Cleanup and refactor, in preparation for plugin support. (#318)

* Work started moving converters to individual files.
* Significant cleanup and refactor.
* Moved everything to a packages subfolder.
* Added sample plugin.
* Added instructions to the README.md
* Bumped version, and added a note about compatibility.

packages/markitdown-sample-plugin/src/markitdown_sample_plugin/__about__.py

@@ -0,0 +1,4 @@
+# SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
+#
+# SPDX-License-Identifier: MIT
+__version__ = "0.0.1a2"

packages/markitdown-sample-plugin/src/markitdown_sample_plugin/__init__.py

@@ -0,0 +1,13 @@
+# SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
+#
+# SPDX-License-Identifier: MIT
+
+from ._plugin import __plugin_interface_version__, register_converters, RtfConverter
+from .__about__ import __version__
+
+__all__ = [
+    "__version__",
+    "__plugin_interface_version__",
+    "register_converters",
+    "RtfConverter",
+]

packages/markitdown-sample-plugin/src/markitdown_sample_plugin/_plugin.py

@@ -0,0 +1,39 @@
+from typing import Union
+from striprtf.striprtf import rtf_to_text
+
+from markitdown import MarkItDown, DocumentConverter, DocumentConverterResult
+
+__plugin_interface_version__ = (
+    1  # The version of the plugin interface that this plugin uses
+)
+
+
+def register_converters(markitdown: MarkItDown, **kwargs):
+    """
+    Called during construction of MarkItDown instances to register converters provided by plugins.
+    """
+
+    # Simply create and attach an RtfConverter instance
+    markitdown.register_converter(RtfConverter())
+
+
+class RtfConverter(DocumentConverter):
+    """
+    Converts an RTF file to in the simplest possible way.
+    """
+
+    def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
+        # Bail if not a DOCX
+        extension = kwargs.get("file_extension", "")
+        if extension.lower() != ".rtf":
+            return None
+
+        # Read the RTF file
+        with open(local_path, "r") as f:
+            rtf = f.read()
+
+        # Return the result
+        return DocumentConverterResult(
+            title=None,
+            text_content=rtf_to_text(rtf),
+        )