From 43bd2ad6423fd153e5bd33af0e82abfb0bb7a3a5 Mon Sep 17 00:00:00 2001
From: Wang Xin <xinwang614@gmail.com>
Date: Sat, 6 Jul 2024 17:29:59 +0800
Subject: [PATCH] fix: table recognition content is not escaped properly
 (#13277)

---
 ppstructure/table/matcher.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/ppstructure/table/matcher.py b/ppstructure/table/matcher.py
index 51e6250f4..ae32b4b15 100755
--- a/ppstructure/table/matcher.py
+++ b/ppstructure/table/matcher.py
@@ -14,6 +14,7 @@
 
 import numpy as np
 from ppstructure.table.table_master_match import deal_eb_token, deal_bb
+import html
 
 
 def distance(box_1, box_2):
@@ -133,6 +134,8 @@ class TableMatch:
                                 and " " != content[-1]
                             ):
                                 content += " "
+                        # escape content
+                        content = html.escape(content)
                         end_html.extend(content)
                     if b_with:
                         end_html.extend("</b>")