去除前端标签

ruoyi-biemo/src/main/java/com/ruoyi/biemo/business/service/DocInfoService.java

@@ -450,13 +450,14 @@ public class DocInfoService extends EsService<DocInfo> {
         return response;
     }
     public List<WordCloudItem> getWordCloudByCateId(String categoryId) {
+        String regex = "<.*?>"; // 匹配HTML标签的正则表达式
         Map<String,Integer> temp = new ConcurrentHashMap<>();
         List<WordCloudItem> wordCloudItemList = new ArrayList<>();
         DocInfo docInfo = new DocInfo();
         docInfo.setCateId(categoryId);
         List<DocInfo> docInfoList = selectDocInfoList(docInfo);
         if(CollectionUtils.isNotEmpty(docInfoList)){
-            List<Term> termList = docInfoList.parallelStream().filter(ObjectUtils::isNotEmpty).flatMap(_docInfo -> NLPTokenizer.segment(_docInfo.getContent()).stream()).collect(Collectors.toList());
+            List<Term> termList = docInfoList.parallelStream().filter(ObjectUtils::isNotEmpty).flatMap(_docInfo -> NLPTokenizer.segment(_docInfo.getContent().replaceAll(regex, "").replaceAll("\\s+","").replaceAll("[,，　　'“”.。]", "").trim()).stream()).collect(Collectors.toList());
             if(CollectionUtils.isNotEmpty(termList)){
                 termList.parallelStream().forEach(term -> {
                     String word = term.word;