chaoqin-li1123 commented on code in PR #46651: URL: https://github.com/apache/spark/pull/46651#discussion_r1606249907
########## sql/core/src/test/scala/org/apache/spark/sql/execution/python/PythonStreamingDataSourceSuite.scala: ########## @@ -763,6 +799,36 @@ class PythonStreamingDataSourceSuite extends PythonDataSourceSuiteBase { } } + // Verify that commit runner work correctly with large timeout interval. + test(s"data source stream write, trigger interval=20 seconds") { + assume(shouldTestPandasUDFs) + val dataSource = + createUserDefinedPythonDataSource(dataSourceName, simpleDataStreamWriterScript) + spark.dataSource.registerPython(dataSourceName, dataSource) + val inputData = MemoryStream[Int](numPartitions = 3) + val df = inputData.toDF() + withTempDir { dir => + val path = dir.getAbsolutePath + val checkpointDir = new File(path, "checkpoint") + checkpointDir.mkdir() + val outputDir = new File(path, "output") + outputDir.mkdir() + val q = df + .writeStream + .format(dataSourceName) + .option("checkpointLocation", checkpointDir.getAbsolutePath) + .trigger(ProcessingTimeTrigger(20 * 1000)) + .start(outputDir.getAbsolutePath) + eventually(timeout(waitTimeout * 5)) { + inputData.addData(1 to 3) + assert(q.lastProgress.batchId >= 2) Review Comment: Change applied. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org