List of usage examples for org.apache.hadoop.mapreduce Job setOutputValueClass
public void setOutputValueClass(Class<?> theClass) throws IllegalStateException
From source file:com.hhscyber.nl.tweets.hbase2.Hbase2.java
@Override public int run(String[] args) throws Exception { Job client = new Job(getConf(), "hbasetest"); client.setSpeculativeExecution(false); client.setMaxMapAttempts(2);// w w w . j a va 2 s. c o m client.setJarByClass(Hbase2.class); client.setOutputKeyClass(Text.class); client.setOutputValueClass(Text.class); client.setInputFormatClass(TextInputFormat.class); TextInputFormat.addInputPath(client, new Path("input/1441737001"));//test one folder TextOutputFormat.setOutputPath(client, new Path("output4")); client.setMapperClass(Hbase2Mapper.class); client.setReducerClass(Hbase2Reducer.class); try { client.waitForCompletion(true); } catch (IOException | InterruptedException | ClassNotFoundException e) { System.out.println(e); } return 0; }
From source file:com.hhscyber.nl.tweets.hbasefill.HbaseFill.java
/** * @param args the command line arguments * @throws java.io.IOException//from w w w .ja v a 2s .c o m */ public static void main(String[] args) throws IOException { conHbase = HBaseConfiguration.create(); Job client = new Job(conHbase); // new configuration client.setJarByClass(HbaseFill.class); client.setOutputKeyClass(Text.class); client.setOutputValueClass(IntWritable.class); client.setInputFormatClass(TextInputFormat.class); TextInputFormat.addInputPath(client, new Path("input/" + test));//test one folder TextOutputFormat.setOutputPath(client, new Path("output3")); client.setMapperClass(HbaseFillMapper.class); try { client.submit(); } catch (IOException | InterruptedException | ClassNotFoundException e) { e.printStackTrace(); } }
From source file:com.hhscyber.nl.tweets.processtweets.ProcessTweets.java
/** * @param args the command line arguments *///from w w w. j a v a 2 s .c o m public static void main(String[] args) throws IOException { Job client = new Job(new Configuration()); client.setJarByClass(ProcessTweets.class); client.setOutputKeyClass(Text.class); client.setOutputValueClass(IntWritable.class); client.setInputFormatClass(TextInputFormat.class); TextInputFormat.addInputPath(client, new Path("input_concat"));// TextOutputFormat.setOutputPath(client, new Path("output2")); client.setMapperClass(ProcessTweetsMapper.class); client.setReducerClass(ProcessTweetsReducer.class); client.setCombinerClass(ProcessTweetsReducer.class); try { client.submit(); } catch (Exception e) { e.printStackTrace(); } }
From source file:com.hn.cluster.hadoop.mrs.SecondarySort.java
License:Apache License
public static void main(String[] args) throws Exception { // ?hadoop?// w w w .j a v a2 s. c o m Configuration conf = new Configuration(); // ? Job job = new Job(conf, "secondary sort"); job.setJarByClass(SecondarySort.class); // Mapper job.setMapperClass(MapClass.class); // Reducer job.setReducerClass(Reduce.class); // job.setPartitionerClass(FirstPartitioner.class); // job.setGroupingComparatorClass(FirstGroupingComparator.class); // map Key job.setMapOutputKeyClass(IntPair.class); // mapValue job.setMapOutputValueClass(IntWritable.class); // rduceKeyTextOutputFormatClassTextOutputFormat job.setOutputKeyClass(Text.class); // rduceValue job.setOutputValueClass(IntWritable.class); /** * ?????splites???RecordReder * ??RecordReder?keyvalue * Map<LongWritable, Text> * Mapmap<LongWritable, Text>Mapmap * ?List<IntPair, IntWritable> * map?job.setPartitionerClassList?reducer */ job.setInputFormatClass(TextInputFormat.class); // ??RecordWriter? job.setOutputFormatClass(TextOutputFormat.class); // hdfs FileInputFormat.addInputPath(job, new Path("hdfs://192.1168.1.12:9000/input/input/soso.txt")); // hdfs FileOutputFormat.setOutputPath(job, new Path("hdfs://192.1168.1.12:9000/output/sort/")); // ??job System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.hortonworks.mapreduce.URLCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = this.getConf(); conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", " "); Job job = Job.getInstance(conf, "URLCount"); job.setJarByClass(getClass());// ww w .j av a 2 s . com job.setInputFormatClass(KeyValueTextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(URLCountM.class); job.setReducerClass(URLCountR.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); return (job.waitForCompletion(true) == true ? 0 : -1); }
