You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
233 lines
8.1 KiB
233 lines
8.1 KiB
18 years ago
|
package de.anomic.data;
|
||
|
|
||
|
public class htmlTools {
|
||
|
|
||
|
/** Replaces special characters from a string. Avoids XSS attacks and ensures correct display of
|
||
|
* special characters in non UTF-8 capable browsers.
|
||
|
* @param text a string that possibly contains HTML
|
||
|
* @return the string with all special characters encoded
|
||
|
*/
|
||
|
//[MN]
|
||
|
public static String replaceHTML(String text) {
|
||
|
text = replace(text, xmlentities);
|
||
|
text = replace(text, htmlentities);
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
/** Replaces special characters from a string. Ensures correct display of
|
||
|
* special characters in non UTF-8 capable browsers.
|
||
|
* @param text a string that possibly contains special characters
|
||
|
* @return the string with all special characters encoded
|
||
|
*/
|
||
|
//[MN]
|
||
|
public static String replaceHTMLEntities(String text) {
|
||
|
text = replace(text, htmlentities);
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
/** Replaces special characters from a string. Avoids XSS attacks.
|
||
|
* @param text a string that possibly contains HTML
|
||
|
* @return the string without any HTML-tags that can be used for XSS
|
||
|
*/
|
||
|
//[MN]
|
||
|
public static String replaceXMLEntities(String text) {
|
||
|
text = replace(text, xmlentities);
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
/** 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]
|
||
|
public static String replace(String text, String[] entities) {
|
||
|
if (text==null) { return null; }
|
||
|
for (int x=0;x<=entities.length-1;x=x+2) {
|
||
|
int p=0;
|
||
|
while ((p=text.indexOf(entities[x],p))>=0) {
|
||
|
text=text.substring(0,p)+entities[x+1]+text.substring(p+entities[x].length());
|
||
|
p+=entities[x+1].length();
|
||
|
}
|
||
|
}
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
public static String deReplaceHTML(String text) {
|
||
|
text = deReplaceHTMLEntities(text);
|
||
|
text = deReplaceXMLEntities(text);
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
public static String deReplaceHTMLEntities(String text) {
|
||
|
return deReplace(text, htmlentities);
|
||
|
}
|
||
|
|
||
|
public static String deReplaceXMLEntities(String text) {
|
||
|
return deReplace(text, xmlentities);
|
||
|
}
|
||
|
|
||
|
public static String deReplace(String text, String[] entities) {
|
||
|
if (text == null) return null;
|
||
|
for (int i=entities.length-1; i>0; i-=2) {
|
||
|
int p = 0;
|
||
|
while ((p = text.indexOf(entities[i])) >= 0) {
|
||
|
text = text.substring(0, p) + entities[i - 1] + text.substring(p + entities[i].length());
|
||
|
p += entities[i - 1].length();
|
||
|
}
|
||
|
}
|
||
|
return text;
|
||
|
}
|
||
|
|
||
|
//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 <pre>
|
||
|
public static final String[] xmlentities={
|
||
|
// 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
|
||
|
};
|
||
|
|
||
|
//This array contains codes (see http://mindprod.com/jgloss/unicode.html for details) and
|
||
|
//patterns 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 <pre>
|
||
|
public static final String[] htmlentities={
|
||
|
"\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"
|
||
|
};
|
||
|
}
|