how to create ruunable jar for hadoop using eclipse - eclipse

Question

//I am getting exception while running hadoop jar file which convert pdf to //text and parse to mapper
java.lang.Exception: java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable
at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:489)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:549)
Caused by: java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java:1072)
at org.apache.hadoop.mapred.MapTask$NewOutputCollector.write(MapTask.java:715)
at org.apache.hadoop.mapreduce.task.TaskInputOutputContextImpl.write(TaskInputOutputContextImpl.java:89)
at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.write(WrappedMapper.java:112)
at org.apache.hadoop.mapreduce.Mapper.map(Mapper.java:125)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:146)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:787)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:270)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
17/06/08 19:12:10 INFO mapreduce.Job: Job job_local815278758_0001 running in uber mode : false
17/06/08 19:12:10 INFO mapreduce.Job: map 0% reduce 0%
17/06/08 19:12:10 INFO mapreduce.Job: Job job_local815278758_0001 failed with state FAILED due to: NA
17/06/08 19:12:10 INFO mapreduce.Job: Counters: 0
//Mapper class
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class WordCountMapper extends
Mapper<Object, Object, Object, Object> {
private Text word = new Text();
private final static LongWritable one = new LongWritable(1);
protected 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());
context.progress();
context.write(word, one);
}
}
}
//Reducer class
package com.amal.pdf;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordCountReducer extends
Reducer<Object, Object, Object, Object> {
protected void reduce(Text key, Iterable<LongWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (LongWritable value : values) {
sum += value.get();
}
context.write(key, new LongWritable(sum));
}
}
//PDF record Reader class
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
public class PdfRecordReader extends RecordReader<Object, Object> {
private String[] lines = null;
private LongWritable key = null;
private Text value = null;
#Override
public void initialize(InputSplit genericSplit, TaskAttemptContext context)
throws IOException, InterruptedException {
FileSplit split = (FileSplit) genericSplit;
Configuration job = context.getConfiguration();
final Path file = split.getPath();
/*
* The below code contains the logic for opening the file and seek to
* the start of the split. Here we are applying the Pdf Parsing logic
*/
FileSystem fs = file.getFileSystem(job);
FSDataInputStream fileIn = fs.open(split.getPath());
PDDocument pdf = null;
String parsedText = null;
PDFTextStripper stripper;
pdf = PDDocument.load(fileIn);
stripper = new PDFTextStripper();
//getting exception because of this line
parsedText = stripper.getText(pdf);
this.lines = parsedText.split("\n"); }
#Override
public boolean nextKeyValue() throws IOException, InterruptedException {
if (key == null) {
key = new LongWritable();
key.set(1);
value = new Text();
value.set(lines[0]);
} else {
int temp = (int) key.get();
if (temp < (lines.length - 1)) {
int count = (int) key.get();
value = new Text();
value.set(lines[count]);
count = count + 1;
key = new LongWritable(count);
} else {
return false;
}
}
if (key == null || value == null) {
return false;
} else {
return true;
}
}
#Override
public LongWritable getCurrentKey() throws IOException,
InterruptedException {
return key;
}
#Override
public Text getCurrentValue() throws IOException, InterruptedException {
return value;
}
#Override
public float getProgress() throws IOException, InterruptedException {
return 0;
}
#Override
public void close() throws IOException {
}
}
//One more thing can anyone help to create runnable jar, configuration is not //showing inside eclipse because main is for hadoop environment.

Answer 1

The error on your console says:
Caused by: java.io.IOException:
Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable
That means that the key-value pair you are providing to your mapper doesn't match it's definition.
Your mapper class should look something like this:
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private Text word = new Text();
private final static IntWritable one = new IntWritable(1);
protected 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());
context.progress();
context.write(word, one);
}
}
}