dantuzi commented on code in PR #12169: URL: https://github.com/apache/lucene/pull/12169#discussion_r1158328631
########## lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/word2vec/Word2VecSynonymFilter.java: ########## @@ -0,0 +1,111 @@ +/* + * 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.analysis.synonym.word2vec; + +import java.io.IOException; +import java.util.LinkedList; +import java.util.List; +import org.apache.lucene.analysis.TokenFilter; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.synonym.SynonymGraphFilter; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; +import org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute; +import org.apache.lucene.analysis.tokenattributes.TypeAttribute; +import org.apache.lucene.search.BoostAttribute; +import org.apache.lucene.util.BytesRef; +import org.apache.lucene.util.BytesRefBuilder; +import org.apache.lucene.util.TermAndBoost; + +/** + * Applies single-token synonyms from a Word2Vec trained network to an incoming {@link TokenStream}. + * + * @lucene.experimental + */ +public final class Word2VecSynonymFilter extends TokenFilter { + + private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); + private final PositionIncrementAttribute posIncrementAtt = + addAttribute(PositionIncrementAttribute.class); + private final PositionLengthAttribute posLenAtt = addAttribute(PositionLengthAttribute.class); + private final BoostAttribute boostAtt = addAttribute(BoostAttribute.class); + private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); + + private final SynonymProvider synonymProvider; + private final int maxSynonymsPerTerm; + private final float minAcceptedSimilarity; + private final LinkedList<TermAndBoost> synonymBuffer = new LinkedList<>(); + private State lastState; + + /** + * Apply previously built synonymProvider to incoming tokens. + * + * @param input input tokenstream + * @param synonymProvider synonym provider + * @param maxSynonymsPerTerm maximum number of result returned by the synonym search + * @param minAcceptedSimilarity minimal value of cosine similarity between the searched vector and + * the retrieved ones + */ + public Word2VecSynonymFilter( + TokenStream input, + SynonymProvider synonymProvider, + int maxSynonymsPerTerm, + float minAcceptedSimilarity) { + super(input); + this.synonymProvider = synonymProvider; + this.maxSynonymsPerTerm = maxSynonymsPerTerm; + this.minAcceptedSimilarity = minAcceptedSimilarity; + } + + @Override + public boolean incrementToken() throws IOException { + + if (!synonymBuffer.isEmpty()) { + TermAndBoost synonym = synonymBuffer.pollFirst(); + clearAttributes(); + restoreState(this.lastState); + termAtt.setEmpty(); Review Comment: This is a good idea, I tried your suggestion and it is much cleaner but it doesn't pass the unit tests because the `BytesTermAttribute` contains a null ByteRef. I don't have much more time now to dedicate to this contribution. Feel free to change it once merged -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
