@Override
public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("UFO count");
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: avro UFO counter <in> <out>");
System.exit(2);
}
FileInputFormat.addInputPath(conf, new Path(otherArgs[0]));
Path outputPath = new Path(otherArgs[1]);
FileOutputFormat.setOutputPath(conf, outputPath);
outputPath.getFileSystem(conf).delete(outputPath);
Schema input_schema = Schema.parse(getClass().getResourceAsStream("ufo.avsc"));
AvroJob.setInputSchema(conf, input_schema);
AvroJob.setMapOutputSchema(
conf,
Pair.getPairSchema(Schema.create(Schema.Type.STRING), Schema.create(Schema.Type.LONG)));
AvroJob.setOutputSchema(conf, OUTPUT_SCHEMA);
AvroJob.setMapperClass(conf, AvroRecordMapper.class);
AvroJob.setReducerClass(conf, AvroRecordReducer.class);
conf.setInputFormat(AvroInputFormat.class);
JobClient.runJob(conf);
return 0;
}
private void testMapFileOutputCommitterInternal(int version) throws Exception {
JobConf conf = new JobConf();
FileOutputFormat.setOutputPath(conf, outDir);
conf.set(JobContext.TASK_ATTEMPT_ID, attempt);
conf.setInt(
org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION,
version);
JobContext jContext = new JobContextImpl(conf, taskID.getJobID());
TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, taskID);
FileOutputCommitter committer = new FileOutputCommitter();
// setup
committer.setupJob(jContext);
committer.setupTask(tContext);
// write output
MapFileOutputFormat theOutputFormat = new MapFileOutputFormat();
RecordWriter theRecordWriter = theOutputFormat.getRecordWriter(null, conf, partFile, null);
writeMapFileOutput(theRecordWriter, tContext);
// do commit
if (committer.needsTaskCommit(tContext)) {
committer.commitTask(tContext);
}
committer.commitJob(jContext);
// validate output
validateMapFileOutputContent(FileSystem.get(conf), outDir);
FileUtil.fullyDelete(new File(outDir.toString()));
}
public void testComplexNameWithRegex() throws Exception {
OutputStream os = getFileSystem().create(new Path(getInputDir(), "text.txt"));
Writer wr = new OutputStreamWriter(os);
wr.write("b a\n");
wr.close();
JobConf conf = createJobConf();
conf.setJobName("name \\Evalue]");
conf.setInputFormat(TextInputFormat.class);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(IdentityMapper.class);
FileInputFormat.setInputPaths(conf, getInputDir());
FileOutputFormat.setOutputPath(conf, getOutputDir());
JobClient.runJob(conf);
Path[] outputFiles =
FileUtil.stat2Paths(getFileSystem().listStatus(getOutputDir(), new OutputLogFilter()));
assertEquals(1, outputFiles.length);
InputStream is = getFileSystem().open(outputFiles[0]);
BufferedReader reader = new BufferedReader(new InputStreamReader(is));
assertEquals("0\tb a", reader.readLine());
assertNull(reader.readLine());
reader.close();
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] remainArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (remainArgs.length != 2) {
System.err.println("Usage: wordcount <input> <output>");
System.exit(1);
}
Job job = new Job(conf, "wordcount");
job.setJarByClass(WordCount.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setNumReduceTasks(4);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileSystem.get(conf).delete(new Path(remainArgs[1]), true);
FileInputFormat.setInputPaths(job, new Path(remainArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(remainArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
@Override
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.err.printf(
"Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("Max temperature");
FileInputFormat.addInputPath(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(MaxTemperatureMapper.class);
conf.setCombinerClass(MaxTemperatureReducer.class);
conf.setReducerClass(MaxTemperatureReducer.class);
// vv MaxTemperatureDriverV6
conf.setProfileEnabled(true);
