manoj mathpal created CARBONDATA-1009:
-----------------------------------------
Summary: Select statement is not working with empty string in
where clause.
Key: CARBONDATA-1009
URL: https://issues.apache.org/jira/browse/CARBONDATA-1009
Project: CarbonData
Issue Type: Bug
Components: sql
Affects Versions: 1.1.0
Environment: SPARK 2.1
Reporter: manoj mathpal
Priority: Trivial
Steps to reproduces:
1- Create table in hive:
CREATE TABLE uniqdata_h (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION
string, DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2
bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2
decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1
int) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' ;
2:Load data in Hive:
load data local inpath '/home/manoj/Downloads/2000_UniqData.csv' into table
uniqdata_h ;
load data local inpath '/home/manoj/Downloads/4000_UniqData.csv' into table
uniqdata_h ;
load data local inpath '/home/manoj/Downloads/6000_UniqData.csv' into table
uniqdata_h ;
load data local inpath '/home/manoj/Downloads/7000_UniqData.csv' into table
uniqdata_h ;
load data local inpath '/home/manoj/3000_1_UniqData.csv' into table uniqdata_h ;
3: Execute Selet queries:
select
CUST_ID,CUST_NAME,DOB,BIGINT_COLUMN1,DECIMAL_COLUMN1,Double_COLUMN1,INTEGER_COLUMN1
from uniqdata_h where CUST_ID in
('10020','10030','10032','10035','10040','10060','',NULL,' ') and
BIGINT_COLUMN1 in
(123372037874,123372037884,123372037886,123372037889,'',NULL,' ') ;
Result:
+----------+------------------+------------------------+-----------------+-------------------------+----------------------+------------------+--+
| CUST_ID | CUST_NAME | DOB | BIGINT_COLUMN1 |
DECIMAL_COLUMN1 | Double_COLUMN1 | INTEGER_COLUMN1 |
+----------+------------------+------------------------+-----------------+-------------------------+----------------------+------------------+--+
| 10020 | CUST_NAME_01020 | 1972-10-17 01:00:03.0 | 123372037874 |
12345679921.1234000000 | 1.12345674897976E10 | 1021 |
| 10030 | CUST_NAME_01030 | 1972-10-27 01:00:03.0 | 123372037884 |
12345679931.1234000000 | 1.12345674897976E10 | 1031 |
| 10032 | CUST_NAME_01032 | 1972-10-29 01:00:03.0 | 123372037886 |
12345679933.1234000000 | 1.12345674897976E10 | 1033 |
| 10035 | CUST_NAME_01035 | 1972-11-01 01:00:03.0 | 123372037889 |
12345679936.1234000000 | 1.12345674897976E10 | 1036 |
+----------+------------------+------------------------+-----------------+-------------------------+----------------------+------------------+--+
........................................................................................................................................
Create table in Carbondata..
1: create table:
CREATE TABLE uniqdata (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION string,
DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2
bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2
decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1
int) STORED BY 'org.apache.carbondata.format' TBLPROPERTIES ("TABLE_BLOCKSIZE"=
"256 MB")
2:Load data in table:
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/2000_UniqData_tabdelm.csv'
into table uniqdata OPTIONS('DELIMITER'='/' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/3000_UniqDatatdelm.csv' into
table uniqdata OPTIONS('DELIMITER'='\t' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/4000_UniqDataquotedelm.csv'
into table uniqdata OPTIONS('DELIMITER'='"' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/5000_UniqData!delm.csv' into
table uniqdata OPTIONS('DELIMITER'='!' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/6000_UniqData|delm.csv' into
table uniqdata OPTIONS('DELIMITER'='|' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/7000_UniqDatadelm.csv' into
table uniqdata OPTIONS('DELIMITER'='' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/3000_1_UniqData.csv' into
table uniqdata OPTIONS('DELIMITER'=',' ,
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
;
3: Execute Selet queries:
select
CUST_ID,CUST_NAME,DOB,BIGINT_COLUMN1,DECIMAL_COLUMN1,Double_COLUMN1,INTEGER_COLUMN1
from uniqdata where CUST_ID in
('10020','10030','10032','10035','10040','10060','',NULL,' ') and
BIGINT_COLUMN1 in
(123372037874,123372037884,123372037886,123372037889,'',NULL,' ') ;
Result:
Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task
1 in stage 56.0 failed 1 times, most recent failure: Lost task 1.0 in stage
56.0 (TID 216, localhost, executor driver):
org.apache.spark.util.TaskCompletionListenerException:
java.util.concurrent.ExecutionException: java.lang.NullPointerException
at
org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
at org.apache.spark.scheduler.Task.run(Task.scala:112)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace: (state=,code=0)
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
