A minimal setup to run hive+postgres-metastore on MacOS arm machines
Inspired from Apache Hive on Docker blog post.
- Download and install Docker for MacOS
- Clone this repo in a local directory
- Run
docker-compose up
- Open a shell in the hive server
$ docker exec -it hive-server /bin/bash
- Create example table structure
root@dc86b2b9e566:/opt# cd /employee
root@dc86b2b9e566:/employee# hive -f employee_table.hql
- Inject CSV data to HDFS
root@dc86b2b9e566:/employee# hadoop fs -put employee.csv hdfs://namenode:8020/user/hive/warehouse/testdb.db/employee
- Query some data
root@df1ac619536c:/employee# hive
hive> show databases;
OK
default
testdb
Time taken: 2.363 seconds, Fetched: 2 row(s)
hive> use testdb;
OK
Time taken: 0.085 seconds
hive> select * from employee;
OK
1 Rudolf Bardin 30 cashier 100 New York 40000 5
2 Rob Trask 22 driver 100 New York 50000 4
3 Madie Nakamura 20 janitor 100 New York 30000 4
4 Alesha Huntley 40 cashier 101 Los Angeles 40000 10
5 Iva Moose 50 cashier 102 Phoenix 50000 20Time taken: 4.237 seconds, Fetched: 5 row(s)