add:add new es search controller

src/main/java/com/jiaruiblog/controller/DocumentController.java

@@ -77,6 +77,32 @@ public BaseApiResult list(@RequestBody DocumentDTO documentDTO)
         return iFileService.list(documentDTO);
     }
 
+    @ApiOperation(value = "2.1 查询文档的分页列表页,限制了分类和标签", notes = "根据参数查询文档列表")
+    @PostMapping(value = "/listNew")
+    public BaseApiResult listNew(@RequestBody DocumentDTO documentDTO)
+            throws IOException {
+        String userId = documentDTO.getUserId();
+        if (StringUtils.hasText(documentDTO.getFilterWord()) &&
+                documentDTO.getType() == FilterTypeEnum.FILTER) {
+            String filterWord = documentDTO.getFilterWord();
+            //非法敏感词汇判断
+            SensitiveFilter filter = SensitiveFilter.getInstance();
+            int n = filter.checkSensitiveWord(filterWord, 0, 1);
+            //存在非法字符
+            if (n > 0) {
+                // todo 非法字符的计算可能不准确：
+                // NullPointer， Null， java， on
+                log.error("这个人输入了非法字符--> {},不知道他到底要查什么~", filterWord);
+            } else {
+                redisService.incrementScoreByUserId(filterWord, RedisServiceImpl.SEARCH_KEY);
+                if (StringUtils.hasText(userId)) {
+                    redisService.addSearchHistoryByUserId(userId, filterWord);
+                }
+            }
+        }
+        return iFileService.listNew(documentDTO);
+    }
+
     @ApiOperation(value = "2.2 查询文档的详细信息", notes = "查询文档的详细信息")
     @GetMapping(value = "/detail")
     public BaseApiResult detail(@RequestParam(value = "docId") String id) {

src/main/java/com/jiaruiblog/entity/vo/DocumentVO.java

@@ -46,4 +46,6 @@ public class DocumentVO {
 
     private Date createTime;
 
+    private List<PageVO> pageVOList;
+
 }

src/main/java/com/jiaruiblog/entity/vo/PageVO.java

@@ -0,0 +1,21 @@
+package com.jiaruiblog.entity.vo;
+
+import lombok.Data;
+
+/**
+ * @ClassName PageVO
+ * @Description TODO
+ * @Author luojiarui
+ * @Date 2024/4/23 22:33
+ * @Version 1.0
+ **/
+@Data
+public class PageVO {
+
+    private Integer order;
+
+    private String content;
+
+    private Integer page;
+
+}

src/main/java/com/jiaruiblog/service/ElasticService.java

@@ -1,10 +1,13 @@
 package com.jiaruiblog.service;
 
 import com.jiaruiblog.entity.FileDocument;
+import com.jiaruiblog.entity.vo.PageVO;
 import com.jiaruiblog.util.BaseApiResult;
 
 import java.io.IOException;
 import java.util.List;
+import java.util.Map;
+import java.util.Set;
 
 /**
  * @author jiarui.luo
@@ -19,6 +22,15 @@ public interface ElasticService {
      */
     List<FileDocument> search(String keyword) throws IOException;
 
+    /**
+     * search
+     * @param keyword String
+     * @param docIdSet 限制其
+     * @return result
+     * @throws IOException exception
+     */
+    Map<String, List<PageVO>> search(String keyword, Set<String> docIdSet) throws IOException;
+
     BaseApiResult getWordStat() throws IOException;
 
 }

src/main/java/com/jiaruiblog/service/IFileService.java

@@ -15,6 +15,7 @@
 import java.util.Collection;
 import java.util.List;
 import java.util.Optional;
+import java.util.Set;
 
 
 /**
@@ -111,6 +112,8 @@ BaseApiResult uploadByUrl(String category, List<String> tags, String name,
      */
     FileDocument getByMd5(String md5);
 
+    List<FileDocument> getByMd5Set(Set<String> md5Set);
+
     /**
      * queryById
      * @param docId String
@@ -152,6 +155,13 @@ BaseApiResult uploadByUrl(String category, List<String> tags, String name,
      */
     BaseApiResult list(DocumentDTO documentDTO);
 
