Package eu.stratosphere.api.java.record.operators

Examples of eu.stratosphere.api.java.record.operators.FileDataSource

69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    int numSubtasksInput2 = (args.length > 4 ? Integer.parseInt(args[4]) : 1);

    // create DataSourceContract for Orders input
    @SuppressWarnings("unchecked")
    CsvInputFormat format1 = new CsvInputFormat('|', IntValue.class, IntValue.class);
    FileDataSource input1 = new FileDataSource(format1, input1Path, "Input 1");
   
    ReduceOperator aggInput1 = ReduceOperator.builder(DummyReduce.class, IntValue.class, 0)
      .input(input1)
      .name("AggOrders")
      .build();

   
    // create DataSourceContract for Orders input
    @SuppressWarnings("unchecked")
    CsvInputFormat format2 = new CsvInputFormat('|', IntValue.class, IntValue.class);
    FileDataSource input2 = new FileDataSource(format2, input2Path, "Input 2");
    input2.setDegreeOfParallelism(numSubtasksInput2);

    ReduceOperator aggInput2 = ReduceOperator.builder(DummyReduce.class, IntValue.class, 0)
      .input(input2)
      .name("AggLines")
      .build();
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
  @Override
  protected Plan getTestJob() {
    String input1Path = config.getString("UnionTest#Input1Path", "").equals("empty") ? emptyInPath : inPath;
    String input2Path = config.getString("UnionTest#Input2Path", "").equals("empty") ? emptyInPath : inPath;

    FileDataSource input1 = new FileDataSource(
      new ContractITCaseInputFormat(), input1Path);
    DelimitedInputFormat.configureDelimitedFormat(input1)
      .recordDelimiter('\n');
    input1.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));
   
    FileDataSource input2 = new FileDataSource(
        new ContractITCaseInputFormat(), input2Path);
    DelimitedInputFormat.configureDelimitedFormat(input2)
      .recordDelimiter('\n');
    input2.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));
   
    MapOperator testMapper = MapOperator.builder(new TestMapper()).build();
    testMapper.setDegreeOfParallelism(config.getInteger("UnionTest#NoSubtasks", 1));

    FileDataSink output = new FileDataSink(
View Full Code Here
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
   
    String lineitemsPath = (args.length > 5 ? args[5] : "");
    String output        = (args.length > 6 ? args[6] : "");

    // create DataSourceContract for Orders input
    FileDataSource orders1 = new FileDataSource(new CsvInputFormat(), orders1Path, "Orders 1");
    CsvInputFormat.configureRecordFormat(orders1)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)    // order id
      .field(IntValue.class, 7)     // ship prio
      .field(StringValue.class, 2, 2)  // order status
      .field(StringValue.class, 4, 10)  // order date
      .field(StringValue.class, 5, 8);  // order prio
   
    FileDataSource orders2 = new FileDataSource(new CsvInputFormat(), orders2Path, "Orders 2");
    CsvInputFormat.configureRecordFormat(orders2)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)    // order id
      .field(IntValue.class, 7)     // ship prio
      .field(StringValue.class, 2, 2)  // order status
      .field(StringValue.class, 4, 10)  // order date
      .field(StringValue.class, 5, 8);  // order prio
   
    // create DataSourceContract for LineItems input
    FileDataSource lineitems = new FileDataSource(new CsvInputFormat(), lineitemsPath, "LineItems");
    CsvInputFormat.configureRecordFormat(lineitems)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)
      .field(DoubleValue.class, 5);

    // create MapOperator for filtering Orders tuples
    MapOperator filterO1 = MapOperator.builder(new FilterO())
      .name("FilterO")
      .input(orders1)
      .build();
    // filter configuration
    filterO1.setParameter(TPCHQuery3.YEAR_FILTER, 1993);
    filterO1.setParameter(TPCHQuery3.PRIO_FILTER, "5");
    filterO1.getCompilerHints().setFilterFactor(0.05f);
   
    // create MapOperator for filtering Orders tuples
    MapOperator filterO2 = MapOperator.builder(new FilterO())
      .name("FilterO")
      .input(orders2)
      .build();
    // filter configuration
    filterO2.setParameter(TPCHQuery3.YEAR_FILTER, 1993);
    filterO2.setParameter(TPCHQuery3.PRIO_FILTER, "5");

    // create JoinOperator for joining Orders and LineItems
    @SuppressWarnings("unchecked")
    JoinOperator joinLiO = JoinOperator.builder(new JoinLiO(), LongValue.class, 0, 0)
      .input1(filterO2, filterO1)
      .input2(lineitems)
      .name("JoinLiO")
      .build();
   
    FileDataSource partJoin1 = new FileDataSource(new CsvInputFormat(), partJoin1Path, "Part Join 1");
    CsvInputFormat.configureRecordFormat(partJoin1)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)
      .field(IntValue.class, 1)
      .field(DoubleValue.class, 2);
   
    FileDataSource partJoin2 = new FileDataSource(new CsvInputFormat(), partJoin2Path, "Part Join 2");
    CsvInputFormat.configureRecordFormat(partJoin2)
      .recordDelimiter('\n')
      .fieldDelimiter('|')
      .field(LongValue.class, 0)
      .field(IntValue.class, 1)
View Full Code Here
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
    int numSubTasks   = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String paths     = (args.length > 1 ? args[1] : "");
    String output    = (args.length > 2 ? args[2] : "");
    boolean rdfInput = (args.length > 3 ? Boolean.parseBoolean(args[3]) : false);

    FileDataSource pathsInput;
   
    if(rdfInput) {
      pathsInput = new FileDataSource(new RDFTripleInFormat(), paths, "RDF Triples");
    } else {
      pathsInput = new FileDataSource(new PathInFormat(), paths, "Paths");
    }
    pathsInput.setDegreeOfParallelism(numSubTasks);

