fanyue-xia commented on code in PR #45971: URL: https://github.com/apache/spark/pull/45971#discussion_r1563379719
########## sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQueryHashPartitionVerifySuite.scala: ########## @@ -0,0 +1,199 @@ +/* + * 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.streaming + +import java.io.{BufferedWriter, DataInputStream, DataOutputStream, File, FileInputStream, FileOutputStream, FileWriter} + +import scala.io.Source +import scala.util.Random + +import com.google.common.io.ByteStreams + +import org.apache.spark.SparkConf +import org.apache.spark.io.CompressionCodec +import org.apache.spark.sql.{RandomDataGenerator, Row} +import org.apache.spark.sql.catalyst.CatalystTypeConverters +import org.apache.spark.sql.catalyst.expressions.{BoundReference, GenericInternalRow, UnsafeProjection, UnsafeRow} +import org.apache.spark.sql.catalyst.plans.physical._ +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.streaming.StreamTest +import org.apache.spark.sql.types.{BinaryType, DataType, DoubleType, FloatType, IntegerType, StringType, StructType} + + +class StreamingQueryHashPartitionVerifySuite extends StreamTest { + override protected def sparkConf: SparkConf = + super.sparkConf + .set(SQLConf.SHUFFLE_PARTITIONS.key, numShufflePartitions.toString) + + // Configs for golden file + val goldenFileURI = this.getClass.getResource("/structured-streaming/partition-tests/").toURI + + val schemaFileName = "randomSchemas" // files for storing random input schemas + val rowAndPartIdFilename = + "rowsAndPartIds" // files for storing random input rows and resulting partition ids + val codec = CompressionCodec.createCodec( + sparkConf) // Used for compressing output to rowAndPartId file + + // Configs for random schema generation + private val variableTypes = Seq(IntegerType, DoubleType, FloatType, BinaryType, StringType) + val numSchemaTypes = 5 + val maxNumFields = 10 + + // Configs for shuffle + val numRows = 10000 + val numShufflePartitions = 100 + private def saveSchemas(schemas: Seq[StructType]) = { + val writer = new BufferedWriter(new FileWriter(new File(goldenFileURI.getPath, schemaFileName))) + schemas.foreach{ schema => + writer.write(schema.json) + writer.newLine() + } + writer.close() + } + + private def readSchemas(): Seq[StructType] = { + val source = Source.fromFile(new File(goldenFileURI.getPath, schemaFileName)) + try{ + source.getLines().map{json => DataType.fromJson(json).asInstanceOf[StructType]} + .toArray // Avoid Stream lazy materialization + .toSeq + } finally + source.close() + } + + private def saveRowsAndPartIds(rows: Seq[UnsafeRow], partIds: Seq[Int], os: DataOutputStream) = { + os.writeInt(rows.length) + rows.foreach { row => + val rowBytes = row.getBytes() + os.writeInt(rowBytes.size) + os.write(rowBytes)} + partIds.foreach {id => os.writeInt(id)} + } + + private def readRowsAndPartIds(is: DataInputStream): (Seq[UnsafeRow], Seq[Int]) = { + val numRows = is.readInt() + val rows = (1 to numRows).map{_ => + val rowSize = is.readInt() + val rowBuffer = new Array[Byte](rowSize) + ByteStreams.readFully(is, rowBuffer, 0, rowSize) + val row = new UnsafeRow(1) + row.pointTo(rowBuffer, rowSize) + row + } + val partIds = (1 to numRows).map(_ => is.readInt()).toArray.toSeq Review Comment: I run the formatter and it doesn't seem to add the space. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
