siddharthteotia commented on a change in pull request #4993: Support Text Search (both offline and realtime) URL: https://github.com/apache/incubator-pinot/pull/4993#discussion_r367830796
########## File path: pinot-core/src/main/java/org/apache/pinot/core/operator/filter/TextMatchFilterOperator.java ########## @@ -0,0 +1,67 @@ +/** + * 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.pinot.core.operator.filter; + +import com.google.common.base.Preconditions; +import org.apache.pinot.core.common.DataSource; +import org.apache.pinot.core.common.Predicate; +import org.apache.pinot.core.operator.blocks.FilterBlock; +import org.apache.pinot.core.operator.docidsets.LuceneIndexDocIdSet; +import org.apache.pinot.core.operator.filter.predicate.PredicateEvaluator; +import org.apache.pinot.core.operator.filter.predicate.TextMatchPredicateEvaluatorFactory; +import org.apache.pinot.core.segment.index.readers.InvertedIndexReader; +import org.apache.pinot.core.segment.index.readers.text.LuceneTextIndexReader; + + +/** + * Filter operator for supporting the execution of text search + * queries: WHERE TEXT_MATCH(column_name, query_string....) + */ +public class TextMatchFilterOperator extends BaseFilterOperator { + private static final String OPERATOR_NAME = "TextMatchFilterOperator"; + + private final Predicate _predicate; + private final DataSource _dataSource; + private final int _startDocId; + private final int _endDocId; + + public TextMatchFilterOperator(PredicateEvaluator predicateEvaluator, DataSource dataSource, int startDocId, int endDocId) { + Preconditions.checkArgument(predicateEvaluator instanceof TextMatchPredicateEvaluatorFactory.RawValueBasedTextMatchPredicateEvaluator && + !predicateEvaluator.isAlwaysTrue() && !predicateEvaluator.isAlwaysFalse()); + TextMatchPredicateEvaluatorFactory.RawValueBasedTextMatchPredicateEvaluator evaluator = (TextMatchPredicateEvaluatorFactory.RawValueBasedTextMatchPredicateEvaluator)predicateEvaluator; + _predicate = evaluator.getPredicate(); + _dataSource = dataSource; + _startDocId = startDocId; + _endDocId = endDocId; + } + + @Override + protected FilterBlock getNextBlock() { + InvertedIndexReader textIndexReader = _dataSource.getInvertedIndex(); + Preconditions.checkNotNull(textIndexReader, "Error: expecting non-null text index"); + LuceneTextIndexReader.LuceneSearchResult luceneSearchResult = (LuceneTextIndexReader.LuceneSearchResult)textIndexReader.getDocIds(_predicate); + // TODO: For the next iteration of this feature, consider using BitMapDocIdSet (and BitMapDocIdIterator) Review comment: Discussed offline. Using BitMapDocIdSet is better for general cases. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org