conf.setProfileParams(
"-agentlib:hprof=cpu=samples,heap=sites,depth=6," + "force=n,thread=y,verbose=n,file=%s");
conf.setProfileTaskRange(true, "0-2");
// ^^ MaxTemperatureDriverV6
JobClient.runJob(conf);
return 0;
}
public void testAbort() throws IOException {
JobConf job = new JobConf();
setConfForFileOutputCommitter(job);
JobContext jContext = new JobContextImpl(job, taskID.getJobID());
TaskAttemptContext tContext = new TaskAttemptContextImpl(job, taskID);
FileOutputCommitter committer = new FileOutputCommitter();
FileOutputFormat.setWorkOutputPath(job, committer.getTempTaskOutputPath(tContext));
// do setup
committer.setupJob(jContext);
committer.setupTask(tContext);
String file = "test.txt";
// A reporter that does nothing
Reporter reporter = Reporter.NULL;
// write output
FileSystem localFs = FileSystem.getLocal(job);
TextOutputFormat theOutputFormat = new TextOutputFormat();
RecordWriter theRecordWriter = theOutputFormat.getRecordWriter(localFs, job, file, reporter);
writeOutput(theRecordWriter, reporter);
// do abort
committer.abortTask(tContext);
File expectedFile =
new File(new Path(committer.getTempTaskOutputPath(tContext), file).toString());
assertFalse("task temp dir still exists", expectedFile.exists());
committer.abortJob(jContext, JobStatus.State.FAILED);
expectedFile = new File(new Path(outDir, FileOutputCommitter.TEMP_DIR_NAME).toString());
assertFalse("job temp dir still exists", expectedFile.exists());
assertEquals("Output directory not empty", 0, new File(outDir.toString()).listFiles().length);
FileUtil.fullyDelete(new File(outDir.toString()));
}
private String runJob() throws Exception {
OutputStream os = getFileSystem().create(new Path(getInputDir(), "text.txt"));
Writer wr = new OutputStreamWriter(os);
wr.write("hello1\n");
wr.write("hello2\n");
wr.write("hello3\n");
wr.close();
JobConf conf = createJobConf();
conf.setJobName("mr");
conf.setJobPriority(JobPriority.HIGH);
conf.setInputFormat(TextInputFormat.class);
conf.setMapOutputKeyClass(LongWritable.class);
conf.setMapOutputValueClass(Text.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
conf.setReducerClass(org.apache.hadoop.mapred.lib.IdentityReducer.class);
FileInputFormat.setInputPaths(conf, getInputDir());
FileOutputFormat.setOutputPath(conf, getOutputDir());
return JobClient.runJob(conf).getID().toString();
}
public static void runSortJob(String... args) throws Exception {
Path input = new Path(args[0]);
Path output = new Path(args[1]);
JobConf job = new JobConf();
job.setNumReduceTasks(2);
job.setInputFormat(KeyValueTextInputFormat.class);
job.setOutputFormat(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, input);
FileOutputFormat.setOutputPath(job, output);
job.setJarByClass(SampleJob.class);
output.getFileSystem(job).delete(output, true);
JobClient jc = new JobClient(job);
JobClient.setTaskOutputFilter(job, JobClient.TaskStatusFilter.ALL);
RunningJob rj = jc.submitJob(job);
try {
if (!jc.monitorAndPrintJob(job, rj)) {
System.out.println("Job Failed: " + rj.getFailureInfo());
throw new IOException("Job failed!");
}
} catch (InterruptedException ie) {
Thread.currentThread().interrupt();
}
}
@Override
public int run(String[] arg0) throws Exception {
// config a job and start it
Configuration conf = getConf();
Job job = new Job(conf, "Index construction..");
job.setJarByClass(IndexConstructorDriver.class);
job.setMapperClass(IndexConstructorMapper.class);
job.setReducerClass(IndexConstructorReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(InvertedListWritable.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
// can add the dir by the config
FileSystem fs = FileSystem.get(conf);
String workdir = conf.get("org.joy.crawler.dir", "crawler/");
fs.delete(new Path(workdir + "indexOutput/"), true);
FileInputFormat.addInputPath(job, new Path(workdir + "content/"));
