vinothchandar commented on a change in pull request #2903: URL: https://github.com/apache/hudi/pull/2903#discussion_r655073962
########## File path: hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/HoodieSparkSqlWriterSuite.scala ########## @@ -229,7 +231,42 @@ class HoodieSparkSqlWriterSuite extends FunSuite with Matchers { } } - test("test bulk insert dataset with datasource impl multiple rounds") { + test("test read of a table with one failed write") { + initSparkContext("test_read_table_with_one_failed_write") + val path = java.nio.file.Files.createTempDirectory("hoodie_test_path") + try { + val hoodieFooTableName = "hoodie_foo_tbl" + val fooTableModifier = Map("path" -> path.toAbsolutePath.toString, + HoodieWriteConfig.TABLE_NAME -> hoodieFooTableName, + DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY -> "_row_key", + DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY -> "partition") + + val fooTableParams = HoodieWriterUtils.parametersWithWriteDefaults(fooTableModifier) + val props = new Properties() + fooTableParams.foreach(entry => props.setProperty(entry._1, entry._2)) + val metaClient = HoodieTableMetaClient.initTableAndGetMetaClient(spark.sparkContext.hadoopConfiguration, path.toAbsolutePath.toString, props) + + val partitionAndFileId = new util.HashMap[String, String]() + partitionAndFileId.put(HoodieTestDataGenerator.DEFAULT_FIRST_PARTITION_PATH, "file-1") + + HoodieTestTable.of(metaClient).withPartitionMetaFiles(HoodieTestDataGenerator.DEFAULT_FIRST_PARTITION_PATH) + .addInflightCommit("001") + .withBaseFilesInPartitions(partitionAndFileId) + + val snapshotDF1 = spark.read.format("org.apache.hudi") + .load(path.toAbsolutePath.toString + "/*/*/*/*") + snapshotDF1.count() + assertFalse(true) + } catch { + case e: InvalidTableException => + assertTrue(e.getMessage.contains("Invalid Hoodie Table")) + } finally { + spark.stop() Review comment: @nsivabalan why are stopping the spark session here? is it not shared outside of a single test? -- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org