Lucene同义词检索同时精确提取自定义关键词（Lucene版本5.3.0）

此博文针对的是Lucene版本5.3.0，若您的Lucene版本为3.X,请移步这里http://write.blog.csdn.net/postedit/78291868（只提取关键词，未包含同义词检索）

本篇文章包含两个功能

1、精确提取自定义关键词

2、同义词检索与提取

废话不多说，直接撸代码

定义同义词分词类如下

package com.daelly.sample.lucene.analyzer.synonyms;

import java.io.File;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.HashMap;
import java.util.Map;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.synonym.SynonymFilterFactory;
import org.apache.lucene.analysis.util.ClasspathResourceLoader;
import org.apache.lucene.analysis.util.FilesystemResourceLoader;
import org.wltea.analyzer.lucene.IKTokenizer;

public class SynonymsAnalyzer extends Analyzer {
	
	private final String synonymsPath;
	
	public SynonymsAnalyzer(String synonymsPath) {
		if(synonymsPath==null || synonymsPath.isEmpty()) {
			throw new IllegalArgumentException("synonymsPath must be provided!");
		}
		this.synonymsPath = synonymsPath;
	}

	@Override
	protected TokenStreamComponents createComponents(String fieldName) {
		SynonymFilterFactory factory = null;
		try {
			factory = getSynonymFilterFactory();
		} catch (IOException e) {
			e.printStackTrace();
		}
		Tokenizer tokenizer = new IKTokenizer(true);
		if(factory != null) {
			TokenStream tokenStream = factory.create(tokenizer);
			return new TokenStreamComponents(tokenizer,tokenStream);
		}
		return new TokenStreamComponents(tokenizer);
	}
	
	private SynonymFilterFactory getSynonymFilterFactory() throws IOException {
		if(synonymsPath.contains("classpath:")) {
			String path = synonymsPath.replace("classpath:", "");
			Map args = new HashMap<String,String>();
			args.put("synonyms", path);
			SynonymFilterFactory factory = new SynonymFil