    JoinOperator concatPaths =
        JoinOperator.builder(new ConcatPaths(), StringValue.class, 0, 1)
      .name("Concat Paths")
      .build();
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
        }
    }

    static Plan getTestPlan(int numSubTasks, String input, String output) {

        FileDataSource initialInput = new FileDataSource(new PointInFormat(), input, "Input");
        initialInput.setDegreeOfParallelism(1);

        BulkIteration iteration = new BulkIteration("Loop");
        iteration.setInput(initialInput);
        iteration.setMaximumNumberOfIterations(2);
View Full Code Here
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
      customersPath = args[3];
      nationsPath = args[4];
      resultPath = args[5];
    }
   
    FileDataSource orders = new FileDataSource(new IntTupleDataInFormat(), ordersPath, "Orders");
    // orders.setOutputContract(UniqueKey.class);
    // orders.getCompilerHints().setAvgNumValuesPerKey(1);

    FileDataSource lineitems = new FileDataSource(new IntTupleDataInFormat(), lineitemsPath, "LineItems");
    // lineitems.getCompilerHints().setAvgNumValuesPerKey(4);

    FileDataSource customers = new FileDataSource(new IntTupleDataInFormat(), customersPath, "Customers");

    FileDataSource nations = new FileDataSource(new IntTupleDataInFormat(), nationsPath, "Nations");


    MapOperator mapO = MapOperator.builder(FilterO.class)
      .name("FilterO")
      .build();
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
  @SuppressWarnings("unchecked")
  public static Plan getPlan(int numSubTasks, String verticesInput, String edgeInput, String output, int maxIterations, boolean extraMap) {

    // data source for initial vertices
    FileDataSource initialVertices = new FileDataSource(new CsvInputFormat(' ', LongValue.class), verticesInput, "Vertices");
   
    MapOperator verticesWithId = MapOperator.builder(DuplicateLongMap.class).input(initialVertices).name("Assign Vertex Ids").build();
   
    // the loop takes the vertices as the solution set and changed vertices as the workset
    // initially, all vertices are changed
    DeltaIteration iteration = new DeltaIteration(0, "Connected Components Iteration");
    iteration.setInitialSolutionSet(verticesWithId);
    iteration.setInitialWorkset(verticesWithId);
    iteration.setMaximumNumberOfIterations(maxIterations);
   
    // data source for the edges
    FileDataSource edges = new FileDataSource(new CsvInputFormat(' ', LongValue.class, LongValue.class), edgeInput, "Edges");

    // join workset (changed vertices) with the edges to propagate changes to neighbors
    JoinOperator joinWithNeighbors = JoinOperator.builder(new NeighborWithComponentIDJoin(), LongValue.class, 0, 0)
        .input1(iteration.getWorkset())
        .input2(edges)
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
    }
  }

  @Override
  protected Plan getTestJob() {
    FileDataSource input = new FileDataSource(
        new ContractITCaseInputFormat(), inPath);
    DelimitedInputFormat.configureDelimitedFormat(input)
      .recordDelimiter('\n');
    input.setDegreeOfParallelism(config.getInteger("MapTest#NoSubtasks", 1));

    MapOperator testMapper = MapOperator.builder(new TestMapper()).build();
    testMapper.setDegreeOfParallelism(config.getInteger("MapTest#NoSubtasks", 1));

    FileDataSink output = new FileDataSink(
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
  public Plan getPlan(String... args) {
    int numSubTasks = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String dataInput = (args.length > 1 ? args[1] : "");
    String output = (args.length > 2 ? args[2] : "");

    FileDataSource source = new FileDataSource(new TextInputFormat(), dataInput, "Input Lines");

    MapOperator mapper = MapOperator.builder(new TokenizeLine()).input(source).name("Tokenize Lines").build();
   
    ReduceOperator reducer = ReduceOperator.builder(CountWords.class, StringValue.class, 0).input(mapper)
        .name("Count Words").build();
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
    }
  }

  @Override
  protected JobGraph getJobGraph() throws Exception {
    FileDataSource input = new FileDataSource(
        new ContractITCaseInputFormat(), inPath);
    DelimitedInputFormat.configureDelimitedFormat(input)
      .recordDelimiter('\n');
    input.setDegreeOfParallelism(config.getInteger("ReduceTest#NoSubtasks", 1));

    ReduceOperator testReducer = ReduceOperator.builder(new TestReducer(), StringValue.class, 0)
      .build();
    testReducer.setDegreeOfParallelism(config.getInteger("ReduceTest#NoSubtasks", 1));
    testReducer.getParameters().setString(PactCompiler.HINT_LOCAL_STRATEGY,
View Full Code Here
TOP

Related Classes of eu.stratosphere.api.java.record.operators.FileDataSource

  • eu.stratosphere.pact.compiler.AdditionalOperatorsTest
  • eu.stratosphere.pact.compiler.BranchingPlansCompilerTest
  • eu.stratosphere.pact.compiler.DOPChangeTest
  • eu.stratosphere.pact.compiler.GroupOrderTest
  • eu.stratosphere.pact.compiler.HardPlansCompilationTest
  • eu.stratosphere.pact.compiler.ReduceAllTest
  • eu.stratosphere.pact.compiler.UnionPropertyPropagationTest
  • eu.stratosphere.pact.compiler.WorksetIterationsRecordApiCompilerTest
  • eu.stratosphere.test.accumulators.AccumulatorITCase
  • eu.stratosphere.test.accumulators.AccumulatorIterativeITCase
    • 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.