hdfs_fdw

pig repo add pgdg -u    # add pgdg repo and update cache

pig install hdfs_fdw;		# install via package name, for the active PG version

pig install hdfs_fdw -v 18;   # install for PG 18
pig install hdfs_fdw -v 17;   # install for PG 17
pig install hdfs_fdw -v 16;   # install for PG 16
pig install hdfs_fdw -v 15;   # install for PG 15
pig install hdfs_fdw -v 14;   # install for PG 14

CREATE EXTENSION hdfs_fdw;

CREATE EXTENSION hdfs_fdw;

CREATE SERVER hdfs_server FOREIGN DATA WRAPPER hdfs_fdw
  OPTIONS (host '127.0.0.1', port '10000', client_type 'hiveserver2');

CREATE USER MAPPING FOR postgres SERVER hdfs_server
  OPTIONS (username 'hive_user', password 'hive_password');

CREATE FOREIGN TABLE weblogs (
  client_ip text,
  http_status_code text,
  uri text,
  request_count bigint
)
SERVER hdfs_server
OPTIONS (dbname 'default', table_name 'weblogs');

SELECT client_ip, count(*) FROM weblogs GROUP BY client_ip ORDER BY count(*) DESC LIMIT 10;

CREATE SERVER spark_server FOREIGN DATA WRAPPER hdfs_fdw
  OPTIONS (host '127.0.0.1', port '10000', client_type 'spark');

CREATE USER MAPPING FOR postgres SERVER spark_server
  OPTIONS (username 'spark_user', password 'spark_pass');

CREATE FOREIGN TABLE spark_table (
  id int,
  name text,
  value double precision
)
SERVER spark_server
OPTIONS (dbname 'default', table_name 'my_table');

SET hdfs_fdw.enable_join_pushdown = on;
SET hdfs_fdw.enable_aggregate_pushdown = on;
SET hdfs_fdw.enable_order_by_pushdown = on;
SET hdfs_fdw.enable_limit_pushdown = on;