Merge branch 'main' into feature/xls-support

.devcontainer/devcontainer.json

@@ -6,7 +6,10 @@
 		// Sets the run context to one level up instead of the .devcontainer folder.
 		"context": "..",
 		// Update the 'dockerFile' property if you aren't using the standard 'Dockerfile' filename.
-		"dockerfile": "../Dockerfile"
+		"dockerfile": "../Dockerfile",
+		"args": {
+			"INSTALL_GIT": "true"
+		}
 	},
 
 	// Features to add to the dev container. More info: https://containers.dev/features.

Dockerfile

@@ -2,10 +2,15 @@ FROM python:3.13-slim-bullseye
 
 USER root
 
+ARG INSTALL_GIT=false
+RUN if [ "$INSTALL_GIT" = "true" ]; then \
+    apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*; \
+    fi
+
 # Runtime dependency
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ffmpeg \
- && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/*
 
 RUN pip install markitdown
 

README.md

@@ -125,7 +125,7 @@ contact [[email protected]](mailto:[email protected]) with any additio
 
 ### How to Contribute
 
-You can help by looking at issues or helping review PRs. Any issue or PR is welcome, but we have also marked some as 'open for contribution' and 'open for reviewing' to help faciliate community contributions. These are ofcourse just suggestions and you are welcome to contribute in any way you like.
+You can help by looking at issues or helping review PRs. Any issue or PR is welcome, but we have also marked some as 'open for contribution' and 'open for reviewing' to help facilitate community contributions. These are ofcourse just suggestions and you are welcome to contribute in any way you like.
 
 
 <div align="center">

pyproject.toml

@@ -36,6 +36,7 @@ dependencies = [
   "pdfminer.six",
   "puremagic",
   "pydub",
+  "olefile",
   "youtube-transcript-api",
   "SpeechRecognition",
   "pathvalidate",

src/markitdown/_markitdown.py

@@ -21,6 +21,7 @@
 
 import mammoth
 import markdownify
+import olefile
 import pandas as pd
 import pdfminer
 import pdfminer.high_level
@@ -33,6 +34,7 @@
 from charset_normalizer import from_path
 
 # Optional Transcription support
+IS_AUDIO_TRANSCRIPTION_CAPABLE = False
 try:
     # Using warnings' catch_warnings to catch
     # pydub's warning of ffmpeg or avconv missing
@@ -1100,6 +1102,79 @@ def _get_llm_description(self, local_path, extension, client, model, prompt=None
         return response.choices[0].message.content
 
 
+class OutlookMsgConverter(DocumentConverter):
+    """Converts Outlook .msg files to markdown by extracting email metadata and content.
+
+    Uses the olefile package to parse the .msg file structure and extract:
+    - Email headers (From, To, Subject)
+    - Email body content
+    """
+
+    def convert(
+        self, local_path: str, **kwargs: Any
+    ) -> Union[None, DocumentConverterResult]:
+        # Bail if not a MSG file
+        extension = kwargs.get("file_extension", "")
+        if extension.lower() != ".msg":
+            return None
+
+        try:
+            msg = olefile.OleFileIO(local_path)
+            # Extract email metadata
+            md_content = "# Email Message\n\n"
+
+            # Get headers
+            headers = {
+                "From": self._get_stream_data(msg, "__substg1.0_0C1F001F"),
+                "To": self._get_stream_data(msg, "__substg1.0_0E04001F"),
+                "Subject": self._get_stream_data(msg, "__substg1.0_0037001F"),
+            }
+
+            # Add headers to markdown
+            for key, value in headers.items():
+                if value:
+                    md_content += f"**{key}:** {value}\n"
+
+            md_content += "\n## Content\n\n"
+
+            # Get email body
+            body = self._get_stream_data(msg, "__substg1.0_1000001F")
+            if body:
+                md_content += body
+
+            msg.close()
+
+            return DocumentConverterResult(
+                title=headers.get("Subject"), text_content=md_content.strip()
+            )
+
+        except Exception as e:
+            raise FileConversionException(
+                f"Could not convert MSG file '{local_path}': {str(e)}"
+            )
+
+    def _get_stream_data(
+        self, msg: olefile.OleFileIO, stream_path: str
+    ) -> Union[str, None]:
+        """Helper to safely extract and decode stream data from the MSG file."""
+        try:
+            if msg.exists(stream_path):
+                data = msg.openstream(stream_path).read()
+                # Try UTF-16 first (common for .msg files)
+                try:
+                    return data.decode("utf-16-le").strip()
+                except UnicodeDecodeError:
+                    # Fall back to UTF-8
+                    try:
+                        return data.decode("utf-8").strip()
+                    except UnicodeDecodeError:
+                        # Last resort - ignore errors
+                        return data.decode("utf-8", errors="ignore").strip()
+        except Exception:
+            pass
+        return None
+
+
 class ZipConverter(DocumentConverter):
     """Converts ZIP files to markdown by extracting and converting all contained files.
 
@@ -1310,6 +1385,7 @@ def __init__(
         self.register_page_converter(IpynbConverter())
         self.register_page_converter(PdfConverter())
         self.register_page_converter(ZipConverter())
+        self.register_page_converter(OutlookMsgConverter())
 
     def convert(
         self, source: Union[str, requests.Response, Path], **kwargs: Any

tests/test_markitdown.py

@@ -69,6 +69,15 @@
     "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
 ]
 
+MSG_TEST_STRINGS = [
+    "# Email Message",
+    "**From:** [email protected]",
+    "**To:** [email protected]",
+    "**Subject:** Test Email Message",
+    "## Content",
+    "This is the body of the test email message",
+]
+
 DOCX_COMMENT_TEST_STRINGS = [
     "314b0a30-5b04-470b-b9f7-eed2c2bec74a",
     "49e168b7-d2ae-407f-a055-2167576f39a1",
@@ -244,6 +253,10 @@ def test_markitdown_local() -> None:
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_mskanji.csv"))
     validate_strings(result, CSV_CP932_TEST_STRINGS)
 
+    # Test MSG (Outlook email) processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_outlook_msg.msg"))
+    validate_strings(result, MSG_TEST_STRINGS)
+
 
 @pytest.mark.skipif(
     skip_exiftool,