View Javadoc

1   // BSD License (http://www.galagosearch.org/license)
2   
3   package org.galagosearch.core.parse;
4   
5   import org.galagosearch.tupleflow.InputClass;
6   import org.galagosearch.tupleflow.OutputClass;
7   import org.galagosearch.tupleflow.StandardStep;
8   import org.galagosearch.tupleflow.execution.Verified;
9   import java.io.IOException;
10  import org.galagosearch.core.types.DocumentExtent;
11  
12  /***
13   * Converts all tags from a document object into DocumentExtent tuples.
14   * @author trevor
15   */
16  @InputClass(className = "org.galagosearch.core.parse.Document")
17  @OutputClass(className = "org.galagosearch.core.types.DocumentExtent")
18  @Verified
19  public class ExtentExtractor extends StandardStep<Document, DocumentExtent> {
20      public void process(Document document) throws IOException {
21          for (Tag tag : document.tags) {
22              processor.process(new DocumentExtent(tag.name,
23                      document.identifier,
24                      tag.begin,
25                      tag.end));
26          }
27      }
28  }