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
|
/*
* 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.tomcat.util.buf;
import java.io.CharArrayWriter;
import java.io.IOException;
import java.io.Writer;
import java.util.BitSet;
/** Efficient implementation for encoders.
* This class is not thread safe - you need one encoder per thread.
* The encoder will save and recycle the internal objects, avoiding
* garbage.
*
* You can add extra characters that you want preserved, for example
* while encoding a URL you can add "/".
*
* @author Costin Manolache
*/
public final class UEncoder {
private static org.apache.juli.logging.Log log=
org.apache.juli.logging.LogFactory.getLog(UEncoder.class );
// Not static - the set may differ ( it's better than adding
// an extra check for "/", "+", etc
private BitSet safeChars=null;
private C2BConverter c2b=null;
private ByteChunk bb=null;
private String encoding="UTF8";
private static final int debug=0;
public UEncoder() {
initSafeChars();
}
public void setEncoding( String s ) {
encoding=s;
}
public void addSafeCharacter( char c ) {
safeChars.set( c );
}
/** URL Encode string, using a specified encoding.
*
* @param buf The writer
* @param s string to be encoded
* @throws IOException If an I/O error occurs
*/
public void urlEncode( Writer buf, String s )
throws IOException
{
if( c2b==null ) {
bb=new ByteChunk(16); // small enough.
c2b=new C2BConverter( bb, encoding );
}
for (int i = 0; i < s.length(); i++) {
int c = (int) s.charAt(i);
if( safeChars.get( c ) ) {
if( debug > 0 ) log("Safe: " + (char)c);
buf.write((char)c);
} else {
if( debug > 0 ) log("Unsafe: " + (char)c);
c2b.convert( (char)c );
// "surrogate" - UTF is _not_ 16 bit, but 21 !!!!
// ( while UCS is 31 ). Amazing...
if (c >= 0xD800 && c <= 0xDBFF) {
if ( (i+1) < s.length()) {
int d = (int) s.charAt(i+1);
if (d >= 0xDC00 && d <= 0xDFFF) {
if( debug > 0 ) log("Unsafe: " + c);
c2b.convert( (char)d);
i++;
}
}
}
c2b.flushBuffer();
urlEncode( buf, bb.getBuffer(), bb.getOffset(),
bb.getLength() );
bb.recycle();
}
}
}
/**
*/
public void urlEncode( Writer buf, byte bytes[], int off, int len)
throws IOException
{
for( int j=off; j< len; j++ ) {
buf.write( '%' );
char ch = Character.forDigit((bytes[j] >> 4) & 0xF, 16);
if( debug > 0 ) log("Encode: " + ch);
buf.write(ch);
ch = Character.forDigit(bytes[j] & 0xF, 16);
if( debug > 0 ) log("Encode: " + ch);
buf.write(ch);
}
}
/**
* Utility funtion to re-encode the URL.
* Still has problems with charset, since UEncoder mostly
* ignores it.
*/
public String encodeURL(String uri) {
String outUri=null;
try {
// XXX optimize - recycle, etc
CharArrayWriter out = new CharArrayWriter();
urlEncode(out, uri);
outUri=out.toString();
} catch (IOException iex) {
}
return outUri;
}
// -------------------- Internal implementation --------------------
//
private void initSafeChars() {
safeChars=new BitSet(128);
int i;
for (i = 'a'; i <= 'z'; i++) {
safeChars.set(i);
}
for (i = 'A'; i <= 'Z'; i++) {
safeChars.set(i);
}
for (i = '0'; i <= '9'; i++) {
safeChars.set(i);
}
//safe
safeChars.set('$');
safeChars.set('-');
safeChars.set('_');
safeChars.set('.');
// Dangerous: someone may treat this as " "
// RFC1738 does allow it, it's not reserved
// safeChars.set('+');
//extra
safeChars.set('!');
safeChars.set('*');
safeChars.set('\'');
safeChars.set('(');
safeChars.set(')');
safeChars.set(',');
}
private static void log( String s ) {
if (log.isDebugEnabled())
log.debug("Encoder: " + s );
}
}
|
