fix: escape directory to prevent \n on Windows directory name to fail on Pathlib + Tests (#4101)

* 📝 (utils.py): add format_directory_path function to properly escape and format directory paths for consistency and validity

* ✨ (test_format_directory_path.py): add unit tests for the format_directory_path function to ensure correct formatting of directory paths
📝 (test_format_directory_path.py): add documentation and examples for different types of directory paths in the unit tests to improve code readability and maintainability

* 🐛 (utils.py): fix the incorrect replacement of backslashes with newline characters in the format_directory_path function
📝 (test_rewrite_file_path.py): update test cases and function names to reflect the changes made in the format_directory_path function in utils.py

* 🐛 (test_format_directory_path.py): update parameter name from 'path' to 'input_path' for clarity and consistency
📝 (test_format_directory_path.py): improve test case descriptions and handle newline characters in paths correctly

src/backend/base/langflow/base/data/utils.py

@@ -44,6 +44,18 @@ def is_hidden(path: Path) -> bool:
     return path.name.startswith(".")
 
 
+def format_directory_path(path: str) -> str:
+    """Format a directory path to ensure it's properly escaped and valid.
+
+    Args:
+    path (str): The input path string.
+
+    Returns:
+    str: A properly formatted path string.
+    """
+    return path.replace("\n", "\\n")
+
+
 def retrieve_file_paths(
     path: str,
     *,
@@ -52,6 +64,7 @@ def retrieve_file_paths(
     depth: int,
     types: list[str] = TEXT_FILE_TYPES,
 ) -> list[str]:
+    path = format_directory_path(path)
     path_obj = Path(path)
     if not path_obj.exists() or not path_obj.is_dir():
         msg = f"Path {path} must exist and be a directory."

src/backend/tests/unit/utils/test_format_directory_path.py

@@ -0,0 +1,46 @@
+import pytest
+from langflow.base.data.utils import format_directory_path
+
+
+@pytest.mark.parametrize(
+    "input_path, expected",
+    [
+        # Test case 1: Standard path with no newlines (no change expected)
+        ("/home/user/documents/file.txt", "/home/user/documents/file.txt"),
+        # Test case 2: Path with newline character (replace \n with \\n)
+        ("/home/user/docu\nments/file.txt", "/home/user/docu\\nments/file.txt"),
+        # Test case 3: Path with multiple newline characters
+        ("/home/user/\ndocu\nments/file.txt", "/home/user/\\ndocu\\nments/file.txt"),
+        # Test case 4: Path with only newline characters
+        ("\n\n\n", "\\n\\n\\n"),
+        # Test case 5: Empty path (as per the original function, this remains an empty string)
+        ("", ""),
+        # Test case 6: Path with mixed newlines and other special characters
+        ("/home/user/my-\ndocs/special_file!.pdf", "/home/user/my-\\ndocs/special_file!.pdf"),
+        # Test case 7: Windows-style path with newline
+        ("C:\\Users\\\nDocuments\\file.txt", "C:\\Users\\\\nDocuments\\file.txt"),  # No conversion of backslashes
+        # Test case 8: Path with trailing newline
+        ("/home/user/documents/\n", "/home/user/documents/\\n"),
+        # Test case 9: Path with leading newline
+        ("\n/home/user/documents/", "\\n/home/user/documents/"),
+        # Test case 10: Path with multiple consecutive newlines
+        ("/home/user/docu\n\nments/file.txt", "/home/user/docu\\n\\nments/file.txt"),
+        # Test case 11: Windows-style path (backslashes remain unchanged)
+        ("C:\\Users\\Documents\\file.txt", "C:\\Users\\Documents\\file.txt"),
+        # Test case 12: Windows path with trailing backslash
+        ("C:\\Users\\Documents\\", "C:\\Users\\Documents\\"),
+        # Test case 13: Mixed separators (leave as is)
+        ("C:/Users\\Documents/file.txt", "C:/Users\\Documents/file.txt"),
+        # Test case 14: Network path (UNC) (leave backslashes as is)
+        ("\\\\server\\share\\file.txt", "\\\\server\\share\\file.txt"),
+    ],
+)
+def test_format_directory_path(input_path, expected):
+    result = format_directory_path(input_path)
+    assert result == expected
+
+
+# Additional test for type checking
+def test_format_directory_path_type():
+    result = format_directory_path("/home/user/file.txt")
+    assert isinstance(result, str)

src/backend/tests/unit/utils/test_rewrite_file_path.py

@@ -1,43 +1,38 @@
-from langflow.graph.utils import rewrite_file_path
+from langflow.base.data.utils import format_directory_path
 import pytest
 
 
 @pytest.mark.parametrize(
-    "file_path, expected",
+    "input_path, expected",
     [
-        # Test case 1: Standard path with multiple directories
-        ("/home/user/documents/file.txt", ["documents/file.txt"]),
-        # Test case 2: Path with only one directory
-        ("/documents/file.txt", ["documents/file.txt"]),
-        # Test case 3: Path with no directories (just filename)
-        ("file.txt", ["file.txt"]),
-        # Test case 4: Path with multiple levels and special characters
-        ("/home/user/my-docs/special_file!.pdf", ["my-docs/special_file!.pdf"]),
-        # Test case 5: Path with trailing slash
-        ("/home/user/documents/", ["user/documents"]),
-        # Test case 6: Empty path
-        ("", [""]),
-        # Test case 7: Path with only slashes
-        ("///", [""]),
-        # Test case 8: Path with dots
-        ("/home/user/../documents/./file.txt", ["./file.txt"]),
-        # Test case 9: Windows-style path
-        ("C:\\Users\\Documents\\file.txt", ["Documents/file.txt"]),
-        # Test case 10: Windows path with trailing backslash
-        ("C:\\Users\\Documents\\", ["Users/Documents"]),
-        # Test case 11: Mixed separators
-        ("C:/Users\\Documents/file.txt", ["Documents/file.txt"]),
-        # Test case 12: Network path (UNC)
-        ("\\\\server\\share\\file.txt", ["share/file.txt"]),
+        # Test case 1: Standard path with no newlines
+        ("/home/user/documents/file.txt", "/home/user/documents/file.txt"),
+        # Test case 2: Path with newline character
+        ("/home/user/docu\nments/file.txt", "/home/user/docu\\nments/file.txt"),
+        # Test case 3: Path with multiple newline characters
+        ("/home/user/\ndocu\nments/file.txt", "/home/user/\\ndocu\\nments/file.txt"),
+        # Test case 4: Path with only newline characters
+        ("\n\n\n", "\\n\\n\\n"),
+        # Test case 5: Empty path
+        ("", ""),
+        # Test case 6: Path with mixed newlines and other special characters
+        ("/home/user/my-\ndocs/special_file!.pdf", "/home/user/my-\\ndocs/special_file!.pdf"),
+        # Test case 7: Windows-style path with newline
+        ("C:\\Users\\\nDocuments\\file.txt", "C:\\Users\\\\nDocuments\\file.txt"),
+        # Test case 8: Path with trailing newline
+        ("/home/user/documents/\n", "/home/user/documents/\\n"),
+        # Test case 9: Path with leading newline
+        ("\n/home/user/documents/", "\\n/home/user/documents/"),
+        # Test case 10: Path with multiple consecutive newlines
+        ("/home/user/docu\n\nments/file.txt", "/home/user/docu\\n\\nments/file.txt"),
     ],
 )
-def test_rewrite_file_path(file_path, expected):
-    result = rewrite_file_path(file_path)
+def test_format_directory_path(input_path, expected):
+    result = format_directory_path(input_path)
     assert result == expected
 
 
 # Additional test for type checking
-def test_rewrite_file_path_type():
-    result = rewrite_file_path("/home/user/file.txt")
-    assert isinstance(result, list)
-    assert all(isinstance(item, str) for item in result)
+def test_format_directory_path_type():
+    result = format_directory_path("/home/user/file.txt")
+    assert isinstance(result, str)