author | mkos |
Sun, 30 Dec 2012 00:00:00 +0100 | |
changeset 22678 | ac1ea46be942 |
parent 12009 | 4abb694f273a |
permissions | -rw-r--r-- |
12009 | 1 |
/* |
22678
ac1ea46be942
8029237: Update copyright year to match last edit in jaxws repository for 2012
mkos
parents:
12009
diff
changeset
|
2 |
* Copyright (c) 1997, 2012, Oracle and/or its affiliates. All rights reserved. |
12009 | 3 |
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
4 |
* |
|
5 |
* This code is free software; you can redistribute it and/or modify it |
|
6 |
* under the terms of the GNU General Public License version 2 only, as |
|
7 |
* published by the Free Software Foundation. Oracle designates this |
|
8 |
* particular file as subject to the "Classpath" exception as provided |
|
9 |
* by Oracle in the LICENSE file that accompanied this code. |
|
10 |
* |
|
11 |
* This code is distributed in the hope that it will be useful, but WITHOUT |
|
12 |
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
|
13 |
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
|
14 |
* version 2 for more details (a copy is included in the LICENSE file that |
|
15 |
* accompanied this code). |
|
16 |
* |
|
17 |
* You should have received a copy of the GNU General Public License version |
|
18 |
* 2 along with this work; if not, write to the Free Software Foundation, |
|
19 |
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
|
20 |
* |
|
21 |
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA |
|
22 |
* or visit www.oracle.com if you need additional information or have any |
|
23 |
* questions. |
|
24 |
*/ |
|
25 |
||
26 |
package com.sun.xml.internal.bind.v2.runtime.output; |
|
27 |
||
28 |
import java.io.IOException; |
|
29 |
||
30 |
/** |
|
31 |
* Buffer for UTF-8 encoded string. |
|
32 |
* |
|
33 |
* See http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8 for the UTF-8 encoding. |
|
34 |
* |
|
35 |
* @author Kohsuke Kawaguchi |
|
36 |
*/ |
|
37 |
public final class Encoded { |
|
38 |
public byte[] buf; |
|
39 |
||
40 |
public int len; |
|
41 |
||
42 |
public Encoded() {} |
|
43 |
||
44 |
public Encoded(String text) { |
|
45 |
set(text); |
|
46 |
} |
|
47 |
||
48 |
public void ensureSize(int size) { |
|
49 |
if(buf==null || buf.length<size) |
|
50 |
buf = new byte[size]; |
|
51 |
} |
|
52 |
||
53 |
public final void set( String text ) { |
|
54 |
int length = text.length(); |
|
55 |
||
56 |
ensureSize(length*3+1); // +1 for append |
|
57 |
||
58 |
int ptr = 0; |
|
59 |
||
60 |
for (int i = 0; i < length; i++) { |
|
61 |
final char chr = text.charAt(i); |
|
62 |
if (chr > 0x7F) { |
|
63 |
if (chr > 0x7FF) { |
|
64 |
if(Character.MIN_HIGH_SURROGATE<=chr && chr<=Character.MAX_LOW_SURROGATE) { |
|
65 |
// surrogate |
|
66 |
int uc = (((chr & 0x3ff) << 10) | (text.charAt(++i) & 0x3ff)) + 0x10000; |
|
67 |
||
68 |
buf[ptr++] = (byte)(0xF0 | ((uc >> 18))); |
|
69 |
buf[ptr++] = (byte)(0x80 | ((uc >> 12) & 0x3F)); |
|
70 |
buf[ptr++] = (byte)(0x80 | ((uc >> 6) & 0x3F)); |
|
71 |
buf[ptr++] = (byte)(0x80 + (uc & 0x3F)); |
|
72 |
continue; |
|
73 |
} |
|
74 |
buf[ptr++] = (byte)(0xE0 + (chr >> 12)); |
|
75 |
buf[ptr++] = (byte)(0x80 + ((chr >> 6) & 0x3F)); |
|
76 |
} else { |
|
77 |
buf[ptr++] = (byte)(0xC0 + (chr >> 6)); |
|
78 |
} |
|
79 |
buf[ptr++] = (byte)(0x80 + (chr & 0x3F)); |
|
80 |
} else { |
|
81 |
buf[ptr++] = (byte)chr; |
|
82 |
} |
|
83 |
} |
|
84 |
||
85 |
len = ptr; |
|
86 |
} |
|
87 |
||
88 |
/** |
|
89 |
* Fill in the buffer by encoding the specified characters |
|
90 |
* while escaping characters like < |
|
91 |
* |
|
92 |
* @param isAttribute |
|
93 |
