src/main/java/org/apache/tika/parser/ParserPostProcessor.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.parser;
  18
  19 import java.io.IOException;
  20 import java.io.InputStream;
  21
  22 import org.apache.tika.exception.TikaException;
  23 import org.apache.tika.metadata.Metadata;
  24 import org.apache.tika.sax.BodyContentHandler;
  25 import org.apache.tika.sax.TeeContentHandler;
  26 import org.apache.tika.utils.RegexUtils;
  27 import org.xml.sax.ContentHandler;
  28 import org.xml.sax.SAXException;
  29
  30 /**
  31  * Parser decorator that post-processes the results from a decorated parser.
  32  * The post-processing takes care of filling in any "fulltext", "summary", and
  33  * regexp {@link Content} objects with the full text content returned by
  34  * the decorated parser. The post-processing also catches and logs any
  35  * exceptions thrown by the decorated parser.
  36  */
  37 public class ParserPostProcessor extends ParserDecorator {
  38
  39     /**
  40      * Creates a post-processing decorator for the given parser.
  41      *
  42      * @param parser the parser to be decorated
  43      */
  44     public ParserPostProcessor(Parser parser) {
  45         super(parser);
  46     }
  47
  48     /**
  49      * Forwards the call to the delegated parser and post-processes the
  50      * results as described above.
  51      */
  52     public void parse(
  53             InputStream stream, ContentHandler handler, Metadata metadata)
  54             throws IOException, SAXException, TikaException {
  55         ContentHandler body = new BodyContentHandler();
  56         super.parse(stream, new TeeContentHandler(handler, body), metadata);
  57
  58         String content = body.toString();
  59         metadata.set("fulltext", content);
  60
  61         int length = Math.min(content.length(), 500);
  62         metadata.set("summary", content.substring(0, length));
  63
  64         for (String link : RegexUtils.extractLinks(content)) {
  65             metadata.add("outlinks", link);
  66         }
  67     }
  68
  69 }