org.elasticsearch.index.mapper.KeywordFieldMapper Maven / Gradle / Ivy

Go to download
/*
 * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
 * or more contributor license agreements. Licensed under the Elastic License
 * 2.0 and the Server Side Public License, v 1; you may not use this file except
 * in compliance with, at your election, the Elastic License 2.0 or the Server
 * Side Public License, v 1.
 */

package org.elasticsearch.index.mapper;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.SortedSetDocValuesField;
import org.apache.lucene.index.FilteredTermsEnum;
import org.apache.lucene.index.IndexOptions;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.MultiTerms;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.automaton.Automata;
import org.apache.lucene.util.automaton.Automaton;
import org.apache.lucene.util.automaton.CompiledAutomaton;
import org.apache.lucene.util.automaton.CompiledAutomaton.AUTOMATON_TYPE;
import org.apache.lucene.util.automaton.MinimizationOperations;
import org.apache.lucene.util.automaton.Operations;
import org.elasticsearch.common.lucene.Lucene;
import org.elasticsearch.common.lucene.search.AutomatonQueries;
import org.elasticsearch.index.analysis.IndexAnalyzers;
import org.elasticsearch.index.analysis.NamedAnalyzer;
import org.elasticsearch.index.fielddata.IndexFieldData;
import org.elasticsearch.index.fielddata.plain.SortedSetOrdinalsIndexFieldData;
import org.elasticsearch.index.query.SearchExecutionContext;
import org.elasticsearch.index.similarity.SimilarityProvider;
import org.elasticsearch.script.Script;
import org.elasticsearch.script.ScriptCompiler;
import org.elasticsearch.script.StringFieldScript;
import org.elasticsearch.search.aggregations.support.CoreValuesSourceType;
import org.elasticsearch.search.lookup.FieldValues;
import org.elasticsearch.search.lookup.SearchLookup;
import org.elasticsearch.xcontent.XContentParser;

import java.io.IOException;
import java.io.UncheckedIOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.Objects;
import java.util.function.Supplier;

/**
 * A field mapper for keywords. This mapper accepts strings and indexes them as-is.
 */
public final class KeywordFieldMapper extends FieldMapper {

    public static final String CONTENT_TYPE = "keyword";

    public static class Defaults {
        public static final FieldType FIELD_TYPE = new FieldType();

        static {
            FIELD_TYPE.setTokenized(false);
            FIELD_TYPE.setOmitNorms(true);
            FIELD_TYPE.setIndexOptions(IndexOptions.DOCS);
            FIELD_TYPE.freeze();
        }
    }

    public static class KeywordField extends Field {

        public KeywordField(String field, BytesRef term, FieldType ft) {
            super(field, term, ft);
        }

    }

    private static KeywordFieldMapper toType(FieldMapper in) {
        return (KeywordFieldMapper) in;
    }

    public static class Builder extends FieldMapper.Builder {

        private final Parameter indexed = Parameter.indexParam(m -> toType(m).indexed, true);
        private final Parameter hasDocValues = Parameter.docValuesParam(m -> toType(m).hasDocValues, true);
        private final Parameter stored = Parameter.storeParam(m -> toType(m).fieldType.stored(), false);

        private final Parameter nullValue = Parameter.stringParam("null_value", false, m -> toType(m).nullValue, null)
            .acceptsNull();

        private final Parameter eagerGlobalOrdinals = Parameter.boolParam(
            "eager_global_ordinals",
            true,
            m -> toType(m).eagerGlobalOrdinals,
            false
        );
        private final Parameter ignoreAbove = Parameter.intParam(
            "ignore_above",
            true,
            m -> toType(m).ignoreAbove,
            Integer.MAX_VALUE
        );

        private final Parameter indexOptions = Parameter.restrictedStringParam(
            "index_options",
            false,
            m -> toType(m).indexOptions,
            "docs",
            "freqs"
        );
        private final Parameter hasNorms = TextParams.norms(false, m -> toType(m).fieldType.omitNorms() == false);
        private final Parameter similarity = TextParams.similarity(m -> toType(m).similarity);

        private final Parameter normalizer = Parameter.stringParam("normalizer", false, m -> toType(m).normalizerName, null)
            .acceptsNull();

        private final Parameter splitQueriesOnWhitespace = Parameter.boolParam(
            "split_queries_on_whitespace",
            true,
            m -> toType(m).splitQueriesOnWhitespace,
            false
        );

        private final Parameter> meta = Parameter.metaParam();
        private final Parameter boost = Parameter.boostParam();

        private final Parameter