From source file:com.howbuy.hadoop.mr.online.SecondarySort.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: secondarysrot <in> <out>"); System.exit(2);/*from w w w . jav a2s . c om*/ } Job job = new Job(conf, "secondary sort"); job.setJarByClass(SecondarySort.class); job.setMapperClass(MapClass.class); job.setReducerClass(Reduce.class); // group and partition by the first int in the pair job.setPartitionerClass(FirstPartitioner.class); job.setGroupingComparatorClass(FirstGroupingComparator.class); // the map output is IntPair, IntWritable job.setMapOutputKeyClass(IntPair.class); job.setMapOutputValueClass(IntWritable.class); // the reduce output is Text, IntWritable job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(TextInputFormat.class); // job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setNumReduceTasks(3); 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.huihui.mr.WordCount.java
License:Apache License
public static void main(String[] args) throws Exception { /*HadoopJava.util.Properties??Apache Jakarta Commons Configuration?? * ????API?org.apache.hadoop.conf.Configuration??? *///from ww w .j av a 2 s . com Configuration conf = new Configuration(); /* * ?HadoopGenericOptionsParser ??? -D mapreduce.job.queuename ??getRemainingArgs()? ?"xrli/STJoin_in","xrli/STJoin_out"?otherArgs ? fs jt libjars files archives D tokenCacheFile */ String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2); } conf.set("fs.defaultFS", "hdfs://localhost:9000"); // Job job = new Job(conf, "word count"); job.setJarByClass(WordCount.class); //??? job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); //Path ???URI?Path???Path String input = "hdfs://localhost:9000/input/"; String output = "hdfs://localhost:9000/user/hdfs/log_kpi/browser1"; FileInputFormat.addInputPath(job, new Path(input)); FileOutputFormat.setOutputPath(job, new Path(output)); //???? System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.hzy.test.WordCount.java
License:Apache License
public static void main(String[] args) throws Exception { // String input = "hdfs://192.168.1.118:9000/user/hdfs/log_kpi/"; // String output = "hdfs://192.168.1.118:9000/user/hdfs/log_kpi/wc/"; String input = "/tmp/data.txt"; // String input = args[0]; String output = "/tmp/t1"; // String output = args[1]; Configuration conf = HdfsDAO.config(); // conf.set("mapreduce.framework.name", "yarn"); //// conf.set("hbase.zookeeper.quorum", "hadoop01:2181"); // conf.set("fs.default.name", "hdfs://hadoop01:9000"); // conf.set("yarn.resourcemanager.resource-tracker.address", "hadoop01:8031"); // conf.set("yarn.resourcemanager.address", "hadoop01:8032"); // conf.set("yarn.resourcemanager.scheduler.address", "hadoop01:8030"); // conf.set("yarn.resourcemanager.admin.address", "hadoop01:8033"); // conf.set("mapreduce.jobhistory.address", "hadoop01:10020"); // conf.set("mapreduce.jobhistory.webapp.address", "hadoop01:19888"); // String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); // if (otherArgs.length < 2) { // System.err.println("Usage: wordcount <in> [<in>...] <out>"); // System.exit(2); // }// w w w . j a v a2s .c o m Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // for (int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(input)); // } FileOutputFormat.setOutputPath(job, new Path(output)); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.ifeng.hadoop.thinker.LogDriver.java
License:Apache License
@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; }/*from w w w . j a v a 2 s . com*/ Job job = Job.getInstance(super.getConf()); job.setJarByClass(getClass()); FileUtil.fullyDelete(new File(args[1])); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(LogMapper.class); job.setReducerClass(LogReducer.class); job.setCombinerClass(LogReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.ifeng.hadoop.thinker.LogLocalDriver.java
License:Apache License
@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; }/* w w w. j a v a 2 s . c om*/ Job job = Job.getInstance(super.getConf()); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(LogMapper.class); job.setReducerClass(LogReducer.class); job.setCombinerClass(LogReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); return job.waitForCompletion(true) ? 0 : 1; }