yihua commented on code in PR #18736: URL: https://github.com/apache/hudi/pull/18736#discussion_r3244386053
########## hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/blob/TestBatchedBlobReaderMerge.scala: ########## @@ -0,0 +1,183 @@ +/* + * 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.blob + +import org.apache.spark.sql.Row +import org.junit.jupiter.api.Assertions._ +import org.junit.jupiter.api.Test + +/** + * Direct unit tests for the merge algorithm in {@link BatchedBlobReader}. + * + * These tests bypass Spark and storage entirely: they construct a reader with + * a null storage (the merge methods do not touch I/O) and call mergeRanges / + * identifyConsecutiveRanges with crafted RowInfo inputs to assert the + * structure of the merged output (counts, boundaries, ordering, grouping). + * + * This complements TestBatchedBlobReader (which verifies data correctness end-to-end) + * by proving the batching algorithm produces the expected merged ranges for + * each input pattern. + */ +class TestBatchedBlobReaderMerge { + + private def reader(maxGapBytes: Int = 4096) = + new BatchedBlobReader(storage = null, maxGapBytes = maxGapBytes, lookaheadRows = 50) + + private def row(filePath: String, offset: Long, length: Long, index: Long = 0L): RowInfo[Row] = + RowInfo[Row]( + originalRow = null.asInstanceOf[Row], + filePath = filePath, + offset = offset, + length = length, + index = index) + + @Test + def testEmptyInputProducesNoRanges(): Unit = { + val merged = reader().mergeRanges(Seq.empty[RowInfo[Row]], maxGap = 100) + assertTrue(merged.isEmpty) + } + + @Test + def testSingleRowProducesSingleRange(): Unit = { + val merged = reader().mergeRanges(Seq(row("/f", 1000, 200, index = 7)), maxGap = 100) + assertEquals(1, merged.size) + val r = merged.head + assertEquals("/f", r.filePath) + assertEquals(1000L, r.startOffset) + assertEquals(1200L, r.endOffset) + assertEquals(1, r.rows.size) + assertEquals(7L, r.rows.head.index) Review Comment: It would be better to test this with SQL so that it works end-to-end. -- 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]
