List of usage examples for org.apache.hadoop.mapred JobConf setMapperClass
public void setMapperClass(Class<? extends Mapper> theClass)
From source file:edu.ubc.mirrors.holographs.mapreduce.Driver.java
License:Open Source License
public int run(String[] args) throws Exception { JobConf job = new JobConf(getConf()); job.setClassLoader(Driver.class.getClassLoader()); job.setInputFormat(SnapshotObjectsOfTypeInputFormat.class); job.setMapperClass(InvokeMethodMapper.class); job.setCombinerClass(TextCountSumReducer.class); job.setReducerClass(TextCountSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.set("snapshotPath", args[0]); job.set("targetClassName", "org.eclipse.cdt.internal.core.dom.parser.cpp.CPPASTName"); job.setInt("splitSize", 10000); job.setInt("maxNumObjects", 100000); FileInputFormat.addInputPath(job, new Path(args[0])); String outputPath = args[1];/*from w w w . j av a2 s . c o m*/ int suffix = 2; while (new File(outputPath).exists()) { outputPath = args[1] + suffix++; } FileOutputFormat.setOutputPath(job, new Path(outputPath)); JobClient.runJob(job); return 0; }
From source file:edu.uci.ics.hyracks.imru.util.DataBalancer.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(DataBalancer.class); job.setJobName(DataBalancer.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setReducerClass(ReduceRecordOnly.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(Integer.parseInt(args[2])); if (args.length > 3) { if (args[3].startsWith("bzip")) FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class); if (args[3].startsWith("gz")) FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class); }/*from w w w . j a va 2s . c o m*/ JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.core.util.DataGenerator.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(DataGenerator.class); FileSystem dfs = FileSystem.get(job); String maxFile = "/maxtemp"; dfs.delete(new Path(maxFile), true); job.setJobName(DataGenerator.class.getSimpleName() + "max ID"); job.setMapperClass(MapMaxId.class); job.setCombinerClass(CombineMaxId.class); job.setReducerClass(ReduceMaxId.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(VLongWritable.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(maxFile)); job.setNumReduceTasks(1);/*from w w w . j ava2 s . co m*/ JobClient.runJob(job); job = new JobConf(DataGenerator.class); job.set("hyracks.maxid.file", maxFile); job.setInt("hyracks.x", Integer.parseInt(args[2])); dfs.delete(new Path(args[1]), true); job.setJobName(DataGenerator.class.getSimpleName()); job.setMapperClass(MapRecordGen.class); job.setReducerClass(ReduceRecordGen.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(Integer.parseInt(args[3])); if (args.length > 4) { if (args[4].startsWith("bzip")) FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class); if (args[4].startsWith("gz")) FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class); } JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.CommonSource.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(GraphPreProcessor.class); job.setJobName(GraphPreProcessor.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setReducerClass(ReduceRecordOnly.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setInputFormat(TextInputFormat.class); for (int i = 0; i < args.length - 2; i++) { FileInputFormat.addInputPath(job, new Path(args[i])); }//from www.j a va 2s. c o m FileOutputFormat.setOutputPath(job, new Path(args[args.length - 2])); job.setNumReduceTasks(Integer.parseInt(args[args.length - 1])); JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.DuplicateGraph.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(DuplicateGraph.class); job.setJobName(DuplicateGraph.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); job.setOutputFormat(TextOutputFormat.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(0);/*from w ww . j a v a2 s . c o m*/ JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.FilterCount.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(GraphPreProcessor.class); job.setJobName(FilterCount.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); job.setInputFormat(TextInputFormat.class); for (int i = 0; i < args.length - 1; i++) { FileInputFormat.addInputPath(job, new Path(args[i])); }/*from w ww .j a va2 s . c o m*/ FileOutputFormat.setOutputPath(job, new Path(args[args.length - 1])); job.setNumReduceTasks(0); JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.FindLargest.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(GraphPreProcessor.class); job.setJobName(GraphPreProcessor.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setReducerClass(ReduceRecordOnly.class); job.setCombinerClass(ReduceRecordOnly.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setInputFormat(TextInputFormat.class); for (int i = 0; i < args.length - 2; i++) { FileInputFormat.addInputPath(job, new Path(args[i])); }//from w w w .j av a 2s . c o m FileOutputFormat.setOutputPath(job, new Path(args[args.length - 2])); job.setNumReduceTasks(Integer.parseInt(args[args.length - 1])); JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.GraphPreProcessor.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(GraphPreProcessor.class); job.setJobName(GraphPreProcessor.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(0);/*from www .j av a2s. c o m*/ JobClient.runJob(job); }
From source file:edu.uci.ics.pregelix.example.utils.VertexAggregator.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(VertexAggregator.class); job.setJobName(VertexAggregator.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setCombinerClass(CombineRecordOnly.class); job.setReducerClass(ReduceRecordOnly.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(LongWritable.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(Integer.parseInt(args[2])); JobClient.runJob(job);//from w w w . j a v a 2s . c om }
From source file:edu.uci.ics.pregelix.example.utils.VertexSorter.java
License:Apache License
public static void main(String[] args) throws IOException { JobConf job = new JobConf(VertexSorter.class); job.setJobName(VertexSorter.class.getSimpleName()); job.setMapperClass(MapRecordOnly.class); job.setReducerClass(ReduceRecordOnly.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setInputFormat(TextInputFormat.class); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(Integer.parseInt(args[2])); JobClient.runJob(job);/*from w w w . j a va 2s. c o m*/ }