URIref


1   /*
2    *  (c) Copyright 2001, 2002, 2003, 2004, 2005 Hewlett-Packard Development Company, LP
3    *  All rights reserved.
4    *
5    * Redistribution and use in source and binary forms, with or without
6    * modification, are permitted provided that the following conditions
7    * are met:
8    * 1. Redistributions of source code must retain the above copyright
9    *    notice, this list of conditions and the following disclaimer.
10   * 2. Redistributions in binary form must reproduce the above copyright
11   *    notice, this list of conditions and the following disclaimer in the
12   *    documentation and/or other materials provided with the distribution.
13   * 3. The name of the author may not be used to endorse or promote products
14   *    derived from this software without specific prior written permission.
15  
16   * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
17   * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
18   * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
19   * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
20   * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
21   * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22   * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23   * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24   * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
25   * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26   
27   * * $Id: URIref.java,v 1.4 2005/02/21 12:18:58 andy_seaborne Exp $
28     
29     AUTHOR:  Jeremy J. Carroll
30  *//*
31   * URIref.java
32   *
33   * Created on September 20, 2001, 12:04 PM
34   */
35  
36  package com.hp.hpl.jena.util;
37  
38  
39  /**
40   * This class provides methods to encode and decode URI References
41   * in accordance with http://www.w3.org/TR/charmod/#sec-URIs .
42   * The details of how the algorithms handle '%' are captured in
43   * http://lists.w3.org/Archives/Public/uri/2001Sep/0009.html
44   * @author  jjc
45   */
46  public class URIref extends Object   {
47      
48      /** Convert a Unicode string, first to UTF-8 and then to
49       * an RFC 2396 compliant URI with optional fragment identifier
50       * using %NN escape mechanism as appropriate.
51       * The '%' character is assumed to already indicated an escape byte.
52       * The '%' character must be followed by two hexadecimal digits.
53       * @param unicode The uri, in characters specified by RFC 2396 + '#'
54       * @return The corresponding Unicode String
55       */ 
56      static public String   encode(String   unicode) {
57          try {
58          byte utf8[] = unicode.getBytes("UTF-8");
59          byte rsltAscii[] = new byte[utf8.length*6];
60          int in = 0;
61          int out = 0;
62          while ( in < utf8.length ) {
63              switch ( utf8[in] ) {
64                  case (byte)'a': case (byte)'b': case (byte)'c': case (byte)'d': case (byte)'e': case (byte)'f': case (byte)'g': case (byte)'h': case (byte)'i': case (byte)'j': case (byte)'k': case (byte)'l': case (byte)'m': case (byte)'n': case (byte)'o': case (byte)'p': case (byte)'q': case (byte)'r': case (byte)'s': case (byte)'t': case (byte)'u': case (byte)'v': case (byte)'w': case (byte)'x': case (byte)'y': case (byte)'z':
65                  case (byte)'A': case (byte)'B': case (byte)'C': case (byte)'D': case (byte)'E': case (byte)'F': case (byte)'G': case (byte)'H': case (byte)'I': case (byte)'J': case (byte)'K': case (byte)'L': case (byte)'M': case (byte)'N': case (byte)'O': case (byte)'P': case (byte)'Q': case (byte)'R': case (byte)'S': case (byte)'T': case (byte)'U': case (byte)'V': case (byte)'W': case (byte)'X': case (byte)'Y': case (byte)'Z':
66                  case (byte)'0': case (byte)'1': case (byte)'2': case (byte)'3': case (byte)'4': case (byte)'5': case (byte)'6': case (byte)'7': case (byte)'8': case (byte)'9':
67                  case (byte)';': case (byte)'/': case (byte)'?': case (byte)':': case (byte)'@': case (byte)'&': case (byte)'=': case (byte)'+': case (byte)'$': case (byte)',':
68                  case (byte)'-': case (byte)'_': case (byte)'.': case (byte)'!': case (byte)'~': case (byte)'*': case (byte)'\'': case (byte)'(': case (byte)')':
69                  case (byte)'#': 
70                  case (byte)'[': case (byte)']':
71                      rsltAscii[out] = utf8[in];
72                      out++;
73                      in++;
74                      break;
75                  case (byte) '%':
76                      try {
77                          if ( in+2 < utf8.length ) {
78                              byte first = hexEncode(hexDecode(utf8[in+1]));
79                              byte second = hexEncode(hexDecode(utf8[in+2]));
80                              rsltAscii[out++] = (byte)'%';
81                              rsltAscii[out++] = first;
82                              rsltAscii[out++] = second;
83                              in += 3;
84                              break;
85                          }
86                      }
87                      catch (IllegalArgumentException   e) {
88                          // Illformed - should issue message ....
