У меня следующий проект в IntelliJ, проблема в том, что Subscribe
внутри KafkaUtils.createDirectStream
выглядит красным, и он выдает Cannot resolve symbol Subscribe
, но я добавил все библиотеки kafka-spark:
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
def startMetaInfoSubscriber(ssc: StreamingContext, kafkaParams: Map[String, Object], metaInfoTopic: String) {
// Set a unique Kafka group identifier to metaInformationStream (each stream requires a unique group ID)
val metaInformationKafkaParamas = kafkaParams ++ Map[String, Object]("group.id" -> RandomStringUtils.randomAlphabetic(10).toUpperCase)
KafkaUtils.createDirectStream[String, String](
ssc,
PreferConsistent,
Subscribe[String, String](metaInfoTopic, metaInformationKafkaParamas)
).foreachRDD(metaInfoRDD =>
if (!metaInfoRDD.isEmpty()) {
println("Saving MetaInformation")
metaInfoRDD
// metaInfoRDD.write.mode("append").format("com.databricks.spark.csv").save(s"hdfs://172.16.8.162:8020/user/sparkload/assetgroup/prueba-kafka")
} else {
println("There is not any message for topic 'tu-topic'")
}
)
}
И следующий мой pom.xml:
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<scala.version>2.11.8</scala.version>
<spark.version>2.3.0</spark.version>
<src.dir>src/main/scala</src.dir>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core_2.11 -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming-kafka_2.11 -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
Когда я пытаюсь скомпилировать, у меня появляется следующая ошибка:
[ERROR] C:\Users\agomez\Desktop\spark-base\spark-kafka-tfm\src\main\scala\spark_load\EjemploApp.scala:90: error: overloaded method value Subscribe with alternatives:
[ERROR] (topics: java.util.Collection[String],kafkaParams: java.util.Map[String,Object])org.apache.spark.streaming.kafka010.ConsumerStrategy[String,String] <and>
[ERROR] (topics: java.util.Collection[String],kafkaParams: java.util.Map[String,Object],offsets: java.util.Map[org.apache.kafka.common.TopicPartition,java.lang.Long])org.apache.spark.streaming.kafka010.ConsumerStrategy[String,String] <and>
[ERROR] (topics: Iterable[String],kafkaParams: scala.collection.Map[String,Object])org.apache.spark.streaming.kafka010.ConsumerStrategy[String,String] <and>
[ERROR] (topics: Iterable[String],kafkaParams: scala.collection.Map[String,Object],offsets: scala.collection.Map[org.apache.kafka.common.TopicPartition,scala.Long])org.apache.spark.streaming.kafka010.ConsumerStrategy[String,String]
[ERROR] cannot be applied to (String, scala.collection.immutable.Map[String,Object])
[ERROR] Subscribe[String, String](metaInfoTopic, metaInformationKafkaParamas)
[ERROR] ^
[ERROR] one error found