1 package org.apache.lucene.index;
3 * Copyright 2007 The Apache Software Foundation
5 * Licensed under the Apache License, Version 2.0 (the "License");
6 * you may not use this file except in compliance with the License.
7 * You may obtain a copy of the License at
9 * http://www.apache.org/licenses/LICENSE-2.0
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
20 * The TermVectorMapper can be used to map Term Vectors into your own
21 * structure instead of the parallel array structure used by
22 * {@link org.apache.lucene.index.IndexReader#getTermFreqVector(int,String)}.
24 * It is up to the implementation to make sure it is thread-safe.
28 public abstract class TermVectorMapper {
30 private boolean ignoringPositions;
31 private boolean ignoringOffsets;
34 protected TermVectorMapper() {
39 * @param ignoringPositions true if this mapper should tell Lucene to ignore positions even if they are stored
40 * @param ignoringOffsets similar to ignoringPositions
42 protected TermVectorMapper(boolean ignoringPositions, boolean ignoringOffsets) {
43 this.ignoringPositions = ignoringPositions;
44 this.ignoringOffsets = ignoringOffsets;
48 * Tell the mapper what to expect in regards to field, number of terms, offset and position storage.
49 * This method will be called once before retrieving the vector for a field.
51 * This method will be called before {@link #map(String,int,TermVectorOffsetInfo[],int[])}.
52 * @param field The field the vector is for
53 * @param numTerms The number of terms that need to be mapped
54 * @param storeOffsets true if the mapper should expect offset information
55 * @param storePositions true if the mapper should expect positions info
57 public abstract void setExpectations(String field, int numTerms, boolean storeOffsets, boolean storePositions);
59 * Map the Term Vector information into your own structure
60 * @param term The term to add to the vector
61 * @param frequency The frequency of the term in the document
62 * @param offsets null if the offset is not specified, otherwise the offset into the field of the term
63 * @param positions null if the position is not specified, otherwise the position in the field of the term
65 public abstract void map(String term, int frequency, TermVectorOffsetInfo [] offsets, int [] positions);
68 * Indicate to Lucene that even if there are positions stored, this mapper is not interested in them and they
69 * can be skipped over. Derived classes should set this to true if they want to ignore positions. The default
70 * is false, meaning positions will be loaded if they are stored.
73 public boolean isIgnoringPositions()
75 return ignoringPositions;
80 * @see #isIgnoringPositions() Same principal as {@link #isIgnoringPositions()}, but applied to offsets. false by default.
83 public boolean isIgnoringOffsets()
85 return ignoringOffsets;
89 * Passes down the index of the document whose term vector is currently being mapped,
90 * once for each top level call to a term vector reader.
92 * Default implementation IGNORES the document number. Override if your implementation needs the document number.
94 * NOTE: Document numbers are internal to Lucene and subject to change depending on indexing operations.
96 * @param documentNumber index of document currently being mapped
98 public void setDocumentNumber(int documentNumber) {