Elasticsearch 之（25）重写IK分词器源码来基于mysql热更新词库

热更新

在上一节《 IK分词器配置文件讲解以及自定义词库》自定义词库，每次都是在es的扩展词典中，手动添加新词语，很坑
（1）每次添加完，都要重启es才能生效，非常麻烦
（2）es是分布式的，可能有数百个节点，你不能每次都一个一个节点上面去修改

es不停机，直接我们在外部某个地方添加新的词语，es中立即热加载到这些新词语

热更新的方案

（1）修改ik分词器源码，然后手动支持从mysql中每隔一定时间，自动加载新的词库
（2）基于ik分词器原生支持的热更新方案，部署一个web服务器，提供一个http接口，通过modified和tag两个http响应头，来提供词语的热更新

用第一种方案，第二种，ik git社区官方都不建议采用，觉得不太稳定

1、下载源码
https://github.com/medcl/elasticsearch-analysis-ik/tree/v5.2.0
ik分词器，是个标准的java maven工程，直接导入eclipse就可以看到源码

2、修改源码

Dictionary单例类的初始化方法initial，在这里需要创建一个我们自定义的线程，并且启动它

/**
 * 词典初始化 由于IK Analyzer的词典采用Dictionary类的静态方法进行词典初始化
 * 只有当Dictionary类被实际调用时，才会开始载入词典， 这将延长首次分词操作的时间 该方法提供了一个在应用加载阶段就初始化字典的手段
 * 
 * @return Dictionary
 */
public static synchronized Dictionary initial(Configuration cfg) {
	if (singleton == null) {
		synchronized (Dictionary.class) {
			if (singleton == null) {


				singleton = new Dictionary(cfg);
				singleton.loadMainDict();
				singleton.loadSurnameDict();
				singleton.loadQuantifierDict();
				singleton.loadSuffixDict();
				singleton.loadPrepDict();
				singleton.loadStopWordDict();
				
				new Thread(new HotDictReloadThread()).start();
				
				if(cfg.isEnableRemoteDict()){
					// 建立监控线程
					for (String location : singleton.getRemoteExtDictionarys()) {
						// 10 秒是初始延迟可以修改的 60是间隔时间 单位秒
						pool.scheduleAtFixedRate(new Monitor(location), 10, 60, TimeUnit.SECONDS);
					}
					for (String location : singleton.getRemoteExtStopWordDictionarys()) {
						pool.scheduleAtFixedRate(new Monitor(location), 10, 60, TimeUnit.SECONDS);
					}
				}


				return singleton;
			}
		}
	}
	return singleton;
}

HotDictReloadThread类：就是死循环，不断调用Dictionary.getSingleton().reLoadMainDict()，去重新加载词典

public class HotDictReloadThread implements Runnable {

private static final Logger logger = ESLoggerFactory.getLogger(HotDictReloadThread.class.getName());

@Override
public void run() {
	while(true) {
		logger.info("[==========]reload hot dict from mysql......");   
		Dictionary.getSingleton().reLoadMainDict();
	}
}

}

Dictionary类：更新词典 this.loadMySQLExtDict()

/**
 * 加载主词典及扩展词典
 */
private void loadMainDict() {
	// 建立一个主词典实例
	_MainDict = new DictSegment((char) 0);

	// 读取主词典文件
	Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_MAIN);

	InputStream is = null;
	try {
		is = new FileInputStream(file.toFile());
	} catch (FileNotFoundException e) {
		logger.error(e.getMessage(), e);
	}

	try {
		BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
		String theWord = null;
		do {
			theWord = br.readLine();
			if (theWord != null && !"".equals(theWord.trim())) {
				_MainDict.fillSegment(theWord.trim().toCharArray());
			}
		} while (theWord != null);

	} catch (IOException e) {
		logger.error("ik-analyzer", e);

	} finally {
		try {
			if (is != null) {
				is.close();
				is = null;
			}
		} catch (IOException e) {
			logger.error("ik-analyzer", e);
		}
	}
	// 加载扩展词典
	this.loadExtDict();
	// 加载远程自定义词库
	this.loadRemoteExtDict();
	// 从mysql加载词典
	this.loadMySQLExtDict();
}

/**
 * 从mysql加载热更新词典
 */
private void loadMySQLExtDict() {
	Connection conn = null;
	Statement stmt = null;
	ResultSet rs = null;
	
	try {
		Path file = PathUtils.get(getDictRoot(), "jdbc-reload.properties");   
		prop.load(new FileInputStream(file.toFile()));
		
		logger.info("[==========]jdbc-reload.properties");
		for(Object key : prop.keySet()) {
			logger.info("[==========]" + key + "=" + prop.getProperty(String.valueOf(key)));      
		}
		
		logger.info("[==========]query hot dict from mysql, " + prop.getProperty("jdbc.reload.sql") + "......");  
		
		conn = DriverManager.getConnection(
				prop.getProperty("jdbc.url"),   
				prop.getProperty("jdbc.user"),  
				prop.getProperty("jdbc.password"));  
		stmt = conn.createStatement();
		rs = stmt.executeQuery(prop.getProperty("jdbc.reload.sql"));  
		
		while(rs.next()) {
			String theWord = rs.getString("word"); 
			logger.info("[==========]hot word from mysql: " + theWord); 
			_MainDict.fillSegment(theWord.trim().toCharArray());
		}
		 
		Thread.sleep(Integer.valueOf(String.valueOf(prop.get("jdbc.reload.interval"))));   
	} catch (Exception e) {
		logger.error("erorr", e); 
	} finally {
		if(rs != null) {
			try {
				rs.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
		if(stmt != null) {
			try {
				stmt.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
		if(conn != null) {
			try {
				conn.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
	}
}

Dictionary类：更新分词 this.loadMySQLStopwordDict();

/**
 * 从mysql加载停用词
 */
private void loadMySQLStopwordDict() {
	Connection conn = null;
	Statement stmt = null;
	ResultSet rs = null;
	
	try {
		Path file = PathUtils.get(getDictRoot(), "jdbc-reload.properties");   
		prop.load(new FileInputStream(file.toFile()));
		
		logger.info("[==========]jdbc-reload.properties");
		for(Object key : prop.keySet()) {
			logger.info("[==========]" + key + "=" + prop.getProperty(String.valueOf(key)));      
		}
		
		logger.info("[==========]query hot stopword dict from mysql, " + prop.getProperty("jdbc.reload.stopword.sql") + "......");  
		
		conn = DriverManager.getConnection(
				prop.getProperty("jdbc.url"),   
				prop.getProperty("jdbc.user"),  
				prop.getProperty("jdbc.password"));  
		stmt = conn.createStatement();
		rs = stmt.executeQuery(prop.getProperty("jdbc.reload.stopword.sql"));  
		
		while(rs.next()) {
			String theWord = rs.getString("word"); 
			logger.info("[==========]hot stopword from mysql: " + theWord); 
			_StopWords.fillSegment(theWord.trim().toCharArray());
		}
		 
		Thread.sleep(Integer.valueOf(String.valueOf(prop.get("jdbc.reload.interval"))));   
	} catch (Exception e) {
		logger.error("erorr", e); 
	} finally {
		if(rs != null) {
			try {
				rs.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
		if(stmt != null) {
			try {
				stmt.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
		if(conn != null) {
			try {
				conn.close();
			} catch (SQLException e) {
				logger.error("error", e); 
			}
		}
	}
}

配置

jdbc.url=jdbc:mysql://localhost:3306/test?serverTimezone=GMT
jdbc.user=root
jdbc.password=root
jdbc.reload.sql=select word from hot_words
jdbc.reload.stopword.sql=select stopword as word from hot_stopwords
jdbc.reload.interval=1000

3、mvn package打包代码

target\releases\elasticsearch-analysis-ik-5.2.0.zip


4、解压缩ik压缩包

将mysql驱动jar，放入ik的目录下


5、重启es



6、在mysql中添加词库与停用词



7、kibana分词验证

GET /my_index/_analyze
{
  "text": "一人饮酒醉",
  "analyzer": "ik_max_word"
}

{
  "tokens": [
    {
      "token": "一人饮酒醉",
      "start_offset": 0,
      "end_offset": 5,
      "type": "CN_WORD",
      "position": 0
    },
    {
      "token": "一人",
      "start_offset": 0,
      "end_offset": 2,
      "type": "CN_WORD",
      "position": 1
    },
    {
      "token": "一",
      "start_offset": 0,
      "end_offset": 1,
      "type": "TYPE_CNUM",
      "position": 2
    },
    {
      "token": "人",
      "start_offset": 1,
      "end_offset": 2,
      "type": "COUNT",
      "position": 3
    },
    {
      "token": "饮酒",
      "start_offset": 2,
      "end_offset": 4,
      "type": "CN_WORD",
      "position": 4
    },
    {
      "token": "饮",
      "start_offset": 2,
      "end_offset": 3,
      "type": "CN_WORD",
      "position": 5
    },
    {
      "token": "酒醉",
      "start_offset": 3,
      "end_offset": 5,
      "type": "CN_WORD",
      "position": 6
    },
    {
      "token": "酒",
      "start_offset": 3,
      "end_offset": 4,
      "type": "CN_WORD",
      "position": 7
    },
    {
      "token": "醉",
      "start_offset": 4,
      "end_offset": 5,
      "type": "CN_WORD",
      "position": 8
    }
  ]
}