springboot elasticsearch vue ik中文分词器实现百度/京东全文搜索

在这里插入图片描述

背景：实现和百度搜索一样效果的，全文搜索引擎支持关键词高亮显示

文章目录

- - - - 1. 企业级搜索引擎解决方案
      - 2. 创建索引规则
      - 3. 数据拉取
      - 4. 搜索高亮
      - 5. 自定义词库
      - 6. 效果图
      - 7. 开源源码

1. 企业级搜索引擎解决方案

分词器：english、standard、ik_max_smart、ik_smart、whitespace等

索引：创建索引时用ik_max_smart进行分词，搜索时使用ik_smart分词器进行搜索
查询：精准匹配使用term；查询匹配使用match
类型：需要分词使用text，部分词精准用keyword，分数用double，经纬度用geo_point，数字用integer

2. 创建索引规则

PUT /jd_goods
{"settings" : {"number_of_shards" : 1,"number_of_replicas" : 1},"mappings": {"properties": {"id":{"type": "integer"},"title":{"type": "text","analyzer": "ik_max_word","search_analyzer": "ik_smart"},"desc":{"type": "text","analyzer": "ik_max_word","search_analyzer": "ik_smart"},"price":{"type": "text"},"img":{"type": "text"}}}
}

3. 数据拉取

http://localhost:9090/parse/vue

    public List<Content> parseJD(String keyword) throws IOException {String baseUrl = "https://search.xxx.com/Search?keyword=";// 解析网页  在线预览中有处理Document document = Jsoup.parse(new URL(baseUrl + keyword), 30000);// 所有js中可以使用的方法，这里都能用Element element = document.getElementById("J_goodsList");//获取搜有的li元素Elements elements = element.getElementsByTag("li");ArrayList<Content> goodList = new ArrayList<>();// 获取元素中的内容，这里el 就是每一个li标签了for (Element el : elements) {//关于这种图片特别多的网站，所有的图片都是拉加载的String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");String price = el.getElementsByClass("p-price").eq(0).text();String title = el.getElementsByClass("p-name").eq(0).text();Content content = new Content();content.setTitle(title);content.setImg(img);content.setPrice("内容标题 " + price);content.setDesc("内容描述 " + title);goodList.add(content);}return goodList;}

在这里插入图片描述

4. 搜索高亮

  //    2. 获取es中的数据，实现基本搜索高亮功能public List<Map<String, Object>> searchPageHighlight(String keyword, int pageNo, int pageSize) throws IOException {if (pageNo <= 1) {pageNo = 1;}//    条件搜索SearchRequest searchRequest = new SearchRequest(ESConst.JD_SEARCH_INDEX);SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();//    分页searchSourceBuilder.from(pageNo);searchSourceBuilder.size(pageSize);//    精准匹配TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery(ESConst.SEARCH_CONDITION_FIELD, keyword);searchSourceBuilder.query(termQueryBuilder);searchSourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS));//构建高亮HighlightBuilder highlightBuilder = new HighlightBuilder();highlightBuilder.field(ESConst.HIGHLIGHT_TITLE);highlightBuilder.field("desc");highlightBuilder.requireFieldMatch(true);//多个高亮 显示highlightBuilder.preTags(ESConst.HIGHLIGHT_PRE_TAGS);highlightBuilder.postTags(ESConst.HIGHLIGHT_POST_TAGS);searchSourceBuilder.highlighter(highlightBuilder);//    执行搜索searchRequest.source(searchSourceBuilder);SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);//    解析结果ArrayList<Map<String, Object>> list = new ArrayList<>();for (SearchHit hit : searchResponse.getHits().getHits()) {//  解析高亮的字段，将原来的字段置换为我们高亮的字段即可！Map<String, HighlightField> highlightFields = hit.getHighlightFields();HighlightField title = highlightFields.get(ESConst.HIGHLIGHT_TITLE);HighlightField desc = highlightFields.get("desc");//    获取原来的结果Map<String, Object> sourceAsMap = hit.getSourceAsMap();if (title != null) {Text[] fragments = title.fragments();String newTitle = "";for (Text text : fragments) {newTitle += text;}//高亮字段替换掉原来的内容即可sourceAsMap.put(ESConst.SEARCH_CONDITION_FIELD, newTitle);}if (desc != null) {Text[] fragments = desc.fragments();String newDesc = "";for (Text text : fragments) {newDesc += text;}//高亮字段替换掉原来的内容即可sourceAsMap.put("desc", newDesc);}// 将结果放入list容器返回list.add(sourceAsMap);}return list;}