|
Lucene example source code file (QueryTermExtractor.java)
The Lucene QueryTermExtractor.java source codepackage org.apache.lucene.search.highlight; /** * 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. */ import java.io.IOException; import java.util.HashSet; import java.util.Iterator; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.Term; import org.apache.lucene.search.BooleanClause; import org.apache.lucene.search.BooleanQuery; import org.apache.lucene.search.FilteredQuery; import org.apache.lucene.search.Query; import org.apache.lucene.util.StringHelper; /** * Utility class used to extract the terms used in a query, plus any weights. * This class will not find terms for MultiTermQuery, TermRangeQuery and PrefixQuery classes * so the caller must pass a rewritten query (see Query.rewrite) to obtain a list of * expanded terms. * */ public final class QueryTermExtractor { /** * Extracts all terms texts of a given Query into an array of WeightedTerms * * @param query Query to extract term texts from * @return an array of the terms used in a query, plus their weights. */ public static final WeightedTerm[] getTerms(Query query) { return getTerms(query,false); } /** * Extracts all terms texts of a given Query into an array of WeightedTerms * * @param query Query to extract term texts from * @param reader used to compute IDF which can be used to a) score selected fragments better * b) use graded highlights eg changing intensity of font color * @param fieldName the field on which Inverse Document Frequency (IDF) calculations are based * @return an array of the terms used in a query, plus their weights. */ public static final WeightedTerm[] getIdfWeightedTerms(Query query, IndexReader reader, String fieldName) { WeightedTerm[] terms=getTerms(query,false, fieldName); int totalNumDocs=reader.numDocs(); for (int i = 0; i < terms.length; i++) { try { int docFreq=reader.docFreq(new Term(fieldName,terms[i].term)); // docFreq counts deletes if(totalNumDocs < docFreq) { docFreq = totalNumDocs; } //IDF algorithm taken from DefaultSimilarity class float idf=(float)(Math.log((float)totalNumDocs/(double)(docFreq+1)) + 1.0); terms[i].weight*=idf; } catch (IOException e) { //ignore } } return terms; } /** * Extracts all terms texts of a given Query into an array of WeightedTerms * * @param query Query to extract term texts from * @param prohibited <code>true to extract "prohibited" terms, too * @param fieldName The fieldName used to filter query terms * @return an array of the terms used in a query, plus their weights. */ public static final WeightedTerm[] getTerms(Query query, boolean prohibited, String fieldName) { HashSet<WeightedTerm> terms=new HashSet Other Lucene examples (source code examples)Here is a short list of links related to this Lucene QueryTermExtractor.java source code file: |
... this post is sponsored by my books ... | |
#1 New Release! |
FP Best Seller |
Copyright 1998-2021 Alvin Alexander, alvinalexander.com
All Rights Reserved.
A percentage of advertising revenue from
pages under the /java/jwarehouse
URI on this website is
paid back to open source projects.