X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=source%2Fmir%2Fmisc%2FStringUtil.java;h=6bdeac7bfbc73375deddd8194953af08062d5db3;hb=10f4bb84a35aadd3a3fd5ba80fcf2ad9f2d54a0c;hp=a65c7109511106b1933fa5442eaebd321cb430dc;hpb=89cd93f1ae7dd083c0a8e8fe25fd544fd529209c;p=mir.git diff --git a/source/mir/misc/StringUtil.java b/source/mir/misc/StringUtil.java index a65c7109..6bdeac7b 100755 --- a/source/mir/misc/StringUtil.java +++ b/source/mir/misc/StringUtil.java @@ -1,1116 +1,235 @@ /* - * put your module comment here + * Copyright (C) 2005 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. + * 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 org.apache.oro.text.regex.Pattern; +import org.apache.oro.text.regex.Perl5Matcher; +import org.apache.oro.text.regex.Perl5Substitution; +import org.apache.oro.text.regex.Util; + +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 */ public final class StringUtil { - private static RE re_newline2br, re_brbr2p, re_mail, re_url, re_tags; - - private StringUtil() { } // this avoids contruction - - static { - try { - //precompile regex - re_newline2br = new RE("(\r?\n){1}"); - re_brbr2p = new RE("(
\r?\n
){1,}"); - re_mail = new RE("([a-zA-Z0-9_.-]+)@([a-zA-Z0-9_-]+).([a-zA-Z0-9_.-]+)"); - 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); - } - catch (REException e){ - System.err.println("FATAL: StringUtil: could not precompile REGEX: "+e.toString()); - } - } - - - /** - * Wandelt Datum in einen 8-ziffrigen String um (yyyymmdd) - * @param theDate - * @return 8-ziffriger String (yyyymmdd) - */ - - public static final String date2webdbDate (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))); - return webdbDate.toString(); - } - - /** - * 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))); - 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) - */ - public static String date2readableDateTime (GregorianCalendar theDate) { - String readable = ""; - int hour; - readable += pad2(theDate.get(Calendar.DATE)); - readable += "." + pad2(theDate.get(Calendar.MONTH) + 1); - readable += "." + String.valueOf(theDate.get(Calendar.YEAR)); - hour = theDate.get(Calendar.HOUR); - if (theDate.get(Calendar.AM_PM) == Calendar.PM) - hour += 12; - readable += " / " + pad2(hour); - readable += ":" + pad2(theDate.get(Calendar.MINUTE)); - return readable; - } - - /** - * wandelt eine Datum in einen 8-buchstabigen String, der durch / - * getrennt ist. - * - * @param webdbDate - * @return String mit /yyyy/mm/dd - */ - public static final String webdbDate2path (String webdbDate) { - StringBuffer path = new StringBuffer(); - path.append("/").append(webdbDate.substring(0, 4)); - path.append("/").append(webdbDate.substring(4, 6)); - path.append("/"); - //who did this? - //path.append("/").append(webdbDate.substring(6, 8)); - return path.toString(); - } - - /** - * wandelt Calendar in dd.mm.yyyy um - * - * @param theDate - * @return String mit dd.mm.yyyy - */ - 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(); - } - - /** - * converts string from format: yyyy-mm-dd__hh:mm:ss.dddddd+TZ - * to yyyy-mm-ddThhmmss+TZ:00 (w3 format for Dublin Core) - */ - public static String webdbdateToDCDate(String date) { - StringBuffer returnDate = new StringBuffer(); - if (date!=null) { - - returnDate.append(date.substring(0,4)); - returnDate.append("-"); - returnDate.append(date.substring(5,7)); - returnDate.append("-"); - returnDate.append(date.substring(8,10)); - returnDate.append("T"); - returnDate.append(date.substring(11,13)); - returnDate.append(":"); - returnDate.append(date.substring(14,16)); - returnDate.append(":"); - returnDate.append(date.substring(17,19)); - //removed until someone tells me - //where the timezone goes -john - //returnDate.append(date.substring(17,22)); - //returnDate.append(":00"); - } - return returnDate.toString(); - } - - - /** - * converts string from format: yyyy-mm-dd__hh:mm:ss.d - * to yyyy - */ - public static String dateToYear (String date) { - StringBuffer returnDate = new StringBuffer(); - if (date!=null) { - - returnDate.append(date.substring(0,4)); - } - return returnDate.toString(); - } - - /** - * converts string from format: yyyy-mm-dd__hh:mm:ss.d - * to [m]m - */ - public static String dateToMonth (String date) { - StringBuffer returnDate = new StringBuffer(); - if (date!=null) { - if (!date.substring(5,6).equalsIgnoreCase("0")) returnDate.append(date.substring(5,7)); - else returnDate.append(date.substring(6,7)); - } - return returnDate.toString(); - } - - /** - * converts string from format: yyyy-mm-dd__hh:mm:ss.d - * to [d]d - */ - public static String dateToDayOfMonth (String date) { - StringBuffer returnDate = new StringBuffer(); - if (date!=null) { - if (!date.substring(8,9).equalsIgnoreCase("0")) returnDate.append(date.substring(8,10)); - else returnDate.append(date.substring(9,10)); - } - return returnDate.toString(); - } - - /** - * converts string from format: yyyy-mm-dd__hh:mm:ss.d - * to hh:mm - */ - public static String dateToTime (String date) { - StringBuffer returnDate = new StringBuffer(); - if (date!=null) { - returnDate.append(date.substring(11,16)); - } - return returnDate.toString(); - } - - /** - * Splits the provided CSV text into a list. stolen wholesale from - * from Jakarta Turbine StrinUtils.java -mh - * - * @param text The CSV list of values to split apart. - * @param separator The separator character. - * @return The list of values. - */ - public static String[] split(String text, String separator) - { - StringTokenizer st = new StringTokenizer(text, separator); - String[] values = new String[st.countTokens()]; - int pos = 0; - while (st.hasMoreTokens()) - { - values[pos++] = st.nextToken(); - } - return values; + private static TimeZone UTC = TimeZone.getTimeZone("UTC"); + + private StringUtil() { } // this avoids contruction + + /** + * 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 + * @return 8-ziffriger String (yyyymmdd) + */ + + public static String date2webdbDate (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))); + + 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 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("-"); } - - /** - * Joins the elements of the provided array into a single string - * containing a list of CSV elements. Stolen wholesale from Jakarta - * Turbine StringUtils.java. -mh - * - * @param list The list of values to join together. - * @param separator The separator character. - * @return The CSV text. - */ - public static String join(String[] list, String separator) - { - StringBuffer csv = new StringBuffer(); - for (int i = 0; i < list.length; i++) - { - if (i > 0) - { - csv.append(separator); - } - csv.append(list[i]); - } - return csv.toString(); + 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) + */ + public static String date2readableDateTime (GregorianCalendar theDate) { + String readable = ""; + int hour; + readable += pad2(theDate.get(Calendar.DATE)); + readable += "." + pad2(theDate.get(Calendar.MONTH) + 1); + readable += "." + String.valueOf(theDate.get(Calendar.YEAR)); + hour = theDate.get(Calendar.HOUR); + if (theDate.get(Calendar.AM_PM) == Calendar.PM) + hour += 12; + readable += " / " + pad2(hour); + readable += ":" + pad2(theDate.get(Calendar.MINUTE)); + return readable; + } + + /** + * wandelt eine Datum in einen 8-buchstabigen String, der durch / + * getrennt ist. + * + * @param webdbDate + * @return String mit /yyyy/mm/dd + */ + public static String webdbDate2path (String webdbDate) { + StringBuffer path = new StringBuffer(); + path.append("/").append(webdbDate.substring(0, 4)); + path.append("/").append(webdbDate.substring(4, 6)); + path.append("/"); + //who did this? + //path.append("/").append(webdbDate.substring(6, 8)); + return path.toString(); + } + + /** + * L?scht / am Ende des Strings, falls vorhanden + * @param path + * @return String ohne / am Ende + */ + public static String removeSlash (String path) { + return path.length() > 1 && path.endsWith("/") ? path.substring(0, path.length() + - 1) : path; + } + + /** + * formatiert eine Zahl (0-99) zweistellig (z.B. 5 -> 05) + * @return zwistellige Zahl + */ + public static String pad2 (int number) { + return number < 10 ? "0" + number : String.valueOf(number); + } + + /** + * formatiert eine Zahl (0-999) dreistellig (z.B. 7 -> 007) + * + * @return 3-stellige Zahl + */ + public static String pad3 (int number) { + return number < 10 ? "00" + number : number < 100 ? "0" + number : String.valueOf(number); + } + + /** + * Liefert Default-Wert def zur?ck, wenn String s + * kein Integer ist. + * + * @param s + * @param def + * @return geparster int aus s oder def + */ + public static int parseInt(String s, int def) { + if (s == null) return def; + try { + return Integer.parseInt(s); + } catch (NumberFormatException e) { + return def; + } + } + + + /** + * Converts mir's horrible internal date format (yyyy-MM-dd HH:mm:ss+zz) into a java Date + * + * @param anInternalDate + */ + 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(UTC); + calendar.set(year, month-1, day, hours, minutes, seconds); + calendar.add(Calendar.HOUR, -timezoneOffset); - /** - * 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 s in ' ein und setzt Backslashes vor - * "gefährliche" Zeichen innerhalb des Strings - * Quotes special SQL-characters in s - * - * @return geqoteter String - */ - public static String quote(String s) - { - String s2 = quote(s, '\''); - s2 = quote(s2, '\"'); - return s2; - } - - /** - * schließt s in ' 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(); - } - - /** - * replaces dangerous characters in s - * - */ - - 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 s das pattern durch substitute - * @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; - } - } - return buf.toString(); - } - - /** - * Ersetzt in String s das Regexp pattern durch substitute - * @param s - * @param pattern - * @param substitute - * @return String mit den Ersetzungen - */ - 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; - } - } - - - - - /** - * 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 / ans ende des Strings and - * @param path - * @return Pfad mit / am Ende - */ - public static final String addSlash (String path) { - return path.length() == 0 || path.endsWith("/") ? path : path + '/'; - } - - /** - * Löscht / am Ende des Strings, falls vorhanden - * @param path - * @return String ohne / am Ende - */ - public static final String removeSlash (String path) { - return path.length() > 1 && path.endsWith("/") ? path.substring(0, path.length() - - 1) : path; - } - - /** - * Checks to see if the path is absolute by looking for a leading file - * separater - * @param path - * @return - */ - public static boolean isAbsolutePath (String path) { - return path.startsWith(File.separator); - } - - /** - * 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 - */ - public static String pad2 (int number) { - return number < 10 ? "0" + number : String.valueOf(number); - } - - /** - * formatiert eine Zahl (0-999) dreistellig (z.B. 7 -> 007) - * - * @return 3-stellige Zahl - */ - public static String pad3 (int number) { - return number < 10 ? "00" + number : number < 100 ? "0" + number : String.valueOf(number); - } - - /** - * 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, to ask for index of every char, in - * case of failure it runs to the end.*/ - if (s.charAt(i)=='&') { - // convert html to xml-parsable representation - if( s.indexOf( "ö", i ) == i ) { - buf.append( "ö" ); i += 5; - continue; - } - if( s.indexOf( "ä", i ) == i ) { - buf.append( "ä" ); i += 5; - continue; - } - if( s.indexOf( "ü", i ) == i ) { - buf.append( "ü" ); i += 5; - continue; - } - if( s.indexOf( "Ö", i ) == i ) { - buf.append( "Ö" ); i += 5; - continue; - } - if( s.indexOf( "Ä", i ) == i ) { - buf.append( "Ä" ); i += 5; - continue; - } - if( s.indexOf( "Ü", i ) == i ) { - buf.append( "Ü" ); i += 5; - continue; - } - if( s.indexOf( "ß", i ) == i ) { - buf.append( "ß" ); i += 6; - continue; - } - - /** @todo should only escape outside of tags */ - - if( s.indexOf( """, i ) == i ) { - buf.append( "ß" ); i += 5; - continue; - } - if( s.indexOf( "–", i ) == i ) { - buf.append( "–" ); i += 6; - continue; - } - if( s.indexOf( "—", i ) == i ) { - buf.append( "—" ); i += 6; - continue; - } - if( s.indexOf( "“", i ) == i ) { - buf.append( "“" ); i += 