From 1366d070fc656813c0c33cb5733290ade0fddf7c Mon Sep 17 00:00:00 2001
From: os1ma <39944763+os1ma@users.noreply.github.com>
Date: Mon, 29 May 2023 04:31:23 +0900
Subject: [PATCH] Add path validation to DirectoryLoader (#5327)

# Add path validation to DirectoryLoader

This PR introduces a minor adjustment to the DirectoryLoader by adding
validation for the path argument. Previously, if the provided path
didn't exist or wasn't a directory, DirectoryLoader would return an
empty document list due to the behavior of the `glob` method. This could
potentially cause confusion for users, as they might expect a
file-loading error instead.

So, I've added two validations to the load method of the
DirectoryLoader:

- Raise a FileNotFoundError if the provided path does not exist
- Raise a ValueError if the provided path is not a directory

Due to the relatively small scope of these changes, a new issue was not
created.

## Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

@eyurtsev
---
 langchain/document_loaders/directory.py       |  5 +++++
 .../document_loaders/test_directory.py        | 19 +++++++++++++++++++
 2 files changed, 24 insertions(+)
 create mode 100644 tests/unit_tests/document_loaders/test_directory.py

diff --git a/langchain/document_loaders/directory.py b/langchain/document_loaders/directory.py
index cf1065f2..003d6f01 100644
--- a/langchain/document_loaders/directory.py
+++ b/langchain/document_loaders/directory.py
@@ -74,6 +74,11 @@ class DirectoryLoader(BaseLoader):
     def load(self) -> List[Document]:
         """Load documents."""
         p = Path(self.path)
+        if not p.exists():
+            raise FileNotFoundError(f"Directory not found: '{self.path}'")
+        if not p.is_dir():
+            raise ValueError(f"Expected directory, got file: '{self.path}'")
+
         docs: List[Document] = []
         items = list(p.rglob(self.glob) if self.recursive else p.glob(self.glob))
 
diff --git a/tests/unit_tests/document_loaders/test_directory.py b/tests/unit_tests/document_loaders/test_directory.py
new file mode 100644
index 00000000..7fadecf3
--- /dev/null
+++ b/tests/unit_tests/document_loaders/test_directory.py
@@ -0,0 +1,19 @@
+import pytest
+
+from langchain.document_loaders import DirectoryLoader
+
+
+def test_raise_error_if_path_not_exist() -> None:
+    loader = DirectoryLoader("./not_exist_directory")
+    with pytest.raises(FileNotFoundError) as e:
+        loader.load()
+
+    assert str(e.value) == "Directory not found: './not_exist_directory'"
+
+
+def test_raise_error_if_path_is_not_directory() -> None:
+    loader = DirectoryLoader(__file__)
+    with pytest.raises(ValueError) as e:
+        loader.load()
+
+    assert str(e.value) == f"Expected directory, got file: '{__file__}'"