jecio/record-assistant-proposals-via-spark-container.sh

49 lines
1.7 KiB
Bash
Raw Permalink Normal View History

#!/usr/bin/env bash
set -euo pipefail
PROPOSAL_TABLE="${PROPOSAL_TABLE:-lake.db1.assistant_proposals}"
PROPOSAL_SET_ID="${1:-}"
CREATED_AT_UTC="${2:-}"
OBJECTIVE_B64="${3:-}"
RELEASE_NAME="${4:-}"
SUMMARY_B64="${5:-}"
SIGNALS_B64="${6:-}"
PROPOSALS_B64="${7:-}"
if [[ -z "$PROPOSAL_SET_ID" || -z "$CREATED_AT_UTC" ]]; then
echo "Usage: $0 <proposal_set_id> <created_at_utc> <objective_b64> <release_name> <summary_b64> <signals_b64> <proposals_b64>" >&2
exit 1
fi
CONTAINER_NAME="${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="${SCRIPT_LOCAL:-./write_assistant_proposals.py}"
SCRIPT_REMOTE="/tmp/write_assistant_proposals.py"
if [[ ! -f "$SCRIPT_LOCAL" ]]; then
echo "write_assistant_proposals.py not found at: $SCRIPT_LOCAL" >&2
exit 1
fi
docker cp "$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" \
--table "$PROPOSAL_TABLE" \
--proposal-set-id "$PROPOSAL_SET_ID" \
--created-at-utc "$CREATED_AT_UTC" \
--objective-b64 "$OBJECTIVE_B64" \
--release-name "$RELEASE_NAME" \
--summary-b64 "$SUMMARY_B64" \
--signals-b64 "$SIGNALS_B64" \
--proposals-b64 "$PROPOSALS_B64"
echo "[DONE] Recorded proposal set ${PROPOSAL_SET_ID} into ${PROPOSAL_TABLE}"