jecio/query-imap-checkpoint-via-spark-container.sh

39 lines
1.2 KiB
Bash
Raw Normal View History

#!/usr/bin/env bash
set -euo pipefail
HOST="${1:-}"
MAILBOX="${2:-}"
USERNAME="${3:-}"
TABLE="${4:-lake.db1.messages}"
if [[ -z "$HOST" || -z "$MAILBOX" || -z "$USERNAME" ]]; then
echo "Usage: $0 <host> <mailbox> <username> [table]" >&2
exit 1
fi
CONTAINER_NAME="${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="${SCRIPT_LOCAL:-./query_imap_checkpoint.py}"
SCRIPT_REMOTE="/tmp/query_imap_checkpoint.py"
if [[ ! -f "$SCRIPT_LOCAL" ]]; then
echo "query_imap_checkpoint.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 "$TABLE" \
--host "$HOST" \
--mailbox "$MAILBOX" \
--username "$USERNAME"