fix: megaparse.load & add tests (#202)

* fix: megaparse.load & add tests

* fix needed version in ReadMe & remove python3.10 test in CI

.github/workflows/CI.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.11", "3.12"]
     steps:
       - name: 👀 Checkout code
         uses: actions/checkout@v2

README.md

@@ -25,6 +25,8 @@ https://github.com/QuivrHQ/MegaParse/assets/19614572/1b4cdb73-8dc2-44ef-b8b4-a75
 
 ## Installation
 
+required python version >= 3.11
+
 ```bash
 pip install megaparse
 ```

libs/megaparse/src/megaparse/megaparse.py

@@ -105,10 +105,24 @@ def load(
         file: BinaryIO | None = None,
         file_extension: str | FileExtension = "",
     ) -> str:
-        loop = asyncio.get_event_loop()
-        return loop.run_until_complete(
-            self.aload(file_path=file_path, file=file, file_extension=file_extension)
+        file_extension = self.validate_input(
+            file=file, file_path=file_path, file_extension=file_extension
         )
+        try:
+            parser = self._select_parser(file_path, file, file_extension)
+            logger.info(f"Parsing using {parser.__class__.__name__} parser.")
+            parsed_document = parser.convert(
+                file_path=file_path, file=file, file_extension=file_extension
+            )
+            # @chloe FIXME: format_checker needs unstructured Elements as input which is to change
+            # if self.format_checker:
+            #     parsed_document: str = await self.format_checker.check(parsed_document
+            self.last_parsed_document = parsed_document
+            return parsed_document
+        except Exception as e:
+            raise ParsingException(
+                f"Error while parsing file {file_path or file}, file_extension: {file_extension}: {e}"
+            )
 
     def _select_parser(
         self,

libs/megaparse/tests/pdf/test_pdf_processing.py

@@ -27,13 +27,21 @@ def test_get_default_processors_megaparse():
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("pdf_name", ["scanned_pdf", "native_pdf"])
-async def test_megaparse_pdf_processor_file_path(pdf_name, request):
+async def test_async_megaparse_pdf_processor_file_path(pdf_name, request):
     pdf = request.getfixturevalue(pdf_name)
     processor = MegaParse()
     result = await processor.aload(file_path=pdf)
     assert len(result) > 0
 
 
+@pytest.mark.parametrize("pdf_name", ["scanned_pdf", "native_pdf"])
+def test_sync_megaparse_pdf_processor_file_path(pdf_name, request):
+    pdf = request.getfixturevalue(pdf_name)
+    processor = MegaParse()
+    result = processor.load(file_path=pdf)
+    assert len(result) > 0
+
+
 @pytest.mark.asyncio
 @pytest.mark.parametrize("pdf_name", ["scanned_pdf", "native_pdf"])
 async def test_megaparse_pdf_processor_file(pdf_name, request):