X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=source%2Fmir%2Fmisc%2FStringUtil.java;h=f9c996a731e0f301df0baaad0b1df11099fb6294;hb=29da699109ce8842d02b60abcdb0dfdc4aa4f0db;hp=9bfb152069ce41927a347e76d45734303a620331;hpb=84722c0556b2100ebf0fd7e769cf89d3fb628ba8;p=mir.git

diff --git a/source/mir/misc/StringUtil.java b/source/mir/misc/StringUtil.java
index 9bfb1520..f9c996a7 100755
--- a/source/mir/misc/StringUtil.java
+++ b/source/mir/misc/StringUtil.java
@@ -1,23 +1,85 @@
 /*
- * put your module comment here
+ * Copyright (C) 2001, 2002 The Mir-coders group
+ *
+ * This file is part of Mir.
+ *
+ * Mir is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Mir is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Mir; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * In addition, as a special exception, The Mir-coders gives permission to link
+ * the code of this program with  any library licensed under the Apache Software License,
+ * The Sun (tm) Java Advanced Imaging library (JAI), The Sun JIMI library
+ * (or with modified versions of the above that use the same license as the above),
+ * and distribute linked combinations including the two.  You must obey the
+ * GNU General Public License in all respects for all of the code used other than
+ * the above mentioned libraries.  If you modify this file, you may extend this
+ * exception to your version of the file, but you are not obligated to do so.
+ * If you do not wish to do so, delete this exception statement from your version.
  */
-
-
 package  mir.misc;
 
-import  java.io.*;
-import  java.lang.*;
-import  java.util.*;
-import  gnu.regexp.*;
+import gnu.regexp.RE;
+import gnu.regexp.REException;
+
+import java.text.NumberFormat;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.GregorianCalendar;
+import java.util.TimeZone;
 
 /**
  * Statische Hilfsmethoden zur Stringbehandlung
  *
- * @version 29.6.99
- * @author RK
+ * @version $Id: StringUtil.java,v 1.33.2.5 2003/10/23 14:55:28 rk Exp $
+ * @author mir-coders group
+ *
  */
 public final class StringUtil {
 
+  private static RE   re_newline2br, re_brbr2p, re_mail, re_url, re_tags,
+                      re_tables, re_forbiddenTags;
+
+  private StringUtil() { }  // this avoids contruction
+
+  static {
+    try {
+      //precompile regex
+      re_newline2br = new RE("(\r?\n){1}");
+      re_brbr2p     = new RE("(<br>\r?\n<br>){1,}");
+      re_mail       = new RE("\\b([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+)\\.([a-zA-Z0-9_.-]+)\\b");
+      re_url        = new RE("((https://)|(http://)|(ftp://)){1}([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>\\)\\]]+[^ \t\r\n.,<>\\)\\]])");
+      re_tags       = new RE("<[^>]*>",RE.REG_ICASE);
+      re_tables = new RE("<[ \t\r\n/]*(table|td|tr)[ \t\r\n]*>",RE.REG_ICASE);
+      re_forbiddenTags = new RE("<[ \t\r\n/]*(html|meta|body|head|script)[ \t\r\n]*>",RE.REG_ICASE);
+    }
+    catch (REException e){
+      System.err.println("FATAL: StringUtil: could not precompile REGEX: "+e.toString());
+    }
+  }
+
+  /**
+   * Formats a number with the specified minimum and maximum number of digits.
+   **/
+  public static synchronized String zeroPaddingNumber(long value, int minDigits,
+      int maxDigits)
+  {
+    NumberFormat numberFormat = NumberFormat.getInstance();
+    numberFormat.setMinimumIntegerDigits(minDigits);
+    numberFormat.setMaximumIntegerDigits(maxDigits);
+    return numberFormat.format(value);
+  }
+
   /**
    * Wandelt Datum in einen 8-ziffrigen String um (yyyymmdd)
    * @param theDate
@@ -33,6 +95,54 @@ public final class StringUtil {
   }
 
   /**
+   * Wandelt Calendar in einen 12-ziffrigen String um (yyyymmddhhmm)
+   * @param theDate
+   * @return 12-ziffriger String (yyyymmdd)
+   */
+
+  public static final String date2webdbDateTime (GregorianCalendar theDate) {
+    StringBuffer webdbDate = new StringBuffer();
+    webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
+    webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
+    webdbDate.append(pad2(theDate.get(Calendar.DATE)));
+    webdbDate.append(pad2(theDate.get(Calendar.HOUR)));
+    webdbDate.append(pad2(theDate.get(Calendar.MINUTE)));
+    return  webdbDate.toString();
+  }
+
+  /**
+   * Return a http://www.w3.org/TR/NOTE-datetime formatted date (yyyy-mm-ddThh:mm:ssTZ)
+   * @param theDate
+   * @return w3approved datetime
+   */
+
+  public static final String date2w3DateTime (GregorianCalendar theDate) {
+    StringBuffer webdbDate = new StringBuffer();
+    webdbDate.append(String.valueOf(theDate.get(Calendar.YEAR)));
+    webdbDate.append("-");
+    webdbDate.append(pad2(theDate.get(Calendar.MONTH) + 1));
+    webdbDate.append("-");
+    webdbDate.append(pad2(theDate.get(Calendar.DATE)));
+    webdbDate.append("T");
+    webdbDate.append(pad2(theDate.get(Calendar.HOUR_OF_DAY)));
+    webdbDate.append(":");
+    webdbDate.append(pad2(theDate.get(Calendar.MINUTE)));
+    webdbDate.append(":");
+    webdbDate.append(pad2(theDate.get(Calendar.SECOND)));
+    //assumes you are an hour-multiple away from UTC....
+    int offset=(theDate.get(Calendar.ZONE_OFFSET)/(60*60*1000));
+    if (offset < 0){
+      webdbDate.append("-");
+    }
+    else{
+      webdbDate.append("+");
+    }
+    webdbDate.append(pad2(Math.abs(offset)));
+    webdbDate.append(":00");
+    return  webdbDate.toString();
+  }
+
+  /**
    * wandelt Calendar in dd.mm.yyyy / hh.mm um
    * @param theDate
    * @return String mit (dd.mm.yyyy / hh.mm um)
@@ -52,6 +162,22 @@ public final class StringUtil {
   }
 
   /**
+  *  deleteForbiddenTags
+  *  this method deletes all <script>, <body> and <head>-tags
+  */
+  public static final String deleteForbiddenTags(String haystack) {
+    return re_forbiddenTags.substituteAll(haystack,"");
+  }
+
+  /**
+   *  deleteHTMLTableTags
+   *  this method deletes all <table>, <tr> and <td>-tags
+   */
+  public static final String deleteHTMLTableTags(String haystack) {
+    return re_tables.substituteAll(haystack,"");
+  }
+
+  /**
    * wandelt eine Datum in einen 8-buchstabigen String, der durch <code>/</code>
    * getrennt ist.
    *
@@ -69,184 +195,23 @@ public final class StringUtil {
   }
 
