bozhang2820 commented on a change in pull request #33763: URL: https://github.com/apache/spark/pull/33763#discussion_r698897236
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/AvailableNowDataStreamWrapper.scala ########## @@ -0,0 +1,88 @@ +/* + * 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.execution.streaming + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.connector.read.streaming.{MicroBatchStream, ReadLimit, SparkDataStream, SupportsAdmissionControl, SupportsTriggerAvailableNow} +import org.apache.spark.sql.connector.read.streaming + +/** + * This class wraps a [[SparkDataStream]] and makes it support Trigger.AvailableNow, by overriding + * its [[latestOffset]] method to always return the latest offset at the beginning of the query. + */ +class AvailableNowDataStreamWrapper(val delegate: SparkDataStream) + extends SparkDataStream with SupportsTriggerAvailableNow with Logging { + + private var fetchedOffset: streaming.Offset = _ + + override def initialOffset(): streaming.Offset = delegate.initialOffset() + + override def deserializeOffset(json: String): streaming.Offset = delegate.deserializeOffset(json) + + override def commit(end: streaming.Offset): Unit = delegate.commit(end) + + override def stop(): Unit = delegate.stop() + + private def getInitialOffset: streaming.Offset = { + delegate match { + case _: Source => null + case m: MicroBatchStream => m.initialOffset + } + } Review comment: We can use null (for v1 sources) and iniitalOffset (for v2 streams) for the startOffset in latestOffset(startOffset, readLimit), since the readLimit is always allAvailable. ########## File path: sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala ########## @@ -1304,6 +1304,140 @@ class FileStreamSourceSuite extends FileStreamSourceTest { } } + test("SPARK-36533: Trigger.AvailableNow") { + withTempDirs { (src, target) => + val checkpoint = new File(target, "chk").getCanonicalPath + val targetDir = new File(target, "data").getCanonicalPath + var lastFileModTime: Option[Long] = None + + /** Create a text file with a single data item */ + def createFile(data: Int): File = { + val file = stringToFile(new File(src, s"$data.txt"), data.toString) + if (lastFileModTime.nonEmpty) file.setLastModified(lastFileModTime.get + 1000) + lastFileModTime = Some(file.lastModified) + file + } + + createFile(1) + createFile(2) + createFile(3) + + // Set up a query to read text files one at a time + val df = spark + .readStream + .option("maxFilesPerTrigger", 1) + .text(src.getCanonicalPath) + + def startQuery(): StreamingQuery = { + df.writeStream + .format("parquet") + .trigger(Trigger.AvailableNow) + .option("checkpointLocation", checkpoint) + .start(targetDir) + } + val q = startQuery() + + try { Review comment: I find it a bit hard to control the order between starting the query and adding new files into the source. Do you know if there is an easy way to do so? -- 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]
