aI am using Spark to write data to Hbase, I can read data just fine but write
is failing with following exception. I found simila issue that got resolved by
adding *site.xml and hbase JARs. But it is npot working for me.
JavaPairRDD<ImmutableBytesWritable, Put> tablePuts =
hBaseRDD.mapToPair(new PairFunction<Tuple2<ImmutableBytesWritable, Result>,
ImmutableBytesWritable, Put>() { @Override public
Tuple2<ImmutableBytesWritable, Put> call(Tuple2<ImmutableBytesWritable, Result>
results) throws Exception { byte[] accountId =
results._2().getValue(Bytes.toBytes(COLFAMILY), Bytes.toBytes("accountId"));
String rowKey = new
String(results._2().getRow());
String accountId2 =
(Bytes.toString(accountId)); String vbMedia2 =
Bytes.toString(vbmedia);
System.out.println("************ accountId " + accountId2);
//int prefix = getHash(rowKey);
String prefix = getMd5Hash(rowKey);
String newrowKey = prefix + rowKey;
System.out.println("************ newrowKey &&&&&&&&&&&&&&&" + newrowKey);
LOG.info("************ newrowKey &&&&&&&&&&&&&&&" +
newrowKey); // Add a single cell def:vbmedia
Put put = new Put( Bytes.toBytes(newrowKey) );
put.addColumn(Bytes.toBytes("def"), Bytes.toBytes("accountId"), accountId);
} }); Job newAPIJobConfiguration =
Job.getInstance(conf);
newAPIJobConfiguration.getConfiguration().set(TableOutputFormat.OUTPUT_TABLE,
OUT_TABLE_NAME);
newAPIJobConfiguration.setOutputFormatClass(org.apache.hadoop.hbase.mapreduce.TableOutputFormat.class);
newAPIJobConfiguration.setOutputKeyClass(org.apache.hadoop.hbase.io.ImmutableBytesWritable.class);
newAPIJobConfiguration.setOutputValueClass(org.apache.hadoop.io.Writable.class);
tablePuts.saveAsNewAPIHadoopDataset(newAPIJobConfiguration.getConfiguration());
Exception in thread "main" java.lang.NullPointerException at
org.apache.hadoop.hbase.security.UserProvider.instantiate(UserProvider.java:123)
at
org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:214)
at
org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:119)
at
org.apache.hadoop.hbase.mapreduce.TableOutputFormat.checkOutputSpecs(TableOutputFormat.java:177)
at
org.apache.spark.internal.io.HadoopMapReduceWriteConfigUtil.assertConf(SparkHadoopWriter.scala:387)
at
org.apache.spark.internal.io.SparkHadoopWriter$.write(SparkHadoopWriter.scala:71)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1083)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1081)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1081)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363) at
org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1081)
at
org.apache.spark.api.java.JavaPairRDD.saveAsNewAPIHadoopDataset(JavaPairRDD.scala:831)
at com.voicebase.etl.s3tohbase.HbaseScan2.main(HbaseScan2.java:148) at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:197) at
org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227) at
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136) at
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
