jecio/create-messages-release-via-spark-container.sh
2026-02-14 21:10:26 +01:00

48 lines
1.7 KiB
Bash
Executable file

#!/usr/bin/env bash
set -euo pipefail
RELEASE_NAME="${1:-rel_$(date -u +%Y-%m-%d)_messages-v1}"
TABLE="${MESSAGES_TABLE:-lake.db1.messages}"
MANIFEST_LOCAL="${2:-./manifests/${RELEASE_NAME}.json}"
DESCRIPTION="${RELEASE_DESCRIPTION:-Messages release for ${TABLE}}"
CREATED_BY="${RELEASE_CREATED_BY:-${USER:-unknown}}"
NESSIE_URI="${NESSIE_URI:-http://nessie:19120/api/v2}"
RELEASES_TABLE="${RELEASES_TABLE:-lake.db1.releases_v2}"
CONTAINER_NAME="${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}"
SCRIPT_LOCAL="${SCRIPT_LOCAL:-./create_release_manifest.py}"
SCRIPT_REMOTE="/tmp/create_release_manifest.py"
MANIFEST_REMOTE="/tmp/${RELEASE_NAME}.json"
if [[ ! -f "$SCRIPT_LOCAL" ]]; then
echo "create_release_manifest.py not found at: $SCRIPT_LOCAL" >&2
exit 1
fi
mkdir -p "$(dirname "$MANIFEST_LOCAL")"
docker cp "$SCRIPT_LOCAL" "$CONTAINER_NAME":"$SCRIPT_REMOTE"
docker exec \
-e AWS_REGION="${AWS_REGION:-us-east-1}" \
-e AWS_DEFAULT_REGION="${AWS_DEFAULT_REGION:-us-east-1}" \
"$CONTAINER_NAME" \
/opt/spark/bin/spark-submit \
--properties-file "$SPARK_PROPS" \
--packages "$PACKAGES" \
"$SCRIPT_REMOTE" \
--release-name "$RELEASE_NAME" \
--table "$TABLE" \
--nessie-uri "$NESSIE_URI" \
--manifest-out "$MANIFEST_REMOTE" \
--description "$DESCRIPTION" \
--created-by "$CREATED_BY" \
--releases-table "$RELEASES_TABLE"
docker cp "$CONTAINER_NAME":"$MANIFEST_REMOTE" "$MANIFEST_LOCAL"
echo "[DONE] Saved manifest: $MANIFEST_LOCAL"