suryaprasanna commented on code in PR #18136: URL: https://github.com/apache/hudi/pull/18136#discussion_r2796107246
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/common/TestROPathFilterOnRead: ########## @@ -0,0 +1,266 @@ +/* + * 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.hudi.common + +/** + * Tests for ROPathFilter optimization with advanced scenarios and edge cases. + */ +class TestROPathFilterAdvanced extends HoodieSparkSqlTestBase { + + val RO_PATH_FILTER_OPT_KEY = "hoodie.datasource.read.file.index.list.file.statuses.using.ro.path.filter" + + test("Test ROPathFilter with empty table") { + withTempDir { tmp => + val tableName = generateTableName + spark.sql( + s""" + |create table $tableName ( + | id int, + | name string, + | price double, + | ts long + |) using hudi + | location '${tmp.getCanonicalPath}' + | tblproperties ( + | primaryKey ='id', + | type = 'cow', + | orderingFields = 'ts' + | ) + """.stripMargin) + + // Query empty table with ROPathFilter enabled + withSQLConf(s"spark.$RO_PATH_FILTER_OPT_KEY" -> "true") { + val result = spark.sql(s"select * from $tableName").collect() + assert(result.length == 0) + } + } + } + + test("Test ROPathFilter with partition pruning") { + withTempDir { tmp => + val tableName = generateTableName + spark.sql( + s""" + |create table $tableName ( + | id int, + | name string, + | price double, + | ts long, + | dt string + |) using hudi + | location '${tmp.getCanonicalPath}' + | tblproperties ( + | primaryKey ='id', + | type = 'cow', + | orderingFields = 'ts' + | ) + | partitioned by (dt) + """.stripMargin) + + // Query empty table with ROPathFilter enabled + withSQLConf(s"spark.$RO_PATH_FILTER_OPT_KEY" -> "true") { + val result = spark.sql(s"select * from $tableName").collect() + assert(result.length == 0) + } + + // Insert data across multiple partitions + spark.sql(s"""insert into $tableName values(1, "a1", 10.0, 1000, "2024-01-01")""") + spark.sql(s"""insert into $tableName values(2, "a2", 20.0, 2000, "2024-01-02")""") + + // Update data in first partition + spark.sql(s"update $tableName set price = 15.0 where id = 1") + + // Query single partition with ROPathFilter Review Comment: Add time travel test case. And use a different name for getAllFilesInPartitions -- 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]
