chaoqin-li1123 commented on code in PR #45023: URL: https://github.com/apache/spark/pull/45023#discussion_r1491464370
########## sql/core/src/test/scala/org/apache/spark/sql/execution/python/PythonStreamingDataSourceSuite.scala: ########## @@ -0,0 +1,229 @@ +/* + * 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.spark.sql.execution.python + +import org.apache.spark.SparkException +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.IntegratedUDFTestUtils.{createUserDefinedPythonDataSource, shouldTestPandasUDFs} +import org.apache.spark.sql.execution.datasources.v2.python.{PythonDataSourceV2, PythonMicroBatchStream, PythonStreamingSourceOffset} +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +class PythonStreamingDataSourceSuite extends PythonDataSourceSuiteBase { + + protected def simpleDataStreamReaderScript: String = + """ + |from pyspark.sql.datasource import DataSourceStreamReader, InputPartition + | + |class SimpleDataStreamReader(DataSourceStreamReader): + | def initialOffset(self): + | return {"offset": "0"} + | def latestOffset(self): + | return {"offset": "2"} + | def partitions(self, start: dict, end: dict): + | return [InputPartition(i) for i in range(int(start["offset"]))] + | def commit(self, end: dict): + | 1 + 2 + | def read(self, partition): + | yield (0, partition.value) + | yield (1, partition.value) + | yield (2, partition.value) + |""".stripMargin + + protected def errorDataStreamReaderScript: String = + """ + |from pyspark.sql.datasource import DataSourceStreamReader, InputPartition + | + |class ErrorDataStreamReader(DataSourceStreamReader): + | def initialOffset(self): + | raise Exception("error reading initial offset") + | def latestOffset(self): + | raise Exception("error reading latest offset") + | def partitions(self, start: dict, end: dict): + | raise Exception("error planning partitions") + | def commit(self, end: dict): + | raise Exception("error committing offset") + | def read(self, partition): + | yield (0, partition.value) + | yield (1, partition.value) + | yield (2, partition.value) + |""".stripMargin + + private val errorDataSourceName = "ErrorDataSource" + + test("simple data stream source") { + assume(shouldTestPandasUDFs) + val dataSourceScript = + s""" + |from pyspark.sql.datasource import DataSource + |$simpleDataStreamReaderScript + | + |class $dataSourceName(DataSource): + | def streamReader(self, schema): + | return SimpleDataStreamReader() + |""".stripMargin + val inputSchema = StructType.fromDDL("input BINARY") + + val dataSource = createUserDefinedPythonDataSource(dataSourceName, dataSourceScript) + spark.dataSource.registerPython(dataSourceName, dataSource) + val pythonDs = new PythonDataSourceV2 + pythonDs.setShortName("SimpleDataSource") + val stream = new PythonMicroBatchStream( + pythonDs, dataSourceName, inputSchema, CaseInsensitiveStringMap.empty()) + + val initialOffset = stream.initialOffset() + assert(initialOffset.json == "{\"offset\": \"0\"}") + for (_ <- 1 to 50) { + val offset = stream.latestOffset() + assert(offset.json == "{\"offset\": \"2\"}") + assert(stream.planInputPartitions(offset, offset).size == 2) + stream.commit(offset) + } + stream.stop() Review Comment: read will be implemented in the next PR, it is executed in executor. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
