kazuyukitanimura commented on code in PR #1715: URL: https://github.com/apache/datafusion-comet/pull/1715#discussion_r2076584499
########## .github/workflows/iceberg_spark_test_native_datafusion.yml: ########## @@ -0,0 +1,80 @@ +# 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: Iceberg Spark SQL Tests (native_datafusion) + +concurrency: + group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }} + cancel-in-progress: true + +on: + push: + paths-ignore: + - "doc/**" + - "docs/**" + - "**.md" + pull_request: + paths-ignore: + - "doc/**" + - "docs/**" + - "**.md" + # manual trigger + # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow + workflow_dispatch: + +env: + RUST_VERSION: stable + +jobs: + iceberg-spark-sql-native-datafusion: + strategy: + matrix: + os: [ubuntu-24.04] + java-version: [11, 17] + iceberg-version: [{short: '1.8', full: '1.8.1'}] + spark-version: [{short: '3.5', full: '3.5.4'}] + scala-version: [ '2.12', '2.13'] + fail-fast: false + name: iceberg-spark-sql-native-datafusion/${{ matrix.os }}/iceberg-${{ matrix.iceberg-version.full }}/spark-${{ matrix.spark-version.full }}/scala-${{ matrix.scala-version }}/java-${{ matrix.java-version }} + runs-on: ${{ matrix.os }} + container: + image: amd64/rust + env: + SPARK_LOCAL_IP: localhost + steps: + - uses: actions/checkout@v4 + - name: Setup Rust & Java toolchain + uses: ./.github/actions/setup-builder + with: + rust-version: ${{env.RUST_VERSION}} + jdk-version: ${{ matrix.java-version }} + - name: Setup Iceberg + uses: ./.github/actions/setup-iceberg-builder + with: + iceberg-version: ${{ matrix.iceberg-version.full }} + iceberg-short-version: ${{ matrix.iceberg-version.short }} + scala-version: ${{ matrix.scala-version }} + spark-short-version: ${{ matrix.spark-version.short }} + - name: Run Iceberg Spark tests + run: | + cd apache-iceberg + rm -rf /root/.m2/repository/org/apache/parquet # somehow parquet cache requires cleanups + ENABLE_COMET=true ENABLE_COMET_SHUFFLE=true COMET_PARQUET_SCAN_IMPL=native_datafusion ./gradlew -DsparkVersions=${{ matrix.spark-version.short }} -DscalaVersion=${{ matrix.scala-version }} -DflinkVersions= -DkafkaVersions= \ Review Comment: hmmm do we expect native_datafusion works for iceberg? ########## dev/diffs/iceberg/1.8.1.diff: ########## @@ -0,0 +1,179 @@ +diff --git a/spark/v3.4/build.gradle b/spark/v3.4/build.gradle +index 6eb26e8..90d848d 100644 +--- a/spark/v3.4/build.gradle ++++ b/spark/v3.4/build.gradle +@@ -75,7 +75,7 @@ project(":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}") { + exclude group: 'org.roaringbitmap' + } + +- compileOnly "org.apache.datafusion:comet-spark-spark${sparkMajorVersion}_${scalaVersion}:0.5.0" ++ compileOnly "org.apache.datafusion:comet-spark-spark${sparkMajorVersion}_${scalaVersion}:0.9.0-SNAPSHOT" + + implementation libs.parquet.column + implementation libs.parquet.hadoop +@@ -185,7 +185,7 @@ project(":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVer + testImplementation libs.avro.avro + testImplementation libs.parquet.hadoop + testImplementation libs.junit.vintage.engine +- testImplementation "org.apache.datafusion:comet-spark-spark${sparkMajorVersion}_${scalaVersion}:0.5.0" ++ testImplementation "org.apache.datafusion:comet-spark-spark${sparkMajorVersion}_${scalaVersion}:0.9.0-SNAPSHOT" + + // Required because we remove antlr plugin dependencies from the compile configuration, see note above + runtimeOnly libs.antlr.runtime +@@ -260,6 +260,7 @@ project(":iceberg-spark:iceberg-spark-runtime-${sparkMajorVersion}_${scalaVersio + integrationImplementation project(path: ':iceberg-hive-metastore', configuration: 'testArtifacts') + integrationImplementation project(path: ":iceberg-spark:iceberg-spark-${sparkMajorVersion}_${scalaVersion}", configuration: 'testArtifacts') + integrationImplementation project(path: ":iceberg-spark:iceberg-spark-extensions-${sparkMajorVersion}_${scalaVersion}", configuration: 'testArtifacts') ++ integrationImplementation "org.apache.datafusion:comet-spark-spark${sparkMajorVersion}_${scalaVersion}:0.9.0-SNAPSHOT" + + // runtime dependencies for running Hive Catalog based integration test + integrationRuntimeOnly project(':iceberg-hive-metastore') +@@ -297,8 +298,8 @@ project(":iceberg-spark:iceberg-spark-runtime-${sparkMajorVersion}_${scalaVersio + relocate 'org.apache.avro', 'org.apache.iceberg.shaded.org.apache.avro' + relocate 'avro.shaded', 'org.apache.iceberg.shaded.org.apache.avro.shaded' + relocate 'com.thoughtworks.paranamer', 'org.apache.iceberg.shaded.com.thoughtworks.paranamer' +- relocate 'org.apache.parquet', 'org.apache.iceberg.shaded.org.apache.parquet' +- relocate 'shaded.parquet', 'org.apache.iceberg.shaded.org.apache.parquet.shaded' ++// relocate 'org.apache.parquet', 'org.apache.iceberg.shaded.org.apache.parquet' ++// relocate 'shaded.parquet', 'org.apache.iceberg.shaded.org.apache.parquet.shaded' Review Comment: do we need this change? -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
