spark sql to Kudu
Hello Team,
I have the following file to load on Kudu.
1829;BN=0;UNIT=VOLUME_ALL;IN=0;TC=0;TCC=0;CT=;FU=1000001;CU=54274;FB=61701;FL=ugw9811_3828500385_360_27153
0=5126742111750858;U=23059268534;SI=6;SG=1;SR=7;SN=BROWSING;SC=BROWSING;BS=60342256;BR=2581143;TU=2021-04-27 14:02:47;TF=2021-04-27 00:00:00;TA=2021-04-27 14:02:47;TB=2021-04-27 00:00:00;TE=2021-04-27 14:02:47;TS=1619517767;D=16292;R=151;E=0;UDR_cu=0;UDR_fb=BROWSING;DCM=0;UP=Prepaid;ST=BROWSING;MSISDN=23059268534;APN=orange;SGSN=196.192.13.113;GGSN=196.192.13.113;IMSI=617010014925066;BU1=23292;BN=0;UNIT=VOLUME_ALL;IN=0;TC=0;TCC=62923399;CT=;FU=1000000;CU=3586;FB=61701;FL=ugw9811_3828490275_312_8799
0=5126752111750858;U=23059268534;SI=6;SG=1;SR=7;SN=BROWSING;SC=BROWSING;BS=0;BR=0;TU=2021-04-27 14:02:47;TF=2021-04-27 00:00:00;TA=2021-04-27 14:02:47;TB=2021-04-27 00:00:00;TE=2021-04-27 14:02:47;TS=1619517767;D=16292;R=151;E=0;UDR_cu=0;UDR_fb=BROWSING;DCM=0;UP=Prepaid;ST=BROWSING;MSISDN=23059268534;APN=orange;SGSN=196.192.13.113;GGSN=196.192.13.113;IMSI=617010014925066;BU1=21829;BN=0;UNIT=VOLUME_ALL;IN=0;TC=0;TCC=0;CT=;FU=1000001;CU=3586;FB=61701;FL=ugw9811_3828490275_312_8799
How can I proceed using Spark SQL?
Table structure on Kudu:
| CREATE EXTERNAL TABLE cdr.mobile_datadbs ( id BIGINT NOT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, msisdn STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, serviceid INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, servicegroup INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, servicerev INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, servicename STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, serviceclass STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, downlink INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, uplink INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, storedtime TIMESTAMP NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, firstaccesstime TIMESTAMP NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, lastaccesstime TIMESTAMP NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, servicebegintime TIMESTAMP NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, sessionendtime TIMESTAMP NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, cdrcreatedtime BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, duration BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, hitsperreq BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, errors1 BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, udrcu INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, udrfb STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, status1 STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, userprofile STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, servicetype STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, subsmsisdn STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, apn STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, sgsnaddress STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, ggsnaddress STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, imsi STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, bonusunit STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, bn INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, unit STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, instatus INT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, totalcost BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, totalcharge BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, terminationcause BIGINT NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, firstrequestedurl STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, cellidinfo STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, idpname STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, failureslist STRING NULL ENCODING AUTO_ENCODING COMPRESSION DEFAULT_COMPRESSION, PRIMARY KEY (id) ) PARTITION BY HASH (id) PARTITIONS 16 STORED AS KUDU TBLPROPERTIES ('external.table.purge'='TRUE', 'kudu.master_addresses'='rb-hadoop-03.mtg.local,rb-hadoop-04.mtg.local,rb-hadoop-05.mtg.local') |

