Add support for detecting and handling application/msword files. (#3318)

Co-authored-by: Douwe Maan <[email protected]>

Author: DenysMoskalenko

pydantic_ai_slim/pydantic_ai/messages.py

@@ -34,6 +34,7 @@
     'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
     'text/html',
     'text/markdown',
+    'application/msword',
     'application/vnd.ms-excel',
 ]
 VideoMediaType: TypeAlias = Literal[
@@ -434,8 +435,12 @@ def _infer_media_type(self) -> str:
             return 'application/pdf'
         elif self.url.endswith('.rtf'):
             return 'application/rtf'
+        elif self.url.endswith('.doc'):
+            return 'application/msword'
         elif self.url.endswith('.docx'):
             return 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
+        elif self.url.endswith('.xls'):
+            return 'application/vnd.ms-excel'
         elif self.url.endswith('.xlsx'):
             return 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
 
@@ -645,6 +650,7 @@ class ToolReturn:
     'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx',
     'text/html': 'html',
     'text/markdown': 'md',
+    'application/msword': 'doc',
     'application/vnd.ms-excel': 'xls',
 }
 _audio_format_lookup: dict[str, AudioFormat] = {

tests/test_messages.py

@@ -147,6 +147,7 @@ def test_binary_content_video(media_type: str, format: str):
         ('application/pdf', 'pdf'),
         ('text/plain', 'txt'),
         ('text/csv', 'csv'),
+        ('application/msword', 'doc'),
         ('application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'docx'),
         ('application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'xlsx'),
         ('text/html', 'html'),
@@ -209,6 +210,7 @@ def test_image_url_invalid():
     pytest.param(DocumentUrl('foobar.pdf'), 'application/pdf', 'pdf', id='pdf'),
     pytest.param(DocumentUrl('foobar.txt'), 'text/plain', 'txt', id='txt'),
     pytest.param(DocumentUrl('foobar.csv'), 'text/csv', 'csv', id='csv'),
+    pytest.param(DocumentUrl('foobar.doc'), 'application/msword', 'doc', id='doc'),
     pytest.param(
         DocumentUrl('foobar.docx'),
         'application/vnd.openxmlformats-officedocument.wordprocessingml.document',