Hi All,
I need to execute Pig script using java client which will read data from Cassandra Column Family but when I am executing the script getting below error. I am using DataStax 3.1.3
Help to resolve the issue is highly appreciated.
ERROR:
Exception in thread "main" org.apache.pig.impl.logicalLayer.FrontendException: ERROR 1066: Unable to open iterator for alias RAW_DATA
at org.apache.pig.PigServer.openIterator(PigServer.java:901)
at com.pig.client.PigClient.main(PigClient.java:28)
Caused by: java.lang.RuntimeException: java.lang.NullPointerException
at org.apache.cassandra.hadoop.pig.AbstractCassandraStorage.initSchema(AbstractCassandraStorage.java:481)
at org.apache.cassandra.hadoop.pig.CassandraStorage.setLocation(CassandraStorage.java:323)
at org.apache.cassandra.hadoop.pig.CassandraStorage.getSchema(CassandraStorage.java:362)
at org.apache.pig.newplan.logical.relational.LOLoad.getSchemaFromMetaData(LOLoad.java:150)
at org.apache.pig.newplan.logical.relational.LOLoad.getSchema(LOLoad.java:109)
at org.apache.pig.newplan.logical.relational.LOStore.getSchema(LOStore.java:68)
at org.apache.pig.newplan.logical.visitor.SchemaAliasVisitor.validate(SchemaAliasVisitor.java:60)
at org.apache.pig.newplan.logical.visitor.SchemaAliasVisitor.visit(SchemaAliasVisitor.java:84)
at org.apache.pig.newplan.logical.relational.LOStore.accept(LOStore.java:77)
at org.apache.pig.newplan.DependencyOrderWalker.walk(DependencyOrderWalker.java:75)
at org.apache.pig.newplan.PlanVisitor.visit(PlanVisitor.java:50)
at org.apache.pig.PigServer$Graph.compile(PigServer.java:1661)
at org.apache.pig.PigServer$Graph.compile(PigServer.java:1655)
at org.apache.pig.PigServer$Graph.access$200(PigServer.java:1378)
at org.apache.pig.PigServer.storeEx(PigServer.java:995)
at org.apache.pig.PigServer.store(PigServer.java:963)
at org.apache.pig.PigServer.openIterator(PigServer.java:876)
... 1 more
Caused by: java.lang.NullPointerException
at org.apache.cassandra.utils.ByteBufferUtil.string(ByteBufferUtil.java:167)
at org.apache.cassandra.utils.ByteBufferUtil.string(ByteBufferUtil.java:124)
at org.apache.cassandra.hadoop.pig.AbstractCassandraStorage.getCfDef(AbstractCassandraStorage.java:589)
at org.apache.cassandra.hadoop.pig.AbstractCassandraStorage.initSchema(AbstractCassandraStorage.java:470)
... 17 more
Java Client code:
import java.util.Iterator;
import java.util.Properties;
import org.apache.pig.ExecType;
import org.apache.pig.PigServer;
import org.apache.pig.data.Tuple;
import org.apache.pig.impl.PigContext;
public class PigClient {
public static void main(String[] args) throws Exception {
System.out.println("Started.................");
Properties props = new Properties();
props.put("cassandra.input.thrift.address", "localhost");
props.put("cassandra.input.partitioner.class", "org.apache.cassandra.dht.Murmur3Partitioner");
props.put("cassandra.output.partitioner.class", "org.apache.cassandra.dht.Murmur3Partitioner");
PigContext context = new PigContext(ExecType.MAPREDUCE, props);
PigServer pig = new PigServer(context);
String script = "RAW_DATA = LOAD 'cassandra://<Keyspace>/<Column Family>' USING org.apache.cassandra.hadoop.pig.CassandraStorage() AS (key, columns: bag {T: tuple (col, val)});";
pig.registerQuery(script);
Iterator<Tuple> itr = pig.openIterator("RAW_DATA");
while (itr.hasNext()) {
Tuple t = itr.next();
System.out.println(t);
}
System.out.println("Done...........");
}
}
Class Path includes below jars from datastax 3.1.3.
dse-3.1.3.jar
pig-0.9.2.jar
xmlenc-0.52.jar
commons-logging-1.0.4.jar
commons-net-1.4.1.jar
core-3.1.1.jar
guava-r06.jar
hsqldb-1.8.0.10.jar
jackson-core-asl-1.4.2.jar
commons-lang-2.5.jar
commons-httpclient-3.1.jar
commons-el-1.0.jar
antlr-runtime-3.2.jar
asm-3.2.jar
avro-1.3.2.jar
commons-cli-1.2.jar
commons-codec-1.4.jar
jackson-mapper-asl-1.4.2.jar
jasper-compiler-5.5.12.jar
paranamer-generator-2.2.jar
pig-0.9.2.jar
qdox-1.10.1.jar
servlet-api-2.5-6.1.14.jar
snappy-java-1.0.5.jar
stringtemplate-3.2.jar
paranamer-ant-2.2.jar
paranamer-2.2.jar
oro-2.0.8.jar
jasper-runtime-5.5.12.jar
jets3t-0.7.1.jar
jline-0.9.94.jar
jsp-2.1-6.1.14.jar
jsp-api-2.1-6.1.14.jar
kfs-0.3.jar
ant-1.6.5.jar
commons-logging-1.1.1.jar
compress-lzf-0.8.4.jar
concurrentlinkedhashmap-lru-1.3.jar
cql-internal-only-1.4.0.zip
guava-13.0.1.jar
high-scale-lib-1.1.2.jar
httpclient-4.0.1.jar
commons-lang-2.6.jar
commons-codec-1.6.jar
antlr-3.2.jar
avro-1.4.0-cassandra-1.jar
cassandra-all-1.2.6.6.jar
cassandra-clientutil-1.2.6.6.jar
cassandra-thrift-1.2.6.6.jar
commons-cli-1.1.jar
httpcore-4.0.1.jar
jackson-core-asl-1.9.2.jar
jackson-mapper-asl-1.9.2.jar
netty-3.5.9.Final.jar
servlet-api-2.5.jar
slf4j-api-1.7.2.jar
snakeyaml-1.6.jar
snappy-java-1.0.5.jar
snaptree-0.1.jar
stringtemplate-3.2.jar
metrics-core-2.0.3.jar
lz4-1.1.0.jar
jamm-0.2.5.jar
jbcrypt-0.3m.jar
jline-1.0.jar
joda-time-1.6.2.jar
json-simple-1.1.jar
libthrift-0.7.0.jar
log4j-1.2.16.jar
antlr-2.7.7.jar
hadoop-tools-1.0.4.8.jar
hadoop-test-1.0.4.8.jar
hadoop-streaming-1.0.4.8.jar
hadoop-fairscheduler-1.0.4.8.jar
hadoop-examples-1.0.4.8.jar
hadoop-core-1.0.4.8.jar
commons-configuration-1.6.jar