1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.catalina.util;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.nio.charset.Charset;
import java.util.BitSet;
/**
* This class is very similar to the java.net.URLEncoder class. Unfortunately, with java.net.URLEncoder there is no way
* to specify to the java.net.URLEncoder which characters should NOT be encoded. This code was moved from
* DefaultServlet.java
*
* @author Craig R. McClanahan
* @author Remy Maucherat
*/
public final class URLEncoder implements Cloneable {
private static final char[] hexadecimal =
{ '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
public static final URLEncoder DEFAULT = new URLEncoder();
public static final URLEncoder QUERY = new URLEncoder();
static {
/*
* Encoder for URI paths, so from the spec:
*
* pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
*
* unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
*
* sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
*/
// ALPHA and DIGIT are always treated as safe characters
// Add the remaining unreserved characters
DEFAULT.addSafeCharacter('-');
DEFAULT.addSafeCharacter('.');
DEFAULT.addSafeCharacter('_');
DEFAULT.addSafeCharacter('~');
// Add the sub-delims
DEFAULT.addSafeCharacter('!');
DEFAULT.addSafeCharacter('$');
DEFAULT.addSafeCharacter('&');
DEFAULT.addSafeCharacter('\'');
DEFAULT.addSafeCharacter('(');
DEFAULT.addSafeCharacter(')');
DEFAULT.addSafeCharacter('*');
DEFAULT.addSafeCharacter('+');
DEFAULT.addSafeCharacter(',');
DEFAULT.addSafeCharacter(';');
DEFAULT.addSafeCharacter('=');
// Add the remaining literals
DEFAULT.addSafeCharacter(':');
DEFAULT.addSafeCharacter('@');
// Add '/' so it isn't encoded when we encode a path
DEFAULT.addSafeCharacter('/');
/*
* Encoder for query strings
* https://www.w3.org/TR/html5/forms.html#application/x-www-form-urlencoded-encoding-algorithm
* // @formatter:off
* 0x20 ' ' -> '+'
* 0x2A, 0x2D, 0x2E, 0x30 to 0x39, 0x41 to 0x5A, 0x5F, 0x61 to 0x7A as-is
* '*', '-', '.', '0' to '9', 'A' to 'Z', '_', 'a' to 'z'
* Also '=' and '&' are not encoded
* Everything else %nn encoded
* // @formatter:on
*/
// Special encoding for space
QUERY.setEncodeSpaceAsPlus(true);
// Alpha and digit are safe by default
// Add the other permitted characters
QUERY.addSafeCharacter('*');
QUERY.addSafeCharacter('-');
QUERY.addSafeCharacter('.');
QUERY.addSafeCharacter('_');
QUERY.addSafeCharacter('=');
QUERY.addSafeCharacter('&');
}
// Array containing the safe characters set.
private final BitSet safeCharacters;
private boolean encodeSpaceAsPlus = false;
public URLEncoder() {
this(new BitSet(256));
for (char i = 'a'; i <= 'z'; i++) {
addSafeCharacter(i);
}
for (char i = 'A'; i <= 'Z'; i++) {
addSafeCharacter(i);
}
for (char i = '0'; i <= '9'; i++) {
addSafeCharacter(i);
}
}
private URLEncoder(BitSet safeCharacters) {
this.safeCharacters = safeCharacters;
}
public void addSafeCharacter(char c) {
safeCharacters.set(c);
}
public void removeSafeCharacter(char c) {
safeCharacters.clear(c);
}
public void setEncodeSpaceAsPlus(boolean encodeSpaceAsPlus) {
this.encodeSpaceAsPlus = encodeSpaceAsPlus;
}
/**
* URL encodes the provided path using the given character set.
*
* @param path The path to encode
* @param charset The character set to use to convert the path to bytes
*
* @return The encoded path
*/
public String encode(String path, Charset charset) {
int maxBytesPerChar = 10;
StringBuilder rewrittenPath = new StringBuilder(path.length());
ByteArrayOutputStream buf = new ByteArrayOutputStream(maxBytesPerChar);
OutputStreamWriter writer = new OutputStreamWriter(buf, charset);
for (int i = 0; i < path.length(); i++) {
int c = path.charAt(i);
if (safeCharacters.get(c)) {
rewrittenPath.append((char) c);
} else if (encodeSpaceAsPlus && c == ' ') {
rewrittenPath.append('+');
} else {
// convert to external encoding before hex conversion
try {
writer.write((char) c);
writer.flush();
} catch (IOException e) {
buf.reset();
continue;
}
byte[] ba = buf.toByteArray();
for (byte toEncode : ba) {
// Converting each byte in the buffer
rewrittenPath.append('%');
int low = toEncode & 0x0f;
int high = (toEncode & 0xf0) >> 4;
rewrittenPath.append(hexadecimal[high]);
rewrittenPath.append(hexadecimal[low]);
}
buf.reset();
}
}
return rewrittenPath.toString();
}
@Override
public Object clone() {
URLEncoder result = new URLEncoder((BitSet) safeCharacters.clone());
result.setEncodeSpaceAsPlus(encodeSpaceAsPlus);
return result;
}
}
|
