我编写了一个自定义输入格式并在作业中进行了配置。仍然没有调用inputformat。在运行代码时我保留了一些SOP来打印，但没有一个正在打印。即使我在驱动程序类中注释自定义inputformat仍然输出仍然相同。我在哪里错过了？
DriverClass
public class TestDriver {
public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException{
Configuration conf = new Configuration();
Job job = new Job(conf,"Custom Format");
job.setMapperClass(CustomInputFormatmapper.class);
job.setReducerClass(CustomInputFormatReducer.class);
job.setInputFormatClass(CustomInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(LongWritable.class);
job.getConfiguration().set("fs.file.impl", "com.learn.WinLocalFileSystem");
String inputPath="In\\VISA_Details.csv";
Path inPath=new Path(inputPath);
String outputPath = "C:\\Users\\Desktop\\Hadoop learning\\output\\run1";
Path outPath=new Path(outputPath);
FileInputFormat.setInputPaths(job, inPath );
FileOutputFormat.setOutputPath(job, outPath);
System.out.println(job.waitForCompletion(true));
}
}
import org.apache.hadoop.mapred.TaskAttemptContext;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
public class CustomInputFormat extends TextInputFormat{
public RecordReader createRecordReader(InputSplit split, TaskAttemptContext context)
{
System.out.println(" ------------ INSIDE createRecordReader()--------------");
return new CustomRecordReader();
}
}
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.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.util.LineReader;
public class CustomRecordReader extends RecordReader {
private CompressionCodecFactory compressionCodecs;
private final int NLINESTOPROCESS = 3;
private long start;
private long pos;
private long end;
private LineReader in;
private int maxLineLength;
private LongWritable key;
private Text value;
@Override
public void close() throws IOException {
// TODO Auto-generated method stub
}
@Override
public Object getCurrentKey() throws IOException, InterruptedException {
// TODO Auto-generated method stub
return null;
}
@Override
public Object getCurrentValue() throws IOException, InterruptedException {
// TODO Auto-generated method stub
return null;
}
@Override
public float getProgress() throws IOException, InterruptedException {
// TODO Auto-generated method stub
return 0;
}
@Override
public void initialize(InputSplit inputsplit,TaskAttemptContext taskattemptcontext)
throws IOException, InterruptedException {
System.out.println(" ---------- INSIDE INITILISE: THIS IS NOT PRINTING----------");
FileSplit split = (FileSplit)inputsplit;
Configuration job = taskattemptcontext.getConfiguration();
maxLineLength = job.getInt("mapred.linerecordreader.maxlength", 2147483647);
start = split.getStart();
end = start + split.getLength();
Path file = split.getPath();
compressionCodecs = new CompressionCodecFactory(job);
CompressionCodec codec = compressionCodecs.getCodec(file);
FileSystem fs = file.getFileSystem(job);
FSDataInputStream fileIn = fs.open(split.getPath());
boolean skipFirstLine = false;
if(codec != null)
{
in = new LineReader(codec.createInputStream(fileIn), job);
end = 9223372036854775807L;
} else
{
if(start != 0L)
{
skipFirstLine = true;
start--;
fileIn.seek(start);
}
in = new LineReader(fileIn, job);
}
if(skipFirstLine)
start += in.readLine(new Text(), 0, (int)Math.min(2147483647L, end - start));
pos = start;
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
System.out.println(" ---------- INSIDE nextKeyValue()------------");
if(key==null){
key = new LongWritable();
}
if(value==null){
value = new Text();
}
key.set(pos);
value.clear();
final Text newLine = new Text("\n");
Text newVal = new Text();
int newSize = 0;
for(int i =0;i<NLINESTOPROCESS;i++){
Text v = new Text();
while(pos<end){
newSize = in.readLine(v, maxLineLength,Math.max((int)Math.min(Integer.MAX_VALUE, end-pos),maxLineLength));
value.append(v.getBytes(),0, v.getLength());
value.append(newLine.getBytes(),0, newLine.getLength());
if (newSize == 0) {
break;
}
pos += newSize;
if (newSize < maxLineLength) {
break;
}
}
}
return false;
}
}
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class CustomInputFormatmapper extends Mapper<LongWritable, Text, LongWritable, LongWritable> {
public void map(LongWritable key, Text val, Context context)throws IOException, InterruptedException{
String value = val.toString();
String[] totalRows = value.split("\n");
int count =totalRows.length;
context.write(new LongWritable(Long.valueOf(count)), new LongWritable(1L));
}
}
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Reducer;
public class CustomInputFormatReducer extends Reducer<LongWritable, LongWritable, LongWritable, LongWritable> {
public void reduce(LongWritable key, Iterable<LongWritable> val, Context context) throws IOException, InterruptedException{
System.out.println(" --------REDUCER--------");
long count =0;
for(LongWritable vals: val){
count++;
}
context.write(key, new LongWritable(count));
}
}
答案 0 :(得分：0)
我正在回答我自己的问题，因为这将有助于其他人解决我所遇到的问题。我导入的包有问题。 提到我所犯的错误。
1）错过了@Override注释 2）从import org.apache.hadoop.mapred.InputSplit导入而不是org.apache.hadoop.mapreduce.InputSplit;
1）导入是从org.apache.hadoop.mapred。*进行的，而不是来自org.apache.hadoop.mapreduce。*;