/* * 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. */ /* * We have to use "com.databricks.spark.avro" because "SchemaConverters.toSqlType" * is only visible in the scope of the package. */ package com.databricks.spark.avro import org.apache.spark.sql.SparkSession import org.apache.spark.sql.functions.col object DebugConfluentSparkAvroUtils { def main(args: Array[String]): Unit = { val kafkaUrl = args(0) val schemaRegistryUrl = args(1) val topic = args(2) val spark = SparkSession.builder().master("local[2]").getOrCreate() val df = spark.read.format("kafka") .option("kafka.bootstrap.servers", kafkaUrl) .option("subscribe", topic) .load() val utils = new ConfluentSparkAvroUtils(schemaRegistryUrl) val keyDes = utils.deserializerForSubject(topic + "-key") val valDes = utils.deserializerForSubject(topic + "-value") df.select( keyDes(col("key")).alias("key"), valDes(col("value")).alias("value") ).show(10) spark.stop() } }