#!/usr/bin/env bash

set -e

# assume this runs in e2e_test/iceberg
commands_dir="$(dirname "$0")"
source "${commands_dir}/common.sh"
iceberg_dir="${commands_dir}/../iceberg"
cd "${iceberg_dir}"


SPARK_FILE="spark-${SPARK_VERSION}-bin-hadoop3.tgz"

if [ ! -d "spark-${SPARK_VERSION}-bin-hadoop3" ]; then
    wget --no-verbose https://rw-ci-deps-dist.s3.amazonaws.com/$SPARK_FILE
    tar -xzf $SPARK_FILE --no-same-owner
fi

# TODO: avoid hardcoded config
# TODO: maybe pyspark is more handy for scripting
./spark-${SPARK_VERSION}-bin-hadoop3/bin/spark-sql --packages $SPARK_PACKAGES \
    --conf spark.sql.catalog.demo=org.apache.iceberg.spark.SparkCatalog \
    --conf spark.sql.catalog.demo.type=hadoop \
    --conf spark.sql.catalog.demo.warehouse=s3a://icebergdata/ \
    --conf spark.sql.catalog.demo.hadoop.fs.s3a.endpoint=http://127.0.0.1:9301 \
    --conf spark.sql.catalog.demo.hadoop.fs.s3a.access.key=hummockadmin \
    --conf spark.sql.catalog.demo.hadoop.fs.s3a.secret.key=hummockadmin \
    --S \
    "$@"
