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
192
193
194
195
196
197
198
199
200
201
202
203
204
|
/*
* Licensed Material - Property of IBM
* (C) Copyright IBM Corp. 2002 - All Rights Reserved.
* US Government Users Restricted Rights - Use, duplication or disclosure
* restricted by GSA ADP Schedule Contract with IBM Corp.
*
* plugins/com.ibm.etools.xmlutility/src/com/ibm/etools/xmlutility/uri/URIEncoder.java, com.ibm.etools.xmlutility, wsa.xml.v51, 20030718_1605.o
*
* @version 1.3 7/18/03
*/
package org.eclipse.wst.wsi.internal;
import java.io.ByteArrayOutputStream;
import java.io.BufferedWriter;
import java.io.OutputStreamWriter;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.util.BitSet;
/**
* This class is a modified version of java.lang.URLEncoder.
*/
public class URIEncoder
{
static BitSet dontNeedEncoding;
static final int caseDiff = ('a' - 'A');
static String dfltEncName = null;
static {
dontNeedEncoding = new BitSet(256);
int i;
for (i = 'a'; i <= 'z'; i++)
{
dontNeedEncoding.set(i);
}
for (i = 'A'; i <= 'Z'; i++)
{
dontNeedEncoding.set(i);
}
for (i = '0'; i <= '9'; i++)
{
dontNeedEncoding.set(i);
}
//dontNeedEncoding.set(' '); // cs.. removed so that space character will be replaced by %20
dontNeedEncoding.set('-');
dontNeedEncoding.set('_');
dontNeedEncoding.set('.');
dontNeedEncoding.set('*');
dontNeedEncoding.set(':'); // cs.. added
dontNeedEncoding.set('/');
// cs.. added so that slashes don't get encoded as %2F
// dfltEncName = (String)AccessController.doPrivileged(new GetPropertyAction("file.encoding"));
// As discussed with Sandy, we should encode URIs with UTF8
dfltEncName = "UTF8";
//System.out.println("dfltEncName " + dfltEncName);
}
/**
* You can't call the constructor.
*/
private URIEncoder()
{
}
/**
* Translates a string into <code>x-www-form-urlencoded</code>
* format. This method uses the platform's default encoding
* as the encoding scheme to obtain the bytes for unsafe characters.
*
* @param s <code>String</code> to be translated.
* @return the translated <code>String</code>.
*/
public static String encode(String s)
{
String str = null;
try
{
str = encode(s, dfltEncName);
}
catch (UnsupportedEncodingException e)
{
// The system should always have the platform default
}
return str;
}
/**
* Translates a string into <code>application/x-www-form-urlencoded</code>
* format using a specific encoding scheme. This method uses the
* supplied encoding scheme to obtain the bytes for unsafe
* characters.
* <p>
* <em><strong>Note:</strong> The <a href=
* "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">
* World Wide Web Consortium Recommendation</a> states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilites.</em>
*
* @param s <code>String</code> to be translated.
* @param enc The name of a supported
* <a href="../lang/package-summary.html#charenc">character
* encoding</a>.
* @return the translated <code>String</code>.
* @exception UnsupportedEncodingException
* If the named encoding is not supported
* @see URLDecoder#decode(java.lang.String, java.lang.String)
*/
public static String encode(String s, String enc)
throws UnsupportedEncodingException
{
boolean needToChange = false;
boolean wroteUnencodedChar = false;
int maxBytesPerChar = 10; // rather arbitrary limit, but safe for now
StringBuffer out = new StringBuffer(s.length());
ByteArrayOutputStream buf = new ByteArrayOutputStream(maxBytesPerChar);
BufferedWriter writer =
new BufferedWriter(new OutputStreamWriter(buf, enc));
for (int i = 0; i < s.length(); i++)
{
int c = (int) s.charAt(i);
//System.out.println("Examining character: " + c);
if (dontNeedEncoding.get(c))
{
//if (c == ' ')
//{
// c = '+';
// needToChange = true;
//}
//System.out.println("Storing: " + c);
out.append((char) c);
wroteUnencodedChar = true;
}
else
{
// convert to external encoding before hex conversion
try
{
if (wroteUnencodedChar)
{ // Fix for 4407610
writer = new BufferedWriter(new OutputStreamWriter(buf, enc));
wroteUnencodedChar = false;
}
writer.write(c);
// If this character represents the start of a Unicode
// surrogate pair, then pass in two characters. It's not
// clear what should be done if a bytes reserved in the
// surrogate pairs range occurs outside of a legal
// surrogate pair. For now, just treat it as if it were
// any other character.
//
if (c >= 0xD800 && c <= 0xDBFF)
{
// System.out.println(Integer.toHexString(c) + " is high surrogate");
if ((i + 1) < s.length())
{
int d = (int) s.charAt(i + 1);
// System.out.println("\tExamining " + Integer.toHexString(d));
if (d >= 0xDC00 && d <= 0xDFFF)
{
// System.out.println("\t" + Integer.toHexString(d) + " is low surrogate");
writer.write(d);
i++;
}
}
}
writer.flush();
}
catch (IOException e)
{
buf.reset();
continue;
}
byte[] ba = buf.toByteArray();
for (int j = 0; j < ba.length; j++)
{
out.append('%');
char ch = Character.forDigit((ba[j] >> 4) & 0xF, 16);
// converting to use uppercase letter as part of
// the hex value if ch is a letter.
if (Character.isLetter(ch))
{
ch -= caseDiff;
}
out.append(ch);
ch = Character.forDigit(ba[j] & 0xF, 16);
if (Character.isLetter(ch))
{
ch -= caseDiff;
}
out.append(ch);
}
buf.reset();
needToChange = true;
}
}
return (needToChange ? out.toString() : s);
}
}
|
