Duplicate "values" for some key in map-reduce java program - java

I am new in mapreduce and hadoop (hadoop 3.2.3 and java 8).
I am trying to separate some lines based on a symbol in a line.
Example: "q1,a,q0," should be return ('a',"q1,a,q0,") as (key, value).
My dataset contains ten(10) lines , five(5) for key 'a' and five for key 'b'.
I expect to get 5 line for each key but i always get five for 'a' and 10 for 'b'
Data
A,q0,a,q1;A,q0,b,q0;A,q1,a,q1;A,q1,b,q2;A,q2,a,q1;A,q2,b,q0;B,s0,a,s0;B,s0,b,s1;B,s1,a,s1;B,s1,b,s0
Mapper class:
import java.io.IOException;
import org.apache.hadoop.io.ByteWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class MyMapper extends Mapper<LongWritable, Text, ByteWritable ,Text>{
private ByteWritable key1 = new ByteWritable();
//private int n ;
private int count =0 ;
private Text wordObject = new Text();
#Override
public void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {
String ftext = value.toString();
for (String line: ftext.split(";")) {
wordObject = new Text();
if (line.split(",")[2].equals("b")) {
key1.set((byte) 'b');
wordObject.set(line) ;
context.write(key1,wordObject);
continue ;
}
key1.set((byte) 'a');
wordObject.set(line) ;
context.write(key1,wordObject);
}
}
}
Reducer class:
import java.io.IOException;
import org.apache.hadoop.io.ByteWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Reducer.Context;
public class MyReducer extends Reducer<ByteWritable, Text, ByteWritable ,Text>{
private Integer count=0 ;
#Override
public void reduce(ByteWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
for(Text val : values ) {
count++ ;
}
Text symb = new Text(count.toString()) ;
context.write(key , symb);
}
}
Driver class:
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.ByteWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class MyDriver extends Configured implements Tool {
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.out.printf("Usage: %s [generic options] <inputdir> <outputdir>\n", getClass().getSimpleName());
return -1;
}
#SuppressWarnings("deprecation")
Job job = new Job(getConf());
job.setJarByClass(MyDriver.class);
job.setJobName("separation ");
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setMapOutputKeyClass(ByteWritable.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(ByteWritable.class);
job.setOutputValueClass(Text.class);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
public static void main(String[] args) throws Exception {
int exitCode = ToolRunner.run(new Configuration(), new MyDriver(), args);
System.exit(exitCode);
}
}

The problem was solved by putting the variable "count" inside the function "Reduce()".

Does your input read more than one line that has 5 more b's? I cannot reproduce for that one line, but your code can be cleaned up.
For the following code, I get output as
a 5
b 5
static class Mapper extends org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, ByteWritable, Text> {
final ByteWritable keyOut = new ByteWritable();
final Text valueOut = new Text();
#Override
protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, ByteWritable, Text>.Context context) throws IOException, InterruptedException {
String line = value.toString();
if (line.isEmpty()) {
return;
}
StringTokenizer tokenizer = new StringTokenizer(line, ";");
while (tokenizer.hasMoreTokens()) {
String token = tokenizer.nextToken();
String[] parts = token.split(",");
String keyStr = parts[2];
if (keyStr.matches("[ab]")) {
keyOut.set((byte) keyStr.charAt(0));
valueOut.set(token);
context.write(keyOut, valueOut);
}
}
}
}
static class Reducer extends org.apache.hadoop.mapreduce.Reducer<ByteWritable, Text, Text, LongWritable> {
static final Text keyOut = new Text();
static final LongWritable valueOut = new LongWritable();
#Override
protected void reduce(ByteWritable key, Iterable<Text> values, org.apache.hadoop.mapreduce.Reducer<ByteWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
keyOut.set(new String(new byte[]{key.get()}, StandardCharsets.UTF_8));
valueOut.set(StreamSupport.stream(values.spliterator(), true)
.mapToLong(v -> 1).sum());
context.write(keyOut, valueOut);
}
}