FileOutputFormat.setOutputPath(job, new Path(workdir + "indexOutput/"));
System.out.println(
"indexer starts to work, it begins to construct the index, please wait ...\n");
return job.waitForCompletion(true) ? 0 : 1;
}
private void testAbortInternal(int version) throws IOException, InterruptedException {
JobConf conf = new JobConf();
FileOutputFormat.setOutputPath(conf, outDir);
conf.set(JobContext.TASK_ATTEMPT_ID, attempt);
conf.setInt(
org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
.FILEOUTPUTCOMMITTER_ALGORITHM_VERSION,
version);
JobContext jContext = new JobContextImpl(conf, taskID.getJobID());
TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, taskID);
FileOutputCommitter committer = new FileOutputCommitter();
// do setup
committer.setupJob(jContext);
committer.setupTask(tContext);
// write output
TextOutputFormat theOutputFormat = new TextOutputFormat();
RecordWriter theRecordWriter = theOutputFormat.getRecordWriter(null, conf, partFile, null);
writeOutput(theRecordWriter, tContext);
// do abort
committer.abortTask(tContext);
File out = new File(outDir.toUri().getPath());
Path workPath = committer.getWorkPath(tContext, outDir);
File wp = new File(workPath.toUri().getPath());
File expectedFile = new File(wp, partFile);
assertFalse("task temp dir still exists", expectedFile.exists());
committer.abortJob(jContext, JobStatus.State.FAILED);
expectedFile = new File(out, FileOutputCommitter.TEMP_DIR_NAME);
assertFalse("job temp dir still exists", expectedFile.exists());
assertEquals("Output directory not empty", 0, out.listFiles().length);
FileUtil.fullyDelete(out);
}
public static void main(String[] args) throws Exception {
final String NAME_NODE = "hdfs://sandbox.hortonworks.com:8020";
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(NullWritable.class);
if (args.length > 2) {
job.setNumReduceTasks(Integer.parseInt(args[2]));
}
job.setMapperClass(CountMapper.class);
job.setReducerClass(CountReducer.class);
job.setJarByClass(WordCount.class);
job.setNumReduceTasks(1);
FileInputFormat.addInputPath(job, new Path(args[0] + "data/plot_summaries.txt"));
FileSystem fs = FileSystem.get(conf);
// handle (e.g. delete) existing output path
Path outputDestination = new Path(args[0] + args[1]);
if (fs.exists(outputDestination)) {
fs.delete(outputDestination, true);
}
// set output path & start job1
FileOutputFormat.setOutputPath(job, outputDestination);
int jobCompletionStatus = job.waitForCompletion(true) ? 0 : 1;
}
/* (non-Javadoc)
* @see eu.stratosphere.pact.common.io.FileOutputFormat#close()
*/
@Override
public void close() throws IOException {
if (wrt != null) {
this.wrt.close();
}
super.close();
}
public static void runJob(String[] args) {
JobConf conf = new JobConf(CassandraBulkLoader.class);
if (args.length >= 4) {
conf.setNumReduceTasks(new Integer(args[3]));
}
try {
// We store the cassandra storage-conf.xml on the HDFS cluster
DistributedCache.addCacheFile(new URI("/cassandra/storage-conf.xml#storage-conf.xml"), conf);
} catch (URISyntaxException e) {
throw new RuntimeException(e);
}
conf.setInputFormat(KeyValueTextInputFormat.class);
conf.setJobName("CassandraBulkLoader_v2");
conf.setMapperClass(Map.class);
conf.setReducerClass(Reduce.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(conf, new Path(args[1]));
FileOutputFormat.setOutputPath(conf, new Path(args[2]));
try {
JobClient.runJob(conf);
} catch (IOException e) {
throw new RuntimeException(e);
}
}
public void inject(Path crawlDb, Path urlDir) throws IOException {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
long start = System.currentTimeMillis();
if (LOG.isInfoEnabled()) {
LOG.info("Injector: starting at " + sdf.format(start));
LOG.info("Injector: crawlDb: " + crawlDb);
LOG.info("Injector: urlDir: " + urlDir);
}
Path tempDir =
new Path(
getConf().get("mapred.temp.dir", ".")
