All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.lucene.analysis.NumericTokenStream Maven / Gradle / Ivy

There is a newer version: 2024.11.18751.20241128T090041Z-241100
Show newest version
/*
 * COPIED FROM APACHE LUCENE 4.7.2
 *
 * Git URL: [email protected]:apache/lucene.git, tag: releases/lucene-solr/4.7.2, path: lucene/core/src/java
 *
 * (see https://issues.apache.org/jira/browse/OAK-10786 for details)
 */

package org.apache.lucene.analysis;

/*
 * 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 org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.document.DoubleField; // for javadocs
import org.apache.lucene.document.FloatField; // for javadocs
import org.apache.lucene.document.IntField; // for javadocs
import org.apache.lucene.document.LongField; // for javadocs
import org.apache.lucene.search.NumericRangeFilter; // for javadocs
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.util.Attribute;
import org.apache.lucene.util.AttributeImpl;
import org.apache.lucene.util.AttributeReflector;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.NumericUtils;

/**
 * Expert: This class provides a {@link TokenStream}
 * for indexing numeric values that can be used by {@link
 * NumericRangeQuery} or {@link NumericRangeFilter}.
 *
 * 

Note that for simple usage, {@link IntField}, {@link * LongField}, {@link FloatField} or {@link DoubleField} is * recommended. These fields disable norms and * term freqs, as they are not usually needed during * searching. If you need to change these settings, you * should use this class. * *

Here's an example usage, for an int field: * *

 *  FieldType fieldType = new FieldType(TextField.TYPE_NOT_STORED);
 *  fieldType.setOmitNorms(true);
 *  fieldType.setIndexOptions(IndexOptions.DOCS_ONLY);
 *  Field field = new Field(name, new NumericTokenStream(precisionStep).setIntValue(value), fieldType);
 *  document.add(field);
 * 
* *

For optimal performance, re-use the TokenStream and Field instance * for more than one document: * *

 *  NumericTokenStream stream = new NumericTokenStream(precisionStep);
 *  FieldType fieldType = new FieldType(TextField.TYPE_NOT_STORED);
 *  fieldType.setOmitNorms(true);
 *  fieldType.setIndexOptions(IndexOptions.DOCS_ONLY);
 *  Field field = new Field(name, stream, fieldType);
 *  Document document = new Document();
 *  document.add(field);
 *
 *  for(all documents) {
 *    stream.setIntValue(value)
 *    writer.addDocument(document);
 *  }
 * 
* *

This stream is not intended to be used in analyzers; * it's more for iterating the different precisions during * indexing a specific numeric value.

*

NOTE: as token streams are only consumed once * the document is added to the index, if you index more * than one numeric field, use a separate NumericTokenStream * instance for each.

* *

See {@link NumericRangeQuery} for more details on the * precisionStep * parameter as well as how numeric fields work under the hood.

