Github user zsxwing commented on a diff in the pull request: https://github.com/apache/spark/pull/15527#discussion_r85258039 --- Diff: external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaSourceSuite.scala --- @@ -133,6 +132,41 @@ class KafkaSourceSuite extends KafkaSourceTest { private val topicId = new AtomicInteger(0) + test("maxOffsetsPerTrigger") { + val topic = newTopic() + testUtils.createTopic(topic, partitions = 3) + testUtils.sendMessages(topic, (100 to 200).map(_.toString).toArray, Some(0)) + testUtils.sendMessages(topic, (10 to 20).map(_.toString).toArray, Some(1)) + testUtils.sendMessages(topic, Array("1"), Some(2)) + + val reader = spark + .readStream + .format("kafka") + .option("kafka.bootstrap.servers", testUtils.brokerAddress) + .option("kafka.metadata.max.age.ms", "1") + .option("maxOffsetsPerTrigger", 10) + .option("subscribe", topic) + .option("startingOffsets", "earliest") + val kafka = reader.load() + .selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)") + .as[(String, String)] + val mapped: org.apache.spark.sql.Dataset[_] = kafka.map(kv => kv._2.toInt) + + val clock = new StreamManualClock + testStream(mapped)( + StartStream(ProcessingTime(100), clock), + AdvanceManualClock(100), + // 1 from smallest, 1 from middle, 8 from biggest + CheckAnswer(1, 10, 100, 101, 102, 103, 104, 105, 106, 107), --- End diff -- FYI, #14553 got merged.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org