fix bugs generated by mypy.

api/core/workflow/nodes/document_extractor/node.py

@@ -413,8 +413,10 @@ def _extract_text_from_csv(file_content: bytes) -> str:
     except Exception as e:
         raise TextExtractionError(f"Failed to extract text from CSV: {str(e)}") from e
 
+
 def _extract_text_from_excel(file_content: bytes) -> str:
     """Extract text from an Excel file using pandas."""
+
     def _construct_markdown_table(df: pd.DataFrame) -> str:
         """Manually construct a Markdown table from a DataFrame."""
         # Construct the header row
@@ -432,6 +434,7 @@ def _extract_text_from_excel(file_content: bytes) -> str:
         # Combine all rows into a single string
         markdown_table = "\n".join([header_row, separator_row] + data_rows)
         return markdown_table
+
     try:
         excel_file = pd.ExcelFile(io.BytesIO(file_content))
         markdown_table = ""
@@ -441,10 +444,10 @@ def _extract_text_from_excel(file_content: bytes) -> str:
                 df.dropna(how="all", inplace=True)
 
                 # Combine multi-line text in each cell into a single line
-                df = df.applymap(lambda x: ' '.join(str(x).splitlines()) if isinstance(x, str) else x)
+                df = df.applymap(lambda x: " ".join(str(x).splitlines()) if isinstance(x, str) else x)  # type: ignore
 
                 # Combine multi-line text in column names into a single line
-                df.columns = [' '.join(col.splitlines()) for col in df.columns]
+                df.columns = pd.Index([" ".join(col.splitlines()) for col in df.columns])
 
                 # Manually construct the Markdown table
                 markdown_table += _construct_markdown_table(df) + "\n\n"