/*
 * 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", the "GNU Affero General Public License v3.0 only", 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", the "GNU Affero General Public
 * License v3.0 only", or the "Server Side Public License, v 1".
 */

package org.elasticsearch.analysis.common;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.pattern.PatternTokenizer;
import org.elasticsearch.common.regex.Regex;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.analysis.AbstractTokenizerFactory;

import java.util.regex.Pattern;

public class PatternTokenizerFactory extends AbstractTokenizerFactory {

    private final Pattern pattern;
    private final int group;

    PatternTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(name);

        String sPattern = settings.get("pattern", "\\W+" /*PatternAnalyzer.NON_WORD_PATTERN*/);
        if (sPattern == null) {
            throw new IllegalArgumentException("pattern is missing for [" + name + "] tokenizer of type 'pattern'");
        }

        this.pattern = Regex.compile(sPattern, settings.get("flags"));
        this.group = settings.getAsInt("group", -1);
    }

    @Override
    public Tokenizer create() {
        return new PatternTokenizer(pattern, group);
    }
}