release-3.1.3(20210813,修复了 新增站点 linkedin 和 ins 查询详情的时候 标题不展示 author 的问题。修复了 离线统计 统计的时候会将粉丝数也一起统计，从而导致task 的统计结果跟查询结果不相符)

cl_query_data_job/src/main/java/com/bfd/mf/job/domain/repository/TaskRepository.java

@@ -17,7 +17,8 @@ public interface TaskRepository extends CrudRepository<Task, Long> {
 
     // 需要统计的任务的查询条件 1、 状态为 1 OR 0；2、状态为3，且任务完成时间再2天前的。
     @Query(value = "SELECT ct.id,ct.app_id,ct.subject_id,ct.external_id,cs.site_type, ct.task_type,ct.cid,ct.crawl_status,ct.crawl_start_time,ct.crawl_end_time,ct.crawl_data_flag,ct.data_total,ct.today_data_total,ct.cache_num,ct.update_time,ct.del,ct.crawl_content_key  FROM `cl_task` ct JOIN intelligent_crawl.cl_site cs ON ct.cid = cs.cid WHERE ct.del = 0 AND ((ct.crawl_status = 1 OR ct.crawl_status = 0) OR (ct.crawl_status = 3 AND ct.end_time > date_sub(curdate(),interval 2 day))); ",nativeQuery = true)
- //   @Query(value = "SELECT ct.id,ct.app_id,ct.subject_id,ct.external_id,cs.site_type, ct.task_type,ct.cid,ct.crawl_status,ct.crawl_start_time,ct.crawl_end_time,ct.crawl_data_flag,ct.data_total,ct.today_data_total,ct.cache_num,ct.update_time,ct.del,ct.crawl_content_key  FROM `cl_task` ct JOIN intelligent_crawl.cl_site cs ON ct.cid = cs.cid WHERE ct.del = 0 AND  ct.subject_id = 12273 ; ",nativeQuery = true)
+    //  @Query(value = "SELECT ct.id,ct.app_id,ct.subject_id,ct.external_id,cs.site_type, ct.task_type,ct.cid,ct.crawl_status,ct.crawl_start_time,ct.crawl_end_time,ct.crawl_data_flag,ct.data_total,ct.today_data_total,ct.cache_num,ct.update_time,ct.del,ct.crawl_content_key  FROM `cl_task` ct JOIN intelligent_crawl.cl_site cs ON ct.cid = cs.cid WHERE ct.del = 0 AND  ct.subject_id = 12505 ; ",nativeQuery = true)
+    //   @Query(value = "SELECT ct.id,ct.app_id,ct.subject_id,ct.external_id,cs.site_type, ct.task_type,ct.cid,ct.crawl_status,ct.crawl_start_time,ct.crawl_end_time,ct.crawl_data_flag,ct.data_total,ct.today_data_total,ct.cache_num,ct.update_time,ct.del,ct.crawl_content_key  FROM `cl_task` ct JOIN intelligent_crawl.cl_site cs ON ct.cid = cs.cid WHERE ct.del = 0 ; ",nativeQuery = true)
     List<Task> findAllBydel0();
 
     @Query(value = "SELECT sum(data_total) FROM cl_task ct JOIN intelligent_crawl.cl_site cs ON ct.cid=cs.cid WHERE ct.del =0 AND ct.subject_id = ?1 AND cs.site_type = ?2",nativeQuery = true)

cl_query_data_job/src/main/java/com/bfd/mf/job/service/es/EsQueryMiniService.java

