org.elasticsearch.index.analysis.StandardTokenizerFactory Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of elasticsearch Show documentation

Elasticsearch subproject :server

There is a newer version: 8.13.4

/*
 * 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.analysis;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;

public class StandardTokenizerFactory extends AbstractTokenizerFactory {

    private final int maxTokenLength;

    public StandardTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, settings, name);
        maxTokenLength = settings.getAsInt("max_token_length", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
    }

    @Override
    public Tokenizer create() {
        StandardTokenizer tokenizer = new StandardTokenizer();
        tokenizer.setMaxTokenLength(maxTokenLength);
        return tokenizer;
    }
}