Docs/getting-started: Switch to use iceberg-aws-bundle jar

getting-started/eclipselink/docker-compose.yml

@@ -76,7 +76,7 @@ services:
       retries: 15
     command: [
       /opt/spark/bin/spark-sql,
-      --packages, "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,software.amazon.awssdk:bundle:2.28.17,software.amazon.awssdk:url-connection-client:2.28.17,org.apache.iceberg:iceberg-gcp-bundle:1.9.0,org.apache.iceberg:iceberg-azure-bundle:1.9.0",
+      --packages, "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.iceberg:iceberg-aws-bundle:1.9.0,org.apache.iceberg:iceberg-gcp-bundle:1.9.0,org.apache.iceberg:iceberg-azure-bundle:1.9.0",
       --conf, "spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions",
       --conf, "spark.sql.catalog.quickstart_catalog=org.apache.iceberg.spark.SparkCatalog",
       --conf, "spark.sql.catalog.quickstart_catalog.type=rest",

getting-started/jdbc/docker-compose.yml

@@ -76,7 +76,7 @@ services:
       retries: 15
     command: [
       /opt/spark/bin/spark-sql,
-      --packages, "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,software.amazon.awssdk:bundle:2.28.17,software.amazon.awssdk:url-connection-client:2.28.17,org.apache.iceberg:iceberg-gcp-bundle:1.9.0,org.apache.iceberg:iceberg-azure-bundle:1.9.0",
+      --packages, "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.iceberg:iceberg-aws-bundle:1.9.0,org.apache.iceberg:iceberg-gcp-bundle:1.9.0,org.apache.iceberg:iceberg-azure-bundle:1.9.0",
       --conf, "spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions",
       --conf, "spark.sql.catalog.polaris=org.apache.iceberg.spark.SparkCatalog",
       --conf, "spark.sql.catalog.polaris.type=rest",

getting-started/spark/notebooks/SparkPolaris.ipynb

@@ -256,7 +256,7 @@
     "\n",
     "spark = (SparkSession.builder\n",
     "  .config(\"spark.sql.catalog.spark_catalog\", \"org.apache.iceberg.spark.SparkSessionCatalog\")\n",
-    "  .config(\"spark.jars.packages\", \"org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.hadoop:hadoop-aws:3.4.0,software.amazon.awssdk:bundle:2.23.19,software.amazon.awssdk:url-connection-client:2.23.19\")\n",
+    "  .config(\"spark.jars.packages\", \"org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.iceberg:iceberg-aws-bundle:1.9.0\")\n",
     "  .config('spark.sql.iceberg.vectorization.enabled', 'false')\n",
     "         \n",
     "  # Configure the 'polaris' catalog as an Iceberg rest catalog\n",

plugins/spark/README.md

@@ -31,7 +31,7 @@ and depends on iceberg-spark-runtime 1.9.0.
 # Build Plugin Jar
 A task createPolarisSparkJar is added to build a jar for the Polaris Spark plugin, the jar is named as:
 `polaris-iceberg-<icebergVersion>-spark-runtime-<sparkVersion>_<scalaVersion>-<polarisVersion>.jar`. For example:
-`polaris-iceberg-1.8.1-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar`.
+`polaris-iceberg-1.9.0-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar`.
 
 - `./gradlew :polaris-spark-3.5_2.12:createPolarisSparkJar` -- build jar for Spark 3.5 with Scala version 2.12.
 - `./gradlew :polaris-spark-3.5_2.13:createPolarisSparkJar` -- build jar for Spark 3.5 with Scala version 2.13.
@@ -53,7 +53,7 @@ jar, and to use the local Polaris server as a Catalog.
 ```shell
 bin/spark-shell \
 --jars <path-to-spark-client-jar> \
---packages org.apache.hadoop:hadoop-aws:3.4.0,io.delta:delta-spark_2.12:3.3.1 \
+--packages org.apache.iceberg:iceberg-aws-bundle:1.9.0,io.delta:delta-spark_2.12:3.3.1 \
 --conf spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,io.delta.sql.DeltaSparkSessionExtension \
 --conf spark.sql.catalog.spark_catalog=org.apache.spark.sql.delta.catalog.DeltaCatalog \
 --conf spark.sql.catalog.<catalog-name>.warehouse=<catalog-name> \
@@ -67,13 +67,13 @@ bin/spark-shell \
 ```
 
