/*
* Copyright (c) 1998, 2006, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code 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
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.net;
import java.io.*;
/**
* Utility class for HTML form decoding. This class contains static methods
* for decoding a String from the <CODE>application/x-www-form-urlencoded</CODE>
* MIME format.
* <p>
* 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:
* "<code>a</code>" through "<code>z</code>",
* "<code>A</code>" through "<code>Z</code>",
* "<code>0</code>" through "<code>9</code>", and
* "<code>-</code>", "<code>_</code>",
* "<code>.</code>", and "<code>*</code>". The
* character "<code>%</code>" is allowed but is interpreted
* as the start of a special escaped sequence.
* <p>
* The following rules are applied in the conversion:
* <p>
* <ul>
* <li>The alphanumeric characters "<code>a</code>" through
* "<code>z</code>", "<code>A</code>" through
* "<code>Z</code>" and "<code>0</code>"
* through "<code>9</code>" remain the same.
* <li>The special characters "<code>.</code>",
* "<code>-</code>", "<code>*</code>", and
* "<code>_</code>" remain the same.
* <li>The plus sign "<code>+</code>" is converted into a
* space character "<code> </code>" .
* <li>A sequence of the form "<code>%<i>xy</i></code>" will be
* treated as representing a byte where <i>xy</i> 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.
* </ul>
* <p>
* 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 <tt>{@link java.lang.IllegalArgumentException}</tt>.
* 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 <code>x-www-form-urlencoded</code> string.
* The platform's default encoding is used to determine what characters
* are represented by any consecutive sequences of the form
* "<code>%<i>xy</i></code>".
* @param s the <code>String</code> 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 <code>String</code>
*/
@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 <code>application/x-www-form-urlencoded</code> string using a specific
* encoding scheme.
* The supplied encoding is used to determine
* what characters are represented by any consecutive sequences of the
* form "<code>%<i>xy</i></code>".
* <p>
* <em><strong>Note:</strong> The <a href=
* "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">
* World Wide Web Consortium Recommendation</a> states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilites.</em>
*
* @param s the <code>String</code> to decode
* @param enc The name of a supported
* <a href="../lang/package-summary.html#charenc">character
* encoding</a>.
* @return the newly decoded <code>String</code>
* @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);
}
}