fix: add error handling in hOCR pipeline

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -89,6 +89,8 @@ def run_hocr_pipeline(
     plugin_manager: OcrmypdfPluginManager,
 ) -> None:
     """Run pipeline to output hOCR."""
+    if options.output_folder is None:
+        raise ValueError("output_folder must be specified for hOCR pipeline")
     with manage_work_folder(
         work_folder=options.output_folder, retain=True, print_location=False
     ) as work_folder:

tests/test_json_serialization.py

@@ -76,7 +76,7 @@ def test_json_serialization_multiprocessing():
         assert result['optimize'] == 2
         assert result['tesseract_timeout'] == 120.0
         assert result['fast_web_view'] == 2.5
-        assert result['extra_attrs_count'] == 3  # Includes lossless_reconstruction
+        assert result['extra_attrs_count'] == 2  # Includes lossless_reconstruction
 
 
 def test_json_serialization_with_streams():