Mega Code Archive
Escape HTML
<![CDATA[
/*
* Static String formatting and query routines.
* Copyright (C) 2001-2005 Stephen Ostermiller
* http://ostermiller.org/contact.pl?regarding=Java+Utilities
*
* This program 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.
*
* This program 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.
*
* See COPYING.TXT for details.
*/
import java.util.HashMap;
import java.util.regex.Pattern;
/**
* Utilities for String formatting, manipulation, and queries.
* More information about this class is available from <a target="_top" href=
* "http://ostermiller.org/utils/StringHelper.html">ostermiller.org</a>.
*
* @author Stephen Ostermiller http://ostermiller.org/contact.pl?regarding=Java+Utilities
* @since ostermillerutils 1.00.00
*/
public class StringHelper {
/**
* Replaces characters that may be confused by a HTML
* parser with their equivalent character entity references.
* <p>
* Any data that will appear as text on a web page should
* be be escaped. This is especially important for data
* that comes from untrusted sources such as Internet users.
* A common mistake in CGI programming is to ask a user for
* data and then put that data on a web page. For example:<pre>
* Server: What is your name?
* User: <b>Joe<b>
* Server: Hello <b>Joe</b>, Welcome</pre>
* If the name is put on the page without checking that it doesn't
* contain HTML code or without sanitizing that HTML code, the user
* could reformat the page, insert scripts, and control the the
* content on your web server.
* <p>
* This method will replace HTML characters such as > with their
* HTML entity reference (&gt;) so that the html parser will
* be sure to interpret them as plain text rather than HTML or script.
* <p>
* This method should be used for both data to be displayed in text
* in the html document, and data put in form elements. For example:<br>
* <code><html><body><i>This in not a &lt;tag&gt;
* in HTML</i></body></html></code><br>
* and<br>
* <code><form><input type="hidden" name="date" value="<i>This data could
* be &quot;malicious&quot;</i>"></form></code><br>
* In the second example, the form data would be properly be resubmitted
* to your cgi script in the URLEncoded format:<br>
* <code><i>This data could be %22malicious%22</i></code>
*
* @param s String to be escaped
* @return escaped String
* @throws NullPointerException if s is null.
*
* @since ostermillerutils 1.00.00
*/
public static String escapeHTML(String s){
int length = s.length();
int newLength = length;
boolean someCharacterEscaped = false;
// first check for characters that might
// be dangerous and calculate a length
// of the string that has escapes.
for (int i=0; i<length; i++){
char c = s.charAt(i);
int cint = 0xffff & c;
if (cint < 32){
switch(c){
case '\r':
case '\n':
case '\t':
case '\f':{
} break;
default: {
newLength -= 1;
someCharacterEscaped = true;
}
}
} else {
switch(c){
case '\"':{
newLength += 5;
someCharacterEscaped = true;
} break;
case '&':
case '\'':{
newLength += 4;
someCharacterEscaped = true;
} break;
case '<':
case '>':{
newLength += 3;
someCharacterEscaped = true;
} break;
}
}
}
if (!someCharacterEscaped){
// nothing to escape in the string
return s;
}
StringBuffer sb = new StringBuffer(newLength);
for (int i=0; i<length; i++){
char c = s.charAt(i);
int cint = 0xffff & c;
if (cint < 32){
switch(c){
case '\r':
case '\n':
case '\t':
case '\f':{
sb.append(c);
} break;
default: {
// Remove this character
}
}
} else {
switch(c){
case '\"':{
sb.append(""");
} break;
case '\'':{
sb.append("'");
} break;
case '&':{
sb.append("&");
} break;
case '<':{
sb.append("<");
} break;
case '>':{
sb.append(">");
} break;
default: {
sb.append(c);
}
}
}
}
return sb.toString();
}
}
]]>