This is the code ubuntu@ip-10-0-2-24:~$ spark-shell --packages com.hortonworks:shc-core:1.1.0-2.1 -s_2.11 --repositories http://repo.hortonworks.com/content/groups/public/ scala> import org.apache.spark.sql.{SQLContext, _} import org.apache.spark.sql.{SQLContext, _} scala> import org.apache.spark.sql.execution.datasources.hbase._ import org.apache.spark.sql.execution.datasources.hbase._ scala> import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.{SparkConf, SparkContext} scala> import spark.sqlContext.implicits._ import spark.sqlContext.implicits._ scala> def catalog = s"""{ | |"table":{"namespace":"default", "name":"Contacts"}, | |"rowkey":"key", | |"columns":{ | |"rowkey":{"cf":"rowkey", "col":"key", "type":"string"}, | |"officeAddress":{"cf":"Office", "col":"Address", "type":"string"}, | |"officePhone":{"cf":"Office", "col":"Phone", "type":"string"}, | |"personalName":{"cf":"Personal", "col":"Name", "type":"string"}, | |"personalPhone":{"cf":"Personal", "col":"Phone", "type":"string"} | |} | |}""".stripMargin catalog: String scala> def withCatalog(cat: String): DataFrame = { | spark.sqlContext | .read | .options(Map(HBaseTableCatalog.tableCatalog->cat)) | .format("org.apache.spark.sql.execution.datasources.hbase") | .load() | } withCatalog: (cat: String)org.apache.spark.sql.DataFrame scala> val df = withCatalog(catalog) df: org.apache.spark.sql.DataFrame = [rowkey: string, officeAddress: string ... 3 more fields] this is the error scala> df.show java.lang.RuntimeException: java.lang.NullPointerException at org.apache.hadoop.hbase.client.RpcRetryingCaller.callWithoutRetries(RpcRetryingCaller.java:208) at org.apache.hadoop.hbase.client.ClientScanner.call(ClientScanner.java:320) at org.apache.hadoop.hbase.client.ClientScanner.nextScanner(ClientScanner.java:295) at org.apache.hadoop.hbase.client.ClientScanner.initializeScannerInConstruction(ClientScanner.java:160) at org.apache.hadoop.hbase.client.ClientScanner.<init>(ClientScanner.java:155) at org.apache.hadoop.hbase.client.HTable.getScanner(HTable.java:821) at org.apache.hadoop.hbase.client.MetaScanner.metaScan(MetaScanner.java:193) at org.apache.hadoop.hbase.client.MetaScanner.metaScan(MetaScanner.java:89) at org.apache.hadoop.hbase.client.MetaScanner.listTableRegionLocations(MetaScanner.java:343) at org.apache.hadoop.hbase.client.HRegionLocator.listRegionLocations(HRegionLocator.java:142) at org.apache.hadoop.hbase.client.HRegionLocator.getStartEndKeys(HRegionLocator.java:118) at org.apache.spark.sql.execution.datasources.hbase.RegionResource$anonfun$1.apply(HBaseResources.scala:109) at org.apache.spark.sql.execution.datasources.hbase.RegionResource$anonfun$1.apply(HBaseResources.scala:108) at org.apache.spark.sql.execution.datasources.hbase.ReferencedResource$class.releaseOnException(HBaseResources.scala:77) at org.apache.spark.sql.execution.datasources.hbase.RegionResource.releaseOnException(HBaseResources.scala:88) at org.apache.spark.sql.execution.datasources.hbase.RegionResource.<init>(HBaseResources.scala:108) at org.apache.spark.sql.execution.datasources.hbase.HBaseTableScanRDD.getPartitions(HBaseTableScan.scala:61) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:252) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:250) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:250) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:252) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:250) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:250) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:252) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:250) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:250) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:252) at org.apache.spark.rdd.RDD$anonfun$partitions$2.apply(RDD.scala:250) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:250) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:314) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$collectFromPlan(Dataset.scala:2861) at org.apache.spark.sql.Dataset$anonfun$head$1.apply(Dataset.scala:2150) at org.apache.spark.sql.Dataset$anonfun$head$1.apply(Dataset.scala:2150) at org.apache.spark.sql.Dataset$anonfun$55.apply(Dataset.scala:2842) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2841) at org.apache.spark.sql.Dataset.head(Dataset.scala:2150) at org.apache.spark.sql.Dataset.take(Dataset.scala:2363) at org.apache.spark.sql.Dataset.showString(Dataset.scala:241) at org.apache.spark.sql.Dataset.show(Dataset.scala:637) at org.apache.spark.sql.Dataset.show(Dataset.scala:596) at org.apache.spark.sql.Dataset.show(Dataset.scala:605) ... 54 elided Caused by: java.lang.NullPointerException at org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher.getMetaReplicaNodes(ZooKeeperWatcher.java:395) at org.apache.hadoop.hbase.zookeeper.MetaTableLocator.blockUntilAvailable(MetaTableLocator.java:553) at org.apache.hadoop.hbase.client.ZooKeeperRegistry.getMetaRegionLocation(ZooKeeperRegistry.java:61) at org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation.locateMeta(ConnectionManager.java:1185) at org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation.locateRegion(ConnectionManager.java:1152) at org.apache.hadoop.hbase.client.RpcRetryingCallerWithReadReplicas.getRegionLocations(RpcRetryingCallerWithReadReplicas.java:300) at org.apache.hadoop.hbase.client.ScannerCallableWithReplicas.call(ScannerCallableWithReplicas.java:151) at org.apache.hadoop.hbase.client.ScannerCallableWithReplicas.call(ScannerCallableWithReplicas.java:59) at org.apache.hadoop.hbase.client.RpcRetryingCaller.callWithoutRetries(RpcRetryingCaller.java:200) ... 103 more ... View more