Related

Map reduce example beside word count

I followed step by step via example in here : https://www.tutorialspoint.com/hadoop/hadoop_mapreduce.htm
I want to find max of each year in file like the following:
1320 23
1221 60
1320 33
1221 66
And the result that I expected is:
1320 33
1221 66
And I did like the following in java:
import java.util.*;
import java.io.IOException;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
public class ProcessUnits {
//Mapper class
public static class E_EMapper extends MapReduceBase implements
Mapper<LongWritable ,/*Input key Type */
Text, /*Input value Type*/
Text, /*Output key Type*/
IntWritable> /*Output value Type*/
{
//Map function
public void map(LongWritable key, Text value,
OutputCollector<Text, IntWritable> output,
Reporter reporter) throws IOException {
String line = value.toString();
String lasttoken = null;
StringTokenizer s = new StringTokenizer(line," ");
String year = s.nextToken();
while(s.hasMoreTokens()) {
lasttoken = s.nextToken();
}
int avgprice = Integer.parseInt(lasttoken);
output.collect(new Text(year), new IntWritable(avgprice));
}
}
//Reducer class
public static class E_EReduce extends MapReduceBase implements Reducer< Text, IntWritable, Text, IntWritable > {
//Reduce function
public void reduce( Text key, Iterator <IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
int maxavg = 0 ;
int val = Integer.MIN_VALUE;
while (values.hasNext()) {
val = values.next().get();
if(val > maxavg) {
maxavg = val ;
}
}
output.collect(key, new IntWritable(maxavg));
}
}
//Main function
public static void main(String args[])throws Exception {
JobConf conf = new JobConf(ProcessUnits.class);
conf.setJobName("max_eletricityunits");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(E_EMapper.class);
conf.setCombinerClass(E_EReduce.class);
conf.setReducerClass(E_EReduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
}
The error I got when I execute this program is the following:
Error: java.util.NoSuchElementException
at java.util.StringTokenizer.nextToken(StringTokenizer.java:349)
at ProcessUnits$E_EMapper.map(ProcessUnits.java:28)
at ProcessUnits$E_EMapper.map(ProcessUnits.java:14)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:54)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:465)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:178)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1845)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:172)
I know this problem is because my program can't maps line by line of file , it maps entire file
String line = value.toString();
String lasttoken = null;
StringTokenizer s = new StringTokenizer(line," ");
String year = s.nextToken();
while(s.hasMoreTokens()) {
lasttoken = s.nextToken();
}
int avgprice = Integer.parseInt(lasttoken);
output.collect(new Text(year), new IntWritable(avgprice));
Any idea to solve this problem from you guys?
Try reading each line from file once and split the values. Map all the corresponding years and prices. Then using reduce function compare the price with some constant if greater assign the value.
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class E_Mapper extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable ikey, Text ivalue, Context context)
throws IOException, InterruptedException {
String line= ivalue.toString();
String [] values = line.splitBy(" ");
for(String price:values)
{
context.write(new Text(year),price);
}}}
public class E_Reducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int avg=0;
for (IntWritable val : values) {
if(val.get()>avg){
context.write(key,new IntWritable(sum));
}}}

Map Reduce program creates an empty directory on execution

I am running the below Map reduce code to calculate sum and average length of words starting with each english alphabet.
For example : If the doc only contains the word 'and' 5 times
letter | total words | average length
a 5 3
The mapreduce program is as below:
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class LetterWiseAvgLengthV1
{
public static class TokenizerMapper
extends Mapper<LongWritable, Text, Text, Text>
{
public void map(LongWritable key, Text value, Context context
) throws IOException, InterruptedException
{
String st [] = value.toString().split("\\s+");
for(String word : st) {
String wordnew=word.replaceAll("[^a-zA-Z]","");
String firstLetter = wordnew.substring(0, 1);
if(!wordnew.isEmpty()){
// write ('a',3) if the word is and
context.write(new Text(firstLetter), new Text(String.valueOf(wordnew.length())));
}
else continue;
}
}
}
public static class IntSumReducer
extends Reducer<Text,Text,Text,Text>
{
public void reduce(Text key, Iterable<Text> values,
Context context
) throws IOException, InterruptedException
{
int sum=0,count=0;
for (Text val : values)
{
sum += Integer.parseInt(val.toString());
count+= 1;
}
float avg=(sum/(float)count);
String op="Average length of " + count + " words = " + avg;
context.write(new Text(key), new Text(op));
}
}
public static void main(String[] args) throws Exception
{
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "wordLenAvgCombiner");
job.setJarByClass(LetterWiseAvgLengthV1.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(IntSumReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
When I execute the program below on a text document, it creates an empty output directory in HDFS. There are no failures during execution, but the output folder is always empty

