ik 分词器远程扩展字典、停用字典配置，热更新扩展字典、停用字典

ik 分词器官网:https://github.com/medcl/elasticsearch-analysis-ik

ik 分词器扩展字典本地配置:https://blog.csdn.net/shfqbluestone/article/details/115524821?spm=1001.2014.3001.5501

1. 首先编辑 ik 的配置文件 /xxx/elasticsearch-7.12.0/plugins/ik/config/IKAnalyzer.cfg.xml :

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
	<comment>IK Analyzer 扩展配置</comment>
	<!--用户可以在这里配置自己的扩展字典 -->
	<entry key="ext_dict">shfq_ext_dic.dic</entry>
	 <!--用户可以在这里配置自己的扩展停止词字典-->
	<entry key="ext_stopwords"></entry>
	<!--用户可以在这里配置远程扩展字典 -->
	<entry key="remote_ext_dict">http://localhost:8162/test/downloadExtDic?fileName=extWords.dic</entry>
	<!--用户可以在这里配置远程扩展停止词字典-->
	<entry key="remote_ext_stopwords">http://localhost:8162/test/downloadExtDic?fileName=stopWords.dic</entry>
</properties>

2. 在下载扩展、停用词典的接口里返回 Last-Modified 或 ETag responder header 。

package com.huitongjy.recommend.exercise.controller;

import com.huitongjy.common.util.LogUtils;
import io.swagger.annotations.Api;
import io.swagger.models.HttpMethod;
import org.apache.commons.lang3.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.core.io.UrlResource;
import org.springframework.http.HttpHeaders;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import javax.servlet.http.HttpServletRequest;
import java.io.File;
import java.io.IOException;
import java.net.MalformedURLException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.attribute.BasicFileAttributes;

@RestController
@Api(value = "PrivateController", tags = "测试")

public class TestController {
    private static final Logger LOG = LoggerFactory.getLogger(PrivateController.class);

    @RequestMapping(value = "/test/downloadExtDic")
    public ResponseEntity<org.springframework.core.io.Resource> downloadFileFromLocal(HttpServletRequest request, String fileName) {
        if (StringUtils.isEmpty(fileName)) {
            return null;
        }
        // 可以把字典的配置文件写到配置中心
        String location = "";
        if (!location.endsWith(File.separator)) {
            location += File.separator;
        }
        String method = request.getMethod();
        boolean isHead = HttpMethod.HEAD.name().equals(method);
        String pathStr = location + fileName;
        File file = new File(pathStr);
        if (!file.exists()) {
            LogUtils.error(LOG, "字典不存在", "path", pathStr);
            return null;
        }

        Path path = Paths.get(pathStr);
        org.springframework.core.io.Resource resource = null;

        try {
            resource = new UrlResource(path.toUri());
        } catch (MalformedURLException e) {
            LogUtils.error(LOG, "加载字典异常", e);
            return null;
        }
        HttpHeaders httpHeaders = new HttpHeaders();
        httpHeaders.add(HttpHeaders.CONTENT_DISPOSITION, "attachment; filename=\"" + fileName + "\"");
        httpHeaders.add(HttpHeaders.ETAG, generateLastUpdateDate(path) + "");
        if (isHead) {
            resource = null;
        }
        return ResponseEntity.ok()
                .contentType(MediaType.TEXT_PLAIN)
                .headers(httpHeaders)
                .body(resource);
    }

    private long generateLastUpdateDate(Path path) {
        try {
            BasicFileAttributes attr = Files.readAttributes(path, BasicFileAttributes.class);
            Long l = attr.lastModifiedTime().toMillis();
            return l;
        } catch (IOException e) {
            return -1;
        }

    }

}

3. 添加扩展字典、停用字典。

ik 分词器会每隔 1 分钟调用一次 head 方法根据 etag 来判断字典是否更新了，如果更新了的话才会调用 get 方法去下载字典。先调用 head 方法确认更新后再调用 get下载，这样就节省了带宽流量，也省的去更新词典了。