chore: enhance Markdown table handling with cell content escaping

--bug=1065801@tapd-62980211 --user=刘瑞斌 【知识库】导出的zip文件导入工作流知识库后不显示内容 https://www.tapd.cn/62980211/s/1836723

Author: liuruibin

apps/common/handle/impl/qa/md_parse_qa_handle.py

@@ -8,6 +8,7 @@
 """
 import re
 import traceback
+from typing import Any
 
 from charset_normalizer import detect
 
@@ -47,7 +48,7 @@ def parse_markdown_table(self, content):
                     line = lines[i].strip()
                     if not line.startswith('|'):
                         break
-                    row = [cell.strip() for cell in line.split('|')[1:-1]]
+                    row = [self._unescape_cell_content(cell) for cell in line.split('|')[1:-1]]
                     if len(row) > 0:
                         table_data.append(row)
                     i += 1
@@ -59,6 +60,11 @@ def parse_markdown_table(self, content):
 
         return tables
 
+    def _unescape_cell_content(self, cell) -> Any:
+        text = cell.strip().replace('|', '|')
+        text = text.replace('|<br>|', '|\n|')
+        return text
+
     def handle(self, file, get_buffer, save_image):
         buffer = get_buffer(file)
         try:

apps/common/handle/impl/text/xlsx_split_handle.py

@@ -153,9 +153,8 @@ def get_content(self, file, save_image):
                 md_table = '| ' + ' | '.join(headers) + ' |\n'
                 md_table += '| ' + ' | '.join(['---'] * len(headers)) + ' |\n'
                 for row in rows:
-                    r = [f'{value}' if value is not None else '' for key, value in row.items()]
-                    md_table += '| ' + ' | '.join(
-                        [str(cell).replace('\n', '<br>') if cell is not None else '' for cell in r]) + ' |\n'
+                    r = [self._escape_cell_content(value) for key, value in row.items()]
+                    md_table += '| ' + ' | '.join(r) + ' |\n'
 
                 md_tables += md_table + '\n\n'
 
@@ -164,6 +163,25 @@ def get_content(self, file, save_image):
             maxkb_logger.error(f'excel split handle error: {e}')
             return f'error: {e}'
 
+    def _escape_cell_content(self, cell_value):
+        """转义单元格内容,避免破坏 Markdown 表格结构"""
+        if cell_value is None:
+            return ''
+
+        cell_str = str(cell_value)
+
+        # 替换换行符为 <br>
+        cell_str = cell_str.replace('\n', '<br>')
+
+        # 转义管道符 | 为 HTML 实体
+        cell_str = cell_str.replace('|', '&#124;')
+
+        # 如果内容包含反引号,需要转义
+        if '`' in cell_str:
+            cell_str = cell_str.replace('`', '&#96;')
+
+        return cell_str
+
     def support(self, file, get_buffer):
         file_name: str = file.name.lower()
         if file_name.endswith(".xlsx"):