singhpk234 commented on code in PR #1402: URL: https://github.com/apache/polaris/pull/1402#discussion_r2056508195
########## plugins/spark/v3.5/regtests/Dockerfile: ########## @@ -0,0 +1,48 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +FROM docker.io/apache/spark:3.5.5-java17 Review Comment: we are running java 21 in CI why are pulling java 17 here then ? ########## plugins/spark/v3.5/regtests/spark_sql.sh: ########## @@ -0,0 +1,81 @@ +#!/bin/bash + +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +SPARK_BEARER_TOKEN="${REGTEST_ROOT_BEARER_TOKEN}" + +CATALOG_NAME="spark_sql_catalog" +curl -i -X POST -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + http://${POLARIS_HOST:-localhost}:8181/api/management/v1/catalogs \ + -d '{"name": "spark_sql_catalog", "id": 100, "type": "INTERNAL", "readOnly": false, "properties": {"default-base-location": "file:///tmp/spark_catalog"}, "storageConfigInfo": {"storageType": "FILE", "allowedLocations": ["file:///tmp"]}}' > /dev/stderr + +# Add TABLE_WRITE_DATA to the catalog's catalog_admin role since by default it can only manage access and metadata +curl -i -X PUT -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + http://${POLARIS_HOST:-localhost}:8181/api/management/v1/catalogs/${CATALOG_NAME}/catalog-roles/catalog_admin/grants \ + -d '{"type": "catalog", "privilege": "TABLE_WRITE_DATA"}' > /dev/stderr + +curl -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + "http://${POLARIS_HOST:-localhost}:8181/api/catalog/v1/config?warehouse=${CATALOG_NAME}"; +echo +echo "Catalog created" +cat << EOF | ${SPARK_HOME}/bin/spark-sql -S --conf spark.sql.catalog.polaris.token="${SPARK_BEARER_TOKEN}" --conf spark.sql.catalog.polaris.warehouse=${CATALOG_NAME} +use polaris; +create namespace db1; +create namespace db2; +show namespaces; + +create namespace db1.schema1; +show namespaces in db1; + +create table db1.schema1.iceberg_tb (col1 int); +show tables in db1; +show tables in db1.schema1; + +use db1.schema1; +insert into iceberg_tb values (123), (234), (111); +select * from iceberg_tb order by col1; + +create table delta_tb1(col1 string) using delta location 'file:///tmp/spark_catalog/delta_tb1'; +insert into delta_tb1 values ('ab'), ('bb'), ('dd'); +select * from delta_tb1 order by col1; + +show tables; + +use db1; +create table delta_tb2(col1 int) using delta location 'file:///tmp/spark_catalog/delta_tb2'; Review Comment: How about CTAS ? should we add that as well ########## plugins/spark/v3.5/regtests/spark_sql.sh: ########## @@ -0,0 +1,81 @@ +#!/bin/bash + +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +SPARK_BEARER_TOKEN="${REGTEST_ROOT_BEARER_TOKEN}" + +CATALOG_NAME="spark_sql_catalog" +curl -i -X POST -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + http://${POLARIS_HOST:-localhost}:8181/api/management/v1/catalogs \ + -d '{"name": "spark_sql_catalog", "id": 100, "type": "INTERNAL", "readOnly": false, "properties": {"default-base-location": "file:///tmp/spark_catalog"}, "storageConfigInfo": {"storageType": "FILE", "allowedLocations": ["file:///tmp"]}}' > /dev/stderr + +# Add TABLE_WRITE_DATA to the catalog's catalog_admin role since by default it can only manage access and metadata +curl -i -X PUT -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + http://${POLARIS_HOST:-localhost}:8181/api/management/v1/catalogs/${CATALOG_NAME}/catalog-roles/catalog_admin/grants \ + -d '{"type": "catalog", "privilege": "TABLE_WRITE_DATA"}' > /dev/stderr + +curl -H "Authorization: Bearer ${SPARK_BEARER_TOKEN}" -H 'Accept: application/json' -H 'Content-Type: application/json' \ + "http://${POLARIS_HOST:-localhost}:8181/api/catalog/v1/config?warehouse=${CATALOG_NAME}"; +echo +echo "Catalog created" +cat << EOF | ${SPARK_HOME}/bin/spark-sql -S --conf spark.sql.catalog.polaris.token="${SPARK_BEARER_TOKEN}" --conf spark.sql.catalog.polaris.warehouse=${CATALOG_NAME} +use polaris; +create namespace db1; +create namespace db2; +show namespaces; + +create namespace db1.schema1; +show namespaces in db1; + +create table db1.schema1.iceberg_tb (col1 int); +show tables in db1; +show tables in db1.schema1; + +use db1.schema1; +insert into iceberg_tb values (123), (234), (111); +select * from iceberg_tb order by col1; + +create table delta_tb1(col1 string) using delta location 'file:///tmp/spark_catalog/delta_tb1'; Review Comment: [doubt] should this be path of s3 ? ########## .github/workflows/spark_client_regtests.yml: ########## @@ -0,0 +1,61 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +name: Spark Client Regression Tests +on: + push: + branches: [ "main" ] + pull_request: + branches: [ "main" ] + +jobs: + regtest: + + runs-on: ubuntu-latest + permissions: + contents: read + + steps: + - uses: actions/checkout@v4 + + - name: Set up JDK 21 + uses: actions/setup-java@v4 + with: + java-version: '21' + distribution: 'temurin' + + - name: Fix permissions + run: mkdir -p regtests/output && chmod 777 regtests/output && chmod 777 regtests/t_*/ref/* + + - name: Project build + run: ./gradlew build + + - name: Image build + run: | + ./gradlew \ + :polaris-quarkus-server:assemble \ + :polaris-quarkus-server:quarkusAppPartsBuild --rerun \ + -Dquarkus.container-image.build=true + + - name: Regression Test + env: + AWS_ACCESS_KEY_ID: ${{secrets.AWS_ACCESS_KEY_ID}} + AWS_SECRET_ACCESS_KEY: ${{secrets.AWS_SECRET_ACCESS_KEY}} Review Comment: [doubt] why only AWS, not GCP / Azure ? ########## plugins/spark/v3.5/regtests/docker-compose.yml: ########## @@ -0,0 +1,73 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +services: + polaris: + image: apache/polaris:latest + ports: + - "8181" + - "8182" + environment: + AWS_REGION: us-west-2 + AWS_ACCESS_KEY_ID: $AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY: $AWS_SECRET_ACCESS_KEY + GOOGLE_APPLICATION_CREDENTIALS: $GOOGLE_APPLICATION_CREDENTIALS + AZURE_TENANT_ID: $AZURE_TENANT_ID + AZURE_CLIENT_ID: $AZURE_CLIENT_ID + AZURE_CLIENT_SECRET: $AZURE_CLIENT_SECRET Review Comment: Are we using it ? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
