Spark-SQL.txt

issue spark-sql or hive command in command line not in pyspark

create database rp_db_txt;
use rp_retail_db_txt;

create table orders (
  order_id int,
  order_date string,
  order_customer_id int,
  order_status string
) row format delimited fields terminated by ','
stored as textfile;
load data local inpath '/data/retail_db/orders' into table orders;


create table order_items (
  order_item_id int,
  order_item_order_id int,
  order_item_product_id int,
  order_item_quantity int,
  order_item_subtotal float,
  order_item_product_price float
) row format delimited fields terminated by ','
stored as textfile;

load data inpath /public/data/retail_db/order_items/' overwrite into table order_items;

overwrite -> will delete the existing data and load the data



create database rp_retail_db_orc;
use rp_retail_db_orc;

create table orders (
  order_id int,
  order_date string,
  order_customer_id int,
  order_status string
) stored as orc;

insert into table orders select * from rp_retail_db_txt.orders;

create table order_items (
  order_item_id int,
  order_item_order_id int,
  order_item_product_id int,
  order_item_quantity int,
  order_item_subtotal float,
  order_item_product_price float
) stored as orc;

insert into table order_items select * from rp_retail_db_txt.order_items;