   /**
-   * wandelt Calendar in dd.mm.yyyy um
-   *
-   * @param theDate
-   * @return String mit  <code>dd.mm.yyyy</code>
-   */
-  public static final String webdbDate2readableDate (String webdbDate) {
-    String date = "";
-    date += webdbDate.substring(6, 8);
-    date += "." + webdbDate.substring(4, 6);
-    date += "." + webdbDate.substring(0, 4);
-    return  date;
-  }
-
-
-  /**
-   * converts string from format: yyyy-mm-dd__hh:mm:ss.d
-   * to dd.mm.yyyy hh:mm
-   */
-  public static String dateToReadableDate(String date) {
-    StringBuffer returnDate = new StringBuffer();
-    if (date!=null) {
-
-      returnDate.append(date.substring(8,10)).append('.');
-      returnDate.append(date.substring(5,7)).append('.');
-      returnDate.append(date.substring(0,4)).append(' ');
-      returnDate.append(date.substring(11,16));
-    }
-    return returnDate.toString();
-  }
-
-
-  /**
-   * schließt einen String in Anführungsszeichen ein, falls er Leerzeichen o.ä. enthält
-   *
-   * @return gequoteter String
-   */
-   public static String quoteIfNecessary(String s) {
-    for (int i = 0; i < s.length(); i++)
-      if (!(Character.isLetterOrDigit(s.charAt(i)) || s.charAt(i) == '.'))
-        return quote(s, '"');
-    return s;
-  }
-
-   /**
-   * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
-   * "gefährliche" Zeichen innerhalb des Strings
-   * Quotes special SQL-characters in <code>s</code>
-   *
-   * @return geqoteter String
-   */
-  public static String quote(String s)
-  {
-    //String s2 = quote(s, '\'');
-
-    //Quickhack
-    //Because of '?-Bug in Postgresql-JDBC-Driver
-    StringBuffer temp = new StringBuffer();
-    for(int i=0;i<s.length();i++){
-      if(s.charAt(i)=='\''){
-        temp.append("&acute;");
-      } else {
-        temp.append(s.charAt(i));
-      }
-    }
-    String s2 = temp.toString();
-    //Quickhack end
-
-    s2 = quote(s2, '\"');
-    return s2;
-  }
-
-  /**
-   * schließt <code>s</code> in <code>'</code> ein und setzt Backslashes vor
-   * "gefährliche" Zeichen innerhalb des Strings
-   *
-   * @param s String, der gequoted werden soll
-   * @param quoteChar zu quotendes Zeichen
-   * @return gequoteter String
-   */
-  public static String quote(String s, char quoteChar)
-  {
-    StringBuffer buf = new StringBuffer(s.length());
-    int pos = 0;
-    while (pos < s.length()) {
-      int i = s.indexOf(quoteChar, pos);
-      if (i < 0) i = s.length();
-      buf.append(s.substring(pos, i));
-      pos = i;
-      if (pos < s.length()) {
-        buf.append('\\');
-        buf.append(quoteChar);
-        pos++;
-      }
-    }
-    return buf.toString();
-  }
-
-  /**
-   * ersetzt gefährliche zeichen in  <code>s</code>
-   *
-   */
-
-  public static String unquote(String s)
-  {
-    char quoteChar='\'';
-    StringBuffer buf = new StringBuffer(s.length());
-    int pos = 0;
-    String searchString = "\\"+quoteChar;
-    while (pos < s.length()) {
-      int i = s.indexOf(searchString, pos);
-      if (i < 0) i = s.length();
-      buf.append(s.substring(pos, i));
-      pos = i+1;
-    }
-    return buf.toString();
-  }
-
-  /**
-   * Wandelet String in byte[] um.
-   * @param s
-   * @return byte[] des String
-   */
-
-  public static byte[] stringToBytes(String s) {
-    String crlf = System.getProperty("line.separator");
-    if (!crlf.equals("\n"))
-      s = replace(s, "\n", crlf);
-    // byte[] buf = new byte[s.length()];
-    byte[] buf = s.getBytes();
-    return buf;
-  }
-
-    /**
-   * Ersetzt in String <code>s</code> das <code>pattern</code> durch <code>substitute</code>
+   * Ersetzt in String <code>s</code> das Regexp <code>pattern</code> durch <code>substitute</code>
    * @param s
    * @param pattern
    * @param substitute
    * @return String mit den Ersetzungen
    */
-  public static String replace(String s, String pattern, String substitute) {
-    int i = 0, pLen = pattern.length(), sLen = substitute.length();
-    StringBuffer buf = new StringBuffer(s.length());
-    while (true) {
-      int j = s.indexOf(pattern, i);
-      if (j < 0) {
-        buf.append(s.substring(i));
-        break;
-      } else {
-        buf.append(s.substring(i, j));
-        buf.append(substitute);
-        i = j+pLen;
-      }
+  public static String regexpReplace(String haystack, String pattern, String substitute) {
+    try {
+      RE regex = new RE(pattern);
+      return regex.substituteAll(haystack,substitute);
+    } catch(REException ex){
+      return null;
     }
-    return buf.toString();
-  }
-
-
-  /**
-   * Fügt einen Separator an den Pfad an
-   * @param path
-   * @return Pfad mit Separator am Ende
-   */
-  public static final String addSeparator (String path) {
-    return  path.length() == 0 || path.endsWith(File.separator) ? path : path
-        + File.separatorChar;
-  }
-
-  /**
-   * Fügt ein <code>/</code> ans ende des Strings and
-   * @param path
-   * @return Pfad mit <code>/</code> am Ende
-   */
-  public static final String addSlash (String path) {
-    return  path.length() == 0 || path.endsWith("/") ? path : path + '/';
   }
 
   /**
-   * Löscht <code>/</code> am Ende des Strings, falls vorhanden
+   * L?scht <code>/</code> am Ende des Strings, falls vorhanden
    * @param path
    * @return String ohne <code>/</code> am Ende
    */
@@ -256,15 +221,6 @@ public final class StringUtil {
   }
 
   /**
-   * Löscht Slash am Anfang des Strings
-   * @param path
-   * @return
-   */
-  public static String removeFirstSlash (String path) {
-    return  path.startsWith("/") ? path.substring(1) : path;
-  }
-
-  /**
    * formatiert eine Zahl (0-99) zweistellig (z.B. 5 -> 05)
    * @return zwistellige Zahl
    */
@@ -282,399 +238,7 @@ public final class StringUtil {
   }
 
