Traceback (most recent call last): File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/_pipeline.py", line 157, in get_pdfinfo return PdfInfo( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 860, in __init__ self._pages = _pdf_pageinfo_concurrent( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 644, in _pdf_pageinfo_concurrent executor( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/_concurrent.py", line 82, in __call__ self._execute( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/builtin_plugins/concurrency.py", line 132, in _execute for result in results: File "/usr/local/Cellar/python@3.9/3.9.5/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 870, in next raise value File "/usr/local/Cellar/python@3.9/3.9.5/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/pool.py", line 125, in worker result = (True, func(*args, **kwds)) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 601, in _pdf_pageinfo_sync page = PageInfo(pdf, pageno, infile, check_pages, detailed_analysis) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 675, in __init__ self._gather_pageinfo(pdf, pageno, infile, check_pages, detailed_analysis) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 721, in _gather_pageinfo for ci in _process_content_streams( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 521, in _process_content_streams contentsinfo = _interpret_contents(container, initial_shorthand) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/pdfinfo/info.py", line 161, in _interpret_contents pikepdf.parse_content_stream(contentstream, operator_whitelist) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/pikepdf/models/__init__.py", line 104, in parse_content_stream raise e from e File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/pikepdf/models/__init__.py", line 92, in parse_content_stream page._parse_page_contents_grouped(operators), pikepdf._qpdf.PdfError: content stream (content stream object 33 0): errors while decoding content stream The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/Users/remidelbouys/Envinorma/data-tasks/tasks/ocr_ap/ocr_ap.py", line 585, in _run_ocr _download_ocr_and_upload_document(id_) File "/Users/remidelbouys/Envinorma/data-tasks/tasks/ocr_ap/ocr_ap.py", line 81, in _download_ocr_and_upload_document _ocr(file_.name, file_.name) File "/Users/remidelbouys/Envinorma/data-tasks/tasks/ocr_ap/ocr_ap.py", line 61, in _ocr ocr(input_filename, output_filename, language=['fra'], progress_bar=False, jobs=1) # type: ignore File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/api.py", line 340, in ocr return run_pipeline(options=options, plugin_manager=plugin_manager, api=True) File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/_sync.py", line 359, in run_pipeline pdfinfo = get_pdfinfo( File "/Users/remidelbouys/Envinorma/data-tasks/venv/lib/python3.9/site-packages/ocrmypdf/_pipeline.py", line 168, in get_pdfinfo raise InputFileError() from e ocrmypdf.exceptions.InputFileError