vinishjail97 commented on code in PR #964: URL: https://github.com/apache/incubator-xtable/pull/964#discussion_r4251863236
########## xtable-spark-runtime/src/main/java/org/apache/xtable/spark/XTableSyncService.java: ########## @@ -0,0 +1,138 @@ +/* + * 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. + */ + +package org.apache.xtable.spark; + +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.Properties; +import java.util.stream.Collectors; + +import lombok.extern.log4j.Log4j2; + +import org.apache.hadoop.conf.Configuration; + +import org.apache.xtable.conversion.ConversionConfig; +import org.apache.xtable.conversion.ConversionController; +import org.apache.xtable.conversion.ConversionSourceProvider; +import org.apache.xtable.conversion.SourceTable; +import org.apache.xtable.conversion.TargetTable; +import org.apache.xtable.delta.DeltaConversionSourceProvider; +import org.apache.xtable.delta.DeltaConversionTargetConfig; +import org.apache.xtable.hudi.HudiConversionSourceProvider; +import org.apache.xtable.hudi.HudiSourceConfig; +import org.apache.xtable.iceberg.IcebergConversionSourceProvider; +import org.apache.xtable.kernel.DeltaKernelConversionSourceProvider; +import org.apache.xtable.model.storage.TableFormat; +import org.apache.xtable.model.sync.SyncMode; +import org.apache.xtable.model.sync.SyncResult; +import org.apache.xtable.paimon.PaimonConversionSourceProvider; +import org.apache.xtable.parquet.ParquetConversionSourceProvider; + +/** + * Runs an incremental {@link ConversionController#sync} for a {@link TableSyncSpec}. The sync falls + * back to a full snapshot when an incremental sync is not safe, so it is safe to call after every + * write. + */ +@Log4j2 +public class XTableSyncService { + + /** Runs a single sync for the given spec, returning the per-format results. */ + public Map<String, SyncResult> sync(TableSyncSpec spec, Configuration hadoopConf) { + Properties sourceProperties = new Properties(); + if (spec.getPartitionSpec() != null && !spec.getPartitionSpec().isEmpty()) { + sourceProperties.put(HudiSourceConfig.PARTITION_FIELD_SPEC_CONFIG, spec.getPartitionSpec()); + } + // Targets write their metadata next to the data files, e.g. <basePath>/data for Iceberg. + String dataPath = + spec.getDataPath() != null && !spec.getDataPath().isEmpty() + ? spec.getDataPath() + : spec.getBasePath(); + SourceTable sourceTable = + SourceTable.builder() + .name(spec.getKey()) + .basePath(spec.getBasePath()) + .dataPath(dataPath) + .namespace(spec.getNamespace()) + .formatName(spec.getSourceFormat()) + .additionalProperties(sourceProperties) + .build(); + + // Read by ConversionTargetFactory to pick the Delta Kernel target. + List<TargetTable> targetTables = + spec.getTargets().stream() + .map( + targetFormat -> { + Properties targetProperties = new Properties(); + if (spec.isUseDeltaKernel()) { + targetProperties.setProperty( + DeltaConversionTargetConfig.USE_KERNEL, Boolean.TRUE.toString()); + } + return TargetTable.builder() + .name(spec.getKey()) + .basePath(dataPath) + .namespace(spec.getNamespace()) + .formatName(targetFormat) + .additionalProperties(targetProperties) + .build(); + }) + .collect(Collectors.toList()); + + ConversionConfig conversionConfig = + ConversionConfig.builder() + .sourceTable(sourceTable) + .targetTables(targetTables) + .syncMode(SyncMode.INCREMENTAL) + .build(); + + ConversionSourceProvider<?> sourceProvider = + sourceProviderFor(spec.getSourceFormat(), spec.isUseDeltaKernel()); + sourceProvider.init(hadoopConf); + + log.info( + "Running XTable sync for table {} ({} -> {}) at {}", + spec.getKey(), + spec.getSourceFormat(), + spec.getTargets(), + spec.getBasePath()); + return new ConversionController(hadoopConf).sync(conversionConfig, sourceProvider); + } + + private static ConversionSourceProvider<?> sourceProviderFor( Review Comment: Filed #968 to track this as a follow-up. ########## .github/workflows/spark-runtime-validation.yml: ########## @@ -0,0 +1,86 @@ +# +# 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 Runtime Bundle Validation + +# Runs ITXTableSparkRuntimeBundle, which spark-submits the shaded bundle. The IT skips itself +# unless SPARK_HOME is set, so it only runs here. + +concurrency: + group: ${{ github.workflow }}-${{ github.ref }} + cancel-in-progress: ${{ !contains(github.ref, 'main') }} + +# No path filter, so the check always reports and can be a required status check. +on: + push: + branches: + - "main" + + pull_request: + branches: + - "main" + + workflow_dispatch: + +env: + SPARK_HADOOP_PROFILE: "hadoop3" + +jobs: + validate-spark-runtime-bundle: + runs-on: ubuntu-latest + timeout-minutes: 30 + strategy: + fail-fast: false + matrix: + # 3.4: Delta via delta-core. 3.5: Delta auto-switches to the Spark-free Delta Kernel. + spark_version: ["3.4.3", "3.5.9"] + env: + SPARK_VERSION: ${{ matrix.spark_version }} + steps: + - uses: actions/checkout@v6 + + - name: Set up JDK 11 + uses: actions/setup-java@v5 + with: + java-version: '11' + distribution: 'temurin' + cache: maven + + - name: Cache Spark distribution Review Comment: Filed #969 to track this as a follow-up. -- 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]