   /**
-   * Konvertiert Unix-Linefeeds in Win-Linefeeds
-   * @param s
-   * @return Konvertierter String
-   */
-  public static String unixLineFeedsToWin(String s) {
-    int i = -1;
-    while (true) {
-      i = s.indexOf('\n', i+1);
-      if (i < 0) break;
-      if ((i == 0 || s.charAt(i-1) != '\r') &&
-        (i == s.length()-1 || s.charAt(i+1) != '\r')) {
-        s = s.substring(0, i)+'\r'+s.substring(i);
-        i++;
-      }
-    }
-    return s;
-  }
-
-
-  /**
-   * verwandelt einen String in eine gültige Url, konvertiert Sonderzeichen
-   * und Spaces werden zu Underscores
-   *
-   * @return gültige Url
-   */
-  public static String convert2url(String s) {
-    s = toLowerCase(s);
-    StringBuffer buf = new StringBuffer();
-    for(int i = 0; i < s.length(); i++ ) {
-        switch( s.charAt( i ) ) {
-        case 'ö':
-      buf.append( "oe" ); break;
-        case 'ä':
-      buf.append( "ae" ); break;
-        case 'ü':
-      buf.append( "ue" ); break;
-        case 'ã':
-      buf.append( "a" ); break;
-        case '´':
-        case '.':
-      buf.append( "_" ); break;
-        case ' ':
-      if( buf.charAt( buf.length() - 1 ) != '_' ) {
-          buf.append( "_" );
-      }
-      break;
-        default:
-      buf.append( s.charAt( i ) );
-        }
-    }
-    return buf.toString();
-  }
-
-  /**
-   * wandelt Sonderzeichen in Quotes um
-   *
-   * @return Kovertierter String
-   */
-  public static String encodeHtml(String s) {
-    StringBuffer buf = new StringBuffer();
-    for(int i=0;i < s.length(); i++ ) {
-
-      /** @todo looks inefficient */
-      if (s.charAt(i)=='&') {
-        // convert html to xml-parsable representation
-        if( s.indexOf( "&ouml;", i ) == i ) {
-          buf.append( "&#246;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&auml;", i ) == i ) {
-          buf.append( "&#228;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&uuml;", i ) == i ) {
-          buf.append( "&#252;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&Ouml;", i ) == i ) {
-          buf.append( "&#214;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&Auml;", i ) == i ) {
-          buf.append( "&#196;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&Uuml;", i ) == i ) {
-          buf.append( "&#220;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&szlig;", i ) == i ) {
-          buf.append( "&#223;" ); i += 6;
-          continue;
-        }
-
-        /** @todo should only escape outside of tags */
-
-        if( s.indexOf( "&quot;", i ) == i ) {
-          buf.append( "&#223;" ); i += 5;
-          continue;
-        }
-        if( s.indexOf( "&ndash;", i ) == i ) {
-          buf.append( "&#8211;" ); i += 6;
-          continue;
-        }
-        if( s.indexOf( "&mdash;", i ) == i ) {
-          buf.append( "&#8212;" ); i += 6;
-          continue;
-        }
-        if( s.indexOf( "&ldquo;", i ) == i ) {
-          buf.append( "&#8220;" ); i += 6;
-          continue;
-        }
-        if( s.indexOf( "&rdquo;", i ) == i ) {
-          buf.append( "&#8221;" ); i += 6;
-          continue;
-        }
-        if( s.indexOf( "&bdquo;", i ) == i ) {
-          buf.append( "&#8222;" ); i += 6;
-          continue;
-        }
-
-        //looks pretty stupid
-        if( s.indexOf( "&lt;", i ) == i ) {
-          buf.append( "&lt;" ); i += 3;
-          continue;
-        }
-        if( s.indexOf( "&gt;", i ) == i ) {
-          buf.append( "&gt;" ); i += 3;
-          continue;
-        }
-        if( s.indexOf( "&acute;", i ) == i ) {
-          buf.append( "&acute;" ); i += 6;
-          continue;
-        }
-        if( s.indexOf( "&nbsp;", i ) == i ) {
-          buf.append( "&nbsp;" ); i += 5;
-          continue;
-        }
-        //has to be the last
-        if( s.indexOf( "&", i ) == i ) {
-          buf.append( "&#38;" ); i += 0;
-          continue;
-        }
-      }
-      // convert umlauts an other special charakters
-      switch( s.charAt(i) ) {
-        case 'ö': buf.append( "&#246;" ); break;
-        case 'ä': buf.append( "&#228;" ); break;
-        case 'ü': buf.append( "&#252;" ); break;
-        case 'Ö': buf.append( "&#214;" ); break;
-        case 'Ä': buf.append( "&#196;" ); break;
-        case 'Ü': buf.append( "&#220;" ); break;
-        case 'ß': buf.append( "&#223;" ); break;
-        case 'é': buf.append( "&#233;" ); break;
-        case 'è': buf.append( "&#232;" ); break;
-        case 'á': buf.append( "&#225;" ); break;
-        case 'à': buf.append( "&#224;" ); break;
-        case 'â': buf.append( "&#226;" ); break;
-        case 'ã': buf.append( "&#227;" ); break;
-        case '¬': buf.append( "&#172;" ); break;
-        case '¹': buf.append( "&#185;" ); break;
-        case '²': buf.append( "&#178;" ); break;
-        case '³': buf.append( "&#179;" ); break;
-        case '¼': buf.append( "&#188;" ); break;
-        case '½': buf.append( "&#189;" ); break;
-        case '¾': buf.append( "&#190;" ); break;
-        case '¶': buf.append( "&#182;" ); break;
-        case 'æ': buf.append( "&#230;" ); break;
-        case 'ð': buf.append( "&#240;" ); break;
-        case '|': buf.append( "&#166;" ); break;
-        case '·': buf.append( "&#183;" ); break;
-        case '°': buf.append( "&#176;" ); break;
-        case '§': buf.append( "&#167;" ); break;
-        case 'ø': buf.append( "&#248;" ); break;
-        case 'ç': buf.append( "&#231;" ); break;
-        case '¤': buf.append( "&#164;" ); break;
-        case 'ª': buf.append( "&#170;" ); break;
-        case 'Ç': buf.append( "&#199;" ); break;
-        case 'Ã': buf.append( "&#195;" ); break;
-        case 'Â': buf.append( "&#194;" ); break;
-        case 'Æ': buf.append( "&#198;" ); break;
-        case '©': buf.append( "&#169;" ); break;
-        case '®': buf.append( "&#174;" ); break;
-        case '¥': buf.append( "&#165;" ); break;
-        case 'Þ': buf.append( "&#254;" ); break;
-        case '¯': buf.append( "&#175;" ); break;
-        case 'Ð': buf.append( "&#208;" ); break;
-        case 'º': buf.append( "&#186;" ); break;
-        case '¡': buf.append( "&#161;" ); break;
-        case '£': buf.append( "&#163;" ); break;
-        case '±': buf.append( "&#177;" ); break;
-        case '¿': buf.append( "&#191;" ); break;
-        case 'Ø': buf.append( "&#216;" ); break;
-        case 'Á': buf.append( "&#192;" ); break;