 Assume the path to the built Spark client jar is
-`/polaris/plugins/spark/v3.5/spark/build/2.12/libs/polaris-iceberg-1.8.1-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar`
+`/polaris/plugins/spark/v3.5/spark/build/2.12/libs/polaris-iceberg-1.9.0-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar`
 and the name of the catalog is `polaris`. The cli command will look like following:
 
 ```shell
 bin/spark-shell \
---jars /polaris/plugins/spark/v3.5/spark/build/2.12/libs/polaris-iceberg-1.8.1-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar \
---packages org.apache.hadoop:hadoop-aws:3.4.0,io.delta:delta-spark_2.12:3.3.1 \
+--jars /polaris/plugins/spark/v3.5/spark/build/2.12/libs/polaris-iceberg-1.9.0-spark-runtime-3.5_2.12-0.10.0-beta-incubating-SNAPSHOT.jar \
+--packages org.apache.iceberg:iceberg-aws-bundle:1.9.0,io.delta:delta-spark_2.12:3.3.1 \
 --conf spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,io.delta.sql.DeltaSparkSessionExtension \
 --conf spark.sql.catalog.spark_catalog=org.apache.spark.sql.delta.catalog.DeltaCatalog \
 --conf spark.sql.catalog.polaris.warehouse=<catalog-name> \

plugins/spark/v3.5/getting-started/notebooks/SparkPolaris.ipynb

@@ -266,8 +266,8 @@
     "from pyspark.sql import SparkSession\n",
     "\n",
     "spark = (SparkSession.builder\n",
-    "  .config(\"spark.jars\", \"../polaris_libs/polaris-iceberg-1.8.1-spark-runtime-3.5_2.12-0.11.0-beta-incubating-SNAPSHOT.jar\")\n",
-    "  .config(\"spark.jars.packages\", \"org.apache.hadoop:hadoop-aws:3.3.4,io.delta:delta-spark_2.12:3.2.1\")\n",
+    "  .config(\"spark.jars\", \"../polaris_libs/polaris-iceberg-1.9.0-spark-runtime-3.5_2.12-0.11.0-beta-incubating-SNAPSHOT.jar\")\n",
+    "  .config(\"spark.jars.packages\", \"org.apache.iceberg:iceberg-aws-bundle:1.9.0,io.delta:delta-spark_2.12:3.2.1\")\n",
     "  .config(\"spark.sql.catalog.spark_catalog\", \"org.apache.spark.sql.delta.catalog.DeltaCatalog\")\n",
     "  .config('spark.sql.iceberg.vectorization.enabled', 'false')\n",
     "\n",

regtests/setup.sh

@@ -114,7 +114,7 @@ else
 cat << EOF >> ${SPARK_CONF}
 
 # POLARIS_TESTCONF_V5
-spark.jars.packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:${ICEBERG_VERSION},org.apache.hadoop:hadoop-aws:3.4.0,software.amazon.awssdk:bundle:2.23.19,software.amazon.awssdk:url-connection-client:2.23.19
+spark.jars.packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:${ICEBERG_VERSION},org.apache.iceberg:iceberg-aws-bundle:${ICEBERG_VERSION}
 spark.hadoop.fs.s3.impl org.apache.hadoop.fs.s3a.S3AFileSystem
 spark.hadoop.fs.AbstractFileSystem.s3.impl org.apache.hadoop.fs.s3a.S3A
 spark.sql.variable.substitute true

regtests/t_pyspark/src/iceberg_spark.py

@@ -75,9 +75,7 @@ def __enter__(self):
     """
     packages = [
       "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0",
-      "org.apache.hadoop:hadoop-aws:3.4.0",
-      "software.amazon.awssdk:bundle:2.23.19",
-      "software.amazon.awssdk:url-connection-client:2.23.19",
+      "org.apache.iceberg:iceberg-aws-bundle:1.9.0",
     ]
     excludes = ["org.checkerframework:checker-qual", "com.google.errorprone:error_prone_annotations"]
 

site/content/in-dev/unreleased/getting-started/using-polaris.md

@@ -154,7 +154,7 @@ _Note: the credentials provided here are those for our principal, not the root c
 
 ```shell
 bin/spark-sql \
---packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.hadoop:hadoop-aws:3.4.0 \
+--packages org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.9.0,org.apache.iceberg:iceberg-aws-bundle:1.9.0 \
 --conf spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions \
 --conf spark.sql.catalog.quickstart_catalog.warehouse=quickstart_catalog \
 --conf spark.sql.catalog.quickstart_catalog.header.X-Iceberg-Access-Delegation=vended-credentials \
@@ -170,7 +170,7 @@ bin/spark-sql \
 
 Similar to the CLI commands above, this configures Spark to use the Polaris running at `localhost:8181`. If your Polaris server is running elsewhere, but sure to update the configuration appropriately.
 
-Finally, note that we include the `hadoop-aws` package here. If your table is using a different filesystem, be sure to include the appropriate dependency.
+Finally, note that we include the `iceberg-aws-bundle` package here. If your table is using a different filesystem, be sure to include the appropriate dependency.
 
 #### Using Spark SQL from a Docker container
 

site/content/in-dev/unreleased/polaris-spark-client.md

@@ -60,7 +60,7 @@ a released Polaris Spark client.
 
 ```shell
 bin/spark-shell \
---packages <polaris-spark-client-package>,org.apache.hadoop:hadoop-aws:3.4.0,io.delta:delta-spark_2.12:3.3.1 \
+--packages <polaris-spark-client-package>,org.apache.iceberg:iceberg-aws-bundle:1.9.0,io.delta:delta-spark_2.12:3.3.1 \
 --conf spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,io.delta.sql.DeltaSparkSessionExtension \
 --conf spark.sql.catalog.spark_catalog=org.apache.spark.sql.delta.catalog.DeltaCatalog \
 --conf spark.sql.catalog.<spark-catalog-name>.warehouse=<polaris-catalog-name> \
@@ -88,7 +88,7 @@ You can also start the connection by programmatically initialize a SparkSession,
 from pyspark.sql import SparkSession
 
 spark = SparkSession.builder
-  .config("spark.jars.packages", "<polaris-spark-client-package>,org.apache.hadoop:hadoop-aws:3.3.4,io.delta:delta-spark_2.12:3.3.1")
+  .config("spark.jars.packages", "<polaris-spark-client-package>,org.apache.iceberg:iceberg-aws-bundle:1.9.0,io.delta:delta-spark_2.12:3.3.1")
   .config("spark.sql.catalog.spark_catalog", "org.apache.spark.sql.delta.catalog.DeltaCatalog")
   .config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,io.delta.sql.DeltaSparkSessionExtension")
   .config("spark.sql.catalog.<spark-catalog-name>", "org.apache.polaris.spark.SparkCatalog")