I_CmsHtmlNodeVisitor


1   /*
2    * File   : $Source: /usr/local/cvs/opencms/src/org/opencms/util/I_CmsHtmlNodeVisitor.java,v $
3    * Date   : $Date: 2006/09/19 14:29:08 $
4    * Version: $Revision: 1.3 $
5    *
6    * This library is part of OpenCms -
7    * the Open Source Content Mananagement System
8    *
9    * Copyright (C) 2005 Alkacon Software GmbH (http://www.alkacon.com)
10   *
11   * This library is free software; you can redistribute it and/or
12   * modify it under the terms of the GNU Lesser General Public
13   * License as published by the Free Software Foundation; either
14   * version 2.1 of the License, or (at your option) any later version.
15   *
16   * This library is distributed in the hope that it will be useful,
17   * but WITHOUT ANY WARRANTY; without even the implied warranty of
18   * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19   * Lesser General Public License for more details.
20   *
21   * For further information about Alkacon Software GmbH, please see the
22   * company website: http://www.alkacon.com
23   *
24   * For further information about OpenCms, please see the
25   * project website: http://www.opencms.org
26   * 
27   * You should have received a copy of the GNU Lesser General Public
28   * License along with this library; if not, write to the Free Software
29   * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
30   */
31  
32  package org.opencms.util;
33  
34  import java.util.List  ;
35  
36  import org.htmlparser.Remark;
37  import org.htmlparser.Tag;
38  import org.htmlparser.Text;
39  import org.htmlparser.util.ParserException;
40  
41  /**
42   * 
43   * Interface for a combination of a visitor of HTML documents along with the hook to start the
44   * parser / lexer that triggers the visit.
45   * <p>
46   * 
47   * 
48   * 
49   * @author Alexander Kandzior
50   * 
51   * @version $Revision: 1.3 $
52   * 
53   * @since 6.1.3
54   * 
55   */
56  public interface I_CmsHtmlNodeVisitor {
57  
58      /**
59       * Returns the configuartion String of this visitor or the empty String if was not provided
60       * before.
61       * <p>
62       * 
63       * @return the configuartion String of this visitor - by this contract never null but an empty
64       *         String if not provided.
65       * 
66       * @see #setConfiguration(String)
67       */
68      String   getConfiguration();
69  
70      /**
71       * Returns the text extraction result.
72       * <p>
73       * 
74       * @return the text extraction result
75       */
76      String   getResult();
77      
78      /**
79       * Extracts the text from the given html content, assuming the given html encoding.
80       * <p>
81       * 
82       * @param html the content to extract the plain text from
83       * @param encoding the encoding to use
84       * 
85       * @return the text extracted from the given html content
86       * 
87       * @throws ParserException if something goes wrong
88       */
89      String   process(String   html, String   encoding) throws ParserException;
90  
91      /**
92       * Set a configuartion String for this visitor.
93       * <p>
94       * 
95       * This will most likely be done with data from an xsd, custom jsp tag, ...
96       * <p>
97       * 
98       * @param configuration the configuration of this visitor to set.
99       */
100     void setConfiguration(String   configuration);
101 
102     /**
103      * Sets a list of upper case tag names for which parsing / visitng should not correct missing closing tags.<p> 
104      * 
105      * This has to be used before <code>{@link #process(String, String)}</code> is invoked to take an effect.<p>
106      * 
107      * @param noAutoCloseTags a list of upper case tag names for which parsing / visiting 
108      *      should not correct missing closing tags to set.
109      */
110     void setNoAutoCloseTags(List   noAutoCloseTags);
111 
112     /**
113      * Visitor method (callback) invoked when a closing Tag is encountered.
114      * <p>
115      * 
116      * @param tag the tag that is ended.
117      * 
118      * @see org.htmlparser.visitors.NodeVisitor#visitEndTag(org.htmlparser.Tag)
119      */
120     void visitEndTag(Tag tag);
121 
122     /**
123      * Visitor method (callback) invoked when a remark Tag (HTML comment) is encountered.
124      * <p>
125      * 
126      * @param remark the remark Tag to visit.
127      * 
128      * @see org.htmlparser.visitors.NodeVisitor#visitRemarkNode(org.htmlparser.Remark)
129      */
130     void visitRemarkNode(Remark remark);
131 
132     /**
133      * 
134      * Visitor method (callback) invoked when a remark Tag (HTML comment) is encountered.
135      * <p>
136      * 
137      * @param text the text that is visited.
138      * 
139      * @see org.htmlparser.visitors.NodeVisitor#visitStringNode(org.htmlparser.Text)
140      */
141     void visitStringNode(Text text);
142     
143     /**
144      * Visitor method (callback) invoked when a starting Tag (HTML comment) is encountered.
145      * <p>
146      * 
147      * @param tag the tag that is visited.
148      * 
149      * @see org.htmlparser.visitors.NodeVisitor#visitTag(org.htmlparser.Tag)
150      */
151     void visitTag(Tag tag);
152 
153 }
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags