sparkocr.transformers.readers.funsd_reader#

Classes#

class FunsdReader(**kwargs)#

FunsdReader( spark_session=spark, root_work_dir=”./Result/FUNSD_PROCESS/”, target_dir=”./Result/FUNSD_RESULT/”, supported_labels=”all”, clean_up=True)()

EXTRACTED = 'funsd'#

FILENAME = 'funsd.zip'#

RESULT = 'funsd_processed'#

URL = 'https://guillaumejaume.github.io/FUNSD/dataset.zip'#

clean_up#

root_work_dir#

schema#

spark#

target_dir#

static create_file_identifier(file_path)#

download_and_extract()#

static funsd_reader(combined_bytes, combined_extension)#

process_funsd_split(load_dir)#