1.7.2rc3

Author: kevinjqliu

dev/Dockerfile

@@ -39,20 +39,21 @@ WORKDIR ${SPARK_HOME}
 # Remember to also update `tests/conftest`'s spark setting
 ENV SPARK_VERSION=3.5.4
 ENV ICEBERG_SPARK_RUNTIME_VERSION=3.5_2.12
-ENV ICEBERG_VERSION=1.8.0
+ENV ICEBERG_VERSION=1.7.1
 ENV PYICEBERG_VERSION=0.9.0
 
+ENV BASE_ARTIFACT_URL=https://repository.apache.org/content/repositories/orgapacheiceberg-1187
 RUN curl --retry 5 -s -C - https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz -o spark-${SPARK_VERSION}-bin-hadoop3.tgz \
  && tar xzf spark-${SPARK_VERSION}-bin-hadoop3.tgz --directory /opt/spark --strip-components 1 \
  && rm -rf spark-${SPARK_VERSION}-bin-hadoop3.tgz
 
 # Download iceberg spark runtime
-RUN curl --retry 5 -s https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}/${ICEBERG_VERSION}/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}-${ICEBERG_VERSION}.jar \
+RUN curl --retry 5 -s ${BASE_ARTIFACT_URL}/org/apache/iceberg/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}/${ICEBERG_VERSION}/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}-${ICEBERG_VERSION}.jar \
       -Lo /opt/spark/jars/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}-${ICEBERG_VERSION}.jar
 
 
 # Download AWS bundle
-RUN curl --retry 5 -s https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-aws-bundle/${ICEBERG_VERSION}/iceberg-aws-bundle-${ICEBERG_VERSION}.jar \
+RUN curl --retry 5 -s ${BASE_ARTIFACT_URL}/org/apache/iceberg/iceberg-aws-bundle/${ICEBERG_VERSION}/iceberg-aws-bundle-${ICEBERG_VERSION}.jar \
       -Lo /opt/spark/jars/iceberg-aws-bundle-${ICEBERG_VERSION}.jar
 
 COPY spark-defaults.conf /opt/spark/conf

tests/conftest.py

@@ -2420,7 +2420,7 @@ def spark() -> "SparkSession":
     # Remember to also update `dev/Dockerfile`
     spark_version = ".".join(importlib.metadata.version("pyspark").split(".")[:2])
     scala_version = "2.12"
-    iceberg_version = "1.8.0"
+    iceberg_version = "1.7.1"
 
     os.environ["PYSPARK_SUBMIT_ARGS"] = (
         f"--packages org.apache.iceberg:iceberg-spark-runtime-{spark_version}_{scala_version}:{iceberg_version},"
@@ -2432,6 +2432,7 @@ def spark() -> "SparkSession":
 
     spark = (
         SparkSession.builder.appName("PyIceberg integration test")
+        .config("spark.jars.repositories", "https://repository.apache.org/content/repositories/orgapacheiceberg-1187/")
         .config("spark.sql.session.timeZone", "UTC")
         .config("spark.sql.shuffle.partitions", "1")
         .config("spark.default.parallelism", "1")