001    /* URLDecoder.java -- Class to decode URL's from encoded form.
002       Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
003    
004    This file is part of GNU Classpath.
005    
006    GNU Classpath is free software; you can redistribute it and/or modify
007    it under the terms of the GNU General Public License as published by
008    the Free Software Foundation; either version 2, or (at your option)
009    any later version.
010    
011    GNU Classpath is distributed in the hope that it will be useful, but
012    WITHOUT ANY WARRANTY; without even the implied warranty of
013    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
014    General Public License for more details.
015    
016    You should have received a copy of the GNU General Public License
017    along with GNU Classpath; see the file COPYING.  If not, write to the
018    Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
019    02110-1301 USA.
020    
021    Linking this library statically or dynamically with other modules is
022    making a combined work based on this library.  Thus, the terms and
023    conditions of the GNU General Public License cover the whole
024    combination.
025    
026    As a special exception, the copyright holders of this library give you
027    permission to link this library with independent modules to produce an
028    executable, regardless of the license terms of these independent
029    modules, and to copy and distribute the resulting executable under
030    terms of your choice, provided that you also meet, for each linked
031    independent module, the terms and conditions of the license of that
032    module.  An independent module is a module which is not derived from
033    or based on this library.  If you modify this library, you may extend
034    this exception to your version of the library, but you are not
035    obligated to do so.  If you do not wish to do so, delete this
036    exception statement from your version. */
037    
038    package java.net;
039    
040    import gnu.java.lang.CPStringBuilder;
041    
042    import java.io.UnsupportedEncodingException;
043    
044    
045    /**
046     * This utility class contains static methods that converts a
047     * string encoded in the x-www-form-urlencoded format to the original
048     * text.  The x-www-form-urlencoded format replaces certain disallowed
049     * characters with encoded equivalents.  All upper case and lower case
050     * letters in the US alphabet remain as is, the space character (' ')
051     * is replaced with '+' sign, and all other characters are converted to a
052     * "%XX" format where XX is the hexadecimal representation of that character
053     * in a given character encoding (default is "UTF-8").
054     * <p>
055     * This method is very useful for decoding strings sent to CGI scripts
056     *
057     * Written using on-line Java Platform 1.2/1.4 API Specification.
058     * Status:  Believed complete and correct.
059     *
060     * @since 1.2
061     *
062     * @author Warren Levy (warrenl@cygnus.com)
063     * @author Aaron M. Renn (arenn@urbanophile.com) (documentation comments)
064     * @author Mark Wielaard (mark@klomp.org)
065     */
066    public class URLDecoder
067    {
068      /**
069       * Public contructor. Note that this class has only static methods.
070       */
071      public URLDecoder()
072      {
073      }
074    
075      /**
076       * This method translates the passed in string from x-www-form-urlencoded
077       * format using the default encoding "UTF-8" to decode the hex encoded
078       * unsafe characters.
079       *
080       * @param s the String to convert
081       *
082       * @return the converted String
083       *
084       * @deprecated
085       */
086      public static String decode(String s)
087      {
088        try
089          {
090            return decode(s, "UTF-8");
091          }
092        catch (UnsupportedEncodingException uee)
093          {
094            // Should never happen since UTF-8 encoding should always be supported
095            return s;
096          }
097      }
098    
099      /**
100       * This method translates the passed in string from x-www-form-urlencoded
101       * format using the given character encoding to decode the hex encoded
102       * unsafe characters.
103       *
104       * This implementation will decode the string even if it contains
105       * unsafe characters (characters that should have been encoded) or if the
106       * two characters following a % do not represent a hex encoded byte.
107       * In those cases the unsafe character or the % character will be added
108       * verbatim to the decoded result.
109       *
110       * @param s the String to convert
111       * @param encoding the character encoding to use the decode the hex encoded
112       *        unsafe characters
113       *
114       * @return the converted String
115       *
116       * @exception UnsupportedEncodingException If the named encoding is not
117       * supported
118       *
119       * @since 1.4
120       */
121      public static String decode(String s, String encoding)
122        throws UnsupportedEncodingException
123      {
124        // First convert all '+' characters to spaces.
125        String str = s.replace('+', ' ');
126    
127        // Then go through the whole string looking for byte encoded characters
128        int i;
129        int start = 0;
130        byte[] bytes = null;
131        int length = str.length();
132        CPStringBuilder result = new CPStringBuilder(length);
133        while ((i = str.indexOf('%', start)) >= 0)
134          {
135            // Add all non-encoded characters to the result buffer
136            result.append(str.substring(start, i));
137            start = i;
138    
139            // Get all consecutive encoded bytes
140            while ((i + 2 < length) && (str.charAt(i) == '%'))
141              i += 3;
142    
143            // Decode all these bytes
144            if ((bytes == null) || (bytes.length < ((i - start) / 3)))
145              bytes = new byte[((i - start) / 3)];
146    
147            int index = 0;
148            try
149              {
150                while (start < i)
151                  {
152                    String sub = str.substring(start + 1, start + 3);
153                    bytes[index] = (byte) Integer.parseInt(sub, 16);
154                    index++;
155                    start += 3;
156                  }
157              }
158            catch (NumberFormatException nfe)
159              {
160                // One of the hex encoded strings was bad
161              }
162    
163            // Add the bytes as characters according to the given encoding
164            result.append(new String(bytes, 0, index, encoding));
165    
166            // Make sure we skip to just after a % sign
167            // There might not have been enough encoded characters after the %
168            // or the hex chars were not actually hex chars (NumberFormatException)
169            if (start < length && s.charAt(start) == '%')
170              {
171                result.append('%');
172                start++;
173              }
174          }
175    
176        // Add any characters left
177        if (start < str.length())
178          result.append(str.substring(start));
179    
180        return result.toString();
181      }
182    } // class URLDecoder