From fd2b9fe3d080525fa06112127b5045b375861a7b Mon Sep 17 00:00:00 2001
From: haiyangpengai <xxxx>
Date: Wed, 4 Jun 2025 12:58:59 +0800
Subject: [PATCH] fix bugs generated by mypy.

---
 .../workflow/nodes/document_extractor/node.py | 25 +++++++++++--------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/api/core/workflow/nodes/document_extractor/node.py b/api/core/workflow/nodes/document_extractor/node.py
index e0d75ddab8..429fed2d04 100644
--- a/api/core/workflow/nodes/document_extractor/node.py
+++ b/api/core/workflow/nodes/document_extractor/node.py
@@ -396,13 +396,13 @@ def _extract_text_from_csv(file_content: bytes) -> str:
 
         if not rows:
             return ""
-        
+
         # Combine multi-line text in the header row
         header_row = [cell.replace("\n", " ").replace("\r", "") for cell in rows[0]]
 
         # Create Markdown table
         markdown_table = "| " + " | ".join(header_row) + " |\n"
-        markdown_table += "| " + " | ".join(["-" * len(col) for col in rows[0]])  + " |\n"
+        markdown_table += "| " + " | ".join(["-" * len(col) for col in rows[0]]) + " |\n"
 
         # Process each data row and combine multi-line text in each cell
         for row in rows[1:]:
@@ -413,25 +413,28 @@ 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
         header_row = "| " + " | ".join(df.columns) + " |"
-        
+
         # Construct the separator row
         separator_row = "| " + " | ".join(["-" * len(col) for col in df.columns]) + " |"
-        
+
         # Construct the data rows
         data_rows = []
         for _, row in df.iterrows():
             data_row = "| " + " | ".join(map(str, row)) + " |"
             data_rows.append(data_row)
-        
+
         # 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 = ""
@@ -439,13 +442,13 @@ def _extract_text_from_excel(file_content: bytes) -> str:
             try:
                 df = excel_file.parse(sheet_name=sheet_name)
                 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"
             except Exception as e:
@@ -616,4 +619,4 @@ def _extract_text_from_properties(file_content: bytes) -> str:
 
         return "\n".join(result)
     except Exception as e:
-        raise TextExtractionError(f"Failed to extract text from properties file: {str(e)}") from e
\ No newline at end of file
+        raise TextExtractionError(f"Failed to extract text from properties file: {str(e)}") from e