Yohahaha commented on code in PR #2956: URL: https://github.com/apache/fluss/pull/2956#discussion_r3042597974
########## fluss-spark/fluss-spark-common/src/main/scala/org/apache/fluss/spark/read/FlussLakeBatch.scala: ########## @@ -0,0 +1,312 @@ +/* + * 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.fluss.spark.read + +import org.apache.fluss.client.initializer.{BucketOffsetsRetrieverImpl, OffsetsInitializer} +import org.apache.fluss.client.table.scanner.log.LogScanner +import org.apache.fluss.config.Configuration +import org.apache.fluss.exception.LakeTableSnapshotNotExistException +import org.apache.fluss.lake.serializer.SimpleVersionedSerializer +import org.apache.fluss.lake.source.{LakeSource, LakeSplit} +import org.apache.fluss.metadata.{ResolvedPartitionSpec, TableBucket, TableInfo, TablePath} +import org.apache.fluss.utils.ExceptionUtils + +import org.apache.spark.sql.connector.read.{InputPartition, PartitionReaderFactory} +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +import scala.collection.JavaConverters._ +import scala.collection.mutable + +/** Batch for reading lake-enabled log table (append-only table with datalake). */ +class FlussLakeAppendBatch( + tablePath: TablePath, + tableInfo: TableInfo, + readSchema: StructType, + options: CaseInsensitiveStringMap, + flussConfig: Configuration) + extends FlussBatch(tablePath, tableInfo, readSchema, flussConfig) { + + // Required by FlussBatch but unused — lake snapshot determines start offsets. + override val startOffsetsInitializer: OffsetsInitializer = OffsetsInitializer.earliest() + + override val stoppingOffsetsInitializer: OffsetsInitializer = { + FlussOffsetInitializers.stoppingOffsetsInitializer(true, options, flussConfig) + } + + private lazy val planned: (Array[InputPartition], Boolean) = doPlan() Review Comment: nit: replace planned variable with (partitions, isFallback) ########## fluss-spark/fluss-spark-iceberg/src/test/scala/org/apache/fluss/spark/lake/SparkLakeIcebergLogTableReadTest.scala: ########## @@ -0,0 +1,85 @@ +/* + * 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.fluss.spark.lake + +import org.apache.fluss.config.Configuration +import org.apache.fluss.flink.tiering.LakeTieringJobBuilder +import org.apache.fluss.flink.tiering.source.TieringSourceOptions +import org.apache.fluss.metadata.{DataLakeFormat, TableBucket} + +import org.apache.flink.api.common.RuntimeExecutionMode +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment + +import java.nio.file.Files +import java.time.Duration + +class SparkLakeIcebergLogTableReadTest extends SparkLakeLogTableReadTestBase { + + override protected def flussConf: Configuration = { + val conf = super.flussConf + conf.setString("datalake.format", DataLakeFormat.ICEBERG.toString) + conf.setString("datalake.iceberg.type", "hadoop") + warehousePath = + Files.createTempDirectory("fluss-testing-iceberg-lake-read").resolve("warehouse").toString + conf.setString("datalake.iceberg.warehouse", warehousePath) + conf + } + + override protected def tierToLake(tableName: String): Unit = { + val tableId = loadFlussTable(createTablePath(tableName)).getTableInfo.getTableId + + val execEnv = StreamExecutionEnvironment.getExecutionEnvironment Review Comment: nit: could we refactor tiering code into base class? ########## fluss-spark/fluss-spark-iceberg/pom.xml: ########## @@ -0,0 +1,179 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + 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. +--> + +<project xmlns="http://maven.apache.org/POM/4.0.0"; + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark</artifactId> + <version>0.10-SNAPSHOT</version> + </parent> + + <artifactId>fluss-spark-iceberg_${scala.binary.version}</artifactId> + <name>Fluss : Engine Spark : Iceberg</name> + + <dependencies> + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark-ut_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark-common_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-server</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-server</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-client</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-common</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <!-- to avoid this issue: https://github.com/apache/arrow/issues/40896 --> + <dependency> + <groupId>org.eclipse.collections</groupId> + <artifactId>eclipse-collections</artifactId> + <version>11.1.0</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-test-utils</artifactId> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-lake-iceberg</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <!-- Flink tiering job dependencies --> + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-flink-common</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-flink-1.20</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.flink</groupId> + <artifactId>flink-connector-base</artifactId> + <version>${flink.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.flink</groupId> + <artifactId>flink-table-test-utils</artifactId> + <version>${flink.version}</version> + <scope>test</scope> + </dependency> + + <!-- for curator TestingServer --> + <dependency> + <groupId>org.apache.curator</groupId> + <artifactId>curator-test</artifactId> + <version>${curator.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-core_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-sql_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-catalyst_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>junit</groupId> + <artifactId>junit</artifactId> + <version>3.8.1</version> + <scope>test</scope> + </dependency> + </dependencies> + + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-surefire-plugin</artifactId> + <configuration> + <skipTests>true</skipTests> Review Comment: same as paimon module ########## fluss-spark/fluss-spark-paimon/pom.xml: ########## @@ -0,0 +1,186 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<project xmlns="http://maven.apache.org/POM/4.0.0"; + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark</artifactId> + <version>0.10-SNAPSHOT</version> + </parent> + + <artifactId>fluss-spark-paimon_${scala.binary.version}</artifactId> + <name>Fluss : Engine Spark : Paimon</name> + + <dependencies> + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark-ut_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-spark-common_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-server</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-server</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-client</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-common</artifactId> + <version>${project.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <!-- to avoid this issue: https://github.com/apache/arrow/issues/40896 --> + <dependency> + <groupId>org.eclipse.collections</groupId> + <artifactId>eclipse-collections</artifactId> + <version>11.1.0</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-test-utils</artifactId> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-lake-paimon</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.paimon</groupId> + <artifactId>paimon-bundle</artifactId> + <version>${paimon.version}</version> + <scope>test</scope> + </dependency> + + <!-- Flink tiering job dependencies --> + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-flink-common</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.fluss</groupId> + <artifactId>fluss-flink-1.20</artifactId> + <version>${project.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.flink</groupId> + <artifactId>flink-connector-base</artifactId> + <version>${flink.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.flink</groupId> + <artifactId>flink-table-test-utils</artifactId> + <version>${flink.version}</version> + <scope>test</scope> + </dependency> + + <!-- for curator TestingServer --> + <dependency> + <groupId>org.apache.curator</groupId> + <artifactId>curator-test</artifactId> + <version>${curator.version}</version> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-core_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-sql_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-catalyst_${scala.binary.version}</artifactId> + <version>${spark.version}</version> + <classifier>tests</classifier> + <scope>test</scope> + </dependency> + + <dependency> + <groupId>junit</groupId> + <artifactId>junit</artifactId> + <version>3.8.1</version> + <scope>test</scope> + </dependency> + </dependencies> + + <build> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-surefire-plugin</artifactId> + <configuration> + <skipTests>true</skipTests> Review Comment: Why was the test skipped? -- 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]
