rlike.py

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
SELECT *
FROM sales_table
WHERE bill_raw_text RLIKE '(ab[cd]{2,4})|(aa[abcde]{1,2})'
'''
sales_table_execution_plan = sales_table.where(
    col('bill_raw_text').rlike("(ab[cd]{2,4})|(aa[abcde]{1,2})")
)

sales_table_execution_plan.show()