src/main/java/org/apache/tika/config/TikaConfig.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.config;
  18
  19 //JDK imports
  20 import java.io.File;
  21 import java.io.IOException;
  22 import java.io.InputStream;
  23 import java.net.URL;
  24 import java.util.HashMap;
  25 import java.util.Map;
  26
  27 //TIKA imports
  28 import org.apache.tika.mime.MimeTypes;
  29 import org.apache.tika.mime.MimeUtils;
  30 import org.apache.tika.parser.Parser;
  31 import org.apache.tika.parser.ParserPostProcessor;
  32 import org.apache.tika.utils.Utils;
  33
  34 //JDOM imports
  35 import org.jdom.Document;
  36 import org.jdom.Element;
  37 import org.jdom.JDOMException;
  38 import org.jdom.input.SAXBuilder;
  39 import org.jdom.xpath.XPath;
  40
  41 /**
  42  * Parse xml config file.
  43  */
  44 public class TikaConfig {
  45
  46     public static final String DEFAULT_CONFIG_LOCATION =
  47         "/org/apache/tika/tika-config.xml";
  48
  49     private final Map<String, Parser> parsers = new HashMap<String, Parser>();
  50
  51     private static MimeUtils mimeTypeRepo;
  52
  53     public TikaConfig(String file) throws JDOMException, IOException {
  54         this(new File(file));
  55     }
  56
  57     public TikaConfig(File file) throws JDOMException, IOException {
  58         this(new SAXBuilder().build(file));
  59     }
  60
  61     public TikaConfig(URL url) throws JDOMException, IOException {
  62         this(new SAXBuilder().build(url));
  63     }
  64
  65     public TikaConfig(InputStream stream) throws JDOMException, IOException {
  66         this(new SAXBuilder().build(stream));
  67     }
  68
  69     public TikaConfig(Document document) throws JDOMException {
  70         this(document.getRootElement());
  71     }
  72
  73     public TikaConfig(Element element) throws JDOMException {
  74         Element mtr = element.getChild("mimeTypeRepository");
  75         String mimeTypeRepoResource = mtr.getAttributeValue("resource");
  76         mimeTypeRepo = new MimeUtils(mimeTypeRepoResource);
  77
  78         for (Object node : XPath.selectNodes(element, "//parser")) {
  79             String className = ((Element) node).getAttributeValue("class");
  80             try {
  81                 Parser parser = new ParserPostProcessor(
  82                         (Parser) Class.forName(className).newInstance());
  83                 for (Object child : ((Element) node).getChildren("mime")) {
  84                     parsers.put(((Element) child).getTextTrim(), parser);
  85                 }
  86             } catch (Exception e) {
  87                 throw new JDOMException(
  88                         "Invalid parser configuration: " + className, e);
  89             }
  90         }
  91     }
  92
  93     /**
  94      * Returns the parser instance configured for the given MIME type.
  95      * Returns <code>null</code> if the given MIME type is unknown.
  96      *
  97      * @param mimeType MIME type
  98      * @return configured Parser instance, or <code>null</code>
  99      */
 100     public Parser getParser(String mimeType) {
 101         return parsers.get(mimeType);
 102     }
 103
 104     public MimeTypes getMimeRepository(){
 105         return mimeTypeRepo.getRepository();
 106     }
 107
 108     /**
 109      * Provides a default configuration (TikaConfig).  Currently creates a
 110      * new instance each time it's called; we may be able to have it
 111      * return a shared instance once it is completely immutable.
 112      *
 113      * @return
 114      * @throws IOException
 115      * @throws JDOMException
 116      */
 117     public static TikaConfig getDefaultConfig()
 118             throws IOException, JDOMException {
 119
 120         return new TikaConfig(
 121                 Utils.class.getResourceAsStream(DEFAULT_CONFIG_LOCATION));
 122     }
 123
 124 }