Updated sample plugin to new Converter interface.

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

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.1a2"
+__version__ = "0.0.1a3"

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

@@ -1,12 +1,26 @@
-from typing import Union
+import locale
+from typing import BinaryIO, Any
 from striprtf.striprtf import rtf_to_text
 
-from markitdown import MarkItDown, DocumentConverter, DocumentConverterResult
+from markitdown import (
+    MarkItDown,
+    DocumentConverter,
+    DocumentConverterResult,
+    StreamInfo,
+)
+
 
 __plugin_interface_version__ = (
     1  # The version of the plugin interface that this plugin uses
 )
 
+ACCEPTED_MIME_TYPE_PREFIXES = [
+    "text/rtf",
+    "application/rtf",
+]
+
+ACCEPTED_FILE_EXTENSIONS = [".rtf"]
+
 
 def register_converters(markitdown: MarkItDown, **kwargs):
     """
@@ -22,18 +36,41 @@ 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 RTF
-        extension = kwargs.get("file_extension", "")
-        if extension.lower() != ".rtf":
-            return None
+    def __init__(
+        self, priority: float = DocumentConverter.PRIORITY_SPECIFIC_FILE_FORMAT
+    ):
+        super().__init__(priority=priority)
 
-        # Read the RTF file
-        with open(local_path, "r") as f:
-            rtf = f.read()
+    def accepts(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,  # Options to pass to the converter
+    ) -> bool:
+        mimetype = (stream_info.mimetype or "").lower()
+        extension = (stream_info.extension or "").lower()
+
+        if extension in ACCEPTED_FILE_EXTENSIONS:
+            return True
+
+        for prefix in ACCEPTED_MIME_TYPE_PREFIXES:
+            if mimetype.startswith(prefix):
+                return True
+
+        return False
+
+    def convert(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,  # Options to pass to the converter
+    ) -> DocumentConverterResult:
+        # Read the file stream into an str using hte provided charset encoding, or using the system default
+        encoding = stream_info.charset or locale.getpreferredencoding()
+        stream_data = file_stream.read().decode(encoding)
 
         # Return the result
         return DocumentConverterResult(
             title=None,
-            text_content=rtf_to_text(rtf),
+            markdown=rtf_to_text(stream_data),
         )

packages/markitdown-sample-plugin/tests/test_sample_plugin.py

@@ -2,7 +2,7 @@
 import os
 import pytest
 
-from markitdown import MarkItDown
+from markitdown import MarkItDown, StreamInfo
 from markitdown_sample_plugin import RtfConverter
 
 TEST_FILES_DIR = os.path.join(os.path.dirname(__file__), "test_files")
@@ -15,18 +15,22 @@ RTF_TEST_STRINGS = {
 
 def test_converter() -> None:
     """Tests the RTF converter dirctly."""
-    converter = RtfConverter()
-    result = converter.convert(
-        os.path.join(TEST_FILES_DIR, "test.rtf"), file_extension=".rtf"
-    )
+    with open(os.path.join(TEST_FILES_DIR, "test.rtf"), "rb") as file_stream:
+        converter = RtfConverter()
+        result = converter.convert(
+            file_stream=file_stream,
+            stream_info=StreamInfo(
+                mimetype="text/rtf", extension=".rtf", filename="test.rtf"
+            ),
+        )
 
-    for test_string in RTF_TEST_STRINGS:
-        assert test_string in result.text_content
+        for test_string in RTF_TEST_STRINGS:
+            assert test_string in result.text_content
 
 
 def test_markitdown() -> None:
     """Tests that MarkItDown correctly loads the plugin."""
-    md = MarkItDown()
+    md = MarkItDown(enable_plugins=True)
     result = md.convert(os.path.join(TEST_FILES_DIR, "test.rtf"))
 
     for test_string in RTF_TEST_STRINGS: