List of usage examples for org.apache.hadoop.mapreduce Job setJarByClass
public void setJarByClass(Class<?> cls)
From source file:com.alectenharmsel.research.hadoop.CodeTokenizer.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MoabLicenses <input> <output>"); System.exit(-1);/* www . j av a 2s. co m*/ } Configuration conf = getConf(); Job job = new Job(conf, "SrcTok"); job.setJarByClass(CodeTokenizer.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(LongWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:com.alectenharmsel.research.hadoop.FileCombine.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: FileCombine <input> <output>"); System.exit(-1);//from ww w . j a va 2 s .c o m } Job job = new Job(getConf(), "FileCombine"); job.setJarByClass(FileCombine.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.alectenharmsel.research.hadoop.LcCounters.java
License:Apache License
public static void main(String[] args) throws Exception { GenericOptionsParser parse = new GenericOptionsParser(new Configuration(), args); Configuration conf = parse.getConfiguration(); String[] remainingArgs = parse.getRemainingArgs(); if (remainingArgs.length != 2) { System.err.println("Usage: LineCount <input> <output>"); System.exit(-1);/* ww w . ja v a2 s . c o m*/ } Job job = Job.getInstance(conf, "LineCount"); job.setJarByClass(LineCount.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.addInputPath(job, new Path(remainingArgs[0])); FileOutputFormat.setOutputPath(job, new Path(remainingArgs[1])); boolean success = job.waitForCompletion(true); //Get the counter here and print it Counters counters = job.getCounters(); long total = counters.findCounter(LcCounters.NUM_LINES).getValue(); System.out.println(Long.toString(total)); int res = success ? 0 : 1; System.exit(res); }
From source file:com.alectenharmsel.research.hadoop.MoabLicenseInfo.java
License:Apache License
public static void main(String[] args) throws Exception { GenericOptionsParser parser = new GenericOptionsParser(new Configuration(), args); Configuration conf = parser.getConfiguration(); conf.set("mapreduce.output.textoutputformat.separator", ","); String[] remainingArgs = parser.getRemainingArgs(); if (remainingArgs.length != 2) { System.err.println("Usage: LineCount <input> <output>"); System.exit(-1);/* w ww.j av a 2s . c om*/ } Job job = Job.getInstance(conf, "MoabLicenseInfo"); job.setJarByClass(MoabLicenseInfo.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(remainingArgs[0])); FileOutputFormat.setOutputPath(job, new Path(remainingArgs[1])); int res = job.waitForCompletion(true) ? 0 : 1; System.exit(res); }
From source file:com.alectenharmsel.research.LcCounters.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: LineCounter <input> <output>"); System.exit(-1);//from www.j a va 2 s . c o m } Job job = new Job(getConf(), "LineCount"); job.setJarByClass(LineCount.class); job.setInputFormatClass(WholeBlockInputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(LineCountMapper.class); job.setReducerClass(LineCountReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); Configuration check = job.getConfiguration(); boolean success = job.waitForCompletion(true); //Get the counter here, output to a file called total in the dir Counters counters = job.getCounters(); //Throw it in the file Path outPath = new Path(args[1]); FileSystem fs = outPath.getFileSystem(check); OutputStream out = fs.create(new Path(outPath, "total")); String total = counters.findCounter(LcCounters.NUM_LINES).getValue() + "\n"; out.write(total.getBytes()); out.close(); return success ? 0 : 1; }
From source file:com.alectenharmsel.research.MoabLicenses.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MoabLicenses <input> <output>"); System.exit(-1);/* ww w . j a va 2 s . c om*/ } Configuration conf = getConf(); Job job = new Job(conf, "MoabLicenses"); job.setJarByClass(MoabLicenses.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(MoabLicensesMapper.class); job.setReducerClass(MoabLicensesReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); Configuration check = job.getConfiguration(); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:com.alectenharmsel.research.MoabLogSearch.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MoabLogSearch <input> <output>"); System.exit(-1);/*from ww w.j a v a 2 s . c o m*/ } Job job = new Job(getConf(), "MoabLogSearch"); job.setJarByClass(MoabLogSearch.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(MoabLogSearchMapper.class); job.setReducerClass(MoabLogSearchReducer.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); Configuration check = job.getConfiguration(); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:com.alectenharmsel.research.SrcTok.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MoabLicenses <input> <output>"); System.exit(-1);// w w w . ja va2 s . c o m } Configuration conf = getConf(); Job job = new Job(conf, "SrcTok"); job.setJarByClass(SrcTok.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(SrcTokMapper.class); job.setReducerClass(SrcTokReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(LongWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:com.alexholmes.hadooputils.combine.seqfile.mapreduce.CombineSequenceFileJob.java
License:Apache License
/** * The driver for the MapReduce job./*from w w w.ja v a2 s .c o m*/ * * @param conf configuration * @param inputDirAsString input directory in CSV-form * @param outputDirAsString output directory * @return true if the job completed successfully * @throws java.io.IOException if something went wrong * @throws java.net.URISyntaxException if a URI wasn't correctly formed */ public boolean runJob(final Configuration conf, final String inputDirAsString, final String outputDirAsString) throws IOException, URISyntaxException, ClassNotFoundException, InterruptedException { Job job = new Job(conf); job.setJarByClass(CombineSequenceFileJob.class); job.setJobName("seqfilecombiner"); job.setNumReduceTasks(0); // job.setMapperClass(IdentityMapper.class); job.setInputFormatClass(CombineSequenceFileInputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); FileInputFormat.setInputPaths(job, inputDirAsString); FileOutputFormat.setOutputPath(job, new Path(outputDirAsString)); Date startTime = new Date(); System.out.println("Job started: " + startTime); boolean jobResult = job.waitForCompletion(true); Date endTime = new Date(); System.out.println("Job ended: " + endTime); System.out.println("The job took " + TimeUnit.MILLISECONDS.toSeconds(endTime.getTime() - startTime.getTime()) + " seconds."); return jobResult; }
From source file:com.alexholmes.json.mapreduce.ExampleJob.java
License:Apache License
/** * The MapReduce driver - setup and launch the job. * * @param args the command-line arguments * @return the process exit code/*from w w w . jav a 2 s. c o m*/ * @throws Exception if something goes wrong */ public int run(final String[] args) throws Exception { String input = args[0]; String output = args[1]; Configuration conf = super.getConf(); writeInput(conf, new Path(input)); Job job = new Job(conf); job.setJarByClass(ExampleJob.class); job.setMapperClass(Map.class); job.setNumReduceTasks(0); Path outputPath = new Path(output); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, outputPath); // use the JSON input format job.setInputFormatClass(MultiLineJsonInputFormat.class); // specify the JSON attribute name which is used to determine which // JSON elements are supplied to the mapper MultiLineJsonInputFormat.setInputJsonMember(job, "colorName"); if (job.waitForCompletion(true)) { return 0; } return 1; }