DocMetadataExtractor.java

package org.apache.lucene.search.concordance.classic;

/*
 * 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.
 */

import java.util.Map;
import java.util.Set;
import org.apache.lucene.document.Document;

/**
 * Simple interface for a component that extracts metadata from
 * a document to be stored with a ConcordanceWindow
 */
public interface DocMetadataExtractor {

  /**
   * @return the fields that need to be retrieved for the document
   * for proper processing
   */
  Set<String> getFieldSelector();

  /**
   * @param document to be processed for metadata.  Only those fields
   *                 that were returned by {@link #getFieldSelector()} will be loaded
   *                 in the document
   * @return document metadata to be stored with each window
   */
  Map<String, String> extract(Document document);

}