the-other-tim-brown commented on code in PR #18347: URL: https://github.com/apache/hudi/pull/18347#discussion_r2990645309
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/blob/BlobTestHelpers.scala: ########## @@ -0,0 +1,129 @@ +/* + * 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.hudi.blob + +import org.apache.hudi.common.schema.{HoodieSchema, HoodieSchemaType} + +import org.apache.spark.sql.{Column, SparkSession} +import org.apache.spark.sql.functions.{lit, struct} +import org.apache.spark.sql.types._ +import org.junit.jupiter.api.Assertions.{assertEquals, assertTrue} + +import java.io.File +import java.nio.file.{Files, Path} + +object BlobTestHelpers { + def blobMetadata: Metadata = { + new MetadataBuilder() + .putString(HoodieSchema.TYPE_METADATA_FIELD, HoodieSchemaType.BLOB.name()) + .build() + } + + def inlineBlobStructCol(name: String, bytesCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.INLINE).as(HoodieSchema.Blob.TYPE), + bytesCol.as(HoodieSchema.Blob.INLINE_DATA_FIELD), + lit(null).cast("struct<externalPath:string,offset:bigint,length:bigint,managed:boolean>") + .as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def wholeFileBlobStructCol(name: String, filePathCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def blobStructCol(name: String, filePathCol: Column, offsetCol: Column, lengthCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + offsetCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lengthCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def createTestFile(tempDir: Path, name: String, size: Int): String = { + val file = new File(tempDir.toString, name) + val bytes = (0 until size).map(i => (i % 256).toByte).toArray + Files.write(file.toPath, bytes) + file.getAbsolutePath + } + + /** + * Assert that byte array contains expected pattern (i % 256) at given offset. + * + * @param data Array of bytes to verify + * @param expectedOffset Starting offset for pattern (default 0) + */ + def assertBytesContent(data: Array[Byte], expectedOffset: Int = 0): Unit = { + for (i <- 0 until data.length) { + assertEquals((expectedOffset + i) % 256, data(i) & 0xFF, + s"Mismatch at byte $i (global offset ${expectedOffset + i})") + } + } Review Comment: Not yet, it was recommended to pull code into separate PRs to reduce the size ########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/blob/BlobTestHelpers.scala: ########## @@ -0,0 +1,129 @@ +/* + * 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.hudi.blob + +import org.apache.hudi.common.schema.{HoodieSchema, HoodieSchemaType} + +import org.apache.spark.sql.{Column, SparkSession} +import org.apache.spark.sql.functions.{lit, struct} +import org.apache.spark.sql.types._ +import org.junit.jupiter.api.Assertions.{assertEquals, assertTrue} + +import java.io.File +import java.nio.file.{Files, Path} + +object BlobTestHelpers { + def blobMetadata: Metadata = { + new MetadataBuilder() + .putString(HoodieSchema.TYPE_METADATA_FIELD, HoodieSchemaType.BLOB.name()) + .build() + } + + def inlineBlobStructCol(name: String, bytesCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.INLINE).as(HoodieSchema.Blob.TYPE), + bytesCol.as(HoodieSchema.Blob.INLINE_DATA_FIELD), + lit(null).cast("struct<externalPath:string,offset:bigint,length:bigint,managed:boolean>") + .as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def wholeFileBlobStructCol(name: String, filePathCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def blobStructCol(name: String, filePathCol: Column, offsetCol: Column, lengthCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + offsetCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lengthCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def createTestFile(tempDir: Path, name: String, size: Int): String = { + val file = new File(tempDir.toString, name) + val bytes = (0 until size).map(i => (i % 256).toByte).toArray + Files.write(file.toPath, bytes) + file.getAbsolutePath + } + + /** + * Assert that byte array contains expected pattern (i % 256) at given offset. + * + * @param data Array of bytes to verify + * @param expectedOffset Starting offset for pattern (default 0) + */ + def assertBytesContent(data: Array[Byte], expectedOffset: Int = 0): Unit = { + for (i <- 0 until data.length) { + assertEquals((expectedOffset + i) % 256, data(i) & 0xFF, + s"Mismatch at byte $i (global offset ${expectedOffset + i})") + } + } + + /** + * Execute