Package org.apache.hadoop.mapreduce

Examples of org.apache.hadoop.mapreduce.Job

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
        conf.set("mapred.output.compression.type", "BLOCK");
        conf.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
        conf.set(SetJoinMapper.INPUTS+".1", Joiner.on(",").join(o.left));
        conf.set(SetJoinMapper.INPUTS+".2", Joiner.on(",").join(o.right));

        Job job=new Job(conf,"diffFacts");
        job.setJarByClass(this.getClass());
        job.setMapperClass(TextSimpleJoinMapper.class);
        job.setReducerClass(DiffFactReducer.class);
        job.setGroupingComparatorClass(TaggedTextKeyGroupComparator.class);
        job.setPartitionerClass(TaggedKeyPartitioner.class);

        if(o.reducerCount<1) {
            o.reducerCount=1;
        }

        job.setNumReduceTasks(o.reducerCount);

        job.setMapOutputKeyClass(TaggedTextItem.class);
        job.setMapOutputValueClass(VIntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        for(String path: Iterables.concat(o.left, o.right)) {
            FileInputFormat.addInputPath(job, new Path(path));
        }

        FileOutputFormat.setOutputPath(job, new Path(o.output));
        FileOutputFormat.setCompressOutput(job, true);
        FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        return job.waitForCompletion(true) ? 0 : 1;
    }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
            conf.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
            conf.set(SetJoinMapper.INPUTS+".1",inputA);
            for(String path:paths)
                conf.set(SetJoinMapper.INPUTS+".2",path);

            Job job=new Job(conf,"fetchTriplesWithMatchingObjects");
            job.setJarByClass(this.getClass());
            job.setMapperClass(FetchTriplesWithMatchingObjectsMapper.class);
            job.setReducerClass(AcceptWithMatchingKeyReducer.class);
            job.setGroupingComparatorClass(TaggedTextKeyGroupComparator.class);
            job.setPartitionerClass(TaggedKeyPartitioner.class);

            if(reduceTasks==null) {
                reduceTasks=1;    // about right for AWS runs
            }

            job.setNumReduceTasks(reduceTasks);

            job.setMapOutputKeyClass(TaggedTextItem.class);
            job.setMapOutputValueClass(TaggedTextItem.class);
            job.setOutputKeyClass(NullWritable.class);
            job.setOutputValueClass(Text.class);


            FileInputFormat.addInputPath(job, new Path(inputA));
            for(String path:paths)
                FileInputFormat.addInputPath(job, new Path(path));

            FileOutputFormat.setOutputPath(job, new Path(output));
            FileOutputFormat.setCompressOutput(job, true);
            FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
            job.setOutputFormatClass(TextOutputFormat.class);

            return job.waitForCompletion(true) ? 0 : 1;
        } catch(Main.IncorrectUsageException iue) {
            return 2;
        }
    }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
            conf.set("mapred.compress.map.output", "true");
            conf.set("mapred.output.compression.type", "BLOCK");
            conf.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");

            Job job=new Job(conf,getJobName());
            job.setSpeculativeExecution(false);
            job.setJarByClass(this.getClass());
            job.setMapperClass(getMapperClass());
            job.setReducerClass(Uniq.class);

            if(reduceTasks==null) {
                reduceTasks=29;    // about right for AWS runs
            }

            job.setNumReduceTasks(reduceTasks);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(LongWritable.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(LongWritable.class);

            for(String input:paths) {
                FileInputFormat.addInputPath(job, new Path(input));
            }

            FileOutputFormat.setOutputPath(job, new Path(output));
            FileOutputFormat.setCompressOutput(job, true);
            FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

            // Gotcha -- this has to run before the definitions above associated with the output format because
            // this is going to be configured against the job as it stands a moment from now

            job.setOutputFormatClass(TextOutputFormat.class);

            return job.waitForCompletion(true) ? 0 : 1;
        } catch(Main.IncorrectUsageException iue) {
            return 2;
        }
    }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
            conf.set("mapred.output.compression.type", "BLOCK");
            conf.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
            conf.set(SetJoinMapper.INPUTS+".1",inputA);
            conf.set(SetJoinMapper.INPUTS+".2",inputB);

            Job job=new Job(conf,"setDifference");
            job.setJarByClass(this.getClass());
            job.setMapperClass(TextSimpleJoinMapper.class);
            job.setReducerClass(SetDifferenceReducer.class);
            job.setGroupingComparatorClass(TaggedTextKeyGroupComparator.class);
            job.setPartitionerClass(TaggedKeyPartitioner.class);

            if(reduceTasks==null) {
                reduceTasks=1;    // about right for AWS runs
            }

            job.setNumReduceTasks(reduceTasks);

            job.setMapOutputKeyClass(TaggedTextItem.class);
            job.setMapOutputValueClass(VIntWritable.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(NullWritable.class);


            FileInputFormat.addInputPath(job, new Path(inputA));
            FileInputFormat.addInputPath(job, new Path(inputB));

            FileOutputFormat.setOutputPath(job, new Path(output));
            FileOutputFormat.setCompressOutput(job, true);
            FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

            // Gotcha -- this has to run before the definitions above associated with the output format because
            // this is going to be configured against the job as it stands a moment from now

            job.setOutputFormatClass(TextOutputFormat.class);

            return job.waitForCompletion(true) ? 0 : 1;
        } catch(Main.IncorrectUsageException iue) {
            return 2;
        }
    }
View Full Code Here
221
222
223
224
225
226
227
228
    @Override
    protected int execute(String[] args) throws Exception {
        Configuration conf = getConf();
        conf.set(StageConstants.PROP_BATCH_ID, getBatchId());
        conf.set(StageConstants.PROP_FLOW_ID, getFlowId());
        Job job = createJob(conf);
        return submit(job);
    }
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
248
     */
    public Job createJob(Configuration conf) throws IOException, InterruptedException {
        if (conf == null) {
            throw new IllegalArgumentException("conf must not be null"); //$NON-NLS-1$
        }
        Job job = JobCompatibility.newJob(conf);
        VariableTable variables = getPathParser(job.getConfiguration());
        configureJobInfo(job, variables);
        configureStageInput(job, variables);
        configureStageOutput(job, variables);
        configureShuffle(job, variables);
        configureStageResource(job, variables);
View Full Code Here
59
60
61
62
63
64
65
     */
    public static Job newJob(Configuration conf) throws IOException {
        if (conf == null) {
            throw new IllegalArgumentException("conf must not be null"); //$NON-NLS-1$
        }
        return new Job(conf);
    }
View Full Code Here
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
        assert name != null;
        assert formatClass != null;
        assert keyClass != null;
        assert valueClass != null;
        assert counters != null;
        Job job = JobCompatibility.newJob(context.getConfiguration());
        job.setOutputFormatClass(formatClass);
        job.setOutputKeyClass(keyClass);
        job.setOutputValueClass(valueClass);
        TaskAttemptContext localContext = JobCompatibility.newTaskAttemptContext(
                job.getConfiguration(),
                context.getTaskAttemptID());
        if (FileOutputFormat.class.isAssignableFrom(formatClass)) {
            setOutputFilePrefix(localContext, name);
        }
        OutputFormat<?, ?> format = ReflectionUtils.newInstance(
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
                getNextDirectory()));
        storage.getFileSystem().delete(getNextDirectory(), true);
    }

    private void update() throws IOException, InterruptedException {
        Job job = JobCompatibility.newJob(getConf());
        job.setJobName("TGC-UPDATE-" + storage.getPatchDirectory());

        List<StageInput> inputList = new ArrayList<StageInput>();
        inputList.add(new StageInput(
                storage.getHeadContents("*").toString(),
                TemporaryInputFormat.class,
                BaseMapper.class));
        inputList.add(new StageInput(
                storage.getPatchContents("*").toString(),
                TemporaryInputFormat.class,
                PatchMapper.class));
        StageInputDriver.set(job, inputList);
        job.setInputFormatClass(StageInputFormat.class);
        job.setMapperClass(StageInputMapper.class);
        job.setMapOutputKeyClass(PatchApplyKey.class);
        job.setMapOutputValueClass(modelClass);

        // combiner may have no effect in normal cases
        job.setReducerClass(PatchApplyReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(modelClass);
        job.setPartitionerClass(PatchApplyKey.Partitioner.class);
        job.setSortComparatorClass(PatchApplyKey.SortComparator.class);
        job.setGroupingComparatorClass(PatchApplyKey.GroupComparator.class);

        TemporaryOutputFormat.setOutputPath(job, getNextDirectory());
        job.setOutputFormatClass(TemporaryOutputFormat.class);
        job.getConfiguration().setClass(
                "mapred.output.committer.class",
                LegacyBridgeOutputCommitter.class,
                org.apache.hadoop.mapred.OutputCommitter.class);

        LOG.info(MessageFormat.format("Applying patch: {0} / {1} -> {2}",
                storage.getPatchContents("*"),
                storage.getHeadContents("*"),
                getNextContents()));
        try {
            boolean succeed = job.waitForCompletion(true);
            LOG.info(MessageFormat.format("Applied patch: succeed={0}, {1} / {2} -> {3}",
                    succeed,
                    storage.getPatchContents("*"),
                    storage.getHeadContents("*"),
                    getNextContents()));
View Full Code Here
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
                false,
                storage.getConfiguration());
    }

    private void create() throws InterruptedException, IOException {
        Job job = JobCompatibility.newJob(getConf());
        job.setJobName("TGC-CREATE-" + storage.getPatchDirectory());

        List<StageInput> inputList = new ArrayList<StageInput>();
        inputList.add(new StageInput(
                storage.getPatchContents("*").toString(),
                TemporaryInputFormat.class,
                DeleteMapper.class));
        StageInputDriver.set(job, inputList);
        job.setInputFormatClass(StageInputFormat.class);
        job.setMapperClass(StageInputMapper.class);
        job.setMapOutputKeyClass(NullWritable.class);
        job.setMapOutputValueClass(modelClass);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(modelClass);

        TemporaryOutputFormat.setOutputPath(job, getNextDirectory());
        job.setOutputFormatClass(TemporaryOutputFormat.class);
        job.getConfiguration().setClass(
                "mapred.output.committer.class",
                LegacyBridgeOutputCommitter.class,
                org.apache.hadoop.mapred.OutputCommitter.class);

        job.setNumReduceTasks(0);

        LOG.info(MessageFormat.format("Applying patch: {0} / (empty) -> {2}",
                storage.getPatchContents("*"),
                storage.getHeadContents("*"),
                getNextContents()));
        try {
            boolean succeed = job.waitForCompletion(true);
            LOG.info(MessageFormat.format("Applied patch: succeed={0}, {1} / (empty) -> {3}",
                    succeed,
                    storage.getPatchContents("*"),
                    storage.getHeadContents("*"),
                    getNextContents()));
View Full Code Here
TOP

Related Classes of org.apache.hadoop.mapreduce.Job

  • bulkimport.BulkImportJobExample
  • co.cask.cdap.internal.app.runtime.batch.MapReduceRuntimeService
  • com.alimama.quanjingmonitor.kmeans.KMeansDriver
  • com.asakusafw.runtime.stage.AbstractStageClient
  • com.asakusafw.thundergate.runtime.cache.mapreduce.CacheBuildClient
  • com.datasalt.pangool.tuplemr.mapred.lib.output.PangoolMultipleOutputs
  • com.datasalt.pangool.tuplemr.mapred.lib.output.TestTupleTextInputOutputFormat
  • com.datasalt.pangool.tuplemr.mapred.TestRollup
  • com.datasalt.pangool.tuplemr.mapred.TestTupleMRJob
  • com.hadoop.compression.lzo.DistributedLzoIndexer
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.