * Ersetzt in String <code>s</code> das Regexp <code>pattern</code> durch <code>substitute</code>
398 * @return String mit den Ersetzungen
400 public static String regexpReplace(String haystack, String pattern, String substitute) {
402 RE regex = new RE(pattern);
403 return regex.substituteAll(haystack,substitute);
404 } catch(REException ex){
413 * Fügt einen Separator an den Pfad an
415 * @return Pfad mit Separator am Ende
417 public static final String addSeparator (String path) {
418 return path.length() == 0 || path.endsWith(File.separator) ? path : path
419 + File.separatorChar;
423 * Fügt ein <code>/</code> ans ende des Strings and
425 * @return Pfad mit <code>/</code> am Ende
427 public static final String addSlash (String path) {
428 return path.length() == 0 || path.endsWith("/") ? path : path + '/';
432 * Löscht <code>/</code> am Ende des Strings, falls vorhanden
434 * @return String ohne <code>/</code> am Ende
436 public static final String removeSlash (String path) {
437 return path.length() > 1 && path.endsWith("/") ? path.substring(0, path.length()
442 * Checks to see if the path is absolute by looking for a leading file
447 public static boolean isAbsolutePath (String path) {
448 return path.startsWith(File.separator);
452 * Löscht Slash am Anfang des Strings
456 public static String removeFirstSlash (String path) {
457 return path.startsWith("/") ? path.substring(1) : path;
461 * formatiert eine Zahl (0-99) zweistellig (z.B. 5 -> 05)
462 * @return zwistellige Zahl
464 public static String pad2 (int number) {
465 return number < 10 ? "0" + number : String.valueOf(number);
469 * formatiert eine Zahl (0-999) dreistellig (z.B. 7 -> 007)
471 * @return 3-stellige Zahl
473 public static String pad3 (int number) {
474 return number < 10 ? "00" + number : number < 100 ? "0" + number : String.valueOf(number);
478 * Konvertiert Unix-Linefeeds in Win-Linefeeds
480 * @return Konvertierter String
482 public static String unixLineFeedsToWin(String s) {
485 i = s.indexOf('\n', i+1);
487 if ((i == 0 || s.charAt(i-1) != '\r') &&
488 (i == s.length()-1 || s.charAt(i+1) != '\r')) {
489 s = s.substring(0, i)+'\r'+s.substring(i);
498 * verwandelt einen String in eine gültige Url, konvertiert Sonderzeichen
499 * und Spaces werden zu Underscores
501 * @return gültige Url
503 public static String convert2url(String s) {
505 StringBuffer buf = new StringBuffer();
506 for(int i = 0; i < s.length(); i++ ) {
507 switch( s.charAt( i ) ) {
509 buf.append( "oe" ); break;
511 buf.append( "ae" ); break;
513 buf.append( "ue" ); break;
515 buf.append( "a" ); break;
518 buf.append( "_" ); break;
520 if( buf.charAt( buf.length() - 1 ) != '_' ) {
525 buf.append( s.charAt( i ) );
528 return buf.toString();
532 * wandelt Sonderzeichen in Quotes um
534 * @return Kovertierter String
536 public static String encodeHtml(String s) {
537 StringBuffer buf = new StringBuffer();
538 for(int i=0;i < s.length(); i++ ) {
540 /** @todo looks inefficient, to ask for index of every char, in
541 * case of failure it runs to the end.*/
542 if (s.charAt(i)=='&') {
543 // convert html to xml-parsable representation
544 if( s.indexOf( "ö", i ) == i ) {
545 buf.append( "ö" ); i += 5;
548 if( s.indexOf( "ä", i ) == i ) {
549 buf.append( "ä" ); i += 5;
552 if( s.indexOf( "ü", i ) == i ) {
553 buf.append( "ü" ); i += 5;
556 if( s.indexOf( "Ö", i ) == i ) {
557 buf.append( "Ö" ); i += 5;
560 if( s.indexOf( "Ä", i ) == i ) {
561 buf.append( "Ä" ); i += 5;
564 if( s.indexOf( "Ü", i ) == i ) {
565 buf.append( "Ü" ); i += 5;
568 if( s.indexOf( "ß", i ) == i ) {
569 buf.append( "ß" ); i += 6;
573 /** @todo should only escape outside of tags */
575 if( s.indexOf( """, i ) == i ) {
576 buf.append( "ß" ); i += 5;
579 if( s.indexOf( "–", i ) == i ) {
580 buf.append( "–" ); i += 6;
583 if( s.indexOf( "—", i ) == i ) {
584 buf.append( "—" ); i += 6;
587 if( s.indexOf( "“", i ) == i ) {
588 buf.append( "“" ); i += 6;
591 if( s.indexOf( "”", i ) == i ) {
592 buf.append( "”" ); i += 6;
595 if( s.indexOf( "„", i ) == i ) {
596 buf.append( "„" ); i += 6;
600 //looks pretty stupid
601 if( s.indexOf( "<", i ) == i ) {
602 buf.append( "<" ); i += 3;
605 if( s.indexOf( ">", i ) == i ) {
606 buf.append( ">" ); i += 3;
609 if( s.indexOf( "´", i ) == i ) {
610 buf.append( "´" ); i += 6;
613 if( s.indexOf( " ", i ) == i ) {
614 buf.append( " " ); i += 5;
618 //if( s.indexOf( "&", i ) == i ) {
619 // buf.append( "&" ); i += 0;
623 // convert umlauts an other special charakters
624 switch( s.charAt(i) ) {
625 case 'ö': buf.append( "ö" ); break;
626 case 'ä': buf.append( "ä" ); break;
627 case 'ü': buf.append( "ü" ); break;
628 case 'Ö': buf.append( "Ö" ); break;
629 case 'Ä': buf.append( "Ä" ); break;
630 case 'Ü': buf.append( "Ü" ); break;
631 case 'ß': buf.append( "ß" ); break;
632 case 'é': buf.append( "é" ); break;
633 case 'è': buf.append( "è" ); break;
634 case 'á': buf.append( "á" ); break;
635 case 'à': buf.append( "à" ); break;
636 case 'â': buf.append( "â" ); break;
637 case 'ã': buf.append( "ã" ); break;
638 case '¬': buf.append( "¬" ); break;
639 case '¹': buf.append( "¹" ); break;
640 case '²': buf.append( "²" ); break;
641 case '³': buf.append( "³" ); break;
642 case '¼': buf.append( "¼" ); break;
643 case '½': buf.append( "½" ); break;
644 case '¾': buf.append( "¾" ); break;
645 case '¶': buf.append( "¶" ); break;
646 case 'æ': buf.append( "æ" ); break;
647 case 'ð': buf.append( "ð" ); break;
648 case '|': buf.append( "¦" ); break;
649 case '·': buf.append( "·" ); break;
650 case '°': buf.append( "°" ); break;
651 case '§': buf.append( "§" ); break;
652 case 'ø': buf.append( "ø" ); break;
653 case 'ç': buf.append( "ç" ); break;
654 case '¤': buf.append( "¤" ); break;
655 case 'ª': buf.append( "ª" ); break;
656 case 'Ç': buf.append( "Ç" ); break;
657 case 'Ã': buf.append( "Ã" ); break;
658 case 'Â': buf.append( "Â" ); break;
659 case 'Æ': buf.append( "Æ" ); break;
660 case '©': buf.append( "©" ); break;
661 case '®': buf.append( "®" ); break;
662 case '¥': buf.append( "¥" ); break;
663 case 'Þ': buf.append( "þ" ); break;
664 case '¯': buf.append( "¯" ); break;
665 case 'Ð': buf.append( "Ð" ); break;
666 case 'º': buf.append( "º" ); break;
667 case '¡': buf.append( "¡" ); break;
668 case '£': buf.append( "£" ); break;
669 case '±': buf.append( "±" ); break;
670 case '¿': buf.append( "¿" ); break;
671 case 'Ø': buf.append( "Ø" ); break;
672 case 'Á': buf.append( "À" ); break;
673 case 'À': buf.append( "Á" ); break;
674 case 'É': buf.append( "È" ); break;
675 case 'È': buf.append( "É" ); break;
676 case 'ù': buf.append( "ú" ); break;
677 case 'ñ': buf.append( "ñ" ); break;
678 case 'Ñ': buf.append( "Ñ" ); break;
679 case 'µ': buf.append( "µ" ); break;
680 case 'Í': buf.append( "Ì" ); break;
681 case 'Ì': buf.append( "Í" ); break;
682 case 'í': buf.append( "ì" ); break;
683 case 'ì': buf.append( "í" ); break;
684 case 'î': buf.append( "î" ); break;
685 case 'Î': buf.append( "Î" ); break;
686 case 'ó': buf.append( "ó" ); break;
687 case 'Ó': buf.append( "Ò" ); break;
688 case 'ò': buf.append( "Î" ); break;
689 case 'Ò': buf.append( "Ó" ); break;
690 case 'ô': buf.append( "ô" ); break;
