From ade3ecd5a18b68b63bbb87d61db4a96432ca1a62 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Fri, 12 Dec 2025 01:19:16 -0800 Subject: [PATCH] fix: add error handling in hOCR pipeline --- src/ocrmypdf/_pipelines/pdf_to_hocr.py | 2 ++ tests/test_json_serialization.py | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/src/ocrmypdf/_pipelines/pdf_to_hocr.py b/src/ocrmypdf/_pipelines/pdf_to_hocr.py index c6c13c3a..9c076667 100644 --- a/src/ocrmypdf/_pipelines/pdf_to_hocr.py +++ b/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: diff --git a/tests/test_json_serialization.py b/tests/test_json_serialization.py index e22c49fb..c2402ff8 100644 --- a/tests/test_json_serialization.py +++ b/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():