package de.anomic.data;
public class htmlTools {
/** Replaces characters in a string with other characters defined in an array.
* @param text a string that possibly contains special characters
* @param entities array that contains characters to be replaced and characters it will be replaced by
* @return the string with all characters replaced by the corresponding character from array
*/
//[FB], changes by [MN], re-implemented by [MC]
public static String encodeUnicode2html(String text, boolean includingAmpersand) {
if (text == null) return null;
int pos = 0;
StringBuffer sb = new StringBuffer(text.length());
search: while (pos < text.length()) {
// find a (forward) mapping
loop: for (int i = (includingAmpersand) ? 0 : 2; i < mapping.length; i += 2) {
if (text.charAt(pos) != mapping[i].charAt(0)) continue loop;
// found match
sb.append(mapping[i + 1]);
pos++;
continue search;
}
// not found match
sb.append(text.charAt(pos));
pos++;
}
return new String(sb);
}
public static String decodeHtml2Unicode(String text) {
if (text == null) return null;
int pos = 0;
StringBuffer sb = new StringBuffer(text.length());
search: while (pos < text.length()) {
// find a reverse mapping. TODO: replace matching with hashtable(s)
loop: for (int i = 0; i < mapping.length; i += 2) {
if (pos + mapping[i + 1].length() > text.length()) continue loop;
for (int j = mapping[i + 1].length() - 1; j >= 0; j--) {
if (text.charAt(pos + j) != mapping[i + 1].charAt(j)) continue loop;
}
// found match
sb.append(mapping[i]);
pos = pos + mapping[i + 1].length();
continue search;
}
// not found match
sb.append(text.charAt(pos));
pos++;
}
return new String(sb);
}
//This array contains codes (see http://mindprod.com/jgloss/unicode.html for details)
//that will be replaced. To add new codes or patterns, just put them at the end
//of the list. Codes or patterns in this list can not be escaped with [= or
private static final String[] mapping = {
// Ampersands _have_ to be replaced first. If they were replaced later,
// other replaced characters containing ampersands would get messed up.
"\u0026","&", //ampersand
"\"",""", //quotation mark
"\u003C","<", //less than
"\u003E",">", //greater than
"\\", "\", // Backslash
"\u005E","^", // Caret
"\u0060","`", // Accent Grave `
"\u007B","{", // {
"\u007C","|", // |
"\u007D","}", // }
"\u007E","~", // ~
"\u0082","‚",
"\u0083","ƒ",
"\u0084","„",
"\u0085","…",
"\u0086","†",
"\u0087","‡",
"\u0088","ˆ",
"\u0089","‰",
"\u008A","Š",
"\u008B","‹",
"\u008C","Œ",
"\u008D","",
"\u008E","Ž",
"\u0091","‘",
"\u0092","’",
"\u0093","“",
"\u0094","”",
"\u0095","•",
"\u0096","–",
"\u0097","—",
"\u0098","˜",
"\u0099","™",
"\u009A","š",
"\u009B","›",
"\u009C","œ",
"\u009D","",
"\u009E","ž",
"\u009F","Ÿ",
"\u00A1","¡", //inverted (spanish) exclamation mark
"\u00A2","¢", //cent
"\u00A3","£", //pound
"\u00A4","¤", //currency
"\u00A5","¥", //yen
"\u00A6","¦", //broken vertical bar
"\u00A7","§", //section sign
"\u00A8","¨", //diaeresis (umlaut)
"\u00A9","©", //copyright sign
"\u00AA","ª", //feminine ordinal indicator
"\u00AB","«", //left-pointing double angle quotation mark
"\u00AC","¬", //not sign
"\u00AD","", //soft hyphen
"\u00AE","®", //registered sign
"\u00AF","¯", //macron
"\u00B0","°", //degree sign
"\u00B1","±", //plus-minus sign
"\u00B2","²", //superscript two
"\u00B3","³", //superscript three
"\u00B4","´", //acute accent
"\u00B5","µ", //micro sign
"\u00B6","¶", //paragraph sign
"\u00B7","·", //middle dot
"\u00B8","¸", //cedilla
"\u00B9","¹", //superscript one
"\u00BA","º", //masculine ordinal indicator
"\u00BB","»", //right-pointing double angle quotation mark
"\u00BC","¼", //fraction 1/4
"\u00BD","½", //fraction 1/2
"\u00BE","¾", //fraction 3/4
"\u00BF","¿", //inverted (spanisch) questionmark
"\u00C0","À",
"\u00C1","Á",
"\u00C2","Â",
"\u00C3","Ã",
"\u00C4","Ä",
"\u00C5","Å",
"\u00C6","Æ",
"\u00C7","Ç",
"\u00C8","È",
"\u00C9","É",
"\u00CA","Ê",
"\u00CB","Ë",
"\u00CC","Ì",
"\u00CD","Í",
"\u00CE","Î",
"\u00CF","Ï",
"\u00D0","Ð",
"\u00D1","Ñ",
"\u00D2","Ò",
"\u00D3","Ó",
"\u00D4","Ô",
"\u00D5","Õ",
"\u00D6","Ö",
"\u00D7","×",
"\u00D8","Ø",
"\u00D9","Ù",
"\u00DA","Ú",
"\u00DB","Û",
"\u00DC","Ü",
"\u00DD","Ý",
"\u00DE","Þ",
"\u00DF","ß",
"\u00E0","à",
"\u00E1","á",
"\u00E2","â",
"\u00E3","ã",
"\u00E4","ä",
"\u00E5","å",
"\u00E6","æ",
"\u00E7","ç",
"\u00E8","è",
"\u00E9","é",
"\u00EA","ê",
"\u00EB","ë",
"\u00EC","ì",
"\u00ED","í",
"\u00EE","î",
"\u00EF","ï",
"\u00F0","ð",
"\u00F1","ñ",
"\u00F2","ò",
"\u00F3","ó",
"\u00F4","ô",
"\u00F5","õ",
"\u00F6","ö",
"\u00F7","÷",
"\u00F8","ø",
"\u00F9","ù",
"\u00FA","ú",
"\u00FB","û",
"\u00FC","ü",
"\u00FD","ý",
"\u00FE","þ",
"\u00FF","ÿ"
};
public static void main(String[] args) {
String text = "Test-Text mit & um zyklische ü & Ersetzungen auszuschliessen ŠšŸ";
String txet = encodeUnicode2html(text, true);
System.out.println(txet);
System.out.println(decodeHtml2Unicode(txet));
if (decodeHtml2Unicode(txet).equals(text)) System.out.println("correct");
}
}