fix layout recovery error: list index out of range (#12541)

ppstructure/recovery/table_process.py

@@ -249,6 +249,9 @@ class HtmlToDocx(HTMLParser):
         table = doc.add_table(len(rows), cols_len)
         table.style = doc.styles["Table Grid"]
 
+        num_rows = len(table.rows)
+        num_cols = len(table.columns)
+
         cell_row = 0
         for index, row in enumerate(rows):
             cols = get_table_columns(row)
@@ -261,6 +264,9 @@ class HtmlToDocx(HTMLParser):
                 if col.name == "th":
                     cell_html = "<b>%s</b>" % cell_html
 
+                if cell_row >= num_rows or cell_col >= num_cols:
+                    continue
+
                 docx_cell = table.cell(cell_row, cell_col)
 
                 while docx_cell.text != "":  # Skip the merged cell