From 1140bd79a0ba3ac7ad4a215f8455e9e93b0987a7 Mon Sep 17 00:00:00 2001
From: Matt Robinson <mrobinson@unstructuredai.io>
Date: Wed, 5 Apr 2023 18:28:14 -0400
Subject: [PATCH] feat: adds support for MSFT Outlook files in
 `UnstructuredEmailLoader` (#2450)

### Summary

Adds support for MSFT Outlook emails saved in `.msg` format to
`UnstructuredEmailLoader`. Works if the user has `unstructured>=0.5.8`
installed.

### Testing

The following tests use the example files under `example-docs` in the
Unstructured repo.

```python
from langchain.document_loaders import UnstructuredEmailLoader

loader = UnstructuredEmailLoader("fake-email.eml")
loader.load()

loader = UnstructuredEmailLoader("fake-email.msg")
loader.load()
```
---
 langchain/document_loaders/email.py | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/langchain/document_loaders/email.py b/langchain/document_loaders/email.py
index b6a31ed7..bd307574 100644
--- a/langchain/document_loaders/email.py
+++ b/langchain/document_loaders/email.py
@@ -4,16 +4,32 @@ from typing import List
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
-from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from langchain.document_loaders.unstructured import (
+    UnstructuredFileLoader,
+    satisfies_min_unstructured_version,
+)
 
 
 class UnstructuredEmailLoader(UnstructuredFileLoader):
     """Loader that uses unstructured to load email files."""
 
     def _get_elements(self) -> List:
-        from unstructured.partition.email import partition_email
+        from unstructured.file_utils.filetype import FileType, detect_filetype
 
-        return partition_email(filename=self.file_path)
+        filetype = detect_filetype(self.file_path)
+
+        if filetype == FileType.EML:
+            from unstructured.partition.email import partition_email
+
+            return partition_email(filename=self.file_path)
+        elif satisfies_min_unstructured_version("0.5.8") and filetype == FileType.MSG:
+            from unstructured.partition.msg import partition_msg
+
+            return partition_msg(filename=self.file_path)
+        else:
+            raise ValueError(
+                f"Filetype {filetype} is not supported in UnstructuredEmailLoader."
+            )
 
 
 class OutlookMessageLoader(BaseLoader):