feat: In FileTypeRouter add .msg to "application/vnd.ms-outlook" mapping (#8910)

* Add .msg mimetype support in file type router

* Add reno

* Update tests

Author: sjrl

haystack/components/routers/file_type_router.py

@@ -15,9 +15,14 @@
 logger = logging.getLogger(__name__)
 
 
-# we add markdown because it is not added by the mimetypes module
-# see https://github.com/python/cpython/pull/17995
-CUSTOM_MIMETYPES = {".md": "text/markdown", ".markdown": "text/markdown"}
+CUSTOM_MIMETYPES = {
+    # we add markdown because it is not added by the mimetypes module
+    # see https://github.com/python/cpython/pull/17995
+    ".md": "text/markdown",
+    ".markdown": "text/markdown",
+    # we add msg because it is not added by the mimetypes module
+    ".msg": "application/vnd.ms-outlook",
+}
 
 
 @component

releasenotes/notes/add-msg-mime-type-file-router-b33d8916caaf5976.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    In the FileTypeRouter add explicit support for classifying .msg files with mimetype "application/vnd.ms-outlook" since the mimetypes module returns None for .msg files by default.

test/components/routers/test_file_router.py

@@ -87,14 +87,16 @@ def test_run(self, test_files_path):
             test_files_path / "txt" / "doc_2.txt",
             test_files_path / "audio" / "the context for this answer is here.wav",
             test_files_path / "images" / "apple.jpg",
+            test_files_path / "msg" / "sample.msg",
         ]
 
-        router = FileTypeRouter(mime_types=[r"text/plain", r"audio/x-wav", r"image/jpeg"])
+        router = FileTypeRouter(mime_types=[r"text/plain", r"audio/x-wav", r"image/jpeg", "application/vnd.ms-outlook"])
         output = router.run(sources=file_paths)
         assert output
         assert len(output[r"text/plain"]) == 2
         assert len(output[r"audio/x-wav"]) == 1
         assert len(output[r"image/jpeg"]) == 1
+        assert len(output["application/vnd.ms-outlook"]) == 1
         assert not output.get("unclassified")
 
     def test_run_with_single_meta(self, test_files_path):