需求:
将一个文件夹里的几个小文件读入并合并,输出为 : 文件路径+文件内容
代码:
public class Fcinputformat extends FileInputFormat<NullWritable, BytesWritable> {
@Override
protected boolean isSplitable(JobContext context, Path filename) {
//不切原来文件
return false;
}
@Override
public RecordReader<NullWritable, BytesWritable> createRecordReader(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
FcRecordReader fc = new FcRecordReader();
return fc;
}
}
-----------------------------------------------------------
public class FcRecordReader extends RecordReader<NullWritable, BytesWritable> {
boolean isProcess = false;
FileSplit sp;
Configuration conf;
BytesWritable value = new BytesWritable();
public void initialize(InputSplit inputSplit, TaskAttemptContext Context) {
this.sp = (FileSplit) inputSplit;
conf = Context.getConfiguration();
}
public boolean nextKeyValue() throws IOException {
if (!isProcess){
FSDataInputStream fis ;
FileSystem fs ;
//1.根据切片长度获得缓冲区
byte [] bur = new byte[(int)sp.getLength()];
//2.获得路径
Path path = sp.getPath();
//3.通过路径获得文件系统
fs = path.getFileSystem(conf);
//4.通过文件系统获得输入流
fis = fs.open(path);
//5.拷贝流
IOUtils.readFully(fis,bur,0,bur.length);
//6.关闭流
value.set(bur, 0, bur.length);
IOUtils.closeStream(fis);
IOUtils.closeStream(fs);
isProcess = true;
return true;
}
return false;
}
public NullWritable getCurrentKey() {
return NullWritable.get();
}
public BytesWritable getCurrentValue() {
return value;
}
public float getProgress() {
return 0;
}
public void close() {
}
}
----------------------------------------------------
public class SquenceDrive {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(SquenceDrive.class);
job.setMapperClass(SquenceMapper.class);
job.setReducerClass(SquenceReducer.class);
job.setInputFormatClass(Fcinputformat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
// job.setOutputFormatClass(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(BytesWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(BytesWritable.class);
FileInputFormat.setInputPaths(job,new Path("B:/测试数据/"));
FileOutputFormat.setOutputPath(job,new Path("B:/测试数据/out"));
boolean b = job.waitForCompletion(true);
System.out.println(b);
}
}
-----------------------------------------------------------------------------------------
public class SquenceMapper extends Mapper<NullWritable, BytesWritable, Text, BytesWritable> {
Text k = new Text();
@Override
protected void setup(Context context) throws IOException, InterruptedException {
FileSplit sp = (FileSplit) context.getInputSplit();
Path path = sp.getPath();
k.set(path.toString());
}
@Override
protected void map(NullWritable key, BytesWritable value, Context context) throws IOException, InterruptedException {
context.write(k,value);
}
}
--------------------------------------------------------------------
public class SquenceReducer extends Reducer<Text, BytesWritable,Text, BytesWritable> {
@Override
protected void reduce(Text key, Iterable<BytesWritable> values, Context context) throws IOException, InterruptedException {
for (BytesWritable v : values){
context.write(key,v);
}
}
}
输入结果:
上面包名不能去掉,用的不多,主要熟悉下Inputformat的过程和写法!