org.elasticsearch.index.mapper.core.TokenCountFieldMapper Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of org.apache.servicemix.bundles.elasticsearch
Show all versions of org.apache.servicemix.bundles.elasticsearch
This OSGi bundle wraps ${pkgArtifactId} ${pkgVersion} jar file.
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch 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.elasticsearch.index.mapper.core;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.FieldType;
import org.elasticsearch.common.Explicit;
import org.elasticsearch.common.Strings;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.xcontent.XContentBuilder;
import org.elasticsearch.index.analysis.NamedAnalyzer;
import org.elasticsearch.index.codec.docvaluesformat.DocValuesFormatProvider;
import org.elasticsearch.index.codec.postingsformat.PostingsFormatProvider;
import org.elasticsearch.index.mapper.*;
import org.elasticsearch.index.mapper.core.StringFieldMapper.ValueAndBoost;
import org.elasticsearch.index.similarity.SimilarityProvider;
import java.io.IOException;
import java.util.List;
import java.util.Map;
import static org.elasticsearch.common.xcontent.support.XContentMapValues.nodeIntegerValue;
import static org.elasticsearch.index.mapper.MapperBuilders.tokenCountField;
import static org.elasticsearch.index.mapper.core.TypeParsers.parseNumberField;
/**
* A {@link FieldMapper} that takes a string and writes a count of the tokens in that string
* to the index. In most ways the mapper acts just like an {@link IntegerFieldMapper}.
*/
public class TokenCountFieldMapper extends IntegerFieldMapper {
public static final String CONTENT_TYPE = "token_count";
public static class Defaults extends IntegerFieldMapper.Defaults {
}
public static class Builder extends NumberFieldMapper.Builder {
private Integer nullValue = Defaults.NULL_VALUE;
private NamedAnalyzer analyzer;
public Builder(String name) {
super(name, new FieldType(Defaults.FIELD_TYPE), Defaults.PRECISION_STEP_32_BIT);
builder = this;
}
public Builder nullValue(int nullValue) {
this.nullValue = nullValue;
return this;
}
public Builder analyzer(NamedAnalyzer analyzer) {
this.analyzer = analyzer;
return this;
}
public NamedAnalyzer analyzer() {
return analyzer;
}
@Override
public TokenCountFieldMapper build(BuilderContext context) {
fieldType.setOmitNorms(fieldType.omitNorms() && boost == 1.0f);
TokenCountFieldMapper fieldMapper = new TokenCountFieldMapper(buildNames(context), fieldType.numericPrecisionStep(), boost, fieldType, docValues, nullValue,
ignoreMalformed(context), coerce(context), postingsProvider, docValuesProvider, similarity, normsLoading, fieldDataSettings, context.indexSettings(),
analyzer, multiFieldsBuilder.build(this, context), copyTo);
fieldMapper.includeInAll(includeInAll);
return fieldMapper;
}
}
public static class TypeParser implements Mapper.TypeParser {
@Override
@SuppressWarnings("unchecked")
public Mapper.Builder parse(String name, Map node, ParserContext parserContext) throws MapperParsingException {
TokenCountFieldMapper.Builder builder = tokenCountField(name);
parseNumberField(builder, name, node, parserContext);
for (Map.Entry entry : node.entrySet()) {
String propName = Strings.toUnderscoreCase(entry.getKey());
Object propNode = entry.getValue();
if (propName.equals("null_value")) {
builder.nullValue(nodeIntegerValue(propNode));
} else if (propName.equals("analyzer")) {
NamedAnalyzer analyzer = parserContext.analysisService().analyzer(propNode.toString());
if (analyzer == null) {
throw new MapperParsingException("Analyzer [" + propNode.toString() + "] not found for field [" + name + "]");
}
builder.analyzer(analyzer);
}
}
if (builder.analyzer() == null) {
throw new MapperParsingException("Analyzer must be set for field [" + name + "] but wasn't.");
}
return builder;
}
}
private NamedAnalyzer analyzer;
protected TokenCountFieldMapper(Names names, int precisionStep, float boost, FieldType fieldType, Boolean docValues, Integer nullValue,
Explicit ignoreMalformed, Explicit coerce, PostingsFormatProvider postingsProvider, DocValuesFormatProvider docValuesProvider,
SimilarityProvider similarity, Loading normsLoading, Settings fieldDataSettings, Settings indexSettings, NamedAnalyzer analyzer,
MultiFields multiFields, CopyTo copyTo) {
super(names, precisionStep, boost, fieldType, docValues, nullValue, ignoreMalformed, coerce, postingsProvider, docValuesProvider,
similarity, normsLoading, fieldDataSettings, indexSettings, multiFields, copyTo);
this.analyzer = analyzer;
}
@Override
protected void parseCreateField(ParseContext context, List fields) throws IOException {
ValueAndBoost valueAndBoost = StringFieldMapper.parseCreateFieldForString(context, null /* Out null value is an int so we convert*/, boost);
if (valueAndBoost.value() == null && nullValue() == null) {
return;
}
if (fieldType.indexed() || fieldType.stored() || hasDocValues()) {
int count;
if (valueAndBoost.value() == null) {
count = nullValue();
} else {
count = countPositions(analyzer.analyzer().tokenStream(name(), valueAndBoost.value()));
}
addIntegerFields(context, fields, count, valueAndBoost.boost());
}
if (fields.isEmpty()) {
context.ignoredValue(names.indexName(), valueAndBoost.value());
}
}
/**
* Count position increments in a token stream. Package private for testing.
* @param tokenStream token stream to count
* @return number of position increments in a token stream
* @throws IOException if tokenStream throws it
*/
static int countPositions(TokenStream tokenStream) throws IOException {
try {
int count = 0;
PositionIncrementAttribute position = tokenStream.addAttribute(PositionIncrementAttribute.class);
tokenStream.reset();
while (tokenStream.incrementToken()) {
count += position.getPositionIncrement();
}
tokenStream.end();
count += position.getPositionIncrement();
return count;
} finally {
tokenStream.close();
}
}
/**
* Name of analyzer.
* @return name of analyzer
*/
public String analyzer() {
return analyzer.name();
}
@Override
protected String contentType() {
return CONTENT_TYPE;
}
@Override
public void merge(Mapper mergeWith, MergeContext mergeContext) throws MergeMappingException {
super.merge(mergeWith, mergeContext);
if (!this.getClass().equals(mergeWith.getClass())) {
return;
}
if (!mergeContext.mergeFlags().simulate()) {
this.analyzer = ((TokenCountFieldMapper) mergeWith).analyzer;
}
}
@Override
protected void doXContentBody(XContentBuilder builder, boolean includeDefaults, Params params) throws IOException {
super.doXContentBody(builder, includeDefaults, params);
builder.field("analyzer", analyzer());
}
@Override
public boolean isGenerated() {
return true;
}
}