更新时间:2023-09-06 15:13:16
您可以使用Hadoop InputFormat和OutputFormat接口创建自定义格式.例如,可以将MapReduce作业的输出格式化为JSON.这个-
you can use Hadoop InputFormat and OutputFormat interfaces to create your custom formats..an example could be to format the output of your MapReduce job as JSON..something like this -
public class JsonOutputFormat extends TextOutputFormat<Text, IntWritable> {
@Override
public RecordWriter<Text, IntWritable> getRecordWriter(
TaskAttemptContext context) throws IOException,
InterruptedException {
Configuration conf = context.getConfiguration();
Path path = getOutputPath(context);
FileSystem fs = path.getFileSystem(conf);
FSDataOutputStream out =
fs.create(new Path(path,context.getJobName()));
return new JsonRecordWriter(out);
}
private static class JsonRecordWriter extends
LineRecordWriter<Text,IntWritable>{
boolean firstRecord = true;
@Override
public synchronized void close(TaskAttemptContext context)
throws IOException {
out.writeChar('{');
super.close(null);
}
@Override
public synchronized void write(Text key, IntWritable value)
throws IOException {
if (!firstRecord){
out.writeChars(",\r\n");
firstRecord = false;
}
out.writeChars("\"" + key.toString() + "\":\""+
value.toString()+"\"");
}
public JsonRecordWriter(DataOutputStream out)
throws IOException{
super(out);
out.writeChar('}');
}
}
}