I am using Spark with scala, I am also using aws glue libraries as well for glue script. When i am using scala version 2.12 I am getting this error.
import com.amazonaws.services.glue.{DataSource, DynamicFrame, GlueContext}
import com.amazonaws.services.glue.util.{GlueArgParser, Job, JsonOptions}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.JavaConverters._
object Test {
def main(systemArgs: Array[String]): Unit = {
val conf = new SparkConf().setAppName("GlueExample").setMaster("local")
val sc = new SparkContext(conf)
sc.hadoopConfiguration.set("fs.s3.impl", "org.apache.hadoop.fs.s3a.S3AFileSystem")
val gc: GlueContext = new GlueContext(sc)
val connectionOptions = JsonOptions(Map(
"paths" -> Seq("s3://bucket_path"),
"groupFiles" -> "inPartition"
))
val source: DataSource = gc.getSourceWithFormat(
connectionType = "s3",
options = connectionOptions,
transformationContext = "",
format = "parquet",
formatOptions = JsonOptions.empty
)
}
}
when i changed the scala version to 2.11 after going through so many similar issues, i am getting this error. error with 2.11 version
it's not even starting SparkConf()
My build.gradle file.
plugins {
id 'scala'
id 'java'
id 'application'
}
repositories {
maven { url 'https://repo1.maven.org/maven2/' }
mavenCentral()
maven { url 'https://aws-glue-etl-artifacts.s3.amazonaws.com/release/' }
}
dependencies {
implementation project(':diff-lib')
implementation 'org.scala-lang:scala-library'
implementation 'com.google.guava:guava'
implementation 'software.amazon.awssdk:glue'
implementation 'com.amazonaws:AWSGlueETL:1.0.0'
implementation "org.apache.spark:spark-core_$scalaVersion"
implementation 'org.slf4j:slf4j-log4j12
}
geadle.properties file
gradleVersion=6.7
lombokVersion=1.18.10
awaitilityVersion=3.1.6
javaVersion=8
projectVersion=1.0.0
awsSdkVersion=2.16.44
junitVersion=5.7.1
log4jVersion=2.14.1
scalaVersion=2.12
scalaLibVersion=2.12.12
sparkVersion=2.4.3
glueEtlVersion=1.0.0
guavaLibVersion=29.0-jre
scalaTestVersion=3.2.0
scalaTestPlusVersion=3.2.0.0
scalaXmlVersion=1.2.0
slf4jLog4j12Version=1.7.10
build.gradle for diff-lib library
plugins {
id 'scala'
id 'java-library'
}
repositories {
maven { url 'https://repo1.maven.org/maven2/' }
mavenCentral()
maven { url 'https://aws-glue-etl-artifacts.s3.amazonaws.com/release/' }
}
dependencies {
implementation 'org.scala-lang:scala-library'
implementation 'com.amazonaws:AWSGlueETL'
implementation 'com.google.guava:guava'
}