Package com.datasalt.pangool.io

Examples of com.datasalt.pangool.io.Tuple

57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
  public static class MyHandler extends TupleMapper<LongWritable, Text> {

    @Override
    public void map(LongWritable key, Text value, TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      ITuple tuple = new Tuple(schema1);
      tuple.set("a", (int) (Math.random() * 1000));
      tuple.set("b", value.toString());

      ITuple mTuple = new Tuple(getMetaSchema1());
      mTuple.set("partition", (int) (Math.random() * 10));
      mTuple.set("tuple", tuple);

      ITuple mTuple2 = new Tuple(getMetaSchema2());
      mTuple2.set("group", value.toString());
      mTuple2.set("metatuple", mTuple);

      collector.write(mTuple2);
    }
View Full Code Here
57
58
59
60
61
62
63
64
    private Tuple tuple;

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      Schema schema = context.getTupleMRConfig().getIntermediateSchema(0);
      this.tuple = new Tuple(schema);
      tuple.set("count", 1);
    }
View Full Code Here
80
81
82
83
84
85
86
    private Tuple tuple;

    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      Schema schema = context.getTupleMRConfig().getIntermediateSchema("schema");
      this.tuple = new Tuple(schema);
    }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
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
96
97
    Schema targetSchema = new Schema("target", Fields.parse("a:string, b:int?, c:double, d:long?, e:boolean?"));
   
    Configuration conf = new Configuration();
    HadoopSerialization hadoopSerDe = new HadoopSerialization(conf);

    ITuple tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("b", 10);
    tuple.set("c", 5d);
   
    SimpleTupleSerializer ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    ser.open(bos);
   
    for(int i = 0; i < 10; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
   
    bos.close();
    ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
   
    SimpleTupleDeserializer des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    ITuple targetTuple = new Tuple(targetSchema);
    for(int i = 0; i < 10; i++) {
      des.deserialize(targetTuple);
    }
   
    assertEquals("foo", targetTuple.getString("a"));
    assertEquals(10, targetTuple.get("b"));
    assertEquals(5d, targetTuple.get("c"));
    assertNull(targetTuple.get("d"));
    assertNull(targetTuple.get("e"));
   
    // Something important is that if we read a file that doesn't contains a field
    // just after a file that contains this field, we should clear the field even
    // in the case that no default value was provided.
    schema = new Schema("schema", Fields.parse("a:string, c:double"));
    tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("c", 5d);
   
    bos = new ByteArrayOutputStream();
    ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ser.open(bos);
   
    for(int i = 0; i < 10; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
    bos.close();   
    bis = new ByteArrayInputStream(bos.toByteArray());   
    des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    for(int i = 0; i < 10; i++) {
      des.deserialize(targetTuple);
    }
   
    assertEquals("foo", targetTuple.getString("a"));
    assertNull(targetTuple.get("b"));
    assertEquals(5d, targetTuple.get("c"));
    assertNull(targetTuple.get("d"));
    assertNull(targetTuple.get("e"));
   
    bis.close();
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
    Configuration conf = getConf();
    String input = TestTupleMRJob.class + "-input";
    String output = TestTupleMRJob.class + "-output";

    ITuple tuple = new Tuple(SCHEMA);
    for(int i = 0; i < NUM_ROWS_TO_GENERATE; i++) {
      withTupleInput(input, fillTuple(true, tuple));
    }

    TupleMRBuilder builder = new TupleMRBuilder(getConf(), "test");
View Full Code Here
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
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
    String input2 = TestTupleMRJob.class.getCanonicalName() + "-input2";
    String output = TestTupleMRJob.class.getCanonicalName() + "-output";

    final Schema schemaNoNulls = new Schema("NoNulls", Fields.parse("f1:int,f2:string"));
    final Schema schemaNulls = new Schema("Nulls", Fields.parse("f1:int?,f2:string?"));
    Tