src/main/java/org/apache/tika/sax/XHTMLContentHandler.java

   1 /**
   2  * Licensed to the Apache Software Foundation (ASF) under one or more
   3  * contributor license agreements.  See the NOTICE file distributed with
   4  * this work for additional information regarding copyright ownership.
   5  * The ASF licenses this file to You under the Apache License, Version 2.0
   6  * (the "License"); you may not use this file except in compliance with
   7  * the License.  You may obtain a copy of the License at
   8  *
   9  *     http://www.apache.org/licenses/LICENSE-2.0
  10  *
  11  * Unless required by applicable law or agreed to in writing, software
  12  * distributed under the License is distributed on an "AS IS" BASIS,
  13  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14  * See the License for the specific language governing permissions and
  15  * limitations under the License.
  16  */
  17 package org.apache.tika.sax;
  18
  19 import org.apache.tika.metadata.Metadata;
  20 import org.xml.sax.Attributes;
  21 import org.xml.sax.ContentHandler;
  22 import org.xml.sax.SAXException;
  23 import org.xml.sax.helpers.AttributesImpl;
  24
  25 /**
  26  * Content handler decorator that simplifies the task of producing XHTML
  27  * events for Tika content parsers.
  28  */
  29 public class XHTMLContentHandler extends ContentHandlerDecorator {
  30
  31     /**
  32      * The XHTML namespace URI
  33      */
  34     public static final String XHTML = "http://www.w3.org/1999/xhtml";
  35
  36     /**
  37      * Metadata associated with the document. Used to fill in the
  38      * &lt;head/&gt; section.
  39      */
  40     private final Metadata metadata;
  41
  42     /**
  43      * Flag to indicate whether the document element has been started.
  44      */
  45     private boolean started = false;
  46
  47     public XHTMLContentHandler(ContentHandler handler, Metadata metadata) {
  48         super(handler);
  49         this.metadata = metadata;
  50     }
  51
  52     /**
  53      * Starts an XHTML document by setting up the namespace mappings.
  54      * The standard XHTML prefix is generated lazily when the first
  55      * element is started.
  56      */
  57     @Override
  58     public void startDocument() throws SAXException {
  59         super.startDocument();
  60         startPrefixMapping("", XHTML);
  61     }
  62
  63     /**
  64      * Generates the following XHTML prefix when called for the first time:
  65      * <pre>
  66      * &lt;html&gt;
  67      *   &lt;head&gt;
  68      *     &lt;title&gt;...&lt;/title&gt;
  69      *   &lt;/head&gt;
  70      *   &lt;body&gt;
  71      * </pre>
  72      */
  73     private void lazyStartDocument() throws SAXException {
  74         if (!started) {
  75             started = true;
  76             startElement("html");
  77             startElement("head");
  78             startElement("title");
  79             String title = metadata.get(Metadata.TITLE);
  80             if (title != null && title.length() > 0) {
  81                 characters(title);
  82             }
  83             endElement("title");
  84             endElement("head");
  85             startElement("body");
  86         }
  87     }
  88
  89     /**
  90      * Ends the XHTML document by writing the following footer and
  91      * clearing the namespace mappings:
  92      * <pre>
  93      *   &lt;/body&gt;
  94      * &lt;/html&gt;
  95      * </pre>
  96      */
  97     @Override
  98     public void endDocument() throws SAXException {
  99         lazyStartDocument();
 100         endElement("body");
 101         endElement("html");
 102         endPrefixMapping("");
 103         super.endDocument();
 104     }
 105
 106     @Override
 107     public void startElement(
 108             String uri, String local, String name, Attributes attributes)
 109             throws SAXException {
 110         lazyStartDocument();
 111         super.startElement(uri, local, name, attributes);
 112     }
 113
 114     public void startElement(String name) throws SAXException {
 115         startElement(XHTML, name, name, new AttributesImpl());
 116     }
 117
 118     public void startElement(String name, String attribute, String value)
 119             throws SAXException {
 120         AttributesImpl attributes = new AttributesImpl();
 121         attributes.addAttribute(XHTML, attribute, attribute, "CDATA", value);
 122         startElement(XHTML, name, name, attributes);
 123     }
 124
 125     public void endElement(String name) throws SAXException {
 126         endElement(XHTML, name, name);
 127     }
 128
 129     public void characters(String characters) throws SAXException {
 130         characters(characters.toCharArray(), 0, characters.length());
 131     }
 132
 133     public void element(String name, String value) throws SAXException {
 134         startElement(name);
 135         characters(value);
 136         endElement(name);
 137     }
 138
 139 }