pg_analytics

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

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

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

CREATE EXTENSION pg_analytics;

CREATE EXTENSION pg_lakehouse;
CREATE FOREIGN DATA WRAPPER parquet_wrapper HANDLER parquet_fdw_handler VALIDATOR parquet_fdw_validator;

-- Provide S3 credentials
CREATE SERVER parquet_server FOREIGN DATA WRAPPER parquet_wrapper;

-- Create foreign table with auto schema creation
CREATE FOREIGN TABLE trips ()
SERVER parquet_server
OPTIONS (files 's3://paradedb-benchmarks/yellow_tripdata_2024-01.parquet');

-- Success! Now you can query the remote Parquet file like a regular Postgres table
SELECT COUNT(*) FROM trips;
  count
---------
 2964624
(1 row)

CREATE EXTENSION pg_lakehouse;

CREATE FOREIGN DATA WRAPPER iceberg_wrapper
    HANDLER iceberg_fdw_handler
    VALIDATOR iceberg_fdw_validator;

CREATE SERVER iceberg_server
    FOREIGN DATA WRAPPER iceberg_wrapper;

-- Replace the dummy schema with the actual schema
CREATE FOREIGN TABLE iceberg_table (x INT)
    SERVER iceberg_server
    OPTIONS (files 's3://bucket/iceberg_folder');

-- Success! You can now query the Iceberg table
SELECT COUNT(*) FROM iceberg_table;