+    /**
+     * 分页检索目前的文档信息
+     * @param documentDTO DocumentDTO
+     * @return result
+     */
+    BaseApiResult listNew(DocumentDTO documentDTO);
+
     /**
      *根据文档的详情，查询该文档的详细信息
      *

src/main/java/com/jiaruiblog/service/impl/ElasticServiceImpl.java

@@ -1,10 +1,12 @@
 package com.jiaruiblog.service.impl;
 
 import com.alibaba.fastjson.JSON;
+import com.google.common.collect.Maps;
 import com.google.common.collect.Sets;
 import com.jiaruiblog.entity.FileDocument;
 import com.jiaruiblog.entity.FileObj;
 import com.jiaruiblog.entity.data.WordCloudItem;
+import com.jiaruiblog.entity.vo.PageVO;
 import com.jiaruiblog.service.ElasticService;
 import com.jiaruiblog.util.BaseApiResult;
 import lombok.extern.slf4j.Slf4j;
@@ -184,6 +186,77 @@ public List<FileDocument> search(String keyword) throws IOException {
         return fileDocumentList;
     }
 
+    @Override
+    public Map<String, List<PageVO>> search(String keyword, Set<String> docIdSet) throws IOException {
+        // 查询es后返回的内容
+        Map<String, List<PageVO>> result = new HashMap<>();
+        SearchRequest searchRequest = new SearchRequest(INDEX_NAME);
+        // 使用lk分词器查询，会把插入的字段分词，然后进行处理
+        SearchSourceBuilder srb = new SearchSourceBuilder();
+        srb.query(QueryBuilders.matchPhraseQuery(PIPELINE_NAME, keyword));
+
+        // 每页10个数据
+        srb.size(10);
+        // 起始位置从0开始
+        srb.from(0);
+
+        //设置highlighting
+        HighlightBuilder highlightBuilder = new HighlightBuilder();
+        HighlightBuilder.Field highlightContent = new HighlightBuilder.Field(PIPELINE_NAME);
+        highlightContent.fragmentSize(100); // 设置片段大小为最大值，即返回全部片段
+        highlightContent.highlighterType("unified");
+        highlightBuilder.field(highlightContent);
+        highlightBuilder.preTags("<em>");
+        highlightBuilder.postTags("</em>");
+        highlightBuilder.numOfFragments(100);
+
+        //highlighting会自动返回匹配到的文本，所以就不需要再次返回文本了
+        String[] includeFields = new String[]{"name", "id"};
+        String[] excludeFields = new String[]{PIPELINE_NAME};
+        srb.fetchSource(includeFields, excludeFields);
+
+        //把刚才设置的值导入进去
+        srb.highlighter(highlightBuilder);
+        searchRequest.source(srb);
+        SearchResponse res;
+        try {
+            res = client.search(searchRequest, RequestOptions.DEFAULT);
+        } catch (ConnectException e) {
+            log.error("连接es失败！", e.getCause());
+            res = null;
+        }
+
+        if (res == null || res.getHits() == null) {
+            return Maps.newHashMap();
+        }
+        //获取hits，这样就可以获取查询到的记录了
+        SearchHits hits = res.getHits();
+
+        //hits是一个迭代器，所以需要迭代返回每一个hits
+        for (SearchHit hit : hits) {
+            //获取返回的字段
+            Map<String, Object> sourceAsMap = hit.getSourceAsMap();
+            //这个就会把匹配到的文本返回，而且只返回匹配到的部分文本
+            Map<String, HighlightField> highlightFields = hit.getHighlightFields();
+            HighlightField highlightField = highlightFields.get(PIPELINE_NAME);
+
+            List<PageVO> pageVOList = new ArrayList<>();
+            for (Text fragment : highlightField.getFragments()) {
+                PageVO pageVO = new PageVO();
+                pageVO.setContent(fragment.string());
+                pageVOList.add(pageVO);
+            }
+
+            if (sourceAsMap.containsKey("id")) {
+                String id = (String) sourceAsMap.get("id");
+                if (Objects.nonNull(id)) {
+                    result.put(id, pageVOList);
+                }
+            }
+        }
+        return result;
+    }
+
     /**
      * @Author luojiarui
      * @Description 根据文档的id删除文档