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/langchain_community/document_loaders/directory.py

@@ -2,7 +2,7 @@ import concurrent
 import logging
 import random
 from pathlib import Path
-from typing import Any, Callable, Iterator, List, Optional, Sequence, Type, Union
+from typing import Any, Callable, Iterator, List, Optional, Sequence, Tuple, Type, Union
 
 from langchain_core.documents import Document
 
@@ -32,7 +32,7 @@ class DirectoryLoader(BaseLoader):
     def __init__(
         self,
         path: str,
-        glob: str = "**/[!.]*",
+        glob: Union[List[str], Tuple[str], str] = "**/[!.]*",
         silent_errors: bool = False,
         load_hidden: bool = False,
         loader_cls: FILE_LOADER_TYPE = UnstructuredFileLoader,
@@ -51,8 +51,8 @@ class DirectoryLoader(BaseLoader):
 
         Args:
             path: Path to directory.
-            glob: Glob pattern to use to find files. Defaults to "**/[!.]*"
-               (all files except hidden).
+            glob: A glob pattern or list of glob patterns to use to find files.
+                Defaults to "**/[!.]*" (all files except hidden).
             exclude: A pattern or list of patterns to exclude from results.
                 Use glob syntax.
             silent_errors: Whether to silently ignore errors. Defaults to False.
@@ -124,7 +124,20 @@ class DirectoryLoader(BaseLoader):
         if not p.is_dir():
             raise ValueError(f"Expected directory, got file: '{self.path}'")
 
-        paths = p.rglob(self.glob) if self.recursive else p.glob(self.glob)
+        # glob multiple patterns if a list is provided, e.g., multiple file extensions
+        if isinstance(self.glob, (list, tuple)):
+            paths = []
+            for pattern in self.glob:
+                paths.extend(
+                    list(p.rglob(pattern) if self.recursive else p.glob(pattern))
+                )
+        elif isinstance(self.glob, str):
+            paths = list(p.rglob(self.glob) if self.recursive else p.glob(self.glob))
+        else:
+            raise TypeError(
+                f"Expected glob to be str or sequence of str, but got {type(self.glob)}"
+            )
+
         items = [
             path
             for path in paths