You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@carbondata.apache.org by "Vinod Rohilla (JIRA)" <ji...@apache.org> on 2017/03/17 11:23:41 UTC
[jira] [Updated] (CARBONDATA-789) Join operation does not work
properly in Carbon data.
[ https://issues.apache.org/jira/browse/CARBONDATA-789?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinod Rohilla updated CARBONDATA-789:
-------------------------------------
Description:
Join operation does not work properly in Carbon data for the int data type.
Steps to Reproduces:
A) Create Table in Hive:
First table:
CREATE TABLE uniqdata_nobucket11_Hive (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 ",";
First table Load:
LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket11_Hive;
Second table :
CREATE TABLE uniqdata_nobucket22_Hive (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 ",";
Second table Load:
LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket22_Hive;
Results in Hive:
| CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 | CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 |
+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
| 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 | 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 |
+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
2,001 rows selected (3.369 seconds)
B) Create table in Carbon data
First Table:
CREATE TABLE uniqdata_nobucket11 (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' ;
Load Data in table:
LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket11 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
Create Second table:
CREATE TABLE uniqdata_nobucket22 (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';
Load data in Table:
LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket22 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
Result in CarbonData:
0: jdbc:hive2://localhost:10000> select * from uniqdata_nobucket11 u1, uniqdata_nobucket22 u2 where u1.cust_id = u2.cust_id;
Error: java.util.EmptyStackException (state=,code=0)
Expected Result: Results should be displayed in carbon data.
was:
Result does not display under carbon data query.
Steps to Reproduces:
A) Create Table in Hive:
First table:
CREATE TABLE uniqdata_nobucket11_Hive (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 ",";
First table Load:
LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket11_Hive;
Second table :
CREATE TABLE uniqdata_nobucket22_Hive (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 ",";
Second table Load:
LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket22_Hive;
Results in Hive:
| CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 | CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 |
+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
| 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 | 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 |
+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
2,001 rows selected (3.369 seconds)
B) Create table in Carbon data
First Table:
CREATE TABLE uniqdata_nobucket11 (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' ;
Load Data in table:
LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket11 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
Create Second table:
CREATE TABLE uniqdata_nobucket22 (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';
Load data in Table:
LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket22 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
Result in CarbonData:
0: jdbc:hive2://localhost:10000> select * from uniqdata_nobucket11 u1, uniqdata_nobucket22 u2 where u1.cust_id = u2.cust_id;
Error: java.util.EmptyStackException (state=,code=0)
Expected Result: Results should be displayed in carbon data.
> Join operation does not work properly in Carbon data.
> -------------------------------------------------------
>
> Key: CARBONDATA-789
> URL: https://issues.apache.org/jira/browse/CARBONDATA-789
> Project: CarbonData
> Issue Type: Bug
> Components: data-query
> Affects Versions: 1.1.0-incubating
> Environment: Spark 2.1
> Reporter: Vinod Rohilla
> Priority: Trivial
> Attachments: 2000_UniqData.csv
>
>
> Join operation does not work properly in Carbon data for the int data type.
> Steps to Reproduces:
> A) Create Table in Hive:
> First table:
> CREATE TABLE uniqdata_nobucket11_Hive (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 ",";
> First table Load:
> LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket11_Hive;
> Second table :
> CREATE TABLE uniqdata_nobucket22_Hive (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 ",";
> Second table Load:
> LOAD DATA LOCAL INPATH '/home/vinod/Desktop/AllCSV/2000_UniqData.csv'OVERWRITE INTO TABLE uniqdata_nobucket22_Hive;
> Results in Hive:
> | CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 | CUST_ID | CUST_NAME | ACTIVE_EMUI_VERSION | DOB | DOJ | BIGINT_COLUMN1 | BIGINT_COLUMN2 | DECIMAL_COLUMN1 | DECIMAL_COLUMN2 | Double_COLUMN1 | Double_COLUMN2 | INTEGER_COLUMN1 |
> +----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
> | 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 | 10999 | CUST_NAME_01999 | ACTIVE_EMUI_VERSION_01999 | 1975-06-23 01:00:03.0 | 1975-06-23 02:00:03.0 | 123372038853 | -223372034855 | 12345680900.1234000000 | 22345680900.1234000000 | 1.12345674897976E10 | -1.12345674897976E10 | 2000 |
> +----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+----------+------------------+----------------------------+------------------------+------------------------+-----------------+-----------------+-------------------------+-------------------------+----------------------+-----------------------+------------------+--+
> 2,001 rows selected (3.369 seconds)
> B) Create table in Carbon data
> First Table:
> CREATE TABLE uniqdata_nobucket11 (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' ;
> Load Data in table:
> LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket11 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
> Create Second table:
> CREATE TABLE uniqdata_nobucket22 (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';
> Load data in Table:
> LOAD DATA INPATH 'hdfs://localhost:54310/2000_UniqData.csv' into table uniqdata_nobucket22 OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1')
> Result in CarbonData:
> 0: jdbc:hive2://localhost:10000> select * from uniqdata_nobucket11 u1, uniqdata_nobucket22 u2 where u1.cust_id = u2.cust_id;
> Error: java.util.EmptyStackException (state=,code=0)
> Expected Result: Results should be displayed in carbon data.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)