From ff834b33106fec4d38ebce16103910870693c02e Mon Sep 17 00:00:00 2001
From: xiaoCJ <406612557@qq.com>
Date: Sun, 25 Jun 2023 11:15:14 +0800
Subject: [PATCH] =?UTF-8?q?=E5=8E=BB=E9=99=A4=E5=89=8D=E7=AB=AF=E6=A0=87?=
 =?UTF-8?q?=E7=AD=BE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../java/com/ruoyi/biemo/business/service/DocInfoService.java  | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/ruoyi-biemo/src/main/java/com/ruoyi/biemo/business/service/DocInfoService.java b/ruoyi-biemo/src/main/java/com/ruoyi/biemo/business/service/DocInfoService.java
index 2fe2937..8138bb3 100644
--- a/ruoyi-biemo/src/main/java/com/ruoyi/biemo/business/service/DocInfoService.java
+++ b/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;