Output file contains Mapper Output instead of Reducer output

Hi I am trying to find average of few numbers using map reduce technique in stand alone mode. I have two input files.It contain values file1: 25 25 25 25 25 and file2: 15 15 15 15 15.
My program is working fine but the output file contains output of the mapper instead of reducer output.
Here is my code :
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.io.Writable;
import java.io.*;
public class Average {
public static class SumCount implements Writable {
public int sum;
public int count;
#Override
public void write(DataOutput out) throws IOException {
out.writeInt(sum);
out.writeInt(count);
}
#Override
public void readFields(DataInput in) throws IOException {
sum = in.readInt();
count =in.readInt();
}
}
public static class TokenizerMapper extends Mapper<Object, Text, Text, Object>{
private final static IntWritable valueofkey = new IntWritable();
private Text word = new Text();
SumCount sc=new SumCount();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
int sum=0;
int count=0;
int v;
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
v=Integer.parseInt(word.toString());
count=count+1;
sum=sum+v;
}
word.set("average");
sc.sum=sum;
sc.count=count;
context.write(word,sc);
}
}
public static class IntSumReducer extends Reducer<Text,Object,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<SumCount> values,Context context) throws IOException, InterruptedException {
int sum = 0;
int count=0;
int wholesum=0;
int wholecount=0;
for (SumCount val : values) {
wholesum=wholesum+val.sum;
wholecount=wholecount+val.count;
}
int res=wholesum/wholecount;
result.set(res);
context.write(key, result );
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "");
job.setJarByClass(Average.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(SumCount.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
after i run the program my output file is like this:
average Average$SumCount#434ba039
average Average$SumCount#434ba039
You can't use your Reducer class IntSumReducer as a combiner. A combiner must receive and emit the same Key/Value types.
So i would remove job.setCombinerClass(IntSumReducer.class);.
Remember the output from the combine is the input to the reduce, so writing out Text and IntWritable isnt going to work.
If your output files looked like part-m-xxxxx then the above issue could mean it only ran the Map phase and stoppped. Your counters would confirm this.
You also have Reducer<Text,Object,Text,IntWritable> which should be Reducer<Text,SumCount,Text,IntWritable>.

FileAlreadyExistsException while running MapReduce code

This program is supposed to accomplish the MapReduce job. The output of the first job has to be taken as the input of the second job.
When I run it, I get two errors:
Exception in thread "main" org.apache.hadoop.mapred.FileAlreadyExistsException
The mapping part is running 100% but the reducer is not running.
Here's my code:
import java.io.IOException;
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;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.LongWritable;
public class MaxPubYear {
public static class FrequencyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
Text word = new Text();
String delim = ";";
Integer year = 0;
String tokens[] = value.toString().split(delim);
if (tokens.length >= 4) {
year = TryParseInt(tokens[3].replace("\"", "").trim());
if (year > 0) {
word = new Text(year.toString());
context.write(word, new IntWritable(1));
}
}
}
}
public static class FrequencyReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
context.write(key, new IntWritable(sum));
}
}
public static class MaxPubYearMapper extends
Mapper<LongWritable, Text, IntWritable, Text> {
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String delim = "\t";
Text valtosend = new Text();
String tokens[] = value.toString().split(delim);
if (tokens.length == 2) {
valtosend.set(tokens[0] + ";" + tokens[1]);
context.write(new IntWritable(1), valtosend);
}
}
}
public static class MaxPubYearReducer extends
Reducer<IntWritable, Text, Text, IntWritable> {
public void reduce(IntWritable key, Iterable<Text> values,
Context context) throws IOException, InterruptedException {
int maxiValue = Integer.MIN_VALUE;
String maxiYear = "";
for (Text value : values) {
String token[] = value.toString().split(";");
if (token.length == 2
&& TryParseInt(token[1]).intValue() > maxiValue) {
maxiValue = TryParseInt(token[1]);
maxiYear = token[0];
}
}
context.write(new Text(maxiYear), new IntWritable(maxiValue));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "Frequency");
job.setJarByClass(MaxPubYear.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(FrequencyMapper.class);
job.setCombinerClass(FrequencyReducer.class);
job.setReducerClass(FrequencyReducer.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1] + "_temp"));
int exitCode = job.waitForCompletion(true) ? 0 : 1;
if (exitCode == 0) {
Job SecondJob = new Job(conf, "Maximum Publication year");
SecondJob.setJarByClass(MaxPubYear.class);
SecondJob.setOutputKeyClass(Text.class);
SecondJob.setOutputValueClass(IntWritable.class);
SecondJob.setMapOutputKeyClass(IntWritable.class);
SecondJob.setMapOutputValueClass(Text.class);
SecondJob.setMapperClass(MaxPubYearMapper.class);
SecondJob.setReducerClass(MaxPubYearReducer.class);
FileInputFormat.addInputPath(SecondJob, new Path(args[1] + "_temp"));
FileOutputFormat.setOutputPath(SecondJob, new Path(args[1]));
System.exit(SecondJob.waitForCompletion(true) ? 0 : 1);
}
}
public static Integer TryParseInt(String trim) {
// TODO Auto-generated method stub
return(0);
}
}
Exception in thread "main"
org.apache.hadoop.mapred.FileAlreadyExistsException
Map-reduce job does not overwrite the contents in a existing directory. Output path to MR job must be a directory path which does not exist. MR job will create a directory at specified path with files within it.
In your code:
FileOutputFormat.setOutputPath(job, new Path(args[1] + "_temp"));
Make sure this path does not exist when you run MR job.

