amaliujia commented on code in PR #40783: URL: https://github.com/apache/spark/pull/40783#discussion_r1169090129
########## connector/connect/client/jvm/src/main/java/org/apache/spark/sql/streaming/Trigger.java: ########## @@ -0,0 +1,180 @@ +/* + * 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.streaming; + +import java.util.concurrent.TimeUnit; + +import scala.concurrent.duration.Duration; + +import org.apache.spark.annotation.Evolving; +import org.apache.spark.sql.execution.streaming.AvailableNowTrigger$; +import org.apache.spark.sql.execution.streaming.ContinuousTrigger; +import org.apache.spark.sql.execution.streaming.OneTimeTrigger$; +import org.apache.spark.sql.execution.streaming.ProcessingTimeTrigger; + +/** + * Policy used to indicate how often results should be produced by a [[StreamingQuery]]. + * + * @since 3.5.0 + */ +@Evolving +public class Trigger { + // This is a copy of the same class in sql/core/.../streaming/Trigger.java + + /** + * A trigger policy that runs a query periodically based on an interval in processing time. + * If `interval` is 0, the query will run as fast as possible. + * + * @since 3.5.0 + */ + public static Trigger ProcessingTime(long intervalMs) { + return ProcessingTimeTrigger.create(intervalMs, TimeUnit.MILLISECONDS); + } + + /** + * (Java-friendly) + * A trigger policy that runs a query periodically based on an interval in processing time. + * If `interval` is 0, the query will run as fast as possible. + * + * {{{ + * import java.util.concurrent.TimeUnit + * df.writeStream().trigger(Trigger.ProcessingTime(10, TimeUnit.SECONDS)) + * }}} + * + * @since 3.5.0 + */ + public static Trigger ProcessingTime(long interval, TimeUnit timeUnit) { + return ProcessingTimeTrigger.create(interval, timeUnit); + } + + /** + * (Scala-friendly) + * A trigger policy that runs a query periodically based on an interval in processing time. + * If `duration` is 0, the query will run as fast as possible. + * + * {{{ + * import scala.concurrent.duration._ + * df.writeStream.trigger(Trigger.ProcessingTime(10.seconds)) + * }}} + * @since 3.5.0 + */ + public static Trigger ProcessingTime(Duration interval) { + return ProcessingTimeTrigger.apply(interval); + } + + /** + * A trigger policy that runs a query periodically based on an interval in processing time. + * If `interval` is effectively 0, the query will run as fast as possible. + * + * {{{ + * df.writeStream.trigger(Trigger.ProcessingTime("10 seconds")) + * }}} + * @since 3.5.0 + */ + public static Trigger ProcessingTime(String interval) { + return ProcessingTimeTrigger.apply(interval); + } + + /** + * A trigger that processes all available data in a single batch then terminates the query. + * + * @since 3.5.0 + * @deprecated This is deprecated as of Spark 3.4.0. Use {@link #AvailableNow()} to leverage + * better guarantee of processing, fine-grained scale of batches, and better gradual + * processing of watermark advancement including no-data batch. + * See the NOTES in {@link #AvailableNow()} for details. + */ + @Deprecated Review Comment: I guess if we want to drop such API, we drop cross the codebase. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
