tmljob commented on code in PR #1695: URL: https://github.com/apache/incubator-seatunnel/pull/1695#discussion_r850549257
########## seatunnel-connectors/seatunnel-connectors-spark/seatunnel-connector-spark-webhook/src/main/scala/org/apache/seatunnel/spark/webhook/source/Webhook.scala: ########## @@ -0,0 +1,50 @@ +/* + * 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.seatunnel.spark.webhook.source + +import org.apache.seatunnel.spark.SparkEnvironment +import org.apache.seatunnel.spark.stream.SparkStreamingSource +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{Dataset, Row, SparkSession, SQLContext} +import org.apache.spark.streaming.dstream.DStream + +class Webhook extends SparkStreamingSource[String] { + + override def start(env: SparkEnvironment, handler: Dataset[Row] => Unit): Unit = { + var spark = env.getSparkSession + // Create HTTP Server and start streaming + implicit val sqlContext: SQLContext = spark.sqlContext + + var port = if (config.hasPath("port")) config.getInt("port") else 9999 + var baseUrl = if (config.hasPath("path")) config.getString("path") else "/" + + val query = new JettyServerStream(port, baseUrl) + .toDF + .writeStream + .foreachBatch((batch, batchId) => { + handler(batch) + }) + .start() + + query.awaitTermination() + } + + override def rdd2dataset(sparkSession: SparkSession, rdd: RDD[String]): Dataset[Row] = { null } + + override def getData(env: SparkEnvironment): DStream[String] = { null } Review Comment: I rewrote the start method, and getData and rdd2dataset are used in the start method, so there is no need to implement these two methods here. -- 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]