@@ -139,19 +139,6 @@ public class EsQueryMiniService {
             if (indexName.contains(indexNamePre)) {
                 boolean isExists = EsUtils.indexExists(clusterName, indexName);
                 if (isExists) {
-//                    // 任务ID 筛选
-//                    TermQueryBuilder cidTermQueryBuilder = QueryBuilders.termQuery(ESConstants.EN_SOURCE, cid);
-//                    TermQueryBuilder taskIdTermQueryBuilder = QueryBuilders.termQuery(ESConstants.CRAWLDATAFLAG, crawlDataFlag);
-//                    qb.must(taskIdTermQueryBuilder).must(cidTermQueryBuilder);
-//                    // 时间范围筛选
-//                    // BoolQueryBuilder shouldbq = QueryBuilders.boolQuery();
-//                    RangeQueryBuilder rangeQueryBuilder = QueryBuilders
-//                            .rangeQuery(ESConstants.PUBTIME)
-//                            .gte(crawlStartTime)
-//                            .lt(crawlEndTime);
-//                    // 不用统计FB 的这种粉丝的量
-//                    TermQueryBuilder pageTypeQueryBuilder = QueryBuilders.termQuery(ESConstants.PAGETYPR,"socialFans");
-//                    qb.mustNot(pageTypeQueryBuilder).must(rangeQueryBuilder);
                     BoolQueryBuilder qb  = getQueryBuilder(cid,crawlDataFlag,crawlStartTime,crawlEndTime);
                     logger.info("QB1 查询总量: indexName: {}. taskId : {}.{\"query\": {}}.", indexName, taskId, qb.toString().replace("\n", "").replace("\r", "").replace(" ", ""));
                     Long count = EsUtils.queryCount(clusterName, indexName, qb);
@@ -202,15 +189,17 @@ public class EsQueryMiniService {
         TermQueryBuilder cidTermQueryBuilder = QueryBuilders.termQuery(ESConstants.EN_SOURCE, cid);
         TermQueryBuilder taskIdTermQueryBuilder = QueryBuilders.termQuery(ESConstants.CRAWLDATAFLAG, crawlDataFlag);
         qb.must(taskIdTermQueryBuilder).must(cidTermQueryBuilder);
-        // 时间范围筛选
-        // BoolQueryBuilder shouldbq = QueryBuilders.boolQuery();
+        // 时间范围筛选 只有主贴评论需要查时间，用户不需要设置时间范围
+        BoolQueryBuilder shouldbq = QueryBuilders.boolQuery();
         RangeQueryBuilder rangeQueryBuilder = QueryBuilders
                 .rangeQuery(ESConstants.PUBTIME)
                 .gte(crawlStartTime)
                 .lt(crawlEndTime);
+        TermQueryBuilder primary1 = QueryBuilders.termQuery(ESConstants.PRIMARY,2);
+        shouldbq.must(rangeQueryBuilder).mustNot(primary1);
         // 不用统计FB 的这种粉丝的量
         TermQueryBuilder pageTypeQueryBuilder = QueryBuilders.termQuery(ESConstants.PAGETYPR,"socialFans");
-        qb.mustNot(pageTypeQueryBuilder).must(rangeQueryBuilder);
+        qb.mustNot(pageTypeQueryBuilder).should(shouldbq);
         return qb;
     }
 }

cl_query_data_job/src/main/java/com/bfd/mf/job/service/query/QueryService.java

@@ -63,7 +63,7 @@ public class QueryService {
         // 注册数据查询来源
 //        EsUtils.registerCluster(config.esNormalClusterName(), config.esNormalAddress());// 配置文件中的  es-source
         EsUtils.registerCluster(config.esMiniClusterName(), config.esMiniAddress()); // 配置文件中的 es-target
-//        pRateLimiter = RateLimiter.create(1.0D / config.getPeriodS());
+        pRateLimiter = RateLimiter.create(1.0D / config.getPeriodS());
         kafkaProducer = Kafka010Utils.getProducer(config.getBrokerList());
 
 //        cRateLimiter = RateLimiter.create(1.0D / config.getPeriodS());
@@ -487,6 +487,7 @@ public class QueryService {
             String videoTime = "";
             try {
                 if(null != downloadUrl && !downloadUrl.contains("si-te.percent.cn")) {
+                    if (downloadUrl.contains("http")) {
                         Map<String, String> pathSizeMap = DownLoadFile.downloadAndSaveFile(downloadUrl, goFastAddr);
                         LOGGER.info("[QueryService] getPathSize goFaskAddr {}. resultMap {}.", goFastAddr, pathSizeMap);
                         if (pathSizeMap.size() > 0) {
@@ -511,8 +512,7 @@ public class QueryService {
                             srcMap.put(downloadUrl, url);
                             // 这个值使用来替换 三个 Path 的  imagePath,videoPath,filePath
                             path.add(url);
-
-
+                        }
                     }
                 }
             } catch (IOException e) {
@@ -574,7 +574,7 @@ public class QueryService {
         try {
             // TermQueryBuilder queryCidBuilders = QueryBuilders.termQuery("enSource",cid);
             TermQueryBuilder queryCrawlDataFlagBuilder = QueryBuilders.termQuery(ESConstants.CRAWLDATAFLAG,crawlDataFlag);
-            if (crawlDataFlag.contains("keyword")) {
+            if (crawlDataFlag.contains("keyword:")) {
                 String keyword = crawlDataFlag.split("keyword:")[1];
                 System.out.println("[buildCrawlDataFlagBuilder] keyword --- " + keyword); // 关键词的话需要去 title 和 content 匹配一下
                 MatchPhraseQueryBuilder titleQuery = QueryBuilders.matchPhraseQuery(ESConstants.TITLE, keyword).slop(0);
@@ -588,14 +588,14 @@ public class QueryService {
                     queryBuilder = QueryBuilders.boolQuery().should(titleFilterQuery).should(contentFilterQuery).should(queryCrawlDataFlagBuilder);
                 }
             }
-            if (crawlDataFlag.contains("url")) {
+            if (crawlDataFlag.contains("url:")) {
                 String url = crawlDataFlag.split("url:")[1];
                 System.out.println("[buildCrawlDataFlagBuilder] url --- " + url); // url 的话直接匹配 url 字段
                 TermQueryBuilder queryUrlBuilders = QueryBuilders.termQuery(ESConstants.URL,url);
                 // QueryBuilder queryBuilder1 = QueryBuilders.boolQuery().must(queryUrlBuilders);
                 queryBuilder = QueryBuilders.boolQuery().should(queryCrawlDataFlagBuilder).should(queryUrlBuilders);
             }
-            if (crawlDataFlag.contains("account")) {
+            if (crawlDataFlag.contains("account:")) {
                 String account = crawlDataFlag.split("account:")[1];
                 System.out.println("[buildCrawlDataFlagBuilder] account --- " + account);
                 TermQueryBuilder queryAccountBuilders = QueryBuilders.termQuery(ESConstants.USER_URL,account);

