Files
dbiz-lake-k8s/images/spark-cdc/Dockerfile
2026-07-08 14:58:58 +07:00

15 lines
694 B
Docker

# Image CDC job: Spark + jar Iceberg/Kafka bundled + script. Reproducible, khởi động nhanh.
FROM spark:3.5.6
USER root
ARG IVY_PKGS="org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.1,org.apache.iceberg:iceberg-aws-bundle:1.9.1,org.apache.spark:spark-sql-kafka-0-10_2.12:3.5.6"
# Tải sẵn các jar vào /opt/spark/jars (không tải runtime mỗi lần pod start)
RUN /opt/spark/bin/spark-shell --packages "${IVY_PKGS}" --conf spark.jars.ivy=/tmp/.ivy <<< 'System.exit(0)' || true \
&& find /root/.ivy2 -name '*.jar' -exec cp {} /opt/spark/jars/ \; 2>/dev/null || true
# Script CDC (copy vào work-dir)
COPY cdc_crm_to_raw.py /opt/spark/work-dir/cdc_crm_to_raw.py
USER 185