89                          System.err.println("Confusing IRI to encode - contains literal '%': " + unicode);
90                          // Fall through.
91                      }
92                  default:
93                          rsltAscii[out++] = (byte)'%';
94                          // Get rid of sign ...
95                          int c = ((int)utf8[in])&255;
96                          rsltAscii[out++] = hexEncode( c/16 );
97                          rsltAscii[out++] = hexEncode( c%16 );
98                          in++;
99                          break;
100             }
101         }
102         return new String  (rsltAscii,0,out,"US-ASCII");
103         }
104         catch ( java.io.UnsupportedEncodingException   e ) {
105             throw new Error  ( "The JVM is required to support UTF-8 and US-ASCII encodings.");
106         }
107     }
108     
109     /** Convert a URI, in US-ASCII, with escaped characters taken from UTF-8, 
110      * to the corresponding Unicode string.
111      * On ill-formed input the results are undefined, specifically if
112      * the unescaped version is not a UTF-8 String, some String will be
113      * returned.
114      * Escaped '%' characters (i.e. "%25") are left unchanged.
115      * @param uri The uri, in characters specified by RFC 2396 + '#'.
116      * @return The corresponding Unicode String.
117      * @exception IllegalArgumentException If a % hex sequence is ill-formed.
118      */
119     static public String   decode(String   uri) {
120         try {
121             byte ascii[] = uri.getBytes("US-ASCII");
122             byte utf8[] = new byte[ascii.length];
123             int in = 0;
124             int out = 0;
125             while ( in < ascii.length ) {
126                 if ( ascii[in] == (byte)'%' 
127                      && ( ascii[in+1] != '2'
128                        || ascii[in+2] != '5' ) ) {
129                     in++;
130                     utf8[out++] = (byte)(hexDecode(ascii[in])*16 | hexDecode(ascii[in+1]));
131                     in += 2;
132                 } else {
133                     utf8[out++] = ascii[in++];
134                 }
135             }
136             return new String  (utf8,0,out,"UTF-8");
137         }
138         catch ( java.io.UnsupportedEncodingException   e ) {
139             throw new Error  ( "The JVM is required to support UTF-8 and US-ASCII encodings.");
140         }
141         catch ( ArrayIndexOutOfBoundsException   ee ) {
142             throw new IllegalArgumentException  ("Incomplete Hex escape sequence in " + uri );
143         }
144     }
145     
146     static private byte hexEncode(int i ) {
147         if (i<10)
148             return (byte) ('0' + i);
149         else
150             return (byte)('A' + i - 10);
151     }
152     
153     static private int hexDecode(byte b ) {
154         switch (b) { 
155             case (byte)'a': case (byte)'b': case (byte)'c': case (byte)'d': case (byte)'e': case (byte)'f':
156              return (((int)b)&255)-'a'+10;
157             case (byte)'A': case (byte)'B': case (byte)'C': case (byte)'D': case (byte)'E': case (byte)'F': 
158             return b - (byte)'A' + 10;
159             case (byte)'0': case (byte)'1': case (byte)'2': case (byte)'3': case (byte)'4': case (byte)'5': case (byte)'6': case (byte)'7': case (byte)'8': case (byte)'9':
160                 return b - (byte)'0';
161                 default:
162                     throw new IllegalArgumentException  ("Bad Hex escape character: " + (((int)b)&255) );
163         }
164     }
165     
166     /** For simple testing ...
167      */
168     static public void main(String   args[]) {
169         for (int i=0; i<args.length; i++) {
170             System.out.println(args[i] + " => " + decode(args[i]) + " => " + encode(decode(args[i])));
171         }
172     }
173 
174     
175 
176 }
177
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags