>>> rdd = sc.sequenceFile("/wmf/data/raw/atskafka_test_webrequest_text/atskafka_test_webrequest_text/hourly/2021/02/21/12/")
>>> webrequest_schema = spark.table("wmf_raw.webrequest").schema                
>>> df = spark.read.schema(webrequest_schema).json(rdd)
>>> df.createOrReplaceGlobalTempView("requests")
21/02/22 16:01:12 WARN Utils: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.debug.maxToStringFields' in SparkEnv.conf.
>>> df2 = spark.sql("select uri_path from global_temp.requests limit 10")
>>> df2.show()
+--------+                                                                      
|uri_path|
+--------+
|    null|
|    null|
|    null|
|    null|
|    null|
|    null|
|    null|
|    null|
|    null|
|    null|
+--------+