691 case 'Ô': buf.append( "Ô" ); break;
692 case 'õ': buf.append( "õ" ); break;
693 case 'Õ': buf.append( "Õ" ); break;
694 case 'ý': buf.append( "ý" ); break;
695 case 'Ý': buf.append( "Ý" ); break;
696 case 'û': buf.append( "û" ); break;
697 case 'Û': buf.append( "Û" ); break;
698 case 'ú': buf.append( "ù" ); break;
699 case 'Ú': buf.append( "Ù" ); break;
700 case 'Ù': buf.append( "Ú" ); break;
701 case 'Ê': buf.append( "Ê" ); break;
702 case 'ê': buf.append( "ê" ); break;
703 case 'å': buf.append( "å" ); break;
704 case 'Å': buf.append( "Å" ); break;
705 case 'ë': buf.append( "ë" ); break;
706 case 'Ë': buf.append( "Ë" ); break;
707 case 'ÿ': buf.append( "ÿ" ); break;
708 case 'ï': buf.append( "ï" ); break;
709 case 'Ï': buf.append( "Ï" ); break;
710 case '«': buf.append( "«" ); break;
711 case '»': buf.append( "»" ); break;
712 case '\'': buf.append( "´" ); break;
713 case '\"': buf.append( """ ); break;
714 //case '\u8211': buf.append( "–" ); break;
715 //case '\u8212': buf.append( "—" ); break;
716 //case '\u8220': buf.append( "“" ); break;
717 //case '\u8221': buf.append( "”" ); break;
718 //case '\u8222': buf.append( "„" ); break;
719 //case '\"': buf.append( """ ); break;
720 default: buf.append( s.charAt(i) );
724 return buf.toString();
728 public static String decodeHTMLinTags(String s){
729 StringBuffer buffer = new StringBuffer();
730 boolean start = false;
731 boolean stop = false;
736 for(int i=0;i<s.length();i++){
737 if(s.charAt(i)=='<'){
740 } else if(s.charAt(i)=='>'){
745 buffer.append(s.substring(temp,startIndex));
746 buffer.append(replaceQuot(s.substring(startIndex,stopIndex+1)));
747 i= temp= stopIndex+1;
753 buffer.append(s.substring(stopIndex+1));
754 return buffer.toString();
760 public static String replaceQuot(String s) {
761 StringBuffer buffer = new StringBuffer();
762 for(int j = 0; j < s.length();j++){
763 if(s.charAt(j)=='&'){
764 if(s.indexOf( """,j) == j) {
765 buffer.append( "\"" );
769 buffer.append(s.charAt(j));
772 return buffer.toString();
775 /** wandelt Quotes in Sonderzeichen um
778 public static String decodeHtml(String s) {
779 StringBuffer buf = new StringBuffer();
780 for(int i=0;i < s.length(); i++ ) {
781 if( s.indexOf( "ö", i ) == i ) {
782 buf.append( "ö" ); i += 5;
785 if( s.indexOf( "ä", i ) == i ) {
786 buf.append( "ä" ); i += 5;
789 if( s.indexOf( "ü", i ) == i ) {
790 buf.append( "ü" ); i += 5;
793 if( s.indexOf( "Ö", i ) == i ) {
794 buf.append( "Ö" ); i += 5;
797 if( s.indexOf( "Ä", i ) == i ) {
798 buf.append( "Ä" ); i += 5;
801 if( s.indexOf( "Ü", i ) == i ) {
802 buf.append( "Ü" ); i += 5;
805 if( s.indexOf( "ß", i ) == i ) {
806 buf.append( "ß" ); i += 6;
809 if( s.indexOf( """, i ) == i ) {
810 buf.append( "\"" ); i += 5;
813 buf.append( s.charAt(i) );
815 return buf.toString();
820 * schnellere Variante der String.toLowerCase()-Routine
822 * @return String in Kleinbuchsten
824 public static String toLowerCase(String s) {
826 char[] a = new char[l];
827 for (int i = 0; i < l; i++)
828 a[i] = Character.toLowerCase(s.charAt(i));
829 return new String(a);
833 * Findet <code>element</code> im String-Array <code>array</code>
836 * @return Fundstelle als int oder -1
838 public static int indexOf(String[] array, String element) {
840 for (int i = 0; i < array.length; i++)
841 if (array[i].equals(element))
847 * Testet auf Vorkommen von <code>element</code> in <code>array</code>
848 * @param array String-Array
850 * @return true wenn <code>element</code> vorkommt, sonst false
852 public static boolean contains(String[] array, String element) {
853 return indexOf(array, element) >= 0;