* if true, characters like \t, \r, and \n are also escaped. |
|
94 |
*/ |
|
95 |
public final void setEscape(String text, boolean isAttribute) { |
|
96 |
int length = text.length(); |
|
97 |
ensureSize(length*6+1); // in the worst case the text is like """""", so we need 6 bytes per char |
|
98 |
||
99 |
int ptr = 0; |
|
100 |
||
101 |
for (int i = 0; i < length; i++) { |
|
102 |
final char chr = text.charAt(i); |
|
103 |
||
104 |
int ptr1 = ptr; |
|
105 |
if (chr > 0x7F) { |
|
106 |
if (chr > 0x7FF) { |
|
107 |
if(Character.MIN_HIGH_SURROGATE<=chr && chr<=Character.MAX_LOW_SURROGATE) { |
|
108 |
// surrogate |
|
109 |
int uc = (((chr & 0x3ff) << 10) | (text.charAt(++i) & 0x3ff)) + 0x10000; |
|
110 |
||
111 |
buf[ptr++] = (byte)(0xF0 | ((uc >> 18))); |
|
112 |
buf[ptr++] = (byte)(0x80 | ((uc >> 12) & 0x3F)); |
|
113 |
buf[ptr++] = (byte)(0x80 | ((uc >> 6) & 0x3F)); |
|
114 |
buf[ptr++] = (byte)(0x80 + (uc & 0x3F)); |
|
115 |
continue; |
|
116 |
} |
|
117 |
buf[ptr1++] = (byte)(0xE0 + (chr >> 12)); |
|
118 |
buf[ptr1++] = (byte)(0x80 + ((chr >> 6) & 0x3F)); |
|
119 |
} else { |
|
120 |
buf[ptr1++] = (byte)(0xC0 + (chr >> 6)); |
|
121 |
} |
|
122 |
buf[ptr1++] = (byte)(0x80 + (chr & 0x3F)); |
|
123 |
} else { |
|
124 |
byte[] ent; |
|
125 |
||
126 |
if((ent=attributeEntities[chr])!=null) { |
|
127 |
// the majority of the case is just printed as a char, |
|
128 |
// so it's very important to reject them as quickly as possible |
|
129 |
||
130 |
// check again to see if this really needs to be escaped |
|
131 |
if(isAttribute || entities[chr]!=null) |
|
132 |
ptr1 = writeEntity(ent,ptr1); |
|
133 |
else |
|
134 |
buf[ptr1++] = (byte)chr; |
|
135 |
} else |
|
136 |
buf[ptr1++] = (byte)chr; |
|
137 |
} |
|
138 |
ptr = ptr1; |
|
139 |
} |
|
140 |
len = ptr; |
|
141 |
} |
|
142 |
||
143 |
private int writeEntity( byte[] entity, int ptr ) { |
|
144 |
System.arraycopy(entity,0,buf,ptr,entity.length); |
|
145 |
return ptr+entity.length; |
|
146 |
} |
|
147 |
||
148 |
/** |
|
149 |
* Writes the encoded bytes to the given output stream. |
|
150 |
*/ |
|
151 |
public final void write(UTF8XmlOutput out) throws IOException { |
|
152 |
out.write(buf,0,len); |
|
153 |
} |
|
154 |
||
155 |
/** |
|
156 |
* Appends a new character to the end of the buffer. |
|
157 |
* This assumes that you have enough space in the buffer. |
|
158 |
*/ |
|
159 |
public void append(char b) { |
|
160 |
buf[len++] = (byte)b; |
|
161 |
} |
|
162 |
||
163 |
/** |
|
164 |
* Reallocate the buffer to the exact size of the data |
|
165 |
* to reduce the memory footprint. |
|
166 |
*/ |
|
167 |
public void compact() { |
|
168 |
byte[] b = new byte[len]; |
|
169 |
System.arraycopy(buf,0,b,0,len); |
|
170 |
buf = b; |
|
171 |
} |
|
172 |
||
173 |
/** |
|
174 |
* UTF-8 encoded entities keyed by their character code. |
|
175 |
* e.g., entities['&'] == AMP_ENTITY. |
|
176 |
* |
|
177 |
* In attributes we need to encode more characters. |
|
178 |
*/ |
|
179 |
private static final byte[][] entities = new byte[0x80][]; |
|
180 |
private static final byte[][] attributeEntities = new byte[0x80][]; |
|
181 |
||
182 |
static { |
|
183 |
add('&',"&",false); |
|
184 |
add('<',"<",false); |
|
185 |
add('>',">",false); |
|
186 |
add('"',""",true); |
|
187 |
add('\t',"	",true); |
|
188 |
add('\r',"
",false); |
|
189 |
add('\n',"
",true); |
|
190 |
} |
|
191 |
||
192 |
private static void add(char c, String s, boolean attOnly) { |
|
193 |
byte[] image = UTF8XmlOutput.toBytes(s); |
|
194 |
attributeEntities[c] = image; |
|
195 |
if(!attOnly) |
|
196 |
entities[c] = image; |
|
197 |
} |
|
198 |
} |