1 /*

     2  * Copyright 1998-2006 Sun Microsystems, Inc.  All Rights Reserved.

     3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

     4  *

     5  * This code is free software; you can redistribute it and/or modify it

     6  * under the terms of the GNU General Public License version 2 only, as

     7  * published by the Free Software Foundation.  Sun designates this

     8  * particular file as subject to the "Classpath" exception as provided

     9  * by Sun in the LICENSE file that accompanied this code.

    10  *

    11  * This code is distributed in the hope that it will be useful, but WITHOUT

    12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

    13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

    14  * version 2 for more details (a copy is included in the LICENSE file that

    15  * accompanied this code).

    16  *

    17  * You should have received a copy of the GNU General Public License version

    18  * 2 along with this work; if not, write to the Free Software Foundation,

    19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

    20  *

    21  * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,

    22  * CA 95054 USA or visit www.sun.com if you need additional information or

    23  * have any questions.

    24  */

    25 

    26 package java.net;

    27 

    28 import java.io.*;

    29 

    30 /**

    31  * Utility class for HTML form decoding. This class contains static methods

    32  * for decoding a String from the <CODE>application/x-www-form-urlencoded</CODE>

    33  * MIME format.

    34  * <p>

    35  * The conversion process is the reverse of that used by the URLEncoder class. It is assumed

    36  * that all characters in the encoded string are one of the following:

    37  * &quot;<code>a</code>&quot; through &quot;<code>z</code>&quot;,

    38  * &quot;<code>A</code>&quot; through &quot;<code>Z</code>&quot;,

    39  * &quot;<code>0</code>&quot; through &quot;<code>9</code>&quot;, and

    40  * &quot;<code>-</code>&quot;, &quot;<code>_</code>&quot;,

    41  * &quot;<code>.</code>&quot;, and &quot;<code>*</code>&quot;. The

    42  * character &quot;<code>%</code>&quot; is allowed but is interpreted

    43  * as the start of a special escaped sequence.

    44  * <p>

    45  * The following rules are applied in the conversion:

    46  * <p>

    47  * <ul>

    48  * <li>The alphanumeric characters &quot;<code>a</code>&quot; through

    49  *     &quot;<code>z</code>&quot;, &quot;<code>A</code>&quot; through

    50  *     &quot;<code>Z</code>&quot; and &quot;<code>0</code>&quot;

    51  *     through &quot;<code>9</code>&quot; remain the same.

    52  * <li>The special characters &quot;<code>.</code>&quot;,

    53  *     &quot;<code>-</code>&quot;, &quot;<code>*</code>&quot;, and

    54  *     &quot;<code>_</code>&quot; remain the same.

    55  * <li>The plus sign &quot;<code>+</code>&quot; is converted into a

    56  *     space character &quot;<code>&nbsp;</code>&quot; .

    57  * <li>A sequence of the form "<code>%<i>xy</i></code>" will be

    58  *     treated as representing a byte where <i>xy</i> is the two-digit

    59  *     hexadecimal representation of the 8 bits. Then, all substrings

    60  *     that contain one or more of these byte sequences consecutively

    61  *     will be replaced by the character(s) whose encoding would result

    62  *     in those consecutive bytes.

    63  *     The encoding scheme used to decode these characters may be specified,

    64  *     or if unspecified, the default encoding of the platform will be used.

    65  * </ul>

    66  * <p>

    67  * There are two possible ways in which this decoder could deal with

    68  * illegal strings.  It could either leave illegal characters alone or

    69  * it could throw an <tt>{@link java.lang.IllegalArgumentException}</tt>.

    70  * Which approach the decoder takes is left to the

    71  * implementation.

    72  *

    73  * @author  Mark Chamness

    74  * @author  Michael McCloskey

    75  * @since   1.2

    76  */

    77 

    78 public class URLDecoder {

    79 

    80     // The platform default encoding

    81     static String dfltEncName = URLEncoder.dfltEncName;

    82 

    83     /**

    84      * Decodes a <code>x-www-form-urlencoded</code> string.

    85      * The platform's default encoding is used to determine what characters

    86      * are represented by any consecutive sequences of the form

    87      * "<code>%<i>xy</i></code>".

    88      * @param s the <code>String</code> to decode

    89      * @deprecated The resulting string may vary depending on the platform's

    90      *          default encoding. Instead, use the decode(String,String) method

    91      *          to specify the encoding.

    92      * @return the newly decoded <code>String</code>

    93      */

    94     @Deprecated

    95     public static String decode(String s) {

    96 

    97         String str = null;

    98 

    99         try {

   100             str = decode(s, dfltEncName);

   101         } catch (UnsupportedEncodingException e) {

   102             // The system should always have the platform default

   103         }

   104 

   105         return str;

   106     }

   107 

   108     /**

   109      * Decodes a <code>application/x-www-form-urlencoded</code> string using a specific

   110      * encoding scheme.

   111      * The supplied encoding is used to determine

   112      * what characters are represented by any consecutive sequences of the

   113      * form "<code>%<i>xy</i></code>".

   114      * <p>

   115      * <em><strong>Note:</strong> The <a href=

   116      * "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">

   117      * World Wide Web Consortium Recommendation</a> states that

   118      * UTF-8 should be used. Not doing so may introduce

   119      * incompatibilites.</em>

   120      *

   121      * @param s the <code>String</code> to decode

   122      * @param enc   The name of a supported

   123      *    <a href="../lang/package-summary.html#charenc">character

   124      *    encoding</a>.

   125      * @return the newly decoded <code>String</code>

   126      * @exception  UnsupportedEncodingException

   127      *             If character encoding needs to be consulted, but

   128      *             named character encoding is not supported

   129      * @see URLEncoder#encode(java.lang.String, java.lang.String)

   130      * @since 1.4

   131      */

   132     public static String decode(String s, String enc)

   133         throws UnsupportedEncodingException{

   134 

   135         boolean needToChange = false;

   136         int numChars = s.length();

   137         StringBuffer sb = new StringBuffer(numChars > 500 ? numChars / 2 : numChars);

   138         int i = 0;

   139 

   140         if (enc.length() == 0) {

   141             throw new UnsupportedEncodingException ("URLDecoder: empty string enc parameter");

   142         }

   143 

   144         char c;

   145         byte[] bytes = null;

   146         while (i < numChars) {

   147             c = s.charAt(i);

   148             switch (c) {

   149             case '+':

   150                 sb.append(' ');

   151                 i++;

   152                 needToChange = true;

   153                 break;

   154             case '%':

   155                 /*

   156                  * Starting with this instance of %, process all

   157                  * consecutive substrings of the form %xy. Each

   158                  * substring %xy will yield a byte. Convert all

   159                  * consecutive  bytes obtained this way to whatever

   160                  * character(s) they represent in the provided

   161                  * encoding.

   162                  */

   163 

   164                 try {

   165 

   166                     // (numChars-i)/3 is an upper bound for the number

   167                     // of remaining bytes

   168                     if (bytes == null)

   169                         bytes = new byte[(numChars-i)/3];

   170                     int pos = 0;

   171 

   172                     while ( ((i+2) < numChars) &&

   173                             (c=='%')) {

   174                         int v = Integer.parseInt(s.substring(i+1,i+3),16);

   175                         if (v < 0)

   176                             throw new IllegalArgumentException("URLDecoder: Illegal hex characters in escape (%) pattern - negative value");

   177                         bytes[pos++] = (byte) v;

   178                         i+= 3;

   179                         if (i < numChars)

   180                             c = s.charAt(i);

   181                     }

   182 

   183                     // A trailing, incomplete byte encoding such as

   184                     // "%x" will cause an exception to be thrown

   185 

   186                     if ((i < numChars) && (c=='%'))

   187                         throw new IllegalArgumentException(

   188                          "URLDecoder: Incomplete trailing escape (%) pattern");

   189 

   190                     sb.append(new String(bytes, 0, pos, enc));

   191                 } catch (NumberFormatException e) {

   192                     throw new IllegalArgumentException(

   193                     "URLDecoder: Illegal hex characters in escape (%) pattern - "

   194                     + e.getMessage());

   195                 }

   196                 needToChange = true;

   197                 break;

   198             default:

   199                 sb.append(c);

   200                 i++;

   201                 break;

   202             }

   203         }

   204 

   205         return (needToChange? sb.toString() : s);

   206     }

   207 }