/*
 * 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.ngram.EdgeNGramTokenizer;
import org.apache.lucene.analysis.ngram.NGramTokenizer;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.analysis.AbstractTokenizerFactory;

import static org.elasticsearch.analysis.common.NGramTokenizerFactory.parseTokenChars;

public class EdgeNGramTokenizerFactory extends AbstractTokenizerFactory {

    private final int minGram;
    private final int maxGram;
    private final CharMatcher matcher;

    EdgeNGramTokenizerFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(name);
        this.minGram = settings.getAsInt("min_gram", NGramTokenizer.DEFAULT_MIN_NGRAM_SIZE);
        this.maxGram = settings.getAsInt("max_gram", NGramTokenizer.DEFAULT_MAX_NGRAM_SIZE);
        this.matcher = parseTokenChars(settings);
    }

    @Override
    public Tokenizer create() {
        if (matcher == null) {
            return new EdgeNGramTokenizer(minGram, maxGram);
        } else {
            return new EdgeNGramTokenizer(minGram, maxGram) {
                @Override
                protected boolean isTokenChar(int chr) {
                    return matcher.isTokenChar(chr);
                }
            };
        }
    }
}