1 package org.apache.lucene.search.highlight;
3 * Licensed to the Apache Software Foundation (ASF) under one or more
4 * contributor license agreements. See the NOTICE file distributed with
5 * this work for additional information regarding copyright ownership.
6 * The ASF licenses this file to You under the Apache License, Version 2.0
7 * (the "License"); you may not use this file except in compliance with
8 * the License. You may obtain a copy of the License at
10 * http://www.apache.org/licenses/LICENSE-2.0
12 * Unless required by applicable law or agreed to in writing, software
13 * distributed under the License is distributed on an "AS IS" BASIS,
14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 * See the License for the specific language governing permissions and
16 * limitations under the License.
19 import java.io.IOException;
20 import java.util.HashSet;
21 import java.util.Iterator;
23 import org.apache.lucene.index.IndexReader;
24 import org.apache.lucene.index.Term;
25 import org.apache.lucene.search.BooleanClause;
26 import org.apache.lucene.search.BooleanQuery;
27 import org.apache.lucene.search.FilteredQuery;
28 import org.apache.lucene.search.Query;
29 import org.apache.lucene.util.StringHelper;
32 * Utility class used to extract the terms used in a query, plus any weights.
33 * This class will not find terms for MultiTermQuery, TermRangeQuery and PrefixQuery classes
34 * so the caller must pass a rewritten query (see Query.rewrite) to obtain a list of
38 public final class QueryTermExtractor
42 * Extracts all terms texts of a given Query into an array of WeightedTerms
44 * @param query Query to extract term texts from
45 * @return an array of the terms used in a query, plus their weights.
47 public static final WeightedTerm[] getTerms(Query query)
49 return getTerms(query,false);
53 * Extracts all terms texts of a given Query into an array of WeightedTerms
55 * @param query Query to extract term texts from
56 * @param reader used to compute IDF which can be used to a) score selected fragments better
57 * b) use graded highlights eg changing intensity of font color
58 * @param fieldName the field on which Inverse Document Frequency (IDF) calculations are based
59 * @return an array of the terms used in a query, plus their weights.
61 public static final WeightedTerm[] getIdfWeightedTerms(Query query, IndexReader reader, String fieldName)
63 WeightedTerm[] terms=getTerms(query,false, fieldName);
64 int totalNumDocs=reader.numDocs();
65 for (int i = 0; i < terms.length; i++)
69 int docFreq=reader.docFreq(new Term(fieldName,terms[i].term));
70 // docFreq counts deletes
71 if(totalNumDocs < docFreq) {
72 docFreq = totalNumDocs;
74 //IDF algorithm taken from DefaultSimilarity class
75 float idf=(float)(Math.log((float)totalNumDocs/(double)(docFreq+1)) + 1.0);
87 * Extracts all terms texts of a given Query into an array of WeightedTerms
89 * @param query Query to extract term texts from
90 * @param prohibited <code>true</code> to extract "prohibited" terms, too
91 * @param fieldName The fieldName used to filter query terms
92 * @return an array of the terms used in a query, plus their weights.
94 public static final WeightedTerm[] getTerms(Query query, boolean prohibited, String fieldName)
96 HashSet<WeightedTerm> terms=new HashSet<WeightedTerm>();
99 fieldName= StringHelper.intern(fieldName);
101 getTerms(query,terms,prohibited,fieldName);
102 return terms.toArray(new WeightedTerm[0]);
106 * Extracts all terms texts of a given Query into an array of WeightedTerms
108 * @param query Query to extract term texts from
109 * @param prohibited <code>true</code> to extract "prohibited" terms, too
110 * @return an array of the terms used in a query, plus their weights.
112 public static final WeightedTerm[] getTerms(Query query, boolean prohibited)
114 return getTerms(query,prohibited,null);
117 //fieldname MUST be interned prior to this call
118 private static final void getTerms(Query query, HashSet<WeightedTerm> terms,boolean prohibited, String fieldName)
122 if (query instanceof BooleanQuery)
123 getTermsFromBooleanQuery((BooleanQuery) query, terms, prohibited, fieldName);
125 if(query instanceof FilteredQuery)
126 getTermsFromFilteredQuery((FilteredQuery)query, terms,prohibited, fieldName);
129 HashSet<Term> nonWeightedTerms=new HashSet<Term>();
130 query.extractTerms(nonWeightedTerms);
131 for (Iterator<Term> iter = nonWeightedTerms.iterator(); iter.hasNext();)
133 Term term = iter.next();
134 if((fieldName==null)||(term.field()==fieldName))
136 terms.add(new WeightedTerm(query.getBoost(),term.text()));
141 catch(UnsupportedOperationException ignore)
143 //this is non-fatal for our purposes
148 * extractTerms is currently the only query-independent means of introspecting queries but it only reveals
149 * a list of terms for that query - not the boosts each individual term in that query may or may not have.
150 * "Container" queries such as BooleanQuery should be unwrapped to get at the boost info held
151 * in each child element.
152 * Some discussion around this topic here:
153 * http://www.gossamer-threads.com/lists/lucene/java-dev/34208?search_string=introspection;#34208
154 * Unfortunately there seemed to be limited interest in requiring all Query objects to implement
155 * something common which would allow access to child queries so what follows here are query-specific
156 * implementations for accessing embedded query elements.
158 private static final void getTermsFromBooleanQuery(BooleanQuery query, HashSet<WeightedTerm> terms, boolean prohibited, String fieldName)
160 BooleanClause[] queryClauses = query.getClauses();
161 for (int i = 0; i < queryClauses.length; i++)
163 if (prohibited || queryClauses[i].getOccur()!=BooleanClause.Occur.MUST_NOT)
164 getTerms(queryClauses[i].getQuery(), terms, prohibited, fieldName);
167 private static void getTermsFromFilteredQuery(FilteredQuery query, HashSet<WeightedTerm> terms, boolean prohibited, String fieldName)
169 getTerms(query.getQuery(),terms,prohibited,fieldName);