code block with temporary Spark configuration. + * Automatically restores previous values after execution. + * + * @param spark SparkSession instance + * @param configs Configuration key-value pairs to set + * @param fn Code block to execute with configs + */ + def withSparkConfig[T](spark: SparkSession, configs: Map[String, String])(fn: => T): T = { + val oldValues = configs.keys.map(k => (k, spark.conf.getOption(k))).toMap + try { + configs.foreach { case (k, v) => spark.conf.set(k, v) } + fn + } finally { + oldValues.foreach { case (k, oldValue) => + oldValue match { + case Some(v) => spark.conf.set(k, v) + case None => spark.conf.unset(k) + } + } + } + } Review Comment: See above ########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/blob/BlobTestHelpers.scala: ########## @@ -0,0 +1,129 @@ +/* + * 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.hudi.blob + +import org.apache.hudi.common.schema.{HoodieSchema, HoodieSchemaType} + +import org.apache.spark.sql.{Column, SparkSession} +import org.apache.spark.sql.functions.{lit, struct} +import org.apache.spark.sql.types._ +import org.junit.jupiter.api.Assertions.{assertEquals, assertTrue} + +import java.io.File +import java.nio.file.{Files, Path} + +object BlobTestHelpers { + def blobMetadata: Metadata = { + new MetadataBuilder() + .putString(HoodieSchema.TYPE_METADATA_FIELD, HoodieSchemaType.BLOB.name()) + .build() + } + + def inlineBlobStructCol(name: String, bytesCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.INLINE).as(HoodieSchema.Blob.TYPE), + bytesCol.as(HoodieSchema.Blob.INLINE_DATA_FIELD), + lit(null).cast("struct<externalPath:string,offset:bigint,length:bigint,managed:boolean>") + .as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def wholeFileBlobStructCol(name: String, filePathCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lit(null).cast("bigint").as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def blobStructCol(name: String, filePathCol: Column, offsetCol: Column, lengthCol: Column): Column = { + struct( + lit(HoodieSchema.Blob.OUT_OF_LINE).as(HoodieSchema.Blob.TYPE), + lit(null).cast("binary").as(HoodieSchema.Blob.INLINE_DATA_FIELD), + struct( + filePathCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_PATH), + offsetCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_OFFSET), + lengthCol.as(HoodieSchema.Blob.EXTERNAL_REFERENCE_LENGTH), + lit(false).as(HoodieSchema.Blob.EXTERNAL_REFERENCE_IS_MANAGED) + ).as(HoodieSchema.Blob.EXTERNAL_REFERENCE) + ).as(name, blobMetadata) + } + + def createTestFile(tempDir: Path, name: String, size: Int): String = { + val file = new File(tempDir.toString, name) + val bytes = (0 until size).map(i => (i % 256).toByte).toArray + Files.write(file.toPath, bytes) + file.getAbsolutePath + } + + /** + * Assert that byte array contains expected pattern (i % 256) at given offset. + * + * @param data Array of bytes to verify + * @param expectedOffset Starting offset for pattern (default 0) + */ + def assertBytesContent(data: Array[Byte], expectedOffset: Int = 0): Unit = { + for (i <- 0 until data.length) { + assertEquals((expectedOffset + i) % 256, data(i) & 0xFF, + s"Mismatch at byte $i (global offset ${expectedOffset + i})") + } + } + + /** + * Execute code block with temporary Spark configuration. + * Automatically restores previous values after execution. + * + * @param spark SparkSession instance + * @param configs Configuration key-value pairs to set + * @param fn Code block to execute with configs + */ + def withSparkConfig[T](spark: SparkSession, configs: Map[String, String])(fn: => T): T = { + val oldValues = configs.keys.map(k => (k, spark.conf.getOption(k))).toMap + try { + configs.foreach { case (k, v) => spark.conf.set(k, v) } + fn + } finally { + oldValues.foreach { case (k, oldValue) => + oldValue match { + case Some(v) => spark.conf.set(k, v) + case None => spark.conf.unset(k) + } + } + } + } + + /** + * Assert that DataFrame contains all specified columns. + * + * @param df DataFrame to check + * @param columnNames Variable number of column names + */ + def assertColumnsExist(df: org.apache.spark.sql.DataFrame, columnNames: String*): Unit = { + columnNames.foreach { colName => + assertTrue(df.columns.contains(colName), + s"DataFrame missing expected column: $colName. Available: ${df.columns.mkString(", ")}") + } + } Review Comment: See above -- 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]
