Add .doc file support via Document Intelligence

Support for legacy .doc format in addition to .docx.

- Added DOC to DocumentIntelligenceFileType enum
- Added .doc MIME type (application/msword)
- Added .doc extension handling
- Updated default file_types to include DOC
- Added DOC to no_ocr_types list

Fixes: #23

Author: RoomWithOutRoof

packages/markitdown/src/markitdown/converters/_doc_intel_converter.py

@@ -56,6 +56,7 @@ class DocumentIntelligenceFileType(str, Enum):
     """Enum of file types supported by the Document Intelligence Converter."""
 
     # No OCR
+    DOC = "doc"
     DOCX = "docx"
     PPTX = "pptx"
     XLSX = "xlsx"
@@ -72,7 +73,9 @@ def _get_mime_type_prefixes(types: List[DocumentIntelligenceFileType]) -> List[s
     """Get the MIME type prefixes for the given file types."""
     prefixes: List[str] = []
     for type_ in types:
-        if type_ == DocumentIntelligenceFileType.DOCX:
+        if type_ == DocumentIntelligenceFileType.DOC:
+            prefixes.append("application/msword")
+        elif type_ == DocumentIntelligenceFileType.DOCX:
             prefixes.append(
                 "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
             )
@@ -105,7 +108,9 @@ def _get_file_extensions(types: List[DocumentIntelligenceFileType]) -> List[str]
     """Get the file extensions for the given file types."""
     extensions: List[str] = []
     for type_ in types:
-        if type_ == DocumentIntelligenceFileType.DOCX:
+        if type_ == DocumentIntelligenceFileType.DOC:
+            extensions.append(".doc")
+        elif type_ == DocumentIntelligenceFileType.DOCX:
             extensions.append(".docx")
         elif type_ == DocumentIntelligenceFileType.PPTX:
             extensions.append(".pptx")
@@ -137,6 +142,7 @@ def __init__(
         api_version: str = "2024-07-31-preview",
         credential: AzureKeyCredential | TokenCredential | None = None,
         file_types: List[DocumentIntelligenceFileType] = [
+            DocumentIntelligenceFileType.DOC,
             DocumentIntelligenceFileType.DOCX,
             DocumentIntelligenceFileType.PPTX,
             DocumentIntelligenceFileType.XLSX,
@@ -215,6 +221,7 @@ def _analysis_features(self, stream_info: StreamInfo) -> List[str]:
 
         # Types that don't support ocr
         no_ocr_types = [
+            DocumentIntelligenceFileType.DOC,
             DocumentIntelligenceFileType.DOCX,
             DocumentIntelligenceFileType.PPTX,
             DocumentIntelligenceFileType.XLSX,