我正在尝试从Spark2查询存储在Hive表中的数据。环境:1.cloudera-quickstart-vm-5.7.0-0-vmware 2.带有Scala2.11.8插件的Eclipse 3. Spark2和Maven
我没有更改spark默认配置。我是否需要在Spark或Hive中配置任何内容?
代码
import org.apache.spark._
import org.apache.spark.sql.SparkSession
object hiveTest {
def main (args: Array[String]){
val sparkSession = SparkSession.builder.
master("local")
.appName("HiveSQL")
.enableHiveSupport()
.getOrCreate()
val data= sparkSession2.sql("select * from test.mark")
}
}
获取错误
16/08/29 00:18:10 INFO SparkSqlParser: Parsing command: select * from test.mark
Exception in thread "main" java.lang.ExceptionInInitializerError
at org.apache.spark.sql.hive.HiveSharedState.metadataHive$lzycompute(HiveSharedState.scala:48)
at org.apache.spark.sql.hive.HiveSharedState.metadataHive(HiveSharedState.scala:47)
at org.apache.spark.sql.hive.HiveSharedState.externalCatalog$lzycompute(HiveSharedState.scala:54)
at org.apache.spark.sql.hive.HiveSharedState.externalCatalog(HiveSharedState.scala:54)
at org.apache.spark.sql.hive.HiveSessionState.catalog$lzycompute(HiveSessionState.scala:50)
at org.apache.spark.sql.hive.HiveSessionState.catalog(HiveSessionState.scala:48)
at org.apache.spark.sql.hive.HiveSessionState$$anon$1.<init>(HiveSessionState.scala:63)
at org.apache.spark.sql.hive.HiveSessionState.analyzer$lzycompute(HiveSessionState.scala:63)
at org.apache.spark.sql.hive.HiveSessionState.analyzer(HiveSessionState.scala:62)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:582)
at hiveTest$.main(hiveTest.scala:34)
at hiveTest.main(hiveTest.scala)
Caused by: java.lang.IllegalArgumentException: requirement failed: Duplicate SQLConfigEntry. spark.sql.hive.convertCTAS has been registered
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.sql.internal.SQLConf$.org$apache$spark$sql$internal$SQLConf$$register(SQLConf.scala:44)
at org.apache.spark.sql.internal.SQLConf$SQLConfigBuilder$$anonfun$apply$1.apply(SQLConf.scala:51)
at org.apache.spark.sql.internal.SQLConf$SQLConfigBuilder$$anonfun$apply$1.apply(SQLConf.scala:51)
at org.apache.spark.internal.config.TypedConfigBuilder$$anonfun$createWithDefault$1.apply(ConfigBuilder.scala:122)
at org.apache.spark.internal.config.TypedConfigBuilder$$anonfun$createWithDefault$1.apply(ConfigBuilder.scala:122)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.internal.config.TypedConfigBuilder.createWithDefault(ConfigBuilder.scala:122)
at org.apache.spark.sql.hive.HiveUtils$.<init>(HiveUtils.scala:103)
at org.apache.spark.sql.hive.HiveUtils$.<clinit>(HiveUtils.scala)
... 14 more
感谢任何建议
感谢
罗宾
答案 0 :(得分:0)
这就是我正在使用的:
import org.apache.spark.sql.SparkSession
object LoadCortexDataLake extends App {
val spark = SparkSession.builder().appName("Cortex-Batch").enableHiveSupport().getOrCreate()
spark.read.parquet(file).createOrReplaceTempView("temp")
spark.sql(s"insert overwrite table $table_nm partition(year='$yr',month='$mth',day='$dt') select * from temp")
我认为你应该使用&#39; sparkSession.sql&#39;而不是&#39; sparkSession2.sql&#39;
答案 1 :(得分:0)
public static IApplicationBuilder UseCorrelationProperties(this IApplicationBuilder app)
{
return app.Use(async (context, next) =>
{
var requestTelemetry = context.Features.Get<RequestTelemetry>();
if (requestTelemetry != null)
{
requestTelemetry.Context.Properties["CorrelationId"] = correlationId;
}
await next.Invoke();
});
}