+ "/inject-temp-"
+ Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
// map text input file to a <url,CrawlDatum> file
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Converting injected urls to crawl db entries.");
}
JobConf sortJob = new NutchJob(getConf());
sortJob.setJobName("inject " + urlDir);
FileInputFormat.addInputPath(sortJob, urlDir);
sortJob.setMapperClass(InjectMapper.class);
FileOutputFormat.setOutputPath(sortJob, tempDir);
sortJob.setOutputFormat(SequenceFileOutputFormat.class);
sortJob.setOutputKeyClass(Text.class);
sortJob.setOutputValueClass(CrawlDatum.class);
sortJob.setLong("injector.current.time", System.currentTimeMillis());
RunningJob mapJob = JobClient.runJob(sortJob);
long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
LOG.info(
"Injector: total number of urls injected after normalization and filtering: "
+ urlsInjected);
// merge with existing crawl db
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Merging injected urls into crawl db.");
}
JobConf mergeJob = CrawlDb.createJob(getConf(), crawlDb);
FileInputFormat.addInputPath(mergeJob, tempDir);
mergeJob.setReducerClass(InjectReducer.class);
JobClient.runJob(mergeJob);
CrawlDb.install(mergeJob, crawlDb);
// clean up
FileSystem fs = FileSystem.get(getConf());
fs.delete(tempDir, true);
long end = System.currentTimeMillis();
LOG.info(
"Injector: finished at "
+ sdf.format(end)
+ ", elapsed: "
+ TimingUtil.elapsedTime(start, end));
}
/**
* @param process
* @param tap
* @param conf
*/
@Override
public void sinkConfInit(
FlowProcess<JobConf> process, Tap<JobConf, RecordReader, OutputCollector> tap, JobConf conf) {
conf.setOutputFormat(MongoOutputFormat.class);
MongoConfigUtil.setOutputURI(conf, this.mongoUri);
FileOutputFormat.setOutputPath(conf, getPath());
}
/* (non-Javadoc)
* @see eu.stratosphere.pact.common.io.FileOutputFormat#open(int)
*/
@Override
public void open(int taskNumber) throws IOException {
super.open(taskNumber);
this.wrt =
this.charsetName == null
? new OutputStreamWriter(new BufferedOutputStream(this.stream, 4096))
: new OutputStreamWriter(new BufferedOutputStream(this.stream, 4096), this.charsetName);
}
public static int main(String[] args) throws Exception {
int i;
String outPath;
int numMaps = 0, numReds = 0;
List<String> other_args = new ArrayList<String>();
for (i = 0; i < args.length; ++i) {
try {
if ("-m".equals(args[i])) {
numMaps = Integer.parseInt(args[++i]);
} else if ("-r".equals(args[i])) {
numReds = Integer.parseInt(args[++i]);
} else {
other_args.add(args[i]);
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + args[i]);
printUsage();
} catch (ArrayIndexOutOfBoundsException except) {
System.out.println("ERROR: Required parameter missing from " + args[i - 1]);
printUsage(); // exits
}
}
// Make sure there are exactly 2 parameters left.
if (other_args.size() != 2) {
System.out.println(
"ERROR: Wrong number of parameters: " + other_args.size() + " instead of 2.");
printUsage();
}
Date startTime = new Date();
System.out.println("Job started: " + startTime);
Date startIteration;
Date endIteration;
JobConf conf = new JobConf(Kmeans.class);
conf.setJobName("kmeans");
conf.setOutputKeyClass(IntWritable.class);
conf.setOutputValueClass(Text.class);
conf.setMapOutputKeyClass(IntWritable.class);
conf.setMapOutputValueClass(ClusterWritable.class);
conf.setMapperClass(MapClass.class);
conf.setReducerClass(Reduce.class);
conf.setNumMapTasks(numMaps);
conf.setNumReduceTasks(numReds);
FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));
outPath = new String(other_args.get(1));
FileOutputFormat.setOutputPath(conf, new Path(outPath));
startIteration = new Date();
JobClient.runJob(conf);
endIteration = new Date();
System.out.println(
"The iteration took "
+ (endIteration.getTime() - startIteration.getTime()) / 1000
+ " seconds.");
return 0;
}
public static void main(String[] args) throws IOException {
/*JobConf conf = new JobConf();
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setMapperClass(IpCounterMapper.class);
conf.setCombinerClass(IpCounterReducer.class);
conf.setReducerClass(IpCounterReducer.class);
String inputDir = args[0];
String outputDir = args[1];
FileInputFormat.setInputPaths(conf, inputDir);
FileOutputFormat.setOutputPath(conf, new Path(outputDir));
boolean flag = JobClient.runJob(conf).isSuccessful();
System.out.println(args.length);*/
if (args.length < 2) {
