List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException
From source file:com.jhkt.playgroundArena.hadoop.tasks.jobs.BloomFilterJob.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = getConf(); Job job = new Job(conf, BloomFilterJob.class.getSimpleName()); job.setJarByClass(BloomFilterJob.class); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setJobName("Sample BloomFilter Job"); job.setMapperClass(BloomFilterMapper.class); job.setReducerClass(BloomFilterReducer.class); job.setNumReduceTasks(1);//from w w w . ja va 2 s. c o m job.setInputFormatClass(TextInputFormat.class); /* * We want our reducer to output the final BloomFilter as a binary file. I think * Hadoop doesn't have this format [check later], so using NullOutpuFormat.class. * * In general life gets a little more dangerous when you deviate from MapReduce's input/output * framework and start working with your own files. Your tasks are no longer guaranteed to be idempotent * and you'll need to understand how various failure scenarios can affect your tasks. For example, your files * may only be partially written when some tasks are restarted. Our example here is safe(r) because all the file * operations take place together only once in the close() method and in only one reducer. A more * careful/paranoid implementation would check each individual file operation more closely. */ job.setOutputFormatClass(NullOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(BloomFilter.class); System.exit(job.waitForCompletion(true) ? 0 : 1); return 0; }
From source file:com.jhkt.playgroundArena.hadoop.tasks.jobs.ChainJob.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = getConf(); Job job = new Job(conf, ChainJob.class.getSimpleName()); job.setJobName("Sample Chain Job"); job.setJarByClass(ChainJob.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); ChainMapper.addMapper(job, ReverseMapper.class, Text.class, Text.class, Text.class, Text.class, new Configuration(false)); ChainMapper.addMapper(job, AverageMapper.class, Text.class, Text.class, Text.class, AverageWritable.class, new Configuration(false)); ChainReducer.setReducer(job, AverageReducer.class, Text.class, AverageWritable.class, Text.class, DoubleWritable.class, new Configuration(false)); System.exit(job.waitForCompletion(true) ? 0 : 1); return 0;/*from w ww . j av a 2 s. c o m*/ }
From source file:com.jhkt.playgroundArena.hadoop.tasks.jobs.CountJob.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = getConf(); Job job = new Job(conf, CountJob.class.getSimpleName()); job.setJarByClass(CountJob.class); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setJobName("Sample Count Job"); job.setMapperClass(CountMapper.class); job.setReducerClass(CountReducer.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(IntWritable.class); System.exit(job.waitForCompletion(true) ? 0 : 1); return 0;// w ww. j a va2 s . c o m }
From source file:com.jhkt.playgroundArena.hadoop.tasks.jobs.DistributedCacheJob.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = getConf(); Job job = new Job(conf, DistributedCacheJob.class.getSimpleName()); job.setJarByClass(DistributedCacheJob.class); /*//from w w w . j a v a 2s . com * The following will disseminate the file to all the nodes and the file defaults to HDFS. * The second and third arguments denote the input and output paths of the standard Hadoop * job. Note that we've limited the number of data sources to two. This is not an inherent * limitation of the technique, but a simplification that makes our code easier to follow. */ //job.addCacheFile(new Path(args[0]).toUri()); Path in = new Path(args[1]); Path out = new Path(args[2]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setJobName("Sample DistributedCache Job"); job.setMapperClass(DistributedCacheMapper.class); /* * Took out the Reduce class as the plan is performing the joining in the map phase and will * configure the job to have no reduce. */ job.setNumReduceTasks(0); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); System.exit(job.waitForCompletion(true) ? 0 : 1); return 0; }
From source file:com.jumptap.h2redis.RedisDriver.java
License:Open Source License
@Override public int run(String[] args) throws Exception { if (args.length < 5) { usage();// ww w .ja v a2 s . co m return 1; } Map<String, String> argMap = new HashMap<String, String>(); String[] kv; for (String arg : args) { kv = arg.split("="); if (kv.length != 2) { usage(); return 1; } argMap.put(kv[0].trim(), kv[1]); } Configuration conf = getConf(); String[] hostPort = argMap.get(REDIS_CMD).split(":"); conf.set(REDIS_HOST, hostPort[0].trim()); conf.setInt(REDIS_PORT, Integer.valueOf(hostPort[1].trim())); conf.setInt(REDIS_KEY_FIELD, Integer.valueOf(argMap.get(KEY_CMD).trim())); conf.setInt(REDIS_HASHKEY_FIELD, Integer.valueOf(argMap.get(HASH_KEY_CMD).trim())); conf.setInt(REDIS_HASHVAL_FIELD, Integer.valueOf(argMap.get(HASH_VAL_CMD).trim())); if (argMap.containsKey(REDIS_DB_CMD)) { conf.set(REDIS_DB, argMap.get(REDIS_DB_CMD).trim()); } if (argMap.containsKey(REDIS_PW_CMD)) { conf.set(REDIS_PW, argMap.get(REDIS_PW_CMD).trim()); } if (argMap.containsKey(KEY_PFX_CMD)) { conf.set(REDIS_KEY_PREFIX, argMap.get(KEY_PFX_CMD).trim()); } if (argMap.containsKey(HASH_KEY_PFX_CMD)) { conf.set(REDIS_HASHKEY_PREFIX, argMap.get(HASH_KEY_PFX_CMD).trim()); } if (argMap.containsKey(KEY_PFX_DELIM_CMD)) { conf.set(REDIS_KEY_PREFIX_DELIM, argMap.get(KEY_PFX_DELIM_CMD).trim()); } if (argMap.containsKey(KEY_FILTER_CMD)) { conf.setPattern(REDIS_KEY_FILTER, Pattern.compile(argMap.get(KEY_FILTER_CMD).trim())); } if (argMap.containsKey(HASH_FILTER_CMD)) { conf.setPattern(REDIS_HASH_FILTER, Pattern.compile(argMap.get(HASH_FILTER_CMD).trim())); } if (argMap.containsKey(VAL_FILTER_CMD)) { conf.setPattern(REDIS_VAL_FILTER, Pattern.compile(argMap.get(VAL_FILTER_CMD).trim())); } if (argMap.containsKey(VAL_FILTER_CMD)) { conf.setPattern(REDIS_VAL_FILTER, Pattern.compile(argMap.get(VAL_FILTER_CMD).trim())); } if (argMap.containsKey(TTL_CMD)) { conf.setInt(REDIS_KEY_TTL, Integer.valueOf(argMap.get(TTL_CMD).trim())); } if (argMap.containsKey(TS_KEY_CMD)) { conf.set(REDIS_KEY_TS, argMap.get(TS_KEY_CMD).trim()); } else { conf.set(REDIS_KEY_TS, "redis.lastupdate"); } Job job = new Job(conf, "RedisDriver"); FileInputFormat.addInputPath(job, new Path(argMap.get(INPUT_CMD))); job.setJarByClass(RedisDriver.class); job.setMapperClass(RedisOutputMapper.class); job.setNumReduceTasks(0); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(RedisOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.juniarto.secondsorter.SsJob.java
public int run(String[] allArgs) throws Exception { Configuration conf = getConf(); Job job = new Job(conf, "secondary sort"); job.setJarByClass(SsJob.class); job.setPartitionerClass(NaturalKeyPartitioner.class); job.setGroupingComparatorClass(NaturalKeyGroupingComparator.class); job.setSortComparatorClass(CompositeKeyComparator.class); job.setMapOutputKeyClass(TextDsi.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(SsMapper.class); job.setReducerClass(SsReducer.class); job.setNumReduceTasks(2);//from www .j a v a 2 s . co m String[] args = new GenericOptionsParser(getConf(), allArgs).getRemainingArgs(); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); //job.submit(); long time1 = System.nanoTime(); boolean status = job.waitForCompletion(true); long time2 = System.nanoTime(); long timeSpent = time2 - time1; LOG.info("TIME: " + timeSpent); return 0; }
From source file:com.kangfoo.study.hadoop1.mp.typeformat.TestMapreduceSequenceInputFormat.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: TestMapreduceSequenceInputFormat <in> <out>"); System.exit(2);/* ww w .j ava 2s .c om*/ } Job job = new Job(conf, "TestMapreduceSequenceInputFormat"); job.setJarByClass(TestMapreduceSequenceInputFormat.class);//? job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(SequenceFileInputFormat.class); // SequenceFileInputFormat FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.kasabi.labs.freebase.mr.Freebase2RDFDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (log.isDebugEnabled()) { log.debug("run({})", Utils.toString(args)); }//from www . j av a 2 s . c o m if (args.length != 2) { System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName()); ToolRunner.printGenericCommandUsage(System.err); return -1; } Configuration configuration = getConf(); boolean useCompression = configuration.getBoolean(Constants.OPTION_USE_COMPRESSION, Constants.OPTION_USE_COMPRESSION_DEFAULT); if (useCompression) { configuration.setBoolean("mapred.compress.map.output", true); configuration.set("mapred.output.compression.type", "BLOCK"); configuration.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec"); } boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERRIDE_OUTPUT, Constants.OPTION_OVERRIDE_OUTPUT_DEFAULT); FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { fs.delete(new Path(args[1]), true); } Job job = new Job(configuration); job.setJobName("Freebase2RDFDriver"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(Freebase2RDFMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setReducerClass(Freebase2RDFReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); Utils.setReducers(job, configuration, log); job.setOutputFormatClass(TextOutputFormat.class); if (log.isDebugEnabled()) Utils.log(job, log); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.knewton.mapreduce.example.SSTableMRExample.java
License:Apache License
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException, URISyntaxException, ParseException { long startTime = System.currentTimeMillis(); Options options = buildOptions();//from w w w. j a va 2 s .c o m CommandLineParser cliParser = new BasicParser(); CommandLine cli = cliParser.parse(options, args); if (cli.getArgs().length < 2 || cli.hasOption('h')) { printUsage(options); } Job job = getJobConf(cli); job.setJarByClass(SSTableMRExample.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(StudentEventWritable.class); job.setMapperClass(StudentEventMapper.class); job.setReducerClass(StudentEventReducer.class); job.setInputFormatClass(SSTableColumnInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // input arg String inputPaths = cli.getArgs()[0]; LOG.info("Setting initial input paths to {}", inputPaths); SSTableInputFormat.addInputPaths(job, inputPaths); // output arg FileOutputFormat.setOutputPath(job, new Path(cli.getArgs()[1])); if (cli.hasOption('c')) { LOG.info("Using compression for output."); FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class); FileOutputFormat.setCompressOutput(job, true); } job.waitForCompletion(true); LOG.info("Total runtime: {}s", (System.currentTimeMillis() - startTime) / 1000); }
From source file:com.knewton.mrtool.example.JsonMRExample.java
License:Apache License
/** * /*from ww w. ja va2 s. c om*/ * @param args * @throws IOException * @throws ClassNotFoundException * @throws InterruptedException */ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Job job = new Job(new Configuration()); job.setInputFormatClass(RecommendationsInputFormat.class); RecommendationsInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(RecommendationWritable.class); job.waitForCompletion(true); }