MetaTagsIndexer.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.nutch.indexer;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.Text;
import org.apache.nutch.crawl.CrawlDatum;
import org.apache.nutch.crawl.Inlinks;
import org.apache.nutch.indexer.lucene.LuceneWriter;
import org.apache.nutch.metadata.Metadata;
import org.apache.nutch.parse.Parse;

/**
 * Indexes field description and keywords provided by the metataparser Note that
 * we limit ourselves to these 2 types of metadata as we must specify the exact
 * values in addIndexBackendOptions
 **/
public class MetaTagsIndexer implements IndexingFilter {
  
  public static final Log LOG = LogFactory.getLog(MetaTagsIndexer.class
      .getName());
  
  private Configuration conf;
  
  public NutchDocument filter(NutchDocument doc, Parse parse, Text url,
      CrawlDatum datum, Inlinks inlinks) throws IndexingException {
    
    Metadata metadata = parse.getData().getParseMeta();
    
    String description = metadata.get("metatag.description");
    String keywords = metadata.get("metatag.keywords");
    
    if (description != null) {
      doc.add("description", description);
      LOG.debug(url.toString() + " : added " + description
          + " to the description Field");
    }
    
    if (keywords != null) {
      // split the keywords and send them as separate fields
      // in SOLR this will allow us to specify a gap in order to prevent
      // cross keywords matching
      String[] kws = keywords.split(" *, *");
      for (String kw : kws) {
        doc.add("keywords", kw);
      }
      LOG.debug(url.toString() + " : added " + kws + " to the keywords Field");
    }
    
    return doc;
    
  }
  
  public void setConf(Configuration conf) {
    this.conf = conf;
  }
  
  public Configuration getConf() {
    return this.conf;
  }
  
  public void addIndexBackendOptions(Configuration conf) {
    LuceneWriter.addFieldOptions("description", LuceneWriter.STORE.YES,
        LuceneWriter.INDEX.TOKENIZED, conf);
    LuceneWriter.addFieldOptions("keywords", LuceneWriter.STORE.NO,
        LuceneWriter.INDEX.TOKENIZED, conf);
  }
  
}