1 /*
2 * ModeShape (http://www.modeshape.org)
3 * See the COPYRIGHT.txt file distributed with this work for information
4 * regarding copyright ownership. Some portions may be licensed
5 * to Red Hat, Inc. under one or more contributor license agreements.
6 * See the AUTHORS.txt file in the distribution for a full listing of
7 * individual contributors.
8 *
9 * ModeShape is free software. Unless otherwise indicated, all code in ModeShape
10 * is licensed to you under the terms of the GNU Lesser General Public License as
11 * published by the Free Software Foundation; either version 2.1 of
12 * the License, or (at your option) any later version.
13 *
14 * ModeShape is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
18 *
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with this software; if not, write to the Free
21 * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
22 * 02110-1301 USA, or see the FSF site: http://www.fsf.org.
23 */
24 package org.modeshape.common.text;
25
26 import java.text.CharacterIterator;
27 import java.text.StringCharacterIterator;
28 import java.util.BitSet;
29 import net.jcip.annotations.Immutable;
30
31 /**
32 * An encoder useful for converting text to be used within a URL, as defined by Section 2.3 of <a
33 * href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>. Note that this class does not encode a complete URL (
34 * {@link java.net.URLEncoder} and {@link java.net.URLDecoder} should be used for such purposes).
35 */
36 @Immutable
37 public class UrlEncoder implements TextEncoder, TextDecoder {
38
39 /**
40 * Data characters that are allowed in a URI but do not have a reserved purpose are called unreserved. These include upper and
41 * lower case letters, decimal digits, and a limited set of punctuation marks and symbols.
42 *
43 * <pre>
44 * unreserved = alphanum | mark
45 * mark = "-" | "_" | "." | "!" | "˜" | "*" | "'" | "(" | ")"
46 * </pre>
47 *
48 * Unreserved characters can be escaped without changing the semantics of the URI, but this should not be done unless the URI
49 * is being used in a context that does not allow the unescaped character to appear.
50 */
51 private static final BitSet RFC2396_UNRESERVED_CHARACTERS = new BitSet(256);
52 private static final BitSet RFC2396_UNRESERVED_WITH_SLASH_CHARACTERS;
53
54 public static final char ESCAPE_CHARACTER = '%';
55
56 static {
57 RFC2396_UNRESERVED_CHARACTERS.set('a', 'z' + 1);
58 RFC2396_UNRESERVED_CHARACTERS.set('A', 'Z' + 1);
59 RFC2396_UNRESERVED_CHARACTERS.set('0', '9' + 1);
60 RFC2396_UNRESERVED_CHARACTERS.set('-');
61 RFC2396_UNRESERVED_CHARACTERS.set('_');
62 RFC2396_UNRESERVED_CHARACTERS.set('.');
63 RFC2396_UNRESERVED_CHARACTERS.set('!');
64 RFC2396_UNRESERVED_CHARACTERS.set('~');
65 RFC2396_UNRESERVED_CHARACTERS.set('*');
66 RFC2396_UNRESERVED_CHARACTERS.set('\'');
67 RFC2396_UNRESERVED_CHARACTERS.set('(');
68 RFC2396_UNRESERVED_CHARACTERS.set(')');
69
70 RFC2396_UNRESERVED_WITH_SLASH_CHARACTERS = (BitSet)RFC2396_UNRESERVED_CHARACTERS.clone();
71 RFC2396_UNRESERVED_WITH_SLASH_CHARACTERS.set('/');
72 }
73
74 private boolean slashEncoded = true;
75
76 /**
77 * {@inheritDoc}
78 */
79 public String encode( String text ) {
80 if (text == null) return null;
81 if (text.length() == 0) return text;
82 return encode(text, isSlashEncoded() ? RFC2396_UNRESERVED_CHARACTERS : RFC2396_UNRESERVED_WITH_SLASH_CHARACTERS);
83 }
84
85 protected String encode( String text,
86 BitSet safeChars ) {
87 final StringBuilder result = new StringBuilder();
88 final CharacterIterator iter = new StringCharacterIterator(text);
89 for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
90 if (safeChars.get(c)) {
91 // Safe character, so just pass through ...
92 result.append(c);
93 } else {
94 // The character is not a safe character, and must be escaped ...
95 result.append(ESCAPE_CHARACTER);
96 result.append(Character.toLowerCase(Character.forDigit(c / 16, 16)));
97 result.append(Character.toLowerCase(Character.forDigit(c % 16, 16)));
98 }
99 }
100 return result.toString();
101 }
102
103 /**
104 * {@inheritDoc}
105 */
106 public String decode( String encodedText ) {
107 if (encodedText == null) return null;
108 if (encodedText.length() == 0) return encodedText;
109 final StringBuilder result = new StringBuilder();
110 final CharacterIterator iter = new StringCharacterIterator(encodedText);
111 for (char c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
112 if (c == ESCAPE_CHARACTER) {
113 boolean foundEscapedCharacter = false;
114 // Found the first character in a potential escape sequence, so grab the next two characters ...
115 char hexChar1 = iter.next();
116 char hexChar2 = hexChar1 != CharacterIterator.DONE ? iter.next() : CharacterIterator.DONE;
117 if (hexChar2 != CharacterIterator.DONE) {
118 // We found two more characters, but ensure they form a valid hexadecimal number ...
119 int hexNum1 = Character.digit(hexChar1, 16);
120 int hexNum2 = Character.digit(hexChar2, 16);
121 if (hexNum1 > -1 && hexNum2 > -1) {
122 foundEscapedCharacter = true;
123 result.append((char)(hexNum1 * 16 + hexNum2));
124 }
125 }
126 if (!foundEscapedCharacter) {
127 result.append(c);
128 if (hexChar1 != CharacterIterator.DONE) result.append(hexChar1);
129 if (hexChar2 != CharacterIterator.DONE) result.append(hexChar2);
130 }
131 } else {
132 result.append(c);
133 }
134 }
135 return result.toString();
136 }
137
138 /**
139 * @return slashEncoded
140 */
141 public boolean isSlashEncoded() {
142 return this.slashEncoded;
143 }
144
145 /**
146 * @param slashEncoded Sets slashEncoded to the specified value.
147 * @return this object, for method chaining
148 */
149 public UrlEncoder setSlashEncoded( boolean slashEncoded ) {
150 this.slashEncoded = slashEncoded;
151 return this;
152 }
153
154 }