6; - continue; - } - if( s.indexOf( "”", i ) == i ) { - buf.append( "”" ); i += 6; - continue; - } - if( s.indexOf( "„", i ) == i ) { - buf.append( "„" ); i += 6; - continue; - } - - //looks pretty stupid - if( s.indexOf( "<", i ) == i ) { - buf.append( "<" ); i += 3; - continue; - } - if( s.indexOf( ">", i ) == i ) { - buf.append( ">" ); i += 3; - continue; - } - if( s.indexOf( "´", i ) == i ) { - buf.append( "´" ); i += 6; - continue; - } - if( s.indexOf( " ", i ) == i ) { - buf.append( " " ); i += 5; - continue; - } - //has to be the last - //if( s.indexOf( "&", i ) == i ) { - // buf.append( "&" ); i += 0; - // continue; - //} - } - // convert umlauts an other special charakters - switch( s.charAt(i) ) { - case 'ö': buf.append( "ö" ); break; - case 'ä': buf.append( "ä" ); break; - case 'ü': buf.append( "ü" ); break; - case 'Ö': buf.append( "Ö" ); break; - case 'Ä': buf.append( "Ä" ); break; - case 'Ü': buf.append( "Ü" ); break; - case 'ß': buf.append( "ß" ); break; - case 'é': buf.append( "é" ); break; - case 'è': buf.append( "è" ); break; - case 'á': buf.append( "á" ); break; - case 'à': buf.append( "à" ); break; - case 'â': buf.append( "â" ); break; - case 'ã': buf.append( "ã" ); break; - case '¬': buf.append( "¬" ); break; - case '¹': buf.append( "¹" ); break; - case '²': buf.append( "²" ); break; - case '³': buf.append( "³" ); break; - case '¼': buf.append( "¼" ); break; - case '½': buf.append( "½" ); break; - case '¾': buf.append( "¾" ); break; - case '¶': buf.append( "¶" ); break; - case 'æ': buf.append( "æ" ); break; - case 'ð': buf.append( "ð" ); break; - case '|': buf.append( "¦" ); break; - case '·': buf.append( "·" ); break; - case '°': buf.append( "°" ); break; - case '§': buf.append( "§" ); break; - case 'ø': buf.append( "ø" ); break; - case 'ç': buf.append( "ç" ); break; - case '¤': buf.append( "¤" ); break; - case 'ª': buf.append( "ª" ); break; - case 'Ç': buf.append( "Ç" ); break; - case 'Ã': buf.append( "Ã" ); break; - case 'Â': buf.append( "Â" ); break; - case 'Æ': buf.append( "Æ" ); break; - case '©': buf.append( "©" ); break; - case '®': buf.append( "®" ); break; - case '¥': buf.append( "¥" ); break; - case 'Þ': buf.append( "þ" ); break; - case '¯': buf.append( "¯" ); break; - case 'Ð': buf.append( "Ð" ); break; - case 'º': buf.append( "º" ); break; - case '¡': buf.append( "¡" ); break; - case '£': buf.append( "£" ); break; - case '±': buf.append( "±" ); break; - case '¿': buf.append( "¿" ); break; - case 'Ø': buf.append( "Ø" ); break; - case 'Á': buf.append( "À" ); break; - case 'À': buf.append( "Á" ); break; - case 'É': buf.append( "È" ); break; - case 'È': buf.append( "É" ); break; - case 'ù': buf.append( "ú" ); break; - case 'ñ': buf.append( "ñ" ); break; - case 'Ñ': buf.append( "Ñ" ); break; - case 'µ': buf.append( "µ" ); break; - case 'Í': buf.append( "Ì" ); break; - case 'Ì': buf.append( "Í" ); break; - case 'í': buf.append( "ì" ); break; - case 'ì': buf.append( "í" ); break; - case 'î': buf.append( "î" ); break; - case 'Î': buf.append( "Î" ); break; - case 'ó': buf.append( "ó" ); break; - case 'Ó': buf.append( "Ò" ); break; - case 'ò': buf.append( "Î" ); break; - case 'Ò': buf.append( "Ó" ); break; - case 'ô': buf.append( "ô" ); break; - case 'Ô': buf.append( "Ô" ); break; - case 'õ': buf.append( "õ" ); break; - case 'Õ': buf.append( "Õ" ); break; - case 'ý': buf.append( "ý" ); break; - case 'Ý': buf.append( "Ý" ); break; - case 'û': buf.append( "û" ); break; - case 'Û': buf.append( "Û" ); break; - case 'ú': buf.append( "ù" ); break; - case 'Ú': buf.append( "Ù" ); break; - case 'Ù': buf.append( "Ú" ); break; - case 'Ê': buf.append( "Ê" ); break; - case 'ê': buf.append( "ê" ); break; - case 'å': buf.append( "å" ); break; - case 'Å': buf.append( "Å" ); break; - case 'ë': buf.append( "ë" ); break; - case 'Ë': buf.append( "Ë" ); break; - case 'ÿ': buf.append( "ÿ" ); break; - case 'ï': buf.append( "ï" ); break; - case 'Ï': buf.append( "Ï" ); break; - case '«': buf.append( "«" ); break; - case '»': buf.append( "»" ); break; - case '\'': buf.append( "´" ); break; - case '\"': buf.append( """ ); break; - //case '\u8211': buf.append( "–" ); break; - //case '\u8212': buf.append( "—" ); break; - //case '\u8220': buf.append( "“" ); break; - //case '\u8221': buf.append( "”" ); break; - //case '\u8222': buf.append( "„" ); break; - //case '\"': buf.append( """ ); 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'){ - 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; - } - } - } - if(stopIndex>0){ - buffer.append(s.substring(stopIndex+1)); - return buffer.toString(); - } else { - return s; - } - } - - 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( """,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( "ö", i ) == i ) { - buf.append( "ö" ); i += 5; - continue; - } - if( s.indexOf( "ä", i ) == i ) { - buf.append( "ä" ); i += 5; - continue; - } - if( s.indexOf( "ü", i ) == i ) { - buf.append( "ü" ); i += 5; - continue; - } - if( s.indexOf( "Ö", i ) == i ) { - buf.append( "Ö" ); i += 5; - continue; - } - if( s.indexOf( "Ä", i ) == i ) { - buf.append( "Ä" ); i += 5; - continue; - } - if( s.indexOf( "Ü", i ) == i ) { - buf.append( "Ü" ); i += 5; - continue; - } - if( s.indexOf( "ß", i ) == i ) { - buf.append( "ß" ); i += 6; - continue; - } - if( s.indexOf( """, 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 element im String-Array array - * @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 element in array - * @param array String-Array - * @param element - * @return true wenn element vorkommt, sonst false - */ - public static boolean contains(String[] array, String element) { - return indexOf(array, element) >= 0; - } - - /** - * Ermittelt CRC-Prüfsumme von String s - * @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 s - * kein Integer ist. - * - * @param s - * @param def - * @return geparster int aus s oder def - */ - public static int parseInt(String s, int def) { - if (s == null) return def; - try { - return Integer.parseInt(s); - } catch (NumberFormatException e) { - return def; - } - } - - /** - * 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 text - * @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 text ab startIndex - * @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); - } - - - /** - * convertNewline2P ist eine regex-routine zum umwandeln von 2 oder mehr newlines (\n) - * in den html-tag

- * nur sinnvoll, wenn text nicht im html-format eingegeben - */ - public static String convertNewline2P(String haystack) { - return re_brbr2p.substituteAll(haystack,"\n

"); - } - - /** - * convertNewline2Break ist eine regex-routine zum umwandeln von 1 newline (\n) - * in den html-tag
- * nur sinnvoll, wenn text nicht im html-format eingegeben - */ - public static String convertNewline2Break(String haystack) { - return re_newline2br.substituteAll(haystack,"$0
"); - } - - /** - * createMailLinks wandelt text im email-adressenformat - * in einen klickbaren link um - * nur sinnvoll, wenn text nicht im html-format eingegeben - */ - public static String createMailLinks(String haystack) { - return re_mail.substituteAll(haystack,"$0"); - } - - - /** - * createMailLinks wandelt text im email-adressenformat - * in einen klickbaren link um - * nur sinnvoll, wenn text nicht im html-format eingegeben - */ - public static String createMailLinks(String haystack, String imageRoot, String mailImage) { - return re_mail.substituteAll(haystack," $0"); - } - - - /** - * createURLLinks wandelt text im url-format - * in einen klickbaren link um - * nur sinnvoll, wenn text nicht im html-format eingegeben - */ - public static String createURLLinks(String haystack) { - return re_url.substituteAll(haystack,"$0"); - } - - /** - * this routine takes text in url format and makes - * a clickaeble "" 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 title, String imageRoot,String extImage) { - if (title == null) { - return re_url.substituteAll(haystack," $0"); - } else { - title = removeHTMLTags(title); - return re_url.substituteAll(haystack," "+title+""); - } - } - - /** - * this routine takes text in url format and makes - * a clickaeble "" 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); - } - - /** - * deleteForbiddenTags - * this method deletes all