application/x-www-form-urlencoded
* MIME format.
*
* The conversion process is the reverse of that used by the URLEncoder class. It is assumed
* that all characters in the encoded string are one of the following:
* "a" through "z",
* "A" through "Z",
* "0" through "9", and
* "-", "_",
* ".", and "*". The
* character "%" is allowed but is interpreted
* as the start of a special escaped sequence.
*
* The following rules are applied in the conversion: *
*
a" through
* "z", "A" through
* "Z" and "0"
* through "9" remain the same.
* .",
* "-", "*", and
* "_" remain the same.
* +" is converted into a
* space character " " .
* %xy" will be
* treated as representing a byte where xy is the two-digit
* hexadecimal representation of the 8 bits. Then, all substrings
* that contain one or more of these byte sequences consecutively
* will be replaced by the character(s) whose encoding would result
* in those consecutive bytes.
* The encoding scheme used to decode these characters may be specified,
* or if unspecified, the default encoding of the platform will be used.
*
* There are two possible ways in which this decoder could deal with
* illegal strings. It could either leave illegal characters alone or
* it could throw an {@link java.lang.IllegalArgumentException}.
* Which approach the decoder takes is left to the
* implementation.
*
* @author Mark Chamness
* @author Michael McCloskey
* @since 1.2
*/
public class URLDecoder {
// The platform default encoding
static String dfltEncName = URLEncoder.dfltEncName;
/**
* Decodes a x-www-form-urlencoded string.
* The platform's default encoding is used to determine what characters
* are represented by any consecutive sequences of the form
* "%xy".
* @param s the String to decode
* @deprecated The resulting string may vary depending on the platform's
* default encoding. Instead, use the decode(String,String) method
* to specify the encoding.
* @return the newly decoded String
*/
@Deprecated
public static String decode(String s) {
String str = null;
try {
str = decode(s, dfltEncName);
} catch (UnsupportedEncodingException e) {
// The system should always have the platform default
}
return str;
}
/**
* Decodes a application/x-www-form-urlencoded string using a specific
* encoding scheme.
* The supplied encoding is used to determine
* what characters are represented by any consecutive sequences of the
* form "%xy".
*
* Note: The
* World Wide Web Consortium Recommendation states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilites.
*
* @param s the String to decode
* @param enc The name of a supported
* character
* encoding.
* @return the newly decoded String
* @exception UnsupportedEncodingException
* If character encoding needs to be consulted, but
* named character encoding is not supported
* @see URLEncoder#encode(java.lang.String, java.lang.String)
* @since 1.4
*/
public static String decode(String s, String enc)
throws UnsupportedEncodingException{
boolean needToChange = false;
int numChars = s.length();
StringBuffer sb = new StringBuffer(numChars > 500 ? numChars / 2 : numChars);
int i = 0;
if (enc.length() == 0) {
throw new UnsupportedEncodingException ("URLDecoder: empty string enc parameter");
}
char c;
byte[] bytes = null;
while (i < numChars) {
c = s.charAt(i);
switch (c) {
case '+':
sb.append(' ');
i++;
needToChange = true;
break;
case '%':
/*
* Starting with this instance of %, process all
* consecutive substrings of the form %xy. Each
* substring %xy will yield a byte. Convert all
* consecutive bytes obtained this way to whatever
* character(s) they represent in the provided
* encoding.
*/
try {
// (numChars-i)/3 is an upper bound for the number
// of remaining bytes
if (bytes == null)
bytes = new byte[(numChars-i)/3];
int pos = 0;
while ( ((i+2) < numChars) &&
(c=='%')) {
int v = Integer.parseInt(s.substring(i+1,i+3),16);
if (v < 0)
throw new IllegalArgumentException("URLDecoder: Illegal hex characters in escape (%) pattern - negative value");
bytes[pos++] = (byte) v;
i+= 3;
if (i < numChars)
c = s.charAt(i);
}
// A trailing, incomplete byte encoding such as
// "%x" will cause an exception to be thrown
if ((i < numChars) && (c=='%'))
throw new IllegalArgumentException(
"URLDecoder: Incomplete trailing escape (%) pattern");
sb.append(new String(bytes, 0, pos, enc));
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"URLDecoder: Illegal hex characters in escape (%) pattern - "
+ e.getMessage());
}
needToChange = true;
break;
default:
sb.append(c);
i++;
break;
}
}
return (needToChange? sb.toString() : s);
}
}