#!/usr/bin/env bash
set -euo pipefail

# Creates Iceberg table for assistant message ingest.
# Default table: lake.db1.messages

CONTAINER_NAME="${SPARK_CONTAINER_NAME:-spark}"
SPARK_PROPS="${SPARK_PROPS:-/opt/lakehouse/spark-conf/lakehouse-spark-defaults.conf}"
PACKAGES="${SPARK_PACKAGES:-org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.10.1,org.apache.iceberg:iceberg-aws-bundle:1.10.1,org.projectnessie.nessie-integrations:nessie-spark-extensions-3.5_2.12:0.104.5}"
MESSAGES_TABLE="${MESSAGES_TABLE:-lake.db1.messages}"

SQL="
CREATE NAMESPACE IF NOT EXISTS lake.db1;

CREATE TABLE IF NOT EXISTS ${MESSAGES_TABLE} (
  thread_id STRING,
  message_id STRING,
  sender STRING,
  channel STRING,
  sent_at TIMESTAMP,
  body STRING,
  metadata_json STRING
)
USING iceberg
PARTITIONED BY (days(sent_at));
"

docker exec \
  -e AWS_REGION="${AWS_REGION:-us-east-1}" \
  -e AWS_DEFAULT_REGION="${AWS_DEFAULT_REGION:-us-east-1}" \
  "$CONTAINER_NAME" \
  /opt/spark/bin/spark-sql \
    --properties-file "$SPARK_PROPS" \
    --packages "$PACKAGES" \
    -e "$SQL"