add testing scripts for extract_text_from_excel.

api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py

@@ -1,5 +1,7 @@
+import io
 from unittest.mock import Mock, patch
 
+import pandas as pd
 import pytest
 from docx.oxml.text.paragraph import CT_P
 
@@ -16,8 +18,7 @@ from core.workflow.nodes.document_extractor.node import (
     _extract_text_from_plain_text,
 )
 from core.workflow.nodes.enums import NodeType
-import pandas as pd
-import io
+
 
 @pytest.fixture
 def document_extractor_node():
@@ -191,10 +192,7 @@ def test_extract_text_from_excel_single_sheet(mock_excel_file):
     """Test extracting text from Excel file with single sheet and multiline content."""
 
     # Test multi-line cell
-    data = {
-        'Name\nwith\nnewline': ['John\nDoe', 'Jane\nSmith'],
-        'Age': [25, 30]
-    }
+    data = {"Name\nwith\nnewline": ["John\nDoe", "Jane\nSmith"], "Age": [25, 30]}
 
     df = pd.DataFrame(data)
 
@@ -212,21 +210,16 @@ def test_extract_text_from_excel_single_sheet(mock_excel_file):
     assert expected_manual == result
     mock_excel_instance.parse.assert_called_once_with(sheet_name="Sheet1")
 
+
 @patch("pandas.ExcelFile")
 def test_extract_text_from_excel_multiple_sheets(mock_excel_file):
     """Test extracting text from Excel file with multiple sheets and multiline content."""
 
     # Test multi-line cell
-    data1 = {
-        'Product\nName': ['Apple\nRed', 'Banana\nYellow'],
-        'Price': [1.50, 0.99]
-    }
+    data1 = {"Product\nName": ["Apple\nRed", "Banana\nYellow"], "Price": [1.50, 0.99]}
     df1 = pd.DataFrame(data1)
 
-    data2 = {
-        'City\nName': ['New\nYork', 'Los\nAngeles'],
-        'Population': [8000000, 3900000]
-    }
+    data2 = {"City\nName": ["New\nYork", "Los\nAngeles"], "Population": [8000000, 3900000]}
     df2 = pd.DataFrame(data2)
 
     # Mock ExcelFile
@@ -248,6 +241,7 @@ def test_extract_text_from_excel_multiple_sheets(mock_excel_file):
 
     assert mock_excel_instance.parse.call_count == 2
 
+
 @patch("pandas.ExcelFile")
 def test_extract_text_from_excel_empty_sheets(mock_excel_file):
     """Test extracting text from Excel file with empty sheets."""
@@ -269,15 +263,13 @@ def test_extract_text_from_excel_empty_sheets(mock_excel_file):
 
     mock_excel_instance.parse.assert_called_once_with(sheet_name="EmptySheet")
 
+
 @patch("pandas.ExcelFile")
 def test_extract_text_from_excel_sheet_parse_error(mock_excel_file):
     """Test handling of sheet parsing errors - should continue with other sheets."""
 
     # Test error
-    data = {
-        'Data': ['Test'],
-        'Value': [123]
-    }
+    data = {"Data": ["Test"], "Value": [123]}
     df = pd.DataFrame(data)
 
     # Mock ExcelFile
@@ -295,15 +287,13 @@ def test_extract_text_from_excel_sheet_parse_error(mock_excel_file):
 
     assert mock_excel_instance.parse.call_count == 2
 
+
 @patch("pandas.ExcelFile")
 def test_extract_text_from_excel_io_bytesio_usage(mock_excel_file):
     """Test that BytesIO is properly used with the file content."""
 
     # Test bytesio
-    data = {
-        'Test': [1],
-        'Data': ['A']
-    }
+    data = {"Test": [1], "Data": ["A"]}
     df = pd.DataFrame(data)
 
     # Mock ExcelFile
@@ -322,6 +312,7 @@ def test_extract_text_from_excel_io_bytesio_usage(mock_excel_file):
     expected_manual = "| Test | Data |\n| ---- | ---- |\n| 1 | A |\n\n"
     assert expected_manual == result
 
+
 @patch("pandas.ExcelFile")
 def test_extract_text_from_excel_all_sheets_fail(mock_excel_file):
     """Test when all sheets fail to parse - should return empty string."""