-        case 'À': buf.append( "&#193;" ); break;
-        case 'É': buf.append( "&#200;" ); break;
-        case 'È': buf.append( "&#201;" ); break;
-        case 'ù': buf.append( "&#250;" ); break;
-        case 'ñ': buf.append( "&#241;" ); break;
-        case 'Ñ': buf.append( "&#209;" ); break;
-        case 'µ': buf.append( "&#181;" ); break;
-        case 'Í': buf.append( "&#204;" ); break;
-        case 'Ì': buf.append( "&#205;" ); break;
-        case 'í': buf.append( "&#236;" ); break;
-        case 'ì': buf.append( "&#237;" ); break;
-        case 'î': buf.append( "&#238;" ); break;
-        case 'Î': buf.append( "&#206;" ); break;
-        case 'ó': buf.append( "&#243;" ); break;
-        case 'Ó': buf.append( "&#210;" ); break;
-        case 'ò': buf.append( "&#206;" ); break;
-        case 'Ò': buf.append( "&#211;" ); break;
-        case 'ô': buf.append( "&#244;" ); break;
-        case 'Ô': buf.append( "&#212;" ); break;
-        case 'õ': buf.append( "&#245;" ); break;
-        case 'Õ': buf.append( "&#213;" ); break;
-        case 'ý': buf.append( "&#253;" ); break;
-        case 'Ý': buf.append( "&#221;" ); break;
-        case 'û': buf.append( "&#251;" ); break;
-        case 'Û': buf.append( "&#219;" ); break;
-        case 'ú': buf.append( "&#249;" ); break;
-        case 'Ú': buf.append( "&#217;" ); break;
-        case 'Ù': buf.append( "&#218;" ); break;
-        case 'Ê': buf.append( "&#202;" ); break;
-        case 'ê': buf.append( "&#234;" ); break;
-        case 'å': buf.append( "&#229;" ); break;
-        case 'Å': buf.append( "&#197;" ); break;
-        case 'ë': buf.append( "&#235;" ); break;
-        case 'Ë': buf.append( "&#203;" ); break;
-        case 'ÿ': buf.append( "&#255;" ); break;
-        case 'ï': buf.append( "&#239;" ); break;
-        case 'Ï': buf.append( "&#207;" ); break;
-        case '«': buf.append( "&#171;" ); break;
-        case '»': buf.append( "&#187;" ); break;
-        case '\'': buf.append( "&acute;" ); break;
-        case '\"': buf.append( "&quot;" ); break;
-        //case '\u8211': buf.append( "&#8211;" ); break;
-        //case '\u8212': buf.append( "&#8212;" ); break;
-        //case '\u8220': buf.append( "&#8220;" ); break;
-        //case '\u8221': buf.append( "&#8221;" ); break;
-        //case '\u8222': buf.append( "&#8222;" ); break;
-        //case '\"': buf.append( "&#34;" ); break;
-        default: buf.append( s.charAt(i) );
-      }
-
-    }
-    return buf.toString();
-  }
-
-
-  public static String decodeHTMLinTags(String s){
-    StringBuffer buffer = new StringBuffer();
-    boolean start = false;
-    boolean stop = false;
-    int startIndex = 0;
-    int stopIndex = 0;
-    int temp = 0;
-
-    for(int i=0;i<s.length();i++){
-      if(s.charAt(i)=='<'){
-        start = true;
-        startIndex = i;
-      } else if(s.charAt(i)=='>'){
-        stop = true;
-        stopIndex = i;
-
-        if(start && stop){
-          buffer.append(s.substring(temp,startIndex));
-          buffer.append(replaceQuot(s.substring(startIndex,stopIndex+1)));
-          i= temp= stopIndex+1;
-          start= stop= false;
-        }
-      }
-    }
-    buffer.append(s.substring(stopIndex+1));
-    return buffer.toString();
-  }
-
-  public static String replaceQuot(String s) {
-    StringBuffer buffer = new StringBuffer();
-    for(int j = 0; j < s.length();j++){
-      if(s.charAt(j)=='&'){
-        if(s.indexOf( "&quot;",j) == j) {
-          buffer.append( "\"" );
-          j += 5;
-        }//if
-      } else {
-        buffer.append(s.charAt(j));
-      }//else
-    }//for
-    return buffer.toString();
-  }
-
-  /** wandelt Quotes in Sonderzeichen um
-   */
-  /**
-  public static String decodeHtml(String s) {
-    StringBuffer buf = new StringBuffer();
-    for(int i=0;i < s.length(); i++ ) {
-      if( s.indexOf( "&ouml;", i ) == i ) {
-        buf.append( "ö" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&auml;", i ) == i ) {
-        buf.append( "ä" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&uuml;", i ) == i ) {
-        buf.append( "ü" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&Ouml;", i ) == i ) {
-        buf.append( "Ö" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&Auml;", i ) == i ) {
-        buf.append( "Ä" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&Uuml;", i ) == i ) {
-        buf.append( "Ü" ); i += 5;
-        continue;
-      }
-      if( s.indexOf( "&szlig;", i ) == i ) {
-        buf.append( "ß" ); i += 6;
-        continue;
-      }
-      if( s.indexOf( "&quot;", i ) == i ) {
-        buf.append( "\"" ); i += 5;
-        continue;
-      }
-      buf.append( s.charAt(i) );
-    }
-    return buf.toString();
-  }
-   */
-
-  /**
-   * schnellere Variante der String.toLowerCase()-Routine
-   *
-   * @return String in Kleinbuchsten
-   */
-  public static String toLowerCase(String s) {
-    int l = s.length();
-    char[] a = new char[l];
-    for (int i = 0; i < l; i++)
-      a[i] = Character.toLowerCase(s.charAt(i));
-    return new String(a);
-  }
-
-    /**
-   * Findet <code>element</code> im String-Array <code>array</code>
-   * @param array
-   * @param element
-   * @return Fundstelle als int oder -1
-   */
-  public static int indexOf(String[] array, String element) {
-    if (array != null)
-      for (int i = 0; i < array.length; i++)
-        if (array[i].equals(element))
-          return i;
-    return -1;
-  }
-
-  /**
-   * Testet auf Vorkommen von <code>element</code> in <code>array</code>
-   * @param array String-Array
-   * @param element
-   * @return true wenn <code>element</code> vorkommt, sonst false
-   */
-  public static boolean contains(String[] array, String element) {
-    return indexOf(array, element) >= 0;
-  }
-
-    /**
-   * Ermittelt CRC-Prüfsumme von String <code>s</code>
-   * @param s
-   * @return CRC-Prüfsumme
-   */
-  public static int getCRC(String s) {
-    int h = 0;
-    char val[] = s.toCharArray();
-    int len = val.length;
-
-    for (int i = 0 ; i < len; i++) {
-      h &= 0x7fffffff;
-      h = (((h >> 30) | (h << 1)) ^ (val[i]+i));
-    }
-
-    return (h << 8) | (len & 0xff);
-  }
-
-    /**
-   * Liefert Default-Wert def zurück, wenn String <code>s</code>
+   * Liefert Default-Wert def zur?ck, wenn String <code>s</code>
    * kein Integer ist.
    *
    * @param s
@@ -690,84 +254,6 @@ public final class StringUtil {
     }
   }
 
