org.apache.lucene.search.suggest.document.SuggestIndexSearcher Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of lucene-suggest Show documentation
Apache Lucene (module: suggest)
There is a newer version: 10.0.0
/*
 * 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.document;

import java.io.IOException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.search.BulkScorer;
import org.apache.lucene.search.CollectionTerminatedException;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.LeafCollector;
import org.apache.lucene.search.Weight;

/**
 * Adds document suggest capabilities to IndexSearcher. Any {@link CompletionQuery} can be used to
 * suggest documents.
 *
 * Use {@link PrefixCompletionQuery} for analyzed prefix queries, {@link RegexCompletionQuery}
 * for regular expression prefix queries, {@link FuzzyCompletionQuery} for analyzed prefix with typo
 * tolerance and {@link ContextQuery} to boost and/or filter suggestions by contexts
 *
 * @lucene.experimental
 */
public class SuggestIndexSearcher extends IndexSearcher {

  // NOTE: we do not accept an ExecutorService here, because at least the dedup
  // logic in TopSuggestDocsCollector/NRTSuggester would not be thread safe (and maybe other things)

  /** Creates a searcher with document suggest capabilities for reader. */
  public SuggestIndexSearcher(IndexReader reader) {
    super(reader);
  }

  /** Returns top n completion hits for query */
  public TopSuggestDocs suggest(CompletionQuery query, int n, boolean skipDuplicates)
      throws IOException {
    TopSuggestDocsCollector collector = new TopSuggestDocsCollector(n, skipDuplicates);
    suggest(query, collector);
    return collector.get();
  }

  /**
   * Lower-level suggest API. Collects completion hits through collector for 
   * query.
   *
   * {@link TopSuggestDocsCollector#collect(int, CharSequence, CharSequence, float)} is called
   * for every matching completion hit.
   */
  public void suggest(CompletionQuery query, TopSuggestDocsCollector collector) throws IOException {
    // TODO use IndexSearcher.rewrite instead
    // have to implement equals() and hashCode() in CompletionQuerys and co
    query = (CompletionQuery) query.rewrite(this);
    Weight weight = query.createWeight(this, collector.scoreMode(), 1f);
    for (LeafReaderContext context : getIndexReader().leaves()) {
      BulkScorer scorer = weight.bulkScorer(context);
      if (scorer != null) {
        LeafCollector leafCollector = null;
        try {
          leafCollector = collector.getLeafCollector(context);
          scorer.score(leafCollector, context.reader().getLiveDocs());
        } catch (
            @SuppressWarnings("unused")
            CollectionTerminatedException e) {
          // collection was terminated prematurely
          // continue with the following leaf
        }
        if (leafCollector != null) {
          leafCollector.finish();
        }
      }
    }
  }
}