community: DocumentLoaderAsParser wrapper (#27749)

## Description

This pull request introduces the `DocumentLoaderAsParser` class, which
acts as an adapter to transform document loaders into parsers within the
LangChain framework. The class enables document loaders that accept a
`file_path` parameter to be utilized as blob parsers. This is
particularly useful for integrating various document loading
capabilities seamlessly into the LangChain ecosystem.

When merged in together with PR
https://github.com/langchain-ai/langchain/pull/27716 It opens options
for `SharePointLoader` / `OneDriveLoader` to process any filetype that
has a document loader.

### Features

- **Flexible Parsing**: The `DocumentLoaderAsParser` class can adapt any
document loader that meets the criteria of accepting a `file_path`
argument, allowing for lazy parsing of documents.
- **Compatibility**: The class has been designed to work with various
document loaders, making it versatile for different use cases.

### Usage Example

To use the `DocumentLoaderAsParser`, you would initialize it with a
suitable document loader class and any required parameters. Here’s an
example of how to do this with the `UnstructuredExcelLoader`:

```python
from langchain_community.document_loaders.blob_loaders import Blob
from langchain_community.document_loaders.parsers.documentloader_adapter import DocumentLoaderAsParser
from langchain_community.document_loaders.excel import UnstructuredExcelLoader

# Initialize the parser adapter with UnstructuredExcelLoader
xlsx_parser = DocumentLoaderAsParser(UnstructuredExcelLoader, mode="paged")

# Use parser, for ex. pass it to MimeTypeBasedParser
MimeTypeBasedParser(
    handlers={
        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": xlsx_parser
    }
)
```


- **Dependencies:** None
- **Twitter handle:** @martintriska1

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>

libs/community/langchain_community/document_loaders/parsers/documentloader_adapter.py

@@ -0,0 +1,67 @@
+import inspect
+from typing import Any, Dict, Iterator, Type
+
+from langchain.document_loaders.base import BaseBlobParser, BaseLoader
+from langchain_core._api import beta
+from langchain_core.documents import Document
+from langchain_core.documents.base import Blob
+
+
+@beta()
+class DocumentLoaderAsParser(BaseBlobParser):
+    """A wrapper class that adapts a document loader to function as a parser.
+
+    This class is a work-around that adapts a document loader to function as a parser.
+    It is recommended to use a proper parser, if available.
+
+    Requires the document loader to accept a `file_path` parameter.
+    """
+
+    DocumentLoaderType: Type[BaseLoader]
+    doc_loader_kwargs: Dict[str, Any]
+
+    def __init__(self, document_loader_class: Type[BaseLoader], **kwargs: Any) -> None:
+        """
+        Initializes the DocumentLoaderAsParser with a specific document loader class
+        and additional arguments.
+
+        Args:
+            document_loader_class (Type[BaseLoader]): The document loader class to adapt
+            as a parser.
+            **kwargs: Additional arguments passed to the document loader's constructor.
+
+        Raises:
+            TypeError: If the specified document loader does not accept a `file_path` parameter,
+                       an exception is raised, as only loaders with this parameter can be adapted.
+
+        Example:
+            ```
+            from langchain_community.document_loaders.excel import UnstructuredExcelLoader
+
+            # Initialize parser adapter with a document loader
+            excel_parser = DocumentLoaderAsParser(UnstructuredExcelLoader, mode="elements")
+            ```
+        """  # noqa: E501
+        super().__init__()
+        self.DocumentLoaderClass = document_loader_class
+        self.document_loader_kwargs = kwargs
+
+        # Ensure the document loader class has a `file_path` parameter
+        init_signature = inspect.signature(document_loader_class.__init__)
+        if "file_path" not in init_signature.parameters:
+            raise TypeError(
+                f"{document_loader_class.__name__} does not accept `file_path`."
+                "Only document loaders with `file_path` parameter"
+                "can be morphed into a parser."
+            )
+
+    def lazy_parse(self, blob: Blob) -> Iterator[Document]:
+        """
+        Use underlying DocumentLoader to lazily parse the blob.
+        """
+        doc_loader = self.DocumentLoaderClass(
+            file_path=blob.path, **self.document_loader_kwargs
+        )  # type: ignore
+        for document in doc_loader.lazy_load():
+            document.metadata.update(blob.metadata)
+            yield document