From 79e2edc8356c23e97886058d04e4433eb1a0d4be Mon Sep 17 00:00:00 2001
From: Jay Xu <mustangxu@users.noreply.github.com>
Date: Tue, 12 Aug 2025 14:58:36 +0800
Subject: [PATCH] Fix "File contains no valid workbook part" (#9360)

### What problem does this PR solve?

fix "File contains no valid workbook part"

stacktrace:
```
Traceback (most recent call last):
  File "/ragflow/deepdoc/parser/excel_parser.py", line 54, in _load_excel_to_workbook
    return RAGFlowExcelParser._dataframe_to_workbook(df)
  File "/ragflow/deepdoc/parser/excel_parser.py", line 69, in _dataframe_to_workbook
    ws.cell(row=row_num, column=col_num, value=value)
  File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/worksheet/worksheet.py", line 246, in cell
    cell.value = value
  File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 218, in value
    self._bind_value(value)
  File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 197, in _bind_value
    value = self.check_string(value)
  File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 165, in check_string
    raise IllegalCharacterError(f"{value} cannot be used in worksheets.")
```

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---
 deepdoc/parser/excel_parser.py | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/deepdoc/parser/excel_parser.py b/deepdoc/parser/excel_parser.py
index 5c1e20219..e0d642775 100644
--- a/deepdoc/parser/excel_parser.py
+++ b/deepdoc/parser/excel_parser.py
@@ -12,6 +12,7 @@
 #
 
 import logging
+import re
 import sys
 from io import BytesIO
 
@@ -20,6 +21,8 @@ from openpyxl import Workbook, load_workbook
 
 from rag.nlp import find_codec
 
+# copied from `/openpyxl/cell/cell.py`
+ILLEGAL_CHARACTERS_RE = re.compile(r'[\000-\010]|[\013-\014]|[\016-\037]')
 
 class RAGFlowExcelParser:
 
@@ -61,8 +64,18 @@ class RAGFlowExcelParser:
             except Exception as e_pandas:
                 raise Exception(f"pandas.read_excel error: {e_pandas}, original openpyxl error: {e}")
 
+    @staticmethod
+    def _clean_dataframe(df: pd.DataFrame):
+        def clean_string(s):
+            if isinstance(s, str):
+                return ILLEGAL_CHARACTERS_RE.sub(" ", s)
+            return s
+
+        return df.apply(lambda col: col.map(clean_string))
+
     @staticmethod
     def _dataframe_to_workbook(df):
+        df = RAGFlowExcelParser._clean_dataframe(df)
         wb = Workbook()
         ws = wb.active
         ws.title = "Data"