857 * Ermittelt CRC-Prüfsumme von String <code>s</code>
859 * @return CRC-Prüfsumme
861 public static int getCRC(String s) {
863 char val[] = s.toCharArray();
864 int len = val.length;
866 for (int i = 0 ; i < len; i++) {
868 h = (((h >> 30) | (h << 1)) ^ (val[i]+i));
871 return (h << 8) | (len & 0xff);
875 * Liefert Default-Wert def zurück, wenn String <code>s</code>
880 * @return geparster int aus s oder def
882 public static int parseInt(String s, int def) {
883 if (s == null) return def;
885 return Integer.parseInt(s);
886 } catch (NumberFormatException e) {
892 * Liefert Defaultwert def zurück, wenn s nicht zu einem float geparsed werden kann.
895 * @return geparster float oder def
897 public static float parseFloat(String s, float def) {
898 if (s == null) return def;
900 return new Float(s).floatValue();
901 } catch (NumberFormatException e) {
907 * Findet Ende eines Satzes in String <code>text</code>
910 * @return index des Satzendes, oder -1
912 public static int findEndOfSentence(String text, int startIndex) {
914 int i = text.indexOf('.', startIndex);
915 if (i < 0) return -1;
916 if (i > 0 && !Character.isDigit(text.charAt(i-1)) &&
917 (i+1 >= text.length()
918 || text.charAt(i+1) == ' '
919 || text.charAt(i+1) == '\n'
920 || text.charAt(i+1) == '\t'))
927 * Findet Wortende in String <code>text</code> ab <code>startIndex</code>
930 * @return Index des Wortendes, oder -1
932 public static int findEndOfWord(String text, int startIndex) {
933 int i = text.indexOf(' ', startIndex),
934 j = text.indexOf('\n', startIndex);
935 if (i < 0) i = text.length();
936 if (j < 0) j = text.length();
937 return Math.min(i, j);
942 * convertNewline2P ist eine regex-routine zum umwandeln von 2 oder mehr newlines (\n)
943 * in den html-tag <p>
944 * nur sinnvoll, wenn text nicht im html-format eingegeben
946 public static String convertNewline2P(String haystack) {
947 return re_brbr2p.substituteAll(haystack,"\n</p><p>");
951 * convertNewline2Break ist eine regex-routine zum umwandeln von 1 newline (\n)
952 * in den html-tag <br>
953 * nur sinnvoll, wenn text nicht im html-format eingegeben
955 public static String convertNewline2Break(String haystack) {
956 return re_newline2br.substituteAll(haystack,"$0<br />");
960 * createMailLinks wandelt text im email-adressenformat
961 * in einen klickbaren link um
962 * nur sinnvoll, wenn text nicht im html-format eingegeben
964 public static String createMailLinks(String haystack) {
965 return re_mail.substituteAll(haystack,"<a href=\"mailto:$0\">$0</a>");
970 * createMailLinks wandelt text im email-adressenformat
971 * in einen klickbaren link um
972 * nur sinnvoll, wenn text nicht im html-format eingegeben
974 public static String createMailLinks(String haystack, String imageRoot, String mailImage) {
975 return re_mail.substituteAll(haystack,"<img src=\""+imageRoot+"/"+mailImage+"\" border=\"0\"/> <a href=\"mailto:$0\">$0</a>");
980 * createURLLinks wandelt text im url-format
981 * in einen klickbaren link um
982 * nur sinnvoll, wenn text nicht im html-format eingegeben
984 public static String createURLLinks(String haystack) {
985 return re_url.substituteAll(haystack,"<a href=\"$0\">$0</a>");
989 * this routine takes text in url format and makes
990 * a clickaeble "<href>" link removing any "illegal" html tags
991 * @param haystack, the url
992 * @param title, the href link text
993 * @param imagRoot, the place to find icons
994 * @param extImage, the url of the icon to show next to the link
995 * @return a String containing the url
997 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage) {
999 return re_url.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">$0</a>");
1001 title = removeHTMLTags(title);
1002 return re_url.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/> <a href=\"$0\">"+title+"</a>");
1007 * this routine takes text in url format and makes
1008 * a clickaeble "<href>" link removing any "illegal" html tags
1009 * @param haystack, the url
1010 * @param imageRoot, the place to find icons
1011 * @param extImage, the url of the icon to show next to the link
1012 * @param intImage, unused
1013 * @return a String containing the url
1015 public static String createURLLinks(String haystack, String title, String imageRoot,String extImage,String intImage) {
1016 return createURLLinks(haystack, title, imageRoot, extImage);
1020 * deleteForbiddenTags
1021 * this method deletes all <script>, <body> and <head>-tags
1023 public static final String deleteForbiddenTags(String haystack) {
1025 RE regex = new RE("<[ \t\r\n](.*?)script(.*?)/script(.*?)>",RE.REG_ICASE);
1026 haystack = regex.substituteAll(haystack,"");
1027 regex = new RE("<head>(.*?)</head>");
1028 haystack = regex.substituteAll(haystack,"");
1029 regex = new RE("<[ \t\r\n/]*body(.*?)>");
1030 haystack = regex.substituteAll(haystack,"");
1032 } catch(REException ex){
1038 * this method deletes all html tags
1040 public static final String removeHTMLTags(String haystack){
1041 return re_tags.substituteAll(haystack,"");
1046 * this method deletes all but the approved tags html tags
1047 * it also deletes approved tags which contain malicious-looking attributes and doesn't work at all
1049 public static String approveHTMLTags(String haystack){
1051 String approvedTags="a|img|h1|h2|h3|h4|h5|h6|br|b|i|strong|p";
1052 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";
1053 String approvedProtocols="rtsp|http|ftp|https|freenet|mailto";
1055 // kill all the bad tags that have attributes
1056 String s = "<\\s*/?\\s*(?!(("+approvedTags+")\\s))\\w+\\s[^>]*>";
1057 RE regex = new RE(s,RE.REG_ICASE);
1058 haystack = regex.substituteAll(haystack,"");
1060 // kill all the bad tags that are attributeless
1061 regex = new RE("<\\s*/?\\s*(?!(("+approvedTags+")\\s*>))\\w+\\s*>",RE.REG_ICASE);
1062 haystack = regex.substituteAll(haystack,"");
1064 // kill all the tags which have a javascript attribute like onLoad
1065 regex = new RE("<[^>]*("+badAttributes+")[^>]*>",RE.REG_ICASE);
1066 haystack = regex.substituteAll(haystack,"");
1068 // kill all the tags which include a url to an unacceptable protocol
1069 regex = new RE("<\\s*a\\s+[^>]*href=(?!(\'|\")?("+approvedProtocols+"))[^>]*>",RE.REG_ICASE);
1070 haystack = regex.substituteAll(haystack,"");
1073 } catch(REException ex){
1074 ex.printStackTrace();
1081 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1082 * htmlcodierten string auf und returnt einen htmlcodierten String
1084 public static String createHTML(String content){
1085 content=convertNewline2Break(content);
1086 content=convertNewline2P(content);
1087 content=createMailLinks(content);
1088 content=createURLLinks(content);
1094 * createHTML ruft alle regex-methoden zum unwandeln eines nicht
1095 * htmlcodierten string auf und returnt einen htmlcodierten String
1097 public static String createHTML(String content,String producerDocRoot,String mailImage,String extImage,String intImage){
1098 content=convertNewline2Break(content);
1099 content=convertNewline2P(content);
1100 content=createMailLinks(content,producerDocRoot,mailImage);
1101 content=createURLLinks(content,null,producerDocRoot,extImage,intImage);