-  /**
-   * Liefert Defaultwert def zurück, wenn s nicht zu einem float geparsed werden kann.
-   * @param s
-   * @param def
-   * @return geparster float oder def
-   */
-  public static float parseFloat(String s, float def) {
-    if (s == null) return def;
-    try {
-      return new Float(s).floatValue();
-    } catch (NumberFormatException e) {
-      return def;
-    }
-  }
-
-    /**
-   * Findet Ende eines Satzes in String <code>text</code>
-   * @param text
-   * @param startIndex
-   * @return index des Satzendes, oder -1
-   */
-  public static int findEndOfSentence(String text, int startIndex) {
-     while (true) {
-       int i = text.indexOf('.', startIndex);
-       if (i < 0) return -1;
-       if (i > 0 && !Character.isDigit(text.charAt(i-1)) &&
-          (i+1 >= text.length()
-          || text.charAt(i+1) == ' '
-          || text.charAt(i+1) == '\n'
-          || text.charAt(i+1) == '\t'))
-          return i+1;
-       startIndex = i+1;
-     }
-  }
-
-    /**
-   * Findet Wortende in String <code>text</code> ab <code>startIndex</code>
-   * @param text
-   * @param startIndex
-   * @return Index des Wortendes, oder -1
-   */
-  public static int findEndOfWord(String text, int startIndex) {
-    int i = text.indexOf(' ', startIndex),
-      j = text.indexOf('\n', startIndex);
-    if (i < 0) i = text.length();
-    if (j < 0) j = text.length();
-    return Math.min(i, j);
-  }
-
-  /**
-   * Diese Routine macht aus links in reinem text browsbare links
-   * @param text
-   * @return Konvertierter String
-   */
-  public static String makeLinks(String text) {
-    int i = 0;
-    StringBuffer buf = new StringBuffer(text.length());
-    while (true) {
-      int j = text.indexOf("http://", i);
-      if (j < 0) {
-        buf.append(text.substring(i));
-        break;
-      } else {
-        buf.append(text.substring(i, j));
-        int k = findEndOfWord(text,j+7);
-        String url="";
-        if (k<0)  url = text.substring(j);
-        else    url = text.substring(j,k);
-
-        buf.append("<a href=\042"+url+"\042>"+url+"</a>");
-        //System.out.println("url mark: " + url);
-        i = j+url.length();
-      }
-    }
-    return buf.toString();
-
-  }
-
 
