UTF8Escaper


1   /*
2   Copyright (c) 2004, Dennis M. Sosnoski.
3   All rights reserved.
4   
5   Redistribution and use in source and binary forms, with or without modification,
6   are permitted provided that the following conditions are met:
7   
8    * Redistributions of source code must retain the above copyright notice, this
9      list of conditions and the following disclaimer.
10   * Redistributions in binary form must reproduce the above copyright notice,
11     this list of conditions and the following disclaimer in the documentation
12     and/or other materials provided with the distribution.
13   * Neither the name of JiBX nor the names of its contributors may be used
14     to endorse or promote products derived from this software without specific
15     prior written permission.
16  
17  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
18  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
19  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
20  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
21  ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
22  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
23  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
24  ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
26  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27  */
28  
29  package org.jibx.runtime.impl;
30  
31  import java.io.IOException  ;
32  import java.io.Writer  ;
33  
34  import org.jibx.runtime.ICharacterEscaper;
35  
36  /**
37   * Handler for writing UTF-8 output stream. This code is specifically for XML
38   * 1.0 and would require changes for XML 1.1 (to handle the added legal
39   * characters, rather than throwing an exception).
40   *
41   * @author Dennis M. Sosnoski
42   * @version 1.0
43   */
44  
45  public class UTF8Escaper implements ICharacterEscaper
46  {
47      /** Singleton instance of class. */
48      private static final UTF8Escaper s_instance = new UTF8Escaper();
49      
50      /**
51       * Private constructor to prevent external creation.
52       */
53      
54      private UTF8Escaper() {}
55      
56      /**
57       * Write attribute value with character entity substitutions. This assumes
58       * that attributes use the regular quote ('"') delimitor.
59       *
60       * @param text attribute value text
61       * @param writer sink for output text
62       * @throws IOException on error writing to document
63       */
64  
65      public void writeAttribute(String   text, Writer   writer) throws IOException   {
66          int mark = 0;
67          for (int i = 0; i < text.length(); i++) {
68              char chr = text.charAt(i);
69              if (chr == '"') {
70                  writer.write(text, mark, i-mark);
71                  mark = i+1;
72                  writer.write("&quot;");
73              } else if (chr == '&') {
74                  writer.write(text, mark, i-mark);
75                  mark = i+1;
76                  writer.write("&amp;");
77              } else if (chr == '<') {
78                  writer.write(text, mark, i-mark);
79                  mark = i+1;
80                  writer.write("&lt;");
81              } else if (chr == '>' && i > 2 && text.charAt(i-1) == ']' &&
82                  text.charAt(i-2) == ']') {
83                  writer.write(text, mark, i-mark-2);
84                  mark = i+1;
85                  writer.write("]]&gt;");
86              } else if (chr < 0x20) {
87                  if (chr != 0x9 && chr != 0xA && chr != 0xD) {
88                      throw new IOException  ("Illegal character code 0x" +
89                          Integer.toHexString(chr) + " in attribute value text");
90                  }
91              } else if (chr > 0xD7FF && (chr < 0xE000 || chr == 0xFFFE ||
92                  chr == 0xFFFF || chr > 0x10FFFF)) {
93                  throw new IOException  ("Illegal character code 0x" +
94                      Integer.toHexString(chr) + " in attribute value text");
95              }
96          }
97          writer.write(text, mark, text.length()-mark);
98      }
99      
100     /**
101      * Write content value with character entity substitutions.
102      *
103      * @param text content value text
104      * @param writer sink for output text
105      * @throws IOException on error writing to document
106      */
107 
108     public void writeContent(String   text, Writer   writer) throws IOException   {
109         int mark = 0;
110         for (int i = 0; i < text.length(); i++) {
111             char chr = text.charAt(i);
112             if (chr == '&') {
113                 writer.write(text, mark, i-mark);
114                 mark = i+1;
115                 writer.write("&amp;");
116             } else if (chr == '<') {
117                 writer.write(text, mark, i-mark);
118                 mark = i+1;
119                 writer.write("&lt;");
120             } else if (chr == '>' && i > 2 && text.charAt(i-1) == ']' &&
121                 text.charAt(i-2) == ']') {
122                 writer.write(text, mark, i-mark-2);
123                 mark = i+1;
124                 writer.write("]]&gt;");
125             } else if (chr < 0x20) {
126                 if (chr != 0x9 && chr != 0xA && chr != 0xD) {
127                     throw new IOException  ("Illegal character code 0x" +
128                         Integer.toHexString(chr) + " in content text");
129                 }
130             } else if (chr > 0xD7FF && (chr < 0xE000 || chr == 0xFFFE ||
131                 chr == 0xFFFF || chr > 0x10FFFF)) {
132                 throw new IOException  ("Illegal character code 0x" +
133                     Integer.toHexString(chr) + " in content text");
134             }
135         }
136         writer.write(text, mark, text.length()-mark);
137     }
138     
139     /**
140      * Write CDATA to document. This writes the beginning and ending sequences
141      * for a CDATA section as well as the actual text, verifying that only
142      * characters allowed by the encoding are included in the text.
143      *
144      * @param text content value text
145      * @param writer sink for output text
146      * @throws IOException on error writing to document
147      */
148 
149     public void writeCData(String   text, Writer   writer) throws IOException   {
150         writer.write("<![CDATA[");
151         for (int i = 0; i < text.length(); i++) {
152             char chr = text.charAt(i);
153             if (chr == '>' && i > 2 && text.charAt(i-1) == ']' &&
154                 text.charAt(i-2) == ']') {
155                 throw new IOException  ("Sequence \"]]>\" is not allowed " +
156                     "within CDATA section text");
157             } else if (chr < 0x20) {
158                 if (chr != 0x9 && chr != 0xA && chr != 0xD) {
159                     throw new IOException  ("Illegal character code 0x" +
160                         Integer.toHexString(chr) + " in CDATA section");
161                 }
162             } else if (chr > 0xD7FF &&
163                 (chr < 0xE000 || chr == 0xFFFE || chr == 0xFFFF)) {
164                 throw new IOException  ("Illegal character code 0x" +
165                     Integer.toHexString(chr) + " in CDATA section");
166             }
167         }
168         writer.write(text);
169         writer.write("]]>");
170     }
171     
172     /**
173      * Get instance of escaper.
174      *
175      * @return escaper instance
176      */
177     
178     public static ICharacterEscaper getInstance() {
179         return s_instance;
180     }
181 }
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags