apache-spark - SparkHadoopWriter 在 UserProvider 出现 NPE 失败

Question

我正在使用 Spark 将数据写入 Hbase，我可以很好地读取数据，但写入失败并出现以下异常。我发现通过添加 *site.xml 和 hbase JAR 解决了类似的问题。但这对我不起作用。我正在尝试从一个表中读取数据，将数据写入另一个表。我可以很好地读取数据，但在写入时出现异常。

     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 prefix = getMd5Hash(rowKey);
                        String newrowKey = prefix + rowKey; 
                        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());

org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java 的 org.apache.hadoop.hbase.security.UserProvider.instantiate(UserProvider.java:123) 的线程“主”java.lang.NullPointerException 中的异常:214) org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:119) org.apache.hadoop.hbase.mapreduce.TableOutputFormat.checkOutputSpecs(TableOutputFormat.java:177) 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$$ anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1083) 在 org.apache.spark.rdd。PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1081) at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1081) at org.apache.spark.rdd。 RDDOperationScope$.withScope(RDDOperationScope.scala:151) 在 org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) 在 org.apache.spark.rdd.RDD.withScope(RDD.scala:363)在 org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1081) 在 org.apache.spark.api.java.JavaPairRDD.saveAsNewAPIHadoopDataset(JavaPairRDD.scala:831) 在 com.voicebase.etl.s3tohbase.HbaseScan2 .main(HbaseScan2.java:148) 在 sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) 在 sun.reflect.NativeMethodAccessorImpl。invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.spark.deploy.JavaMainApplication .start(SparkApplication.scala:52) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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$.main(SparkSubmit.scala:136 ) 在 org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)reflect.Method.invoke(Method.java:498) at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy $SparkSubmit$$runMain(SparkSubmit.scala:879) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:197) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala :227) 在 org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136) 在 org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)reflect.Method.invoke(Method.java:498) at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy $SparkSubmit$$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) 在 org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136) 在 org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)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)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)

标签： apache-sparkhbase