   /**
    *  convertNewline2P ist eine regex-routine zum umwandeln von 2 oder mehr newlines (\n)
@@ -775,12 +261,7 @@ public final class StringUtil {
    *  nur sinnvoll, wenn text nicht im html-format eingegeben
    */
   public static String convertNewline2P(String haystack) {
-    try {
-      RE regex = new RE("(<br>\r?\n<br>){1,}");
-      return regex.substituteAll(haystack,"\n</p><p>");
-    } catch(REException ex){
-      return null;
-    }
+    return re_brbr2p.substituteAll(haystack,"\n</p><p>");
   }
 
   /**
@@ -789,12 +270,7 @@ public final class StringUtil {
    *  nur sinnvoll, wenn text nicht im html-format eingegeben
    */
   public static String convertNewline2Break(String haystack) {
-    try {
-      RE regex = new RE("(\r?\n){1}");
-      return regex.substituteAll(haystack,"$0<br>");
-    } catch(REException ex){
-      return null;
-    }
+    return re_newline2br.substituteAll(haystack,"$0<br />");
   }
 
   /**
@@ -803,12 +279,7 @@ public final class StringUtil {
    *  nur sinnvoll, wenn text nicht im html-format eingegeben
    */
   public static String createMailLinks(String haystack) {
-    try {
-      RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
-      return regex.substituteAll(haystack,"<a href=\"mailto:$0\">$0</a>");
-    } catch(REException ex){
-      return null;
-    }
+    return re_mail.substituteAll(haystack,"<a href=\"mailto:$0\">$0</a>");
   }
 
 
@@ -818,12 +289,7 @@ public final class StringUtil {
    *  nur sinnvoll, wenn text nicht im html-format eingegeben
    */
   public static String createMailLinks(String haystack, String imageRoot, String mailImage) {
-    try {
-      RE regex = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)");
-      return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+mailImage+"\" border=\"0\"/>&#160;<a href=\"mailto:$0\">$0</a>");
-    } catch(REException ex){
-      return null;
-    }
+    return re_mail.substituteAll(haystack,"<img src=\""+imageRoot+"/"+mailImage+"\" border=\"0\"/>&#160;<a href=\"mailto:$0\">$0</a>");
   }
 
 
@@ -833,48 +299,82 @@ public final class StringUtil {
    *  nur sinnvoll, wenn text nicht im html-format eingegeben
    */
   public static String createURLLinks(String haystack) {
-    try {
-      //dieser Ausdruck brauch dringend fachliche Beratung
-      RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/([^ \t\r\n<>]+[^ \t\r\n.,<>])");
-      return regex.substituteAll(haystack,"<a href=\"$0\">$0</a>");
-    } catch(REException ex){
-      return null;
-    }
+    return re_url.substituteAll(haystack,"<a href=\"$0\">$0</a>");
   }
 
   /**
-   *  createURLLinks wandelt text im url-format
-   *  in einen klickbaren link um
-   *  nur sinnvoll, wenn text nicht im html-format eingegeben
+   * this routine takes text in url format and makes
+   * a clickaeble "<href>" link removing any "illegal" html tags
+   * @param haystack, the url
+   * @param title, the href link text
+   * @param imagRoot, the place to find icons
+   * @param extImage, the url of the icon to show next to the link
+   * @return a String containing the url
    */
-  public static String createURLLinks(String haystack,String imageRoot,String extImage,String intImage) {
-    try {
-      //dieser Ausdruck brauch dringend fachliche Beratung
-      RE regex = new RE("((https://)|(http://)|(ftp://))+([a-zA-Z0-9_-]+).([a-zA-Z0-9_.:-]+)/?([^ \t\r\n<>]+[^ \t\r\n.,<>])");
-      return regex.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/>&#160;<a href=\"$0\">$0</a>");
-    } catch(REException ex){
-      return null;
+  public static String createURLLinks(String haystack, String title, String imageRoot,String extImage) {
+    if (title == null) {
+      return re_url.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/>&#160;<a href=\"$0\">$0</a>");
+    } else {
+      title = removeHTMLTags(title);
+      return re_url.substituteAll(haystack,"<img src=\""+imageRoot+"/"+extImage+"\" border=\"0\"/>&#160;<a href=\"$0\">"+title+"</a>");
     }
   }
 
