KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > htmlparser > scanners > ImageScanner


1 // $Header: /home/cvs/jakarta-jmeter/src/htmlparser/org/htmlparser/scanners/ImageScanner.java,v 1.5 2004/02/10 13:41:09 woolfel Exp $
2 /*
3  * ====================================================================
4  * Copyright 2002-2004 The Apache Software Foundation.
5  *
6  * Licensed under the Apache License, Version 2.0 (the "License");
7  * you may not use this file except in compliance with the License.
8  * You may obtain a copy of the License at
9  *
10  * http://www.apache.org/licenses/LICENSE-2.0
11  *
12  * Unless required by applicable law or agreed to in writing, software
13  * distributed under the License is distributed on an "AS IS" BASIS,
14  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15  * See the License for the specific language governing permissions and
16  * limitations under the License.
17  *
18  */
19
20 // The developers of JMeter and Apache are greatful to the developers
21 // of HTMLParser for giving Apache Software Foundation a non-exclusive
22 // license. The performance benefits of HTMLParser are clear and the
23 // users of JMeter will benefit from the hard work the HTMLParser
24 // team. For detailed information about HTMLParser, the project is
25 // hosted on sourceforge at http://htmlparser.sourceforge.net/.
26 //
27 // HTMLParser was originally created by Somik Raha in 2000. Since then
28 // a healthy community of users has formed and helped refine the
29 // design so that it is able to tackle the difficult task of parsing
30 // dirty HTML. Derrick Oswald is the current lead developer and was kind
31 // enough to assist JMeter.
32
33 package org.htmlparser.scanners;
34 //////////////////
35 // Java Imports //
36 //////////////////
37 import java.util.Hashtable JavaDoc;
38
39 import org.htmlparser.tags.ImageTag;
40 import org.htmlparser.tags.Tag;
41 import org.htmlparser.tags.data.TagData;
42 import org.htmlparser.util.LinkProcessor;
43 import org.htmlparser.util.ParserException;
44 import org.htmlparser.util.ParserUtils;
45 /**
46  * Scans for the Image Tag. This is a subclass of TagScanner, and is called using a
47  * variant of the template method. If the evaluate() method returns true, that means the
48  * given string contains an image tag. Extraction is done by the scan method thereafter
49  * by the user of this class.
50  */
51 public class ImageScanner extends TagScanner
52 {
53     public static final String JavaDoc IMAGE_SCANNER_ID = "IMG";
54     private Hashtable JavaDoc table;
55     private LinkProcessor processor;
56     /**
57      * Overriding the default constructor
58      */
59     public ImageScanner()
60     {
61         super();
62         processor = new LinkProcessor();
63     }
64     /**
65      * Overriding the constructor to accept the filter
66      */
67     public ImageScanner(String JavaDoc filter, LinkProcessor processor)
68     {
69         super(filter);
70         this.processor = processor;
71     }
72     /**
73      * Extract the location of the image, given the string to be parsed, and the url
74      * of the html page in which this tag exists.
75      * @param s String to be parsed
76      * @param url URL of web page being parsed
77      */
78     public String JavaDoc extractImageLocn(Tag tag, String JavaDoc url) throws ParserException
79     {
80         String JavaDoc relativeLink = null;
81         try
82         {
83             table = tag.getAttributes();
84             relativeLink = (String JavaDoc) table.get("SRC");
85
86             if (relativeLink != null)
87             {
88                 relativeLink = ParserUtils.removeChars(relativeLink, '\n');
89                 relativeLink = ParserUtils.removeChars(relativeLink, '\r');
90             }
91             if (relativeLink == null || relativeLink.length() == 0)
92             {
93                 // try fix
94 String JavaDoc tagText = tag.getText().toUpperCase();
95                 int indexSrc = tagText.indexOf("SRC");
96                 if (indexSrc != -1)
97                 {
98                     // There is a missing equals.
99 tag.setText(
100                         tag.getText().substring(0, indexSrc + 3)
101                             + "="
102                             + tag.getText().substring(
103                                 indexSrc + 3,
104                                 tag.getText().length()));
105                     table = tag.redoParseAttributes();
106                     relativeLink = (String JavaDoc) table.get("SRC");
107
108                 }
109             }
110             if (relativeLink == null)
111                 return "";
112             else
113                 return processor.extract(relativeLink, url);
114         }
115         catch (Exception JavaDoc e)
116         {
117             throw new ParserException(
118                 "HTMLImageScanner.extractImageLocn() : Error in extracting image location, relativeLink = "
119                     + relativeLink
120                     + ", url = "
121                     + url,
122                 e);
123         }
124     }
125
126     public String JavaDoc[] getID()
127     {
128         String JavaDoc[] ids = new String JavaDoc[1];
129         ids[0] = IMAGE_SCANNER_ID;
130         return ids;
131     }
132
133     protected Tag createTag(TagData tagData, Tag tag, String JavaDoc url)
134         throws ParserException
135     {
136         String JavaDoc link = extractImageLocn(tag, url);
137         return new ImageTag(tagData, link);
138     }
139
140 }
141
Popular Tags