import java.io.DataOutputStream;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class LineRecordWriter<K, V> extends RecordWriter<K, V> {
private static final String utf8 = "UTF-8";
private static final byte[] newline;
static {
try {
newline = "\n".getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
protected DataOutputStream out;
private final byte[] keyValueSeparator;
public LineRecordWriter(DataOutputStream out, String keyValueSeparator) {
this.out = out;
try {
this.keyValueSeparator = keyValueSeparator.getBytes(utf8);
} catch (UnsupportedEncodingException uee) {
throw new IllegalArgumentException("can't find " + utf8 + " encoding");
}
}
public LineRecordWriter(DataOutputStream out) {
this(out, "\t");
}
private void writeObject(Object o) throws IOException {
if (o instanceof Text) {
Text to = (Text) o;
out.write(to.getBytes(), 0, to.getLength());
} else {
out.write(o.toString().getBytes(utf8));
}
}
public synchronized void write(K key, V value) throws IOException {
boolean nullKey = key == null || key instanceof NullWritable;
boolean nullValue = value == null || value instanceof NullWritable;
if (nullKey && nullValue) {
return;
}
/* if (!nullKey) {
writeObject(key);
}
if (!(nullKey || nullValue)) {
out.write(keyValueSeparator);
} */
if (!nullValue) {
writeObject(value);
}
out.write(newline);
}
public synchronized void close(TaskAttemptContext context) throws IOException {
out.close();
}
}
import java.io.DataOutputStream;
import java.io.IOException;
import java.util.HashMap;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.FileAlreadyExistsException;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
public abstract class MultipleOutputFormat<K extends WritableComparable, V extends Writable>
extends FileOutputFormat<K, V> {
private MultiRecordWriter writer = null;
public RecordWriter<K, V> getRecordWriter(TaskAttemptContext job) throws IOException,
InterruptedException {
if (writer == null) {
writer = new MultiRecordWriter(job, getTaskOutputPath(job));
}
return writer;
}
private Path getTaskOutputPath(TaskAttemptContext conf) throws IOException {
Path workPath = null;
OutputCommitter committer = super.getOutputCommitter(conf);
if (committer instanceof FileOutputCommitter) {
workPath = ((FileOutputCommitter) committer).getWorkPath();
} else {
Path outputPath = super.getOutputPath(conf);
if (outputPath == null) {
throw new IOException("Undefined job output-path");
}
workPath = outputPath;
}
return workPath;
}
protected abstract String generateFileNameForKeyValue(K key, V value, TaskAttemptContext job);//Configuration conf);
public class MultiRecordWriter extends RecordWriter<K, V> {
private HashMap<String, RecordWriter<K, V>> recordWriters = null;
private TaskAttemptContext job = null;
private Path workPath = null;
public MultiRecordWriter(TaskAttemptContext job, Path workPath) {
super();
this.job = job;
this.workPath = workPath;
recordWriters = new HashMap<String, RecordWriter<K, V>>();
}
@Override
public void close(TaskAttemptContext context) throws IOException, InterruptedException {
Iterator<RecordWriter<K, V>> values = this.recordWriters.values().iterator();
while (values.hasNext()) {
values.next().close(context);
}
this.recordWriters.clear();
}
@Override
public void write(K key, V value) throws IOException, InterruptedException {
String baseName = generateFileNameForKeyValue(key, value, job);
RecordWriter<K, V> rw = this.recordWriters.get(baseName);
if (rw == null) {
rw = getBaseRecordWriter(job, baseName);
this.recordWriters.put(baseName, rw);
}
rw.write(key, value);//change
}
private RecordWriter<K, V> getBaseRecordWriter(TaskAttemptContext job, String baseName)
throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
boolean isCompressed = getCompressOutput(job);
String keyValueSeparator = "***"; //change
//ods_aos_mps/2013/09/01/part-r-000
// String pathname=baseName.substring(0, baseName.indexOf("/")); //change
workPath = new Path(job.getConfiguration().get("mapred.output.dir"));
RecordWriter<K, V> recordWriter = null;
if (isCompressed) {
Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(job,
GzipCodec.class);
CompressionCodec codec = ReflectionUtils.newInstance(codecClass, conf);
Path file = new Path(workPath+"/"+baseName + codec.getDefaultExtension()); //change
FSDataOutputStream fileOut = file.getFileSystem(conf).create(file, true);
recordWriter = new LineRecordWriter<K, V>(new DataOutputStream(codec.createOutputStream(fileOut)), keyValueSeparator);
} else {
Path file = new Path(workPath+"/"+baseName); //change
FSDataOutputStream fileOut = file.getFileSystem(conf).create(file, true);
recordWriter = new LineRecordWriter<K, V>(fileOut, keyValueSeparator);
}
return recordWriter;
}
}
@Override
public void checkOutputSpecs(JobContext job)
throws FileAlreadyExistsException, IOException {
//
}
}
import java.text.NumberFormat;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.TaskID;
public class MyMutiFile extends MultipleOutputFormat<Text, Text>{
private static final NumberFormat NUMBER_FORMAT = NumberFormat.getInstance();
static {
NUMBER_FORMAT.setMinimumIntegerDigits(5);
NUMBER_FORMAT.setGroupingUsed(false);
}
public static String FILENAME ="";
public static String getFILENAME() {
return FILENAME;
}
public static void setFILENAME(String fILENAME) {
FILENAME = fILENAME;
}
@Override
protected String generateFileNameForKeyValue(Text key, Text value,
TaskAttemptContext job) {
TaskID taskId = job.getTaskAttemptID().getTaskID();
int partition = taskId.getId();
StringBuilder result = new StringBuilder();
result.append(key.toString());
result.append(job.getConfiguration().get("customTime"));
result.append("part");
result.append('-');
result.append(taskId.isMap() ? 'm' : 'r');
result.append('-');
result.append(NUMBER_FORMAT.format(partition));
// result.append(extension);
return result.toString();
}
}