community: glob multiple patterns when using DirectoryLoader (#22852)

- **Description:** Updated
*community.langchain_community.document_loaders.directory.py* to enable
the use of multiple glob patterns in the `DirectoryLoader` class. Now,
the glob parameter is of type `list[str] | str` and still defaults to
the same value as before. I updated the docstring of the class to
reflect this, and added a unit test to
*community.tests.unit_tests.document_loaders.test_directory.py* named
`test_directory_loader_glob_multiple`. This test also shows an example
of how to use the new functionality.
- ~~Issue:~~**Discussion Thread:**
https://github.com/langchain-ai/langchain/discussions/18559
- **Dependencies:** None
- **Twitter handle:** N/a

- [x] **Add tests and docs**
    - Added test (described above)
    - Updated class docstring

- [x] **Lint and test**

---------

Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>

libs/community/tests/unit_tests/document_loaders/test_directory.py

@@ -5,6 +5,7 @@ import pytest
 from langchain_core.documents import Document
 
 from langchain_community.document_loaders import DirectoryLoader
+from langchain_community.document_loaders.text import TextLoader
 
 
 def test_raise_error_if_path_not_exist() -> None:
@@ -23,7 +24,7 @@ def test_raise_error_if_path_is_not_directory() -> None:
     assert str(e.value) == f"Expected directory, got file: '{__file__}'"
 
 
-class CustomLoader:
+class CustomLoader(TextLoader):
     """Test loader. Mimics interface of existing file loader."""
 
     def __init__(self, path: Path, **kwargs: Any) -> None:
@@ -56,3 +57,44 @@ def test_exclude_ignores_matching_files(tmp_path: Path) -> None:
 def test_exclude_as_string_converts_to_sequence() -> None:
     loader = DirectoryLoader("./some_directory", exclude="*.py")
     assert loader.exclude == ("*.py",)
+
+
+class CustomLoaderMetadataOnly(CustomLoader):
+    """Test loader that just returns the file path in metadata. For test_directory_loader_glob_multiple."""  # noqa: E501
+
+    def load(self) -> List[Document]:
+        metadata = {"source": self.path}
+        return [Document(page_content="", metadata=metadata)]
+
+    def lazy_load(self) -> Iterator[Document]:
+        return iter(self.load())
+
+
+def test_directory_loader_glob_multiple() -> None:
+    """Verify that globbing multiple patterns in a list works correctly."""
+
+    path_to_examples = "tests/examples/"
+    list_extensions = [".rst", ".txt"]
+    list_globs = [f"**/*{ext}" for ext in list_extensions]
+    is_file_type_loaded = {ext: False for ext in list_extensions}
+
+    loader = DirectoryLoader(
+        path=path_to_examples, glob=list_globs, loader_cls=CustomLoaderMetadataOnly
+    )
+
+    list_documents = loader.load()
+
+    for doc in list_documents:
+        path_doc = Path(doc.metadata.get("source", ""))
+        ext_doc = path_doc.suffix
+
+        if is_file_type_loaded.get(ext_doc, False):
+            continue
+        elif ext_doc in list_extensions:
+            is_file_type_loaded[ext_doc] = True
+        else:
+            # Loaded a filetype that was not specified in extensions list
+            assert False
+
+    for ext in list_extensions:
+        assert is_file_type_loaded.get(ext, False)