Parsing and writing log data from mapreduce to hive

Ive written a small hadoop map program to parse(regex) information from log files generated from other apps. I found this article http://www.nearinfinity.com//blogs/stephen_mouring_jr/2013/01/04/writing-hive-tables-from-mapreduce.html
This article explains how to parse and write it into the hive table
Here is my code
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class ParseDataToDB {
public static final String SEPARATOR_FIELD = new String(new char[] {1});
public static final String SEPARATOR_ARRAY_VALUE = new String(new char[] {2});
public static final BytesWritable NULL_KEY = new BytesWritable();
public static class MyMapper extends Mapper<LongWritable, Text, BytesWritable, Text> {
//private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private ArrayList<String> bazValues = new ArrayList<String>();
public void map(LongWritable key, Text value,
OutputCollector<BytesWritable, Text> context)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while(tokenizer.hasMoreTokens()){
word.set(tokenizer.nextToken());
if(word.find("extract") > -1) {
System.out.println("in herer");
bazValues.add(line);
}
}
// Build up the array values as a delimited string.
StringBuilder bazValueBuilder = new StringBuilder();
int i = 0;
for (String bazValue : bazValues) {
bazValueBuilder.append(bazValue);
++i;
if (i < bazValues.size()) {
bazValueBuilder.append(SEPARATOR_ARRAY_VALUE);
}
}
// Build up the column values / fields as a delimited string.
String hiveRow = new String();
hiveRow += "fooValue";
hiveRow += SEPARATOR_FIELD;
hiveRow += "barValue";
hiveRow += SEPARATOR_FIELD;
hiveRow += bazValueBuilder.toString();
System.out.println("in herer hiveRow" + hiveRow);
// StringBuilder hiveRow = new StringBuilder();
// hiveRow.append("fooValue");
// hiveRow.append(SEPARATOR_FIELD);
// hiveRow.append("barValue");
// hiveRow.append(SEPARATOR_FIELD);
// hiveRow.append(bazValueBuilder.toString());
// Emit a null key and a Text object containing the delimited fields
context.collect(NULL_KEY, new Text(hiveRow));
}
}
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
Job job = new Job(conf, "MyTest");
job.setJarByClass(ParseDataToDB.class);
job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(BytesWritable.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(BytesWritable.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
But when i run this app, i get an error saying "expected ByteWritable but recieved LongWritable. Can someone tell me what im doing wrong? Im new to hadoop programming. Im also open to creating external tables and pointing that to hdfs, again im struggling with implementation.
Thanks.
from looking at article you provided LINK, Show NULL_KEY that you haven't set any value.
It should be
public static final BytesWritable NULL_KEY = new BytesWritable(null);
I think as you are trying to output NULL as key from the map so you can use NullWritable. So your code would be something as below:-
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class ParseDataToDB {
public static final String SEPARATOR_FIELD = new String(new char[] {1});
public static final String SEPARATOR_ARRAY_VALUE = new String(new char[] {2});
public static class MyMapper extends Mapper<LongWritable, Text, NullWritable, Text> {
//private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private ArrayList<String> bazValues = new ArrayList<String>();
public void map(LongWritable key, Text value,
OutputCollector<NullWritable, Text> context)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while(tokenizer.hasMoreTokens()){
word.set(tokenizer.nextToken());
if(word.find("extract") > -1) {
System.out.println("in herer");
bazValues.add(line);
}
}
// Build up the array values as a delimited string.
StringBuilder bazValueBuilder = new StringBuilder();
int i = 0;
for (String bazValue : bazValues) {
bazValueBuilder.append(bazValue);
++i;
if (i < bazValues.size()) {
bazValueBuilder.append(SEPARATOR_ARRAY_VALUE);
}
}
// Build up the column values / fields as a delimited string.
String hiveRow = new String();
hiveRow += "fooValue";
hiveRow += SEPARATOR_FIELD;
hiveRow += "barValue";
hiveRow += SEPARATOR_FIELD;
hiveRow += bazValueBuilder.toString();
System.out.println("in herer hiveRow" + hiveRow);
// Emit a null key and a Text object containing the delimited fields
context.collect(NullWritable.get(), new Text(hiveRow));
}
}
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
Job job = new Job(conf, "MyTest");
job.setJarByClass(ParseDataToDB.class);
job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(NullWritable.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

Categories

Resources