如何在 hadoop 中将完整的输入拆分读取为单个记录

Question

默认情况下，Hadoop使用行记录读取器，该读取器逐行读取输入。我要求在一次读取中读取完整的输入拆分，即作为单个记录。谁能帮我。

Answer 1

您需要编写自己的自定义记录阅读器以便它将整个文件作为单个记录读取

您可以在"Hadoop权威指南第4版"中看到这一点 页 - 228

这个例子可能会对你有所帮助

public class WholeFileInputFormat
extends FileInputFormat<NullWritable, BytesWritable> {
@Override
protected boolean isSplitable(JobContext context, Path file) {
return false;
}
@Override
public RecordReader<NullWritable, BytesWritable> createRecordReader(
InputSplit split, TaskAttemptContext context) throws IOException,
InterruptedException {
WholeFileRecordReader reader = new WholeFileRecordReader();
reader.initialize(split, context);
return reader;
}
}

class WholeFileRecordReader extends RecordReader<NullWritable, BytesWritable> {
private FileSplit fileSplit;
private Configuration conf;
private BytesWritable value = new BytesWritable();
private boolean processed = false;
@Override
public void initialize(InputSplit split, TaskAttemptContext context)
throws IOException, InterruptedException {
this.fileSplit = (FileSplit) split;
this.conf = context.getConfiguration();
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
if (!processed) {
byte[] contents = new byte[(int) fileSplit.getLength()];
Path file = fileSplit.getPath();
FileSystem fs = file.getFileSystem(conf);
FSDataInputStream in = null;
try {
in = fs.open(file);
IOUtils.readFully(in, contents, 0, contents.length);
value.set(contents, 0, contents.length);
} finally {
IOUtils.closeStream(in);
}
processed = true;
return true;
}
return false;
}
@Override
public NullWritable getCurrentKey() throws IOException, InterruptedException {
return NullWritable.get();
}
@Override
public BytesWritable getCurrentValue() throws IOException,
InterruptedException {
return value;
}
@Override
Input Formats | 229
public float getProgress() throws IOException {
return processed ? 1.0f : 0.0f;
}
@Override
public void close() throws IOException {
// do nothing
}
}

public class SmallFilesToSequenceFileConverter extends Configured
implements Tool {
static class SequenceFileMapper
extends Mapper<NullWritable, BytesWritable, Text, BytesWritable> {
private Text filenameKey;
@Override
protected void setup(Context context) throws IOException,
InterruptedException {
InputSplit split = context.getInputSplit();
Path path = ((FileSplit) split).getPath();
filenameKey = new Text(path.toString());
}
@Override
protected void map(NullWritable key, BytesWritable value, Context context)
throws IOException, InterruptedException {
context.write(filenameKey, value);
}
}
@Override
public int run(String[] args) throws Exception {
Job job = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (job == null) {
return -1;
}
job.setInputFormatClass(WholeFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(BytesWritable.class);
job.setMapperClass(SequenceFileMapper.class);
return job.waitForCompletion(true) ? 0 : 1;
}
public static void main(String[] args) throws Exception {
int exitCode = ToolRunner.run(new SmallFilesToSequenceFileConverter(), args);
System.exit(exitCode);
}
}