[jira] [Created] (CARBONDATA-1103) Integer datatype as a long datatype in carbondata on cluster

[Akash R Nilugal (Jira)]

Vandana Yadav created CARBONDATA-1103:
-----------------------------------------

             Summary: Integer datatype as a long datatype in carbondata on cluster
                 Key: CARBONDATA-1103
                 URL: https://issues.apache.org/jira/browse/CARBONDATA-1103
             Project: CarbonData
          Issue Type: Bug
          Components: sql
    Affects Versions: 1.2.0
         Environment: spark 1.6
            Reporter: Vandana Yadav
            Priority: Minor


Integer datatype as a long datatype in carbondata on cluster

Steps to reproduce Bug:

In CarbonData:

Create Table:

create table myvmall (imei String,uuid String,MAC String,device_color String,device_shell_color String,device_name String,product_name String,ram String,rom String,cpu_clock String,series String,check_date String,check_year int,check_month int ,check_day int,check_hour int,bom String,inside_name String,packing_date String,packing_year String,packing_month String,packing_day String,packing_hour String,customer_name String,deliveryAreaId String,deliveryCountry String,deliveryProvince String,deliveryCity String,deliveryDistrict String,packing_list_no String,order_no String,Active_check_time String,Active_check_year int,Active_check_month int,Active_check_day int,Active_check_hour int,ActiveAreaId String,ActiveCountry String,ActiveProvince String,Activecity String,ActiveDistrict String,Active_network String,Active_firmware_version String,Active_emui_version String,Active_os_version String,Latest_check_time String,Latest_check_year int,Latest_check_month int,Latest_check_day int,Latest_check_hour int,Latest_areaId String,Latest_country String,Latest_province String,Latest_city String,Latest_district String,Latest_firmware_version String,Latest_emui_version String,Latest_os_version String,Latest_network String,site String,site_desc String,product String,product_desc String) STORED BY 'org.apache.carbondata.format' TBLPROPERTIES ('DICTIONARY_INCLUDE'='check_year,check_month,check_day,check_hour,Active_check_year,Active_check_month,Active_check_day,Active_check_hour,Latest_check_year,Latest_check_month,Latest_check_day')

 Load Data:

LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/100_VMALL_1_Day_DATA_2015-09-15.csv' INTO table myvmall options('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='imei,uuid,MAC,device_color,device_shell_color,device_name,product_name,ram,rom,cpu_clock,series,check_date,check_year,check_month,check_day,check_hour,bom,inside_name,packing_date,packing_year,packing_month,packing_day,packing_hour,customer_name,deliveryAreaId,deliveryCountry,deliveryProvince,deliveryCity,deliveryDistrict,packing_list_no,order_no,Active_check_time,Active_check_year,Active_check_month,Active_check_day,Active_check_hour,ActiveAreaId,ActiveCountry,ActiveProvince,Activecity,ActiveDistrict,Active_network,Active_firmware_version,Active_emui_version,Active_os_version,Latest_check_time,Latest_check_year,Latest_check_month,Latest_check_day,Latest_check_hour,Latest_areaId,Latest_country,Latest_province,Latest_city,Latest_district,Latest_firmware_version,Latest_emui_version,Latest_os_version,Latest_network,site,site_desc,product,product_desc')

description in carbondata:

+--------------------------+------------+----------+--+
|         col_name         | data_type  | comment  |
+--------------------------+------------+----------+--+
| imei                     | string     |          |
| uuid                     | string     |          |
| mac                      | string     |          |
| device_color             | string     |          |
| device_shell_color       | string     |          |
| device_name              | string     |          |
| product_name             | string     |          |
| ram                      | string     |          |
| rom                      | string     |          |
| cpu_clock                | string     |          |
| series                   | string     |          |
| check_date               | string     |          |
| check_year               | int        |          |
| check_month              | int        |          |
| check_day                | int        |          |
| check_hour               | int        |          |
| bom                      | string     |          |
| inside_name              | string     |          |
| packing_date             | string     |          |
| packing_year             | string     |          |
| packing_month            | string     |          |
| packing_day              | string     |          |
| packing_hour             | string     |          |
| customer_name            | string     |          |
| deliveryareaid           | string     |          |
| deliverycountry          | string     |          |
| deliveryprovince         | string     |          |
| deliverycity             | string     |          |
| deliverydistrict         | string     |          |
| packing_list_no          | string     |          |
| order_no                 | string     |          |
| active_check_time        | string     |          |
| active_check_year        | int        |          |
| active_check_month       | int        |          |
| active_check_day         | int        |          |
| active_check_hour        | int        |          |
| activeareaid             | string     |          |
| activecountry            | string     |          |
| activeprovince           | string     |          |
| activecity               | string     |          |
| activedistrict           | string     |          |
| active_network           | string     |          |
| active_firmware_version  | string     |          |
| active_emui_version      | string     |          |
| active_os_version        | string     |          |
| latest_check_time        | string     |          |
| latest_check_year        | int        |          |
| latest_check_month       | int        |          |
| latest_check_day         | int        |          |
| latest_check_hour        | bigint     |          |
| latest_areaid            | string     |          |
| latest_country           | string     |          |
| latest_province          | string     |          |
| latest_city              | string     |          |
| latest_district          | string     |          |
| latest_firmware_version  | string     |          |
| latest_emui_version      | string     |          |
| latest_os_version        | string     |          |
| latest_network           | string     |          |
| site                     | string     |          |
| site_desc                | string     |          |
| product                  | string     |          |
| product_desc             | string     |          |
+--------------------------+------------+----------+--+

Query Executed:

select imei,latest_check_hour from myvmall where myvmall.latest_check_hour  IN (10,14) and myvmall.imei IN ('imeiA009945257','imeiA009945258') and myvmall.check_year IN (2015)

Result in CarbonData:
+-----------------+--------------------+--+
|      imei       | latest_check_hour  |
+-----------------+--------------------+--+
| imeiA009945257  | 14                 |
| imeiA009945258  | 14                 |
+-----------------+--------------------+--+


In hive:

Create Table:

create table hivevmall (imei String,uuid String,MAC String,device_color String,device_shell_color String,device_name String,product_name String,ram String,rom String,cpu_clock String,series String,check_date String,check_year int,check_month int ,check_day int,check_hour int,bom String,inside_name String,packing_date String,packing_year String,packing_month String,packing_day String,packing_hour String,customer_name String,deliveryAreaId String,deliveryCountry String,deliveryProvince String,deliveryCity String,deliveryDistrict String,packing_list_no String,order_no String,Active_check_time String,Active_check_year int,Active_check_month int,Active_check_day int,Active_check_hour int,ActiveAreaId String,ActiveCountry String,ActiveProvince String,Activecity String,ActiveDistrict String,Active_network String,Active_firmware_version String,Active_emui_version String,Active_os_version String,Latest_check_time String,Latest_check_year int,Latest_check_month int,Latest_check_day int,Latest_check_hour int,Latest_areaId String,Latest_country String,Latest_province String,Latest_city String,Latest_district String,Latest_firmware_version String,Latest_emui_version String,Latest_os_version String,Latest_network String,site String,site_desc String,product String,product_desc String)ROW FORMAT DELIMITED FIELDS TERMINATED BY ','

Load data:

load data local inpath  '/opt/Carbon/CarbonData/TestData/Data/100_VMALL_1_Day_DATA_2015-09-15.csv' OVERWRITE INTO TABLE hivevmall


description in hive:

+--------------------------+------------+----------+--+
|         col_name         | data_type  | comment  |
+--------------------------+------------+----------+--+
| imei                     | string     | NULL     |
| uuid                     | string     | NULL     |
| mac                      | string     | NULL     |
| device_color             | string     | NULL     |
| device_shell_color       | string     | NULL     |
| device_name              | string     | NULL     |
| product_name             | string     | NULL     |
| ram                      | string     | NULL     |
| rom                      | string     | NULL     |
| cpu_clock                | string     | NULL     |
| series                   | string     | NULL     |
| check_date               | string     | NULL     |
| check_year               | int        | NULL     |
| check_month              | int        | NULL     |
| check_day                | int        | NULL     |
| check_hour               | int        | NULL     |
| bom                      | string     | NULL     |
| inside_name              | string     | NULL     |
| packing_date             | string     | NULL     |
| packing_year             | string     | NULL     |
| packing_month            | string     | NULL     |
| packing_day              | string     | NULL     |
| packing_hour             | string     | NULL     |
| customer_name            | string     | NULL     |
| deliveryareaid           | string     | NULL     |
| deliverycountry          | string     | NULL     |
| deliveryprovince         | string     | NULL     |
| deliverycity             | string     | NULL     |
| deliverydistrict         | string     | NULL     |
| packing_list_no          | string     | NULL     |
| order_no                 | string     | NULL     |
| active_check_time        | string     | NULL     |
| active_check_year        | int        | NULL     |
| active_check_month       | int        | NULL     |
| active_check_day         | int        | NULL     |
| active_check_hour        | int        | NULL     |
| activeareaid             | string     | NULL     |
| activecountry            | string     | NULL     |
| activeprovince           | string     | NULL     |
| activecity               | string     | NULL     |
| activedistrict           | string     | NULL     |
| active_network           | string     | NULL     |
| active_firmware_version  | string     | NULL     |
| active_emui_version      | string     | NULL     |
| active_os_version        | string     | NULL     |
| latest_check_time        | string     | NULL     |
| latest_check_year        | int        | NULL     |
| latest_check_month       | int        | NULL     |
| latest_check_day         | int        | NULL     |
| latest_check_hour        | int        | NULL     |
| latest_areaid            | string     | NULL     |
| latest_country           | string     | NULL     |
| latest_province          | string     | NULL     |
| latest_city              | string     | NULL     |
| latest_district          | string     | NULL     |
| latest_firmware_version  | string     | NULL     |
| latest_emui_version      | string     | NULL     |
| latest_os_version        | string     | NULL     |
| latest_network           | string     | NULL     |
| site                     | string     | NULL     |
| site_desc                | string     | NULL     |
| product                  | string     | NULL     |
| product_desc             | string     | NULL     |
+--------------------------+------------+----------+--+


Query Executed:

select imei,latest_check_hour from hivevmall where hivevmall.latest_check_hour  IN (10,14) and hivevmall.imei IN ('imeiA009945257','imeiA009945258') and hivevmall.check_year IN (2015)

Result In hive:
+-----------------+--------------------+--+
|      imei       | latest_check_hour  |
+-----------------+--------------------+--+
| imeiA009945257  | 14                 |
| imeiA009945258  | 14                 |
+-----------------+--------------------+--+

Result On Automation:
1)In CarbonData:
imei StringType,latest_check_hour LongType
imeiA009945257,14
imeiA009945258,14

2)In hive:
imei StringType,latest_check_hour IntegerType
imeiA009945257,14
imeiA009945258,14

camparison failur because of datatype( latest_check_hour   int in hive and  latest_check_hour  bigint in carbondata)


testCase id:1) Pushup_filter_myvmall_tc013
            2) Pushup_filter_myvmall_tc019
            3) Pushup_filter_myvmall_tc021
     4) Pushup_filter_myvmall_tc022




--
This message was sent by Atlassian JIRA
(v6.3.15#6346)