System.out.println("args not right!");
return;
}
JobConf conf = new JobConf(IpCount1.class);
// set output key class
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
// set mapper & reducer class
conf.setMapperClass(IpCounterMapper.class);
conf.setCombinerClass(IpCounterReducer.class);
conf.setReducerClass(IpCounterReducer.class);
// set format
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
String inputDir = args[0];
String outputDir = args[1];
// FileInputFormat.setInputPaths(conf, "/user/hadoop/rongxin/locationinput/");
FileInputFormat.setInputPaths(conf, inputDir);
FileOutputFormat.setOutputPath(conf, new Path(outputDir));
boolean flag = JobClient.runJob(conf).isSuccessful();
}
@Override
public void configure(Configuration parameters) {
super.configure(parameters);
// read own parameters
this.blockSize = parameters.getLong(BLOCK_SIZE_PARAMETER_KEY, NATIVE_BLOCK_SIZE);
if (this.blockSize < 1 && this.blockSize != NATIVE_BLOCK_SIZE)
throw new IllegalArgumentException("The block size parameter must be set and larger than 0.");
if (this.blockSize > Integer.MAX_VALUE)
throw new UnsupportedOperationException(
"Currently only block size up to Integer.MAX_VALUE are supported");
}
@Override
public void open(int taskNumber, int numTasks) throws IOException {
super.open(taskNumber, numTasks);
final long blockSize =
this.blockSize == NATIVE_BLOCK_SIZE
? this.outputFilePath.getFileSystem().getDefaultBlockSize()
: this.blockSize;
this.blockBasedInput = new BlockBasedOutput(this.stream, (int) blockSize);
this.dataOutputStream = new DataOutputStream(this.blockBasedInput);
}
/** Configure a job given argv. */
public static boolean parseArgs(String[] argv, JobConf job) throws IOException {
if (argv.length < 1) {
return 0 == printUsage();
}
for (int i = 0; i < argv.length; ++i) {
if (argv.length == i + 1) {
System.out.println("ERROR: Required parameter missing from " + argv[i]);
return 0 == printUsage();
}
try {
if ("-m".equals(argv[i])) {
job.setNumMapTasks(Integer.parseInt(argv[++i]));
} else if ("-r".equals(argv[i])) {
job.setNumReduceTasks(Integer.parseInt(argv[++i]));
} else if ("-inFormat".equals(argv[i])) {
job.setInputFormat(Class.forName(argv[++i]).asSubclass(InputFormat.class));
} else if ("-outFormat".equals(argv[i])) {
job.setOutputFormat(Class.forName(argv[++i]).asSubclass(OutputFormat.class));
} else if ("-outKey".equals(argv[i])) {
job.setOutputKeyClass(Class.forName(argv[++i]).asSubclass(WritableComparable.class));
} else if ("-outValue".equals(argv[i])) {
job.setOutputValueClass(Class.forName(argv[++i]).asSubclass(Writable.class));
} else if ("-keepmap".equals(argv[i])) {
job.set(
org.apache.hadoop.mapreduce.GenericMRLoadGenerator.MAP_PRESERVE_PERCENT, argv[++i]);
} else if ("-keepred".equals(argv[i])) {
job.set(
org.apache.hadoop.mapreduce.GenericMRLoadGenerator.REDUCE_PRESERVE_PERCENT,
argv[++i]);
} else if ("-outdir".equals(argv[i])) {
FileOutputFormat.setOutputPath(job, new Path(argv[++i]));
} else if ("-indir".equals(argv[i])) {
FileInputFormat.addInputPaths(job, argv[++i]);
} else if ("-inFormatIndirect".equals(argv[i])) {
job.setClass(
org.apache.hadoop.mapreduce.GenericMRLoadGenerator.INDIRECT_INPUT_FORMAT,
Class.forName(argv[++i]).asSubclass(InputFormat.class),
InputFormat.class);
job.setInputFormat(IndirectInputFormat.class);
} else {
System.out.println("Unexpected argument: " + argv[i]);
return 0 == printUsage();
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + argv[i]);
return 0 == printUsage();
} catch (Exception e) {
throw (IOException) new IOException().initCause(e);
}
}
return true;
}
public void testFailAbort() throws IOException {
JobConf job = new JobConf();
job.set(FileSystem.FS_DEFAULT_NAME_KEY, "faildel:///");
job.setClass("fs.faildel.impl", FakeFileSystem.class, FileSystem.class);
setConfForFileOutputCommitter(job);
JobContext jContext = new JobContextImpl(job, taskID.getJobID());
TaskAttemptContext tContext = new TaskAttemptContextImpl(job, taskID);
FileOutputCommitter committer = new FileOutputCommitter();
FileOutputFormat.setWorkOutputPath(job, committer.getTempTaskOutputPath(tContext));
// do setup
committer.setupJob(jContext);
committer.setupTask(tContext);
String file = "test.txt";
// A reporter that does nothing
Reporter reporter = Reporter.NULL;
// write output
FileSystem localFs = new FakeFileSystem();
TextOutputFormat theOutputFormat = new TextOutputFormat();
