Hi Dear
Plateform: Ubuntu
Hadoop & Hbase From CDH3
Tool: NetBeans 6.0.9
I am trying to write Hbase Batch Import Insertion Method, I am new in Hbase
& Hadoop.
Can any one tell me example, Or can give info link.
I have tried this one, Please see it and indicate any error, I will be thank
full to you,
import org.apache.hadoop.hbase.HBaseConfiguration;
> import org.apache.hadoop.hbase.client.HTable;
> import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat;
> import org.apache.hadoop.mapreduce.Mapper.Context;
>
> import java.io.IOException;
> import java.util.*;
>
> import org.apache.hadoop.fs.Path;
> import org.apache.hadoop.conf.*;
> import org.apache.hadoop.hbase.KeyValue;
> import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
> import org.apache.hadoop.hbase.util.Bytes;
> import org.apache.hadoop.io.*;
> import org.apache.hadoop.mapreduce.*;
> import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
> import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
> import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
> import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
>
> public class NewMain {
>
> //public static class Map extends Mapper<LongWritable, Text, Text,
> IntWritable> {
>
> public static class Map extends Mapper {
>
> public void map(LongWritable key, Text value, Context context) throws
> IOException, InterruptedException {
>
>
> String line = value.toString();
> StringTokenizer tokenizer = new StringTokenizer(line);
> while (tokenizer.hasMoreTokens()) {
> //word.set(tokenizer.nextToken());
> System.out.println(tokenizer.nextToken());
> ImmutableBytesWritable r = new
> ImmutableBytesWritable(Bytes.toBytes(tokenizer.nextToken()));
> KeyValue kv = new
> KeyValue(Bytes.toBytes(tokenizer.nextToken()),Bytes.toBytes(tokenizer.nextToken()),
> Bytes.toBytes(tokenizer.nextToken()), Bytes.toBytes(tokenizer.nextToken()));
> context.write(r,kv);
> }
> }
> }
>
> public static class KeyValueSortReducer extends Reducer{
>
> protected void reduce(ImmutableBytesWritable row,
> java.lang.Iterable<IntWritable> kvs,Reducer.Context context)
> throws java.io.IOException, InterruptedException {
> // for each key value k, context.write(row, k);
> int sum = 0;
> for (IntWritable val : kvs) {
> sum += val.get();
> }
> context.write( row, new IntWritable(sum));
> }
>
> }
>
>
>
> public static void main(String[] args) throws Exception {
>
> Configuration config = new Configuration();
> Job job = new Job(config);
> job.setJobName("Member Claims Schema type 2 Load Job Optimisation 1");
>
> Configuration conf = HBaseConfiguration.create();
> Job jobh = new Job(conf, "Hbase");
> HTable htable = new HTable(conf, "MemberDemographicsClaim");
> //htable.setAutoFlush(false);
> //job.setJarByClass(MemberClaimsBulkLoader.class);
> job.setMapperClass(Map.class);
> job.setMapOutputKeyClass(ImmutableBytesWritable.class);
> job.setMapOutputValueClass(KeyValue.class);
>
> job.setInputFormatClass(TextInputFormat.class);
> //job.setOutputFormatClass(TextOutputFormat.class);
>
> HFileOutputFormat.configureIncrementalLoad(job, htable); // table where
> data to be imported which must exist in HBase and need to be passed as
> parameter here
> Path p1 = new Path("/root/NetBeansProjects/ILHbase/InputFiles");
> Path p2 = new Path("/root/NetBeansProjects/ILHbase/OutputFiles");
>
> FileInputFormat.addInputPath( job, p1);
> //FileInputFormat.setInputPaths(job, new Path(args[1]));
> FileOutputFormat.setOutputPath(job, p2);
> job.waitForCompletion(true);
> }
>
> }
>
My input file look like this one
RowId Column Family Column Value
> 1 demographics name N
> 2 demographics address MMM
> 3 claim c1 A
> 4 claim c2 B
>
Errors that i am getting with this code
- java.lang.IllegalArgumentException: Can't read partitions file
- Caused by: java.io.FileNotFoundException: File _partition.lst does not
exist.
