fix: table recognition content is not escaped properly

GreatV · Jul 6, 2024 · 50e025b · 50e025b
1 parent 7a3c580
commit 50e025b
Showing 1 changed file with 3 additions and 0 deletions.
diff --git 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 @@ def get_pred_html(self, pred_structures, matched_index, ocr_contents):
                                 and " " != content[-1]
                             ):
                                 content += " "
+                        # escape content
+                        content = html.escape(content)
                         end_html.extend(content)
                     if b_with:
                         end_html.extend("</b>")