* * @since 2.9 */ public final class NumericTokenStream extends TokenStream { /** The full precision token gets this token type assigned. */ public static final String TOKEN_TYPE_FULL_PREC = "fullPrecNumeric"; /** The lower precision tokens gets this token type assigned. */ public static final String TOKEN_TYPE_LOWER_PREC = "lowerPrecNumeric"; /** Expert: Use this attribute to get the details of the currently generated token. * @lucene.experimental * @since 4.0 */ public interface NumericTermAttribute extends Attribute { /** Returns current shift value, undefined before first token */ int getShift(); /** Returns current token's raw value as {@code long} with all {@link #getShift} applied, undefined before first token */ long getRawValue(); /** Returns value size in bits (32 for {@code float}, {@code int}; 64 for {@code double}, {@code long}) */ int getValueSize(); /** Don't call this method! * @lucene.internal */ void init(long value, int valSize, int precisionStep, int shift); /** Don't call this method! * @lucene.internal */ void setShift(int shift); /** Don't call this method! * @lucene.internal */ int incShift(); } // just a wrapper to prevent adding CTA private static final class NumericAttributeFactory extends AttributeFactory { private final AttributeFactory delegate; NumericAttributeFactory(AttributeFactory delegate) { this.delegate = delegate; } @Override public AttributeImpl createAttributeInstance(Class attClass) { if (CharTermAttribute.class.isAssignableFrom(attClass)) throw new IllegalArgumentException("NumericTokenStream does not support CharTermAttribute."); return delegate.createAttributeInstance(attClass); } } /** Implementation of {@link NumericTermAttribute}. * @lucene.internal * @since 4.0 */ public static final class NumericTermAttributeImpl extends AttributeImpl implements NumericTermAttribute,TermToBytesRefAttribute { private long value = 0L; private int valueSize = 0, shift = 0, precisionStep = 0; private BytesRef bytes = new BytesRef(); /** * Creates, but does not yet initialize this attribute instance * @see #init(long, int, int, int) */ public NumericTermAttributeImpl() {} @Override public BytesRef getBytesRef() { return bytes; } @Override public int fillBytesRef() { assert valueSize == 64 || valueSize == 32; return (valueSize == 64) ? NumericUtils.longToPrefixCoded(value, shift, bytes) : NumericUtils.intToPrefixCoded((int) value, shift, bytes); } @Override public int getShift() { return shift; } @Override public void setShift(int shift) { this.shift = shift; } @Override public int incShift() { return (shift += precisionStep); } @Override public long getRawValue() { return value & ~((1L << shift) - 1L); } @Override public int getValueSize() { return valueSize; } @Override public void init(long value, int valueSize, int precisionStep, int shift) { this.value = value; this.valueSize = valueSize; this.precisionStep = precisionStep; this.shift = shift; } @Override public void clear() { // this attribute has no contents to clear! // we keep it untouched as it's fully controlled by outer class. } @Override public void reflectWith(AttributeReflector reflector) { fillBytesRef(); reflector.reflect(TermToBytesRefAttribute.class, "bytes", BytesRef.deepCopyOf(bytes)); reflector.reflect(NumericTermAttribute.class, "shift", shift); reflector.reflect(NumericTermAttribute.class, "rawValue", getRawValue()); reflector.reflect(NumericTermAttribute.class, "valueSize", valueSize); } @Override public void copyTo(AttributeImpl target) { final NumericTermAttribute a = (NumericTermAttribute) target; a.init(value, valueSize, precisionStep, shift); } } /** * Creates a token stream for numeric values using the default precisionStep * {@link NumericUtils#PRECISION_STEP_DEFAULT} (4). The stream is not yet initialized, * before using set a value using the various set???Value() methods. */ public NumericTokenStream() { this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, NumericUtils.PRECISION_STEP_DEFAULT); } /** * Creates a token stream for numeric values with the specified * precisionStep. The stream is not yet initialized, * before using set a value using the various set???Value() methods. */ public NumericTokenStream(final int precisionStep) { this(AttributeFactory.DEFAULT_ATTRIBUTE_FACTORY, precisionStep); } /** * Expert: Creates a token stream for numeric values with the specified * precisionStep using the given * {@link org.apache.lucene.util.AttributeSource.AttributeFactory}. * The stream is not yet initialized, * before using set a value using the various set???Value() methods. */ public NumericTokenStream(AttributeFactory factory, final int precisionStep) { super(new NumericAttributeFactory(factory)); if (precisionStep < 1) throw new IllegalArgumentException("precisionStep must be >=1"); this.precisionStep = precisionStep; numericAtt.setShift(-precisionStep); } /** * Initializes the token stream with the supplied long value. * @param value the value, for which this TokenStream should enumerate tokens. * @return this instance, because of this you can use it the following way: * new Field(name, new NumericTokenStream(precisionStep).setLongValue(value)) */ public NumericTokenStream setLongValue(final long value) { numericAtt.init(value, valSize = 64, precisionStep, -precisionStep); return this; } /** * Initializes the token stream with the supplied int value. * @param value the value, for which this TokenStream should enumerate tokens. * @return this instance, because of this you can use it the following way: * new Field(name, new NumericTokenStream(precisionStep).setIntValue(value)) */ public NumericTokenStream setIntValue(final int value) { numericAtt.init(value, valSize = 32, precisionStep, -precisionStep); return this; } /** * Initializes the token stream with the supplied double value. * @param value the value, for which this TokenStream should enumerate tokens. * @return this instance, because of this you can use it the following way: * new Field(name, new NumericTokenStream(precisionStep).setDoubleValue(value)) */ public NumericTokenStream setDoubleValue(final double value) { numericAtt.init(NumericUtils.doubleToSortableLong(value), valSize = 64, precisionStep, -precisionStep); return this; } /** * Initializes the token stream with the supplied float value. * @param value the value, for which this TokenStream should enumerate tokens. * @return this instance, because of this you can use it the following way: * new Field(name, new NumericTokenStream(precisionStep).setFloatValue(value)) */ public NumericTokenStream setFloatValue(final float value) { numericAtt.init(NumericUtils.floatToSortableInt(value), valSize = 32, precisionStep, -precisionStep); return this; } @Override public void reset() { if (valSize == 0) throw new IllegalStateException("call set???Value() before usage"); numericAtt.setShift(-precisionStep); } @Override public boolean incrementToken() { if (valSize == 0) throw new IllegalStateException("call set???Value() before usage"); // this will only clear all other attributes in this TokenStream clearAttributes(); final int shift = numericAtt.incShift(); typeAtt.setType((shift == 0) ? TOKEN_TYPE_FULL_PREC : TOKEN_TYPE_LOWER_PREC); posIncrAtt.setPositionIncrement((shift == 0) ? 1 : 0); return (shift < valSize); } /** Returns the precision step. */ public int getPrecisionStep() { return precisionStep; } // members private final NumericTermAttribute numericAtt = addAttribute(NumericTermAttribute.class); private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class); private int valSize = 0; // valSize==0 means not initialized private final int precisionStep; }




© 2015 - 2024 Weber Informatics LLC | Privacy Policy