Elasticsearch-IK分词器源码学习01

一、说明

本文是简单介绍IK分词器的源码，整体的结构，不涉及详细具体的源码分析，请知晓。

1、源码参考

地址：[email protected]:medcl/elasticsearch-analysis-ik.git
tag为：5.3.2

2、IDE

Intellij idea+Maven 3.0

3、Demo

package iktest;

import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.elasticsearch.common.settings.Settings;
import org.junit.Test;
import org.wltea.analyzer.cfg.Configuration;
import org.wltea.analyzer.lucene.IKTokenizer;

import java.io.IOException;
import java.io.StringReader;
import java.util.concurrent.ConcurrentHashMap;

public class IKTestOne {
   

    public final String TEXT_Chinese = "上海迪士尼乐园";

    @Test
    public void test1() throws IOException {
   
        Settings settings = Settings.EMPTY;
        Configuration conf = new Configuration(null, settings);
        //use ik_smart
        conf.setUseSmart(true);
        IKTokenizer tokenizer = new IKTokenizer(conf);
        tokenizer.setReader(