热更新
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
ik分词器,是个标准的java maven工程,直接导入IDE
2、修改源码
pom.xml:
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>8.0.17</version>
</dependency>
以下修改 Dictionary.java
/**
* 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 void 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();
// TODO 自定义的线程,并启动(新增)
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);
}
}
}
}
}
}
/**
* 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);
loadDictFile(_MainDict, file, false, "Main Dict");
// 加载扩展词典
this.loadExtDict();
// 加载远程自定义词库
this.loadRemoteExtDict();
// TODO 从mysql加载词典(新增方法)
this.loadMySQLExtDict();
}
/**
* 从 mysql 加载热更新词典(新增方法)
*/
private void loadMySQLExtDict() {
Connection conn = null;
Statement stmt = null;
ResultSet rs = null;
try {
Path file = PathUtils.get(getDictRoot(), "jdbc-reload.properties");
props.load(new FileInputStream(file.toFile()));
logger.info("[==========]jdbc-reload.properties");
for(Object key : props.keySet()) {
logger.info("[==========]" + key + "=" + props.getProperty(String.valueOf(key)));
}
logger.info("[==========]query hot dict from mysql, " + props.getProperty("jdbc.reload.sql") + "......");
conn = DriverManager.getConnection(
props.getProperty("jdbc.url"),
props.getProperty("jdbc.user"),
props.getProperty("jdbc.password"));
stmt = conn.createStatement();
rs = stmt.executeQuery(props.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(props.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);
}
}
}
}
/**
* 加载用户扩展的停止词词典
*/
private void loadStopWordDict() {
.........
// TODO 新增方法
this.loadMySQLStopwordDict();
}
/**
* 从mysql加载停用词(新增方法)
*/
private void loadMySQLStopwordDict() {
Connection conn = null;
Statement stmt = null;
ResultSet rs = null;
try {
Path file = PathUtils.get(getDictRoot(), "jdbc-reload.properties");
props.load(new FileInputStream(file.toFile()));
logger.info("[==========]jdbc-reload.properties");
for(Object key : props.keySet()) {
logger.info("[==========]" + key + "=" + props.getProperty(String.valueOf(key)));
}
logger.info("[==========]query hot stopword dict from mysql, " + props.getProperty("jdbc.reload.stopword.sql") + "......");
conn = DriverManager.getConnection(
props.getProperty("jdbc.url"),
props.getProperty("jdbc.user"),
props.getProperty("jdbc.password"));
stmt = conn.createStatement();
rs = stmt.executeQuery(props.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(props.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);
}
}
}
}
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 = ESPluginLoggerFactory.getLogger(HotDictReloadThread.class.getName());
@Override
public void run() {
while(true) {
logger.info("[==========]reload hot dict from mysql......");
Dictionary.getSingleton().reLoadMainDict();
}
}
}
plugin.xml
<dependencySet>
<outputDirectory/>
<useProjectArtifact>true</useProjectArtifact>
<useTransitiveFiltering>true</useTransitiveFiltering>
<includes>
<include>mysql:mysql-connector-java</include>
</includes>
</dependencySet>
jdbc相关配置 jdbc-reload.properties
jdbc.url=jdbc\:mysql\://localhost\:3306/ik-words?serverTimezone=UTC
jdbc.user=root
jdbc.password=123456
# 词库 sql
jdbc.reload.sql=select word from hot_words
# 停用词 sql
jdbc.reload.stopword.sql=select stop_word as word from stop_words
# 间隔时长
jdbc.reload.interval=1000
3、mvn package打包代码
target\releases\elasticsearch-analysis-ik-X.X.X.zip
6、重启es
https://blog.csdn.net/hqd1870299/article/details/106660017
https://blog.csdn.net/qq_35524586/article/details/88553670
https://blog.csdn.net/weixin_43315211/article/details/99650363