View Javadoc

1   /*
2    * $Header$
3    * $Revision: 1128 $
4    * $Date: 2006-02-05 13:49:04 -0800 (Sun, 05 Feb 2006) $
5    *
6    * ====================================================================
7    *
8    * Copyright 2000-2002 bob mcwhirter & James Strachan.
9    * All rights reserved.
10   *
11   * Redistribution and use in source and binary forms, with or without
12   * modification, are permitted provided that the following conditions are
13   * met:
14   * 
15   *   * Redistributions of source code must retain the above copyright
16   *     notice, this list of conditions and the following disclaimer.
17   * 
18   *   * Redistributions in binary form must reproduce the above copyright
19   *     notice, this list of conditions and the following disclaimer in the
20   *     documentation and/or other materials provided with the distribution.
21   * 
22   *   * Neither the name of the Jaxen Project nor the names of its
23   *     contributors may be used to endorse or promote products derived 
24   *     from this software without specific prior written permission.
25   * 
26   * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
27   * IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
28   * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
29   * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
30   * OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
31   * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
32   * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
33   * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
34   * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
35   * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
36   * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
37   *
38   * ====================================================================
39   * This software consists of voluntary contributions made by many 
40   * individuals on behalf of the Jaxen Project and was originally 
41   * created by bob mcwhirter <bob@werken.com> and 
42   * James Strachan <jstrachan@apache.org>.  For more information on the 
43   * Jaxen Project, please see <http://www.jaxen.org/>.
44   * 
45   * $Id: NormalizeSpaceFunction.java 1128 2006-02-05 21:49:04Z elharo $
46   */
47  
48  
49  package org.jaxen.function;
50  
51  import java.util.List;
52  
53  import org.jaxen.Context;
54  import org.jaxen.Function;
55  import org.jaxen.FunctionCallException;
56  import org.jaxen.Navigator;
57  
58  /**
59   * <p>
60   * <b>4.2</b> <code><i>string</i> normalize-space(<i>string</i>)</code>
61   * </p>
62   * 
63   * <blockquote src="http://www.w3.org/TR/xpath#function-normalize-space"> 
64   * The <b>normalize-space</b> function
65   * returns the argument string with whitespace normalized by stripping
66   * leading and trailing whitespace and replacing sequences of whitespace
67   * characters by a single space. Whitespace characters are the same as
68   * those allowed by the <a href="http://www.w3.org/TR/REC-xml#NT-S" target="_top">S</a>
69   * production in XML. If the argument is omitted, it defaults to the
70   * context node converted to a string, in other words the <a
71   * href="http://www.w3.org/TR/xpath#dt-string-value"  
72   * target="_top">string-value</a> of the context node.
73   * </blockquote>
74   * 
75   * @author James Strachan (james@metastuff.com)
76   * @see <a href="http://www.w3.org/TR/xpath#function-normalize-space"
77   *      target="_top">Section 4.2 of the XPath Specification</a>
78   */
79  public class NormalizeSpaceFunction implements Function
80  {
81  
82  
83      /**
84       * Create a new <code>NormalizeSpaceFunction</code> object.
85       */
86      public NormalizeSpaceFunction() {}
87      
88      /** 
89       * Returns the string-value of the first item in <code>args</code>
90       * after removing all leading and trailing white space, and 
91       * replacing each other sequence of whitespace by a single space.
92       * Whitespace consists of the characters space (0x32), carriage return (0x0D),
93       * linefeed (0x0A), and tab (0x09).
94       *
95       * @param context the context at the point in the
96       *         expression when the function is called
97       * @param args a list that contains exactly one item
98       * 
99       * @return a normalized <code>String</code>
100      * 
101      * @throws FunctionCallException if <code>args</code> does not have length one
102      */
103     public Object call(Context context,
104                        List args) throws FunctionCallException
105     {
106         
107         if (args.size() == 0) {
108             return evaluate( context.getNodeSet(),
109                              context.getNavigator() );
110         }
111         else if (args.size() == 1)
112         {
113             return evaluate( args.get(0),
114                              context.getNavigator() );
115         }
116     
117         throw new FunctionCallException( "normalize-space() cannot have more than one argument" );
118     }
119 
120     /** 
121      * Returns the string-value of <code>strArg</code> after removing
122      * all leading and trailing white space, and 
123      * replacing each other sequence of whitespace by a single space.
124      * Whitespace consists of the characters space (0x32), carriage return (0x0D),
125      * linefeed (0x0A), and tab (0x09).
126      *
127      * @param strArg the object whose string-value is normalized
128      * @param nav the context at the point in the
129      *         expression when the function is called
130      * 
131      * @return the normalized string-value
132      */
133     public static String evaluate(Object strArg,
134                                   Navigator nav) 
135     {
136         String str = StringFunction.evaluate( strArg,
137                                               nav );
138 
139         char[] buffer = str.toCharArray();
140         int write = 0;
141         int lastWrite = 0;
142         boolean wroteOne = false;
143         int read = 0;
144         while (read < buffer.length)
145         {
146             if (isXMLSpace(buffer[read]))
147             {
148                 if (wroteOne)
149                 {
150                     buffer[write++] = ' ';
151                 }
152                 do
153                 {
154                     read++;
155                 }
156                 while(read < buffer.length && isXMLSpace(buffer[read]));
157             }
158             else
159             {
160                 buffer[write++] = buffer[read++];
161                 wroteOne = true;
162                 lastWrite = write;
163             }
164         }
165 
166         return new String(buffer, 0, lastWrite);
167     }
168     
169     
170     private static boolean isXMLSpace(char c) {
171         return c == ' ' || c == '\n' || c == '\r' || c == '\t';
172     }
173     
174 }