sparkocr.transformers.readers.tacd_reader#

Classes#

class TACDReader(**kwargs)#

TACDReader(

spark_session=spark, root_work_dir=”./Result/TACD_Process”, target_dir=”./Result/TACD_Result”, clean_up=True, AWS_ACCESS_KEY_ID = ‘AWS_ACCESS_KEY_ID’, AWS_SECRET_ACCESS_KEY = ‘AWS_SECRET_ACCESS_KEY’, AWS_SESSION_TOKEN = ‘AWS_SESSION_TOKEN’)()

AWS_KEY_ID#

AWS_SECRET_KEY#

AWS_SESSION_TOKEN#

FILE_NAME#

S3_URI = 's3://dev.johnsnowlabs.com/ocr/datasets/TACD.zip'#

clean_up#

root_work_dir#

schema#

spark#

target_dir#

static create_file_identifier(file_path)#

download_and_extract()#

process_tacd_split(load_dir)#

static tacd_reader(combined_bytes, combined_extension)#