cl_query_data_job/src/main/java/com/bfd/mf/job/service/statistics/StatisticsService.java

@@ -242,6 +242,7 @@ public class StatisticsService {
                 String indexNamePre = config.getIndexNamePre();
                 Map<String, Long> countMap = new HashMap<>();
                 if(null != task.getCid() && !task.getCid().equals("test")) {
+                    // 获取任务数量
                     countMap = esQueryMiniService.getTaskCount(miniName, taskId, task, crawlDataFlag, indexNamePre);
                     // 直接更新 cl_task 表中的 data_total 和 today_data_total
                     long totalCount = 0L;
@@ -253,6 +254,7 @@ public class StatisticsService {
                     if(countMap.containsKey(ESConstants.TOTALCOUNT) && countMap.containsKey(ESConstants.TODAYCOUNT)) {
                         totalCount = countMap.get(ESConstants.TOTALCOUNT);
                         todayCount = countMap.get(ESConstants.TODAYCOUNT);
+                        System.out.println("******* " + totalCount);
 //                        imageCount = countMap.get(ESConstants.IMAGECOUNT);
 //                        videoCount = countMap.get(ESConstants.VIDEOCOUNT);
 //                        fileCount = countMap.get(ESConstants.FILECOUNT);

cl_query_data_job/src/main/java/com/bfd/mf/job/worker/QueryProducer.java

@@ -34,10 +34,10 @@ public class QueryProducer extends AbstractWorker {
        // LOGGER.info("[QueryProducer] work start ... ");
         queryBacktraceService.tryAcquire();
         queryBacktraceService.produce();
-//        try {
-//            Thread.sleep(config.getIntervalTime());
-//        } catch (InterruptedException e) {
-//            e.printStackTrace();
-//        }
+        try {
+            Thread.sleep(6000);
+        } catch (InterruptedException e) {
+            e.printStackTrace();
+        }
     }
 }

cl_search_api/src/main/java/com/bfd/mf/controller/SearchDataController.java

@@ -47,6 +47,7 @@ public class SearchDataController {
         logger.info("[queryDataList] partial / Params: {}", JSONObject.toJSONString(queryRequest));
         JSONObject result = new JSONObject();
         try {
+            long start = System.currentTimeMillis();
             String scorllId = queryRequest.getScrollId();
             String subjectId = queryRequest.getSubjectId();
             if(null != scorllId ){// 导出数据
@@ -85,6 +86,8 @@ public class SearchDataController {
                     return ResponseWrapper.buildResponse(RTCodeEnum.C_SUBJECT_GRAMMAR_ERROR, "总数和分页不匹配");
                 }
             }
+            long end = System.currentTimeMillis();
+            logger.info("接口查询时长：statr:"+ start +" ; end:"+end + " ; time = " + (end - start) +  " ; count = "+result.get(ESConstant.ALLDOCNUMBER));
         } catch (Exception e) {
             logger.error("[queryData] Failed,The error message is :{}", e);
             return ResponseWrapper.buildResponse(RTCodeEnum.C_SERVICE_NOT_AVAILABLE, "Query failed");