RecordWriter theRecordWriter = theOutputFormat.getRecordWriter(localFs, job, file, reporter);
writeOutput(theRecordWriter, reporter);
// do abort
Throwable th = null;
try {
committer.abortTask(tContext);
} catch (IOException ie) {
th = ie;
}
assertNotNull(th);
assertTrue(th instanceof IOException);
assertTrue(th.getMessage().contains("fake delete failed"));
File jobTmpDir = new File(new Path(outDir, FileOutputCommitter.TEMP_DIR_NAME).toString());
File taskTmpDir = new File(jobTmpDir, "_" + taskID);
File expectedFile = new File(taskTmpDir, file);
assertTrue(expectedFile + " does not exists", expectedFile.exists());
th = null;
try {
committer.abortJob(jContext, JobStatus.State.FAILED);
} catch (IOException ie) {
th = ie;
}
assertNotNull(th);
assertTrue(th instanceof IOException);
assertTrue(th.getMessage().contains("fake delete failed"));
assertTrue("job temp dir does not exists", jobTmpDir.exists());
}
private static void runIOTest(Class<? extends Mapper> mapperClass, Path outputDir)
throws IOException {
JobConf job = new JobConf(fsConfig, DFSCIOTest.class);
FileInputFormat.setInputPaths(job, CONTROL_DIR);
job.setInputFormat(SequenceFileInputFormat.class);
job.setMapperClass(mapperClass);
job.setReducerClass(AccumulatingReducer.class);
FileOutputFormat.setOutputPath(job, outputDir);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setNumReduceTasks(1);
JobClient.runJob(job);
}
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(HadoopNBFilter.class);
job.setJobName("hadoopnbfilter");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(Integer.parseInt(args[2]));
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean jobCompleted = job.waitForCompletion(true);
return jobCompleted ? 0 : 1;
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(Add1.class);
conf.setJobName("sumar1");
conf.setOutputKeyClass(IntWritable.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
// Main function
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
JobConf conf = new JobConf(ProcessUnits.class);
conf.setJobName("max_eletricityunits");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(EE_Mapper.class);
conf.setCombinerClass(EE_Reducer.class);
conf.setReducerClass(EE_Reducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void seekTest(FileSystem fs, boolean fastCheck) throws Exception {
fs.delete(READ_DIR, true);
JobConf job = new JobConf(conf, TestFileSystem.class);
job.setBoolean("fs.test.fastCheck", fastCheck);
FileInputFormat.setInputPaths(job, CONTROL_DIR);
job.setInputFormat(SequenceFileInputFormat.class);
job.setMapperClass(SeekMapper.class);
job.setReducerClass(LongSumReducer.class);
FileOutputFormat.setOutputPath(job, READ_DIR);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
job.setNumReduceTasks(1);
JobClient.runJob(job);
}
public int run(String[] args) throws Exception {
if (args.length < 4) {
System.out.println("ERROR: Please Enter args : input output type(text|seq) splitChar(9=\t)");
return JobClient.SUCCESS;
}
String input = args[0];
String output = args[1];
String type = args[2];
String splitChar = args[3];
JobConf config = new JobConf(getConf(), getClass());
config.set("user.split", splitChar);
config.setJobName("File Filter -" + System.currentTimeMillis());
config.setNumReduceTasks(10);
config.setReducerClass(IdentityReducer.class);
config.setMapperClass(FileTestMapper.class);
if ("text".equals(type)) {
config.setInputFormat(TextInputFormat.class);
TextInputFormat.addInputPath(config, new Path(input));
} else {
config.setInputFormat(SequenceFileInputFormat.class);
SequenceFileInputFormat.addInputPath(config, new Path(input));
}
config.setMapOutputKeyClass(Text.class);
config.setMapOutputValueClass(Text.class);
config.setOutputKeyClass(Text.class);
config.setOutputValueClass(Text.class);
// if output path exists then return
FileSystem fs = FileSystem.get(config);
Path outputPath = new Path(output);
FileOutputFormat.setOutputPath(config, outputPath);
if (!fs.exists(outputPath)) {
JobClient.runJob(config);
} else {
System.out.println("You has finished this job today ! " + outputPath);
}
return JobClient.SUCCESS;
}
public int run(String[] args) throws Exception {
Path tempDir = new Path("/user/akhfa/temp");
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(AuthorCounter.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, tempDir);
System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}
