wypoon commented on code in PR #4588: URL: https://github.com/apache/iceberg/pull/4588#discussion_r876497934
########## spark/v3.2/spark/src/test/java/org/apache/iceberg/spark/source/TestSparkReaderDeleteCount.java: ########## @@ -0,0 +1,109 @@ +/* + * 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.iceberg.spark.source; + +import java.io.IOException; +import java.util.Iterator; +import java.util.List; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.util.StructLikeSet; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.util.CaseInsensitiveStringMap; +import org.apache.spark.sql.vectorized.ColumnarBatch; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestSparkReaderDeleteCount extends SparkDeleteReadTestsBase { + + private long deleteCount; + + public TestSparkReaderDeleteCount(String format, boolean vectorized) { + super(format, vectorized); + } + + @Parameterized.Parameters(name = "format = {0}, vectorized = {1}") + public static Object[][] parameters() { + return new Object[][] { + new Object[] {"parquet", true}, + new Object[] {"orc", false}, + new Object[] {"avro", false} + }; + } + + @Override + protected boolean countDeletes() { + return true; + } + + private void setDeleteCount(long count) { + deleteCount = count; + } + + @Override + protected long deleteCount() { + return deleteCount; + } + + @Override + public StructLikeSet rowSet(String name, Table table, String... columns) throws IOException { + Schema schema = table.schema().select(columns); + StructType sparkSchema = SparkSchemaUtil.convert(schema); + Types.StructType type = schema.asStruct(); + StructLikeSet set = StructLikeSet.create(type); + + SparkScanBuilder scanBuilder = new SparkScanBuilder(spark, table, CaseInsensitiveStringMap.empty()); Review Comment: Let me look into that approach. -- 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]
