java/gov/nist/javax/sip/address/RFC2396UrlDecoder.java

/*
* Conditions Of Use 
* 
* This software was developed by employees of the National Institute of
* Standards and Technology (NIST), an agency of the Federal Government.
* Pursuant to title 15 Untied States Code Section 105, works of NIST
* employees are not subject to copyright protection in the United States
* and are considered to be in the public domain.  As a result, a formal
* license is not needed to use the software.
* 
* This software is provided by NIST as a service and is expressly
* provided "AS IS."  NIST MAKES NO WARRANTY OF ANY KIND, EXPRESS, IMPLIED
* OR STATUTORY, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTY OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT
* AND DATA ACCURACY.  NIST does not warrant or make any representations
* regarding the use of the software or the results thereof, including but
* not limited to the correctness, accuracy, reliability or usefulness of
* the software.
* 
* Permission to use this software is contingent upon your acceptance
* of the terms of this agreement
*  
* .
* 
*/
package gov.nist.javax.sip.address;

import java.io.UnsupportedEncodingException;

/**
 * Copied from Apache Excalibur project.
 * Source code available at http://www.google.com/codesearch?hl=en&q=+excalibur+decodePath+show:sK_gDY0W5Rw:OTjCHAiSuF0:th3BdHtpX20&sa=N&cd=1&ct=rc&cs_p=http://apache.edgescape.com/excalibur/excalibur-sourceresolve/source/excalibur-sourceresolve-1.1-src.zip&cs_f=excalibur-sourceresolve-1.1/src/java/org/apache/excalibur/source/SourceUtil.java
 * @author <A HREF="mailto:jean.deruelle@gmail.com">Jean Deruelle</A> 
 *
 */
public class RFC2396UrlDecoder {

    /**
     * Decode a path.
     *
     * <p>Interprets %XX (where XX is hexadecimal number) as UTF-8 encoded bytes.
     * <p>The validity of the input path is not checked (i.e. characters that
     * were not encoded will not be reported as errors).
     * <p>This method differs from URLDecoder.decode in that it always uses UTF-8
     * (while URLDecoder uses the platform default encoding, often ISO-8859-1),
     * and doesn't translate + characters to spaces.
     *
     * @param uri the path to decode
     * @return the decoded path
     */
    public static String decode(String uri) {
        StringBuffer translatedUri = new StringBuffer(uri.length());
        byte[] encodedchars = new byte[uri.length() / 3];
        int i = 0;
        int length = uri.length();
        int encodedcharsLength = 0;
        while (i < length) {
            if (uri.charAt(i) == '%') {
                //we must process all consecutive %-encoded characters in one go, because they represent
                //an UTF-8 encoded string, and in UTF-8 one character can be encoded as multiple bytes
                while (i < length && uri.charAt(i) == '%') {
                    if (i + 2 < length) {
                        try {
                            byte x = (byte)Integer.parseInt(uri.substring(i + 1, i + 3), 16);
                            encodedchars[encodedcharsLength] = x;
                        } catch (NumberFormatException e) {
                            throw new IllegalArgumentException("Illegal hex characters in pattern %" + uri.substring(i + 1, i + 3));
                        }
                        encodedcharsLength++;
                        i += 3;
                    } else {
                        throw new IllegalArgumentException("% character should be followed by 2 hexadecimal characters.");
                    }
                }
                try {
                    String translatedPart = new String(encodedchars, 0, encodedcharsLength, "UTF-8");
                    translatedUri.append(translatedPart);
                } catch (UnsupportedEncodingException e) {
                    //the situation that UTF-8 is not supported is quite theoretical, so throw a runtime exception
                    throw new RuntimeException("Problem in decodePath: UTF-8 encoding not supported.");
                }
                encodedcharsLength = 0;
            } else {
                //a normal character
                translatedUri.append(uri.charAt(i));
                i++;
            }
        }
        return translatedUri.toString();
    }
}