cl_search_api/src/main/java/com/bfd/mf/service/SearchDataService.java

@@ -433,6 +433,7 @@ public class SearchDataService extends CrudService<SentimentModify, SentimentRep
                 esMonitorEntity.setQuoteCount(quoteCount);
                 esMonitorEntity.setAttitudesCount(attitudeCount);
                 esMonitorEntity.setCollectCount(collentCount);
+                // 视频、音频
                 esMonitorEntity.setOcrText(ocrText);
                 esMonitorEntity.setAsrText(asrText);
                 // 用户字段
@@ -599,6 +600,11 @@ public class SearchDataService extends CrudService<SentimentModify, SentimentRep
         return jsonObject;
     }
 
+    /**
+     *  根据docId 查询一条数据的详情及评论列表
+     * @param queryRequest
+     * @return
+     */
     public JSONObject queryOneDataByDocId(QueryRequest queryRequest) {
         logger.info("[SearchDataService] queryOneDataByDocId start ... ");
         // 先确认一下 要查的主贴是属于 专题还是 全部数据，因此需要查 subjectId,如果没有 subjectId 这个字段说明要查的是 日期索引的ES
@@ -616,14 +622,7 @@ public class SearchDataService extends CrudService<SentimentModify, SentimentRep
         String docId = queryRequest.getDocId();
         // 根据ID 获取一条详情数据
         JSONObject jsonObject =  getOneDataByDocId(docId, cluster, currentIndexList);
-        if(!jsonObject.containsKey(ESConstant.VALUELABEL) || null == jsonObject.get(ESConstant.VALUELABEL)){
-            jsonObject.put(ESConstant.VALUELABEL,"");
-        }else{
-            jsonObject.put(ESConstant.VALUELABEL,jsonObject.get(ESConstant.VALUELABEL).toString());
-        }
-        if(!jsonObject.containsKey(ESConstant.CATEGORYLABEL)){
-            jsonObject.put(ESConstant.CATEGORYLABEL,"");
-        }
+        jsonObject = setLable(jsonObject);
         // 替换几个 pathSize 中的链接的前缀
         if(jsonObject.containsKey(ESConstant.IMAGEPATHSIZE)){ //http://172.18.1.113:8080
             List<Map<String,String>>imagePathSize = (List<Map<String, String>>) jsonObject.get(ESConstant.IMAGEPATHSIZE);
@@ -663,6 +662,20 @@ public class SearchDataService extends CrudService<SentimentModify, SentimentRep
         return jsonObject;
     }
 
+    // 崔老师那个版本，需要添加 分类标签和 价值标签
+    private JSONObject setLable(JSONObject jsonObject) {
+        if(!jsonObject.containsKey(ESConstant.VALUELABEL) || null == jsonObject.get(ESConstant.VALUELABEL)){
+            jsonObject.put(ESConstant.VALUELABEL,"");
+        }else{
+            jsonObject.put(ESConstant.VALUELABEL,jsonObject.get(ESConstant.VALUELABEL).toString());
+        }
+        if(!jsonObject.containsKey(ESConstant.CATEGORYLABEL)){
+            jsonObject.put(ESConstant.CATEGORYLABEL,"");
+        }
+        return jsonObject;
+    }
+
+
     private JSONObject getSite(JSONObject jsonObject, String enSource) {
         List<Map<String, Object>> site = siteRepository.findSiteByEnSource(enSource);
         Map<String,Map<String,Object>> siteMap = new HashMap<>();
@@ -741,11 +754,11 @@ public class SearchDataService extends CrudService<SentimentModify, SentimentRep
      * 社交媒体类数据，将作者替换到 标题中做显示
      */
     private JSONObject socialDataChangeAuthorAndTitle(JSONObject jsonObject) {
-        if(jsonObject.containsKey(ESConstant.EN_SOURCE)){
-            if(jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.TWITTER)
-                    || jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.FACEBOOK)
-                    || jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.SINA))
-            {
+        if(jsonObject.containsKey(ESConstant.DOC_TYPE)){
+//            if(jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.TWITTER)
+//                    || jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.FACEBOOK)
+//                    || jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.SINA)) {
+            if(jsonObject.get(ESConstant.DOC_TYPE).equals(ESConstant.SOCIAL)){
                 String author = jsonObject.getString(ESConstant.AUTHOR);
                 jsonObject.put(ESConstant.TITLE,author);
                 if(jsonObject.get(ESConstant.EN_SOURCE).equals(ESConstant.SINA)){