Html Escape for Java
Source code for the Html Escape class, for escaping text on the fly, using Java.The Html Escape tool for Java, escapes all characters, known to cause problems on Html pages.
The escaped result is compatible with pages encoded in ISO-8859-X and UTF-8.
The two main methods of the HtmlEscape class are:
escape(String)
Which escapes everything, including new line and returns the escaped result
escapeTextArea(String)
Which escapes everything, except new line, for use in textarea or wysiwyg editors.
package net.htmlescape;
/**
* HtmlEscape in Java, which is compatible with utf-8
* @author Ulrich Jensen, http://www.htmlescape.net
* Feel free to get inspired, use or steal this code and use it in your
* own projects.
* License:
* You have the right to use this code in your own project or publish it
* on your own website.
* If you are going to use this code, please include the author lines.
* Use this code at your own risk. The author does not warrent or assume any
* legal liability or responsibility for the accuracy, completeness or usefullness of
* this program code.
*/
public class HtmlEscape {
private static char[] hex={'0','1','2','3','4','5','6','7','8','9','a','b','c','d','e','f'};
/**
* Method for html escaping a String, for use in a textarea
* @param original The String to escape
* @return The escaped String
*/
public static String escapeTextArea(String original)
{
return escapeSpecial(escapeTags(original));
}
/**
* Normal escape function, for Html escaping Strings
* @param original The original String
* @return The escape String
*/
public static String escape(String original)
{
return escapeSpecial(escapeBr(escapeTags(original)));
}
public static String escapeTags(String original)
{
if(original==null) return "";
StringBuffer out=new StringBuffer("");
char[] chars=original.toCharArray();
for(int i=0;i<chars.length;i++)
{
boolean found=true;
switch(chars[i])
{
case 60:out.append("<"); break; //<
case 62:out.append(">"); break; //>
case 34:out.append("""); break; //"
default:found=false;break;
}
if(!found) out.append(chars[i]);
}
return out.toString();
}
public static String escapeBr(String original)
{
if(original==null) return "";
StringBuffer out=new StringBuffer("");
char[] chars=original.toCharArray();
for(int i=0;i<chars.length;i++)
{
boolean found=true;
switch(chars[i])
{
case '\n': out.append("<br/>"); break; //newline
case '\r': break;
default:found=false;break;
}
if(!found) out.append(chars[i]);
}
return out.toString();
}
public static String escapeSpecial(String original)
{
if(original==null) return "";
StringBuffer out=new StringBuffer("");
char[] chars=original.toCharArray();
for(int i=0;i<chars.length;i++)
{
boolean found=true;
switch(chars[i]) {
case 38:out.append("&"); break; //&
case 198:out.append("Æ"); break; //Æ
case 193:out.append("Á"); break; //Á
case 194:out.append("Â"); break; //Â
case 192:out.append("À"); break; //À
case 197:out.append("Å"); break; //Å
case 195:out.append("Ã"); break; //Ã
case 196:out.append("Ä"); break; //Ä
case 199:out.append("Ç"); break; //Ç
case 208:out.append("Ð"); break; //Ð
case 201:out.append("É"); break; //É
case 202:out.append("Ê"); break; //Ê
case 200:out.append("È"); break; //È
case 203:out.append("Ë"); break; //Ë
case 205:out.append("Í"); break; //Í
case 206:out.append("Î"); break; //Î
case 204:out.append("Ì"); break; //Ì
case 207:out.append("Ï"); break; //Ï
case 209:out.append("Ñ"); break; //Ñ
case 211:out.append("Ó"); break; //Ó
case 212:out.append("Ô"); break; //Ô
case 210:out.append("Ò"); break; //Ò
case 216:out.append("Ø"); break; //Ø
case 213:out.append("Õ"); break; //Õ
case 214:out.append("Ö"); break; //Ö
case 222:out.append("Þ"); break; //Þ
case 218:out.append("Ú"); break; //Ú
case 219:out.append("Û"); break; //Û
case 217:out.append("Ù"); break; //Ù
case 220:out.append("Ü"); break; //Ü
case 221:out.append("Ý"); break; //Ý
case 225:out.append("á"); break; //á
case 226:out.append("â"); break; //â
case 230:out.append("æ"); break; //æ
case 224:out.append("à"); break; //à
case 229:out.append("å"); break; //å
case 227:out.append("ã"); break; //ã
case 228:out.append("ä"); break; //ä
case 231:out.append("ç"); break; //ç
case 233:out.append("é"); break; //é
case 234:out.append("ê"); break; //ê
case 232:out.append("è"); break; //è
case 240:out.append("ð"); break; //ð
case 235:out.append("ë"); break; //ë
case 237:out.append("í"); break; //í
case 238:out.append("î"); break; //î
case 236:out.append("ì"); break; //ì
case 239:out.append("ï"); break; //ï
case 241:out.append("ñ"); break; //ñ
case 243:out.append("ó"); break; //ó
case 244:out.append("ô"); break; //ô
case 242:out.append("ò"); break; //ò
case 248:out.append("ø"); break; //ø
case 245:out.append("õ"); break; //õ
case 246:out.append("ö"); break; //ö
case 223:out.append("ß"); break; //ß
case 254:out.append("þ"); break; //þ
case 250:out.append("ú"); break; //ú
case 251:out.append("û"); break; //û
case 249:out.append("ù"); break; //ù
case 252:out.append("ü"); break; //ü
case 253:out.append("ý"); break; //ý
case 255:out.append("ÿ"); break; //ÿ
case 162:out.append("¢"); break; //¢
default:
found=false;
break;
}
if(!found)
{
if(chars[i]>127) {
char c=chars[i];
int a4=c%16;
c=(char) (c/16);
int a3=c%16;
c=(char) (c/16);
int a2=c%16;
c=(char) (c/16);
int a1=c%16;
out.append("&#x"+hex[a1]+hex[a2]+hex[a3]+hex[a4]+";");
}
else
{
out.append(chars[i]);
}
}
}
return out.toString();
}
}