   /**
-   *  deleteForbiddenTags
-   *  this method deletes all <script>, <body> and <head>-tags
+   * this routine takes text in url format and makes
+   * a clickaeble "<href>" link removing any "illegal" html tags
+   * @param haystack, the url
+   * @param imageRoot, the place to find icons
+   * @param extImage, the url of the icon to show next to the link
+   * @param intImage, unused
+   * @return a String containing the url
+   */
+  public static String createURLLinks(String haystack, String title, String imageRoot,String extImage,String intImage) {
+    return createURLLinks(haystack, title, imageRoot, extImage);
+  }
+
+  /**
+   * this method deletes all html tags
    */
-  public static String deleteForbiddenTags(String haystack) {
+  public static final String removeHTMLTags(String haystack){
+    return re_tags.substituteAll(haystack,"");
+  }
+
+  /**
+   * this method deletes all but the approved tags html tags
+   * it also deletes approved tags which contain malicious-looking attributes and doesn't work at all
+   */
+  public static String approveHTMLTags(String haystack){
     try {
-      RE regex = new RE("<[ \t\r\n](.*?)script(.*?)/script(.*?)>",RE.REG_ICASE);
+      String approvedTags="a|img|h1|h2|h3|h4|h5|h6|br|b|i|strong|p";
+      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";
+      String approvedProtocols="rtsp|http|ftp|https|freenet|mailto";
+
+      // kill all the bad tags that have attributes
+      String s = "<\\s*/?\\s*(?!(("+approvedTags+")\\s))\\w+\\s[^>]*>";
+      RE regex = new RE(s,RE.REG_ICASE);
       haystack = regex.substituteAll(haystack,"");
-      regex = new RE("<head>(.*?)</head>");
+
+      // kill all the bad tags that are attributeless
+      regex = new RE("<\\s*/?\\s*(?!(("+approvedTags+")\\s*>))\\w+\\s*>",RE.REG_ICASE);
       haystack = regex.substituteAll(haystack,"");
-      regex = new RE("<[ \t\r\n/]*body(.*?)>");
+
+      // kill all the tags which have a javascript attribute like onLoad
+      regex = new RE("<[^>]*("+badAttributes+")[^>]*>",RE.REG_ICASE);
+      haystack = regex.substituteAll(haystack,"");
+
+      // kill all the tags which include a url to an unacceptable protocol
+      regex = new RE("<\\s*a\\s+[^>]*href=(?!(\'|\")?("+approvedProtocols+"))[^>]*>",RE.REG_ICASE);
       haystack = regex.substituteAll(haystack,"");
+
       return haystack;
     } catch(REException ex){
+      ex.printStackTrace();
       return null;
     }
   }
 
+
   /**
    *  createHTML ruft alle regex-methoden zum unwandeln eines nicht
    *  htmlcodierten string auf und returnt einen htmlcodierten String
@@ -887,6 +387,7 @@ public final class StringUtil {
     return content;
   }
 
+
   /**
    *  createHTML ruft alle regex-methoden zum unwandeln eines nicht
    *  htmlcodierten string auf und returnt einen htmlcodierten String
@@ -895,8 +396,44 @@ public final class StringUtil {
     content=convertNewline2Break(content);
     content=convertNewline2P(content);
     content=createMailLinks(content,producerDocRoot,mailImage);
-    content=createURLLinks(content,producerDocRoot,extImage,intImage);
+    content=createURLLinks(content,null,producerDocRoot,extImage,intImage);
     return content;
   }
 
+  /**
+   * Converts mir's horrible internal date format (yyyy-MM-dd HH:mm:ss+zz) into a java Date
+   *
+   * @param anInternalDate
+   * @return
+   */
+  public static Date convertMirInternalDateToDate(String anInternalDate) {
+    Calendar calendar = new GregorianCalendar();
+
+    int year;
+    int month;
+    int day;
+    int hours;
+    int minutes;
+    int seconds;
+    int timezoneOffset;
+
+    year = Integer.parseInt(anInternalDate.substring(0,4));
+    month = Integer.parseInt(anInternalDate.substring(5,7));
+    day = Integer.parseInt(anInternalDate.substring(8,10));
+    hours = Integer.parseInt(anInternalDate.substring(11,13));
+    minutes = Integer.parseInt(anInternalDate.substring(14,16));
+    seconds = Integer.parseInt(anInternalDate.substring(17,19));
+
+    timezoneOffset = Integer.parseInt(anInternalDate.substring(20,22));
+    if (anInternalDate.charAt(19) == '-')
+      timezoneOffset = -timezoneOffset;
+
+    calendar.setTimeZone(TimeZone.getTimeZone("UTC"));
+    calendar.set(year, month-1, day, hours, minutes, seconds);
+    calendar.add(Calendar.HOUR, -timezoneOffset);
+
+    return calendar.getTime();
+  }
+
 }
+