sparkocr.tests.ocr.pipelines.test_pdf#

Classes#

class TestPdfOcrPipeline#

PIPELINE_PATH = 'pdf_ocr_pipeline'#

get_pipeline(auto_skew_correction=False)#

teardown_method(method)#

test_ocr_with_skew_correction(spark_session, pdf_rotated_df, pdf_rotated_text)#

test_saving_and_loading_pipeline(spark_session, pdf_rotated_df, pdf_rotated_text)#