org.apache.lucene.search.suggest.DocumentValueSourceDictionary Maven / Gradle / Ivy

Go to download
/*
 * 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.lucene.search.suggest;

import java.io.IOException;
import java.util.List;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.ReaderUtil;
import org.apache.lucene.search.LongValues;
import org.apache.lucene.search.LongValuesSource;

/**
 * Dictionary with terms and optionally payload and optionally contexts information taken from
 * stored fields in a Lucene index. Similar to {@link DocumentDictionary}, except it obtains the
 * weight of the terms in a document based on a {@link LongValuesSource}. NOTE:
 *
 * 
 *   The term field has to be stored; if it is missing, the document is skipped.
 *   
The payload and contexts field are optional and are not required to be stored.
 * 
 *
 * In practice the {@link LongValuesSource} will likely be obtained using the lucene expression
 * module. The following example shows how to create a {@link LongValuesSource} from a simple
 * addition of two fields: 
 *    Expression expression = JavascriptCompiler.compile("f1 + f2");
 *    SimpleBindings bindings = new SimpleBindings();
 *    bindings.add("f1", DoubleValuesSource.fromLongField("f1"));
 *    bindings.add("f2", DoubleValuesSource.fromLongField("f2"));
 *    LongValuesSource valueSource = expression.getDoubleValuesSource(bindings).toLongValuesSource();
 *  
 */
public class DocumentValueSourceDictionary extends DocumentDictionary {

  private final LongValuesSource weightsValueSource;

  /**
   * Creates a new dictionary with the contents of the fields named field for the
   * terms, payload for the corresponding payloads, contexts for the
   * associated contexts and uses the weightsValueSource supplied to determine the
   * score.
   */
  public DocumentValueSourceDictionary(
      IndexReader reader,
      String field,
      LongValuesSource weightsValueSource,
      String payload,
      String contexts)
      throws IOException {
    super(reader, field, null, payload, contexts);
    this.weightsValueSource = weightsValueSource;
  }

  /**
   * Creates a new dictionary with the contents of the fields named field for the
   * terms, payloadField for the corresponding payloads and uses the 
   * weightsValueSource supplied to determine the score.
   */
  public DocumentValueSourceDictionary(
      IndexReader reader, String field, LongValuesSource weightsValueSource, String payload)
      throws IOException {
    super(reader, field, null, payload);
    this.weightsValueSource = weightsValueSource;
  }

  /**
   * Creates a new dictionary with the contents of the fields named field for the terms
   * and uses the weightsValueSource supplied to determine the score.
   */
  public DocumentValueSourceDictionary(
      IndexReader reader, String field, LongValuesSource weightsValueSource) throws IOException {
    super(reader, field, null, null);
    this.weightsValueSource = weightsValueSource;
  }

  @Override
  public InputIterator getEntryIterator() throws IOException {
    return new DocumentValueSourceInputIterator(payloadField != null, contextsField != null);
  }

  final class DocumentValueSourceInputIterator extends DocumentDictionary.DocumentInputIterator {

    private LongValues currentWeightValues;

    /** leaves of the reader */
    private final List leaves;

    /** starting docIds of all the leaves */
    private final int[] starts;

    /** current leave index */
    private int currentLeafIndex = 0;

    public DocumentValueSourceInputIterator(boolean hasPayloads, boolean hasContexts)
        throws IOException {
      super(hasPayloads, hasContexts);
      leaves = reader.leaves();
      starts = new int[leaves.size() + 1];
      for (int i = 0; i < leaves.size(); i++) {
        starts[i] = leaves.get(i).docBase;
      }
      starts[leaves.size()] = reader.maxDoc();
      currentWeightValues =
          (leaves.size() > 0)
              ? weightsValueSource.getValues(leaves.get(currentLeafIndex), null)
              : null;
    }

    /**
     * Returns the weight for the current docId as computed by the 
     * weightsValueSource
     */
    @Override
    protected long getWeight(Document doc, int docId) throws IOException {
      if (currentWeightValues == null) {
        return 0;
      }
      int subIndex = ReaderUtil.subIndex(docId, starts);
      if (subIndex != currentLeafIndex) {
        currentLeafIndex = subIndex;
        currentWeightValues = weightsValueSource.getValues(leaves.get(currentLeafIndex), null);
      }
      if (currentWeightValues.advanceExact(docId - starts[subIndex])) {
        return currentWeightValues.longValue();
      } else {
        return 0;
      }
    }
  }
}