KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > jdesktop > jdic > desktop > internal > impl > URLUTF8Encoder


1 /*
2  * Copyright (C) 2004 Sun Microsystems, Inc. All rights reserved. Use is
3  * subject to license terms.
4  *
5  * This program is free software; you can redistribute it and/or modify
6  * it under the terms of the Lesser GNU General Public License as
7  * published by the Free Software Foundation; either version 2 of the
8  * License, or (at your option) any later version.
9  *
10  * This program is distributed in the hope that it will be useful, but
11  * WITHOUT ANY WARRANTY; without even the implied warranty of
12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13  * General Public License for more details.
14  *
15  * You should have received a copy of the GNU General Public License
16  * along with this program; if not, write to the Free Software
17  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
18  * USA.
19  */

20  
21 package org.jdesktop.jdic.desktop.internal.impl;
22
23 /**
24  * This class provides a method to encode any string into a URL-safe form.
25  * <p>
26  * Non-ASCII characters are first encoded as sequences of two or three bytes,
27  * using the UTF-8 algorithm, before being encoded as %HH escapes.
28  */

29 public class URLUTF8Encoder {
30
31   final static String JavaDoc[] hex = {
32     "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
33     "%08", "%09", "%0a", "%0b", "%0c", "%0d", "%0e", "%0f",
34     "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17",
35     "%18", "%19", "%1a", "%1b", "%1c", "%1d", "%1e", "%1f",
36     "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
37     "%28", "%29", "%2a", "%2b", "%2c", "%2d", "%2e", "%2f",
38     "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37",
39     "%38", "%39", "%3a", "%3b", "%3c", "%3d", "%3e", "%3f",
40     "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47",
41     "%48", "%49", "%4a", "%4b", "%4c", "%4d", "%4e", "%4f",
42     "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57",
43     "%58", "%59", "%5a", "%5b", "%5c", "%5d", "%5e", "%5f",
44     "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67",
45     "%68", "%69", "%6a", "%6b", "%6c", "%6d", "%6e", "%6f",
46     "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77",
47     "%78", "%79", "%7a", "%7b", "%7c", "%7d", "%7e", "%7f",
48     "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87",
49     "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f",
50     "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97",
51     "%98", "%99", "%9a", "%9b", "%9c", "%9d", "%9e", "%9f",
52     "%a0", "%a1", "%a2", "%a3", "%a4", "%a5", "%a6", "%a7",
53     "%a8", "%a9", "%aa", "%ab", "%ac", "%ad", "%ae", "%af",
54     "%b0", "%b1", "%b2", "%b3", "%b4", "%b5", "%b6", "%b7",
55     "%b8", "%b9", "%ba", "%bb", "%bc", "%bd", "%be", "%bf",
56     "%c0", "%c1", "%c2", "%c3", "%c4", "%c5", "%c6", "%c7",
57     "%c8", "%c9", "%ca", "%cb", "%cc", "%cd", "%ce", "%cf",
58     "%d0", "%d1", "%d2", "%d3", "%d4", "%d5", "%d6", "%d7",
59     "%d8", "%d9", "%da", "%db", "%dc", "%dd", "%de", "%df",
60     "%e0", "%e1", "%e2", "%e3", "%e4", "%e5", "%e6", "%e7",
61     "%e8", "%e9", "%ea", "%eb", "%ec", "%ed", "%ee", "%ef",
62     "%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
63     "%f8", "%f9", "%fa", "%fb", "%fc", "%fd", "%fe", "%ff"
64   };
65
66   /**
67    * Encode a string to the "x-www-form-urlencoded" form, enhanced
68    * with the UTF-8-in-URL proposal. This is what happens:
69    *
70    * <ul>
71    * <li><p>The ASCII characters 'a' through 'z', 'A' through 'Z',
72    * and '0' through '9' remain the same.
73    *
74    * <li><p>The unreserved characters - _ . ! ~ * ' ( ) remain the same.
75    *
76    * <li><p>The space character ' ' is converted into a plus sign '+'.
77    *
78    * <li><p>All other ASCII characters are converted into the
79    * 3-character string "%xy", where xy is
80    * the two-digit hexadecimal representation of the character
81    * code
82    *
83    * <li><p>All non-ASCII characters are encoded in two steps: first
84    * to a sequence of 2 or 3 bytes, using the UTF-8 algorithm;
85    * secondly each of these bytes is encoded as "%xx".
86    * </ul>
87    *
88    * @param s The string to be encoded
89    * @return The encoded string
90    */

91   public static String JavaDoc encode(String JavaDoc s)
92   {
93     StringBuffer JavaDoc sbuf = new StringBuffer JavaDoc();
94     int len = s.length();
95     for (int i = 0; i < len; i++) {
96         int ch = s.charAt(i);
97         if ('A' <= ch && ch <= 'Z') { // 'A'..'Z'
98
sbuf.append((char) ch);
99         } else if ('a' <= ch && ch <= 'z') { // 'a'..'z'
100
sbuf.append((char) ch);
101         } else if ('0' <= ch && ch <= '9') { // '0'..'9'
102
sbuf.append((char) ch);
103         } else if (ch == ' ') { // space
104
sbuf.append("%20");
105         } else if (
106             ch == '-'
107                 || ch == '_' // unreserved
108
|| ch == '.'
109                 || ch == '!'
110                 || ch == '~'
111                 || ch == '*'
112                 || ch == '\''
113                 || ch == '('
114                 || ch == ')') {
115             sbuf.append((char) ch);
116         } else if (ch <= 0x007f) { // other ASCII
117
sbuf.append(hex[ch]);
118         } else if (ch <= 0x07FF) { // non-ASCII <= 0x7FF
119
sbuf.append(hex[0xc0 | (ch >> 6)]);
120             sbuf.append(hex[0x80 | (ch & 0x3F)]);
121         } else { // 0x7FF < ch <= 0xFFFF
122
sbuf.append(hex[0xe0 | (ch >> 12)]);
123             sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]);
124             sbuf.append(hex[0x80 | (ch & 0x3F)]);
125         }
126     }
127     
128     return sbuf.toString();
129     }
130 }
131
Popular Tags