net.sf.okapi.lib.search.lucene.query.TmFuzzyQuery Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of okapi-lib Show documentation
There is a newer version: 1.47.0
package net.sf.okapi.lib.search.lucene.query;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Set;

import net.sf.okapi.lib.search.lucene.scorer.TmFuzzyScorer;

import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.*;


@SuppressWarnings("serial")
public class TmFuzzyQuery extends Query {
	float threshold;
	List terms;
	String termCountField;

	public TmFuzzyQuery(float threshold, String termCountField) {
		this.threshold = threshold;
		this.terms = new ArrayList<>();
		this.termCountField = termCountField;
	}

	public void add(Term term) {
		terms.add(term);
	}

	@Override
	public Weight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException {
		return new TmFuzzyWeight(this);
	}

	@Override
	public Query rewrite(IndexReader reader) throws IOException {
		return this; // Is this acceptable? This query isn't made of other Query objects...
	}

	// equals and hashCode were generated by Intellij Idea
	@Override
	public boolean equals(Object o) {
		if (this == o) return true;
		if (!(o instanceof TmFuzzyQuery)) return false;

		TmFuzzyQuery that = (TmFuzzyQuery) o;

		if (Float.compare(that.threshold, threshold) != 0) return false;
		if (!terms.equals(that.terms)) return false;
		return termCountField.equals(that.termCountField);
	}

	@Override
	public int hashCode() {
		int result = (threshold != +0.0f ? Float.floatToIntBits(threshold) : 0);
		result = 31 * result + terms.hashCode();
		result = 31 * result + termCountField.hashCode();
		return result;
	}

	@Override
	public String toString(String field) {
		return terms.toString();
	}

	protected class TmFuzzyWeight extends Weight {

		public TmFuzzyWeight(Query query) throws IOException {
			super(query);
		}

		@Override
		public void extractTerms(Set set) {
			/*
			 * This is deprecated.  Following the suggestion found in Weight#extractTerms(Set):
			 * Use Query.visit(QueryVisitor) with QueryVisitor.termCollector(Set)
 			*/
			getQuery().visit(QueryVisitor.termCollector(set));
		}

		@Override
		public Explanation explain(LeafReaderContext leafReaderContext, int i) throws IOException {
			//TODO:Implement me

			// Was:	return new Explanation(getValue(), toString());
			/* Hint. This is what explain looks like for TermQuery.TermWeight
			  TermScorer scorer = (TermScorer) scorer(context);
			  if (scorer != null) {
				int newDoc = scorer.iterator().advance(doc);
				if (newDoc == doc) {
				  float freq = scorer.freq();
				  LeafSimScorer docScorer = new LeafSimScorer(simScorer, context.reader(), term.field(), true);
				  Explanation freqExplanation = Explanation.match(freq, "freq, occurrences of term within document");
				  Explanation scoreExplanation = docScorer.explain(doc, freqExplanation);
				  return Explanation.match(
					  scoreExplanation.getValue(),
					  "weight(" + getQuery() + " in " + doc + ") ["
						  + similarity.getClass().getSimpleName() + "], result of:",
					  scoreExplanation);
				}
			  }
			  return Explanation.noMatch("no matching term");

			 */
			return Explanation.match(Float.valueOf(1.0f), "Sorry, TmFuzzyWeight.explain(...) not fully implemented");
		}

		@Override
		public Scorer scorer(LeafReaderContext leafReaderContext) throws IOException {
			// optimize zero-term or no match case
			if (terms.size() == 0)
				return null;

			return new TmFuzzyScorer(threshold, this, terms, leafReaderContext.reader(), termCountField);
		}

		@Override
		public boolean isCacheable(LeafReaderContext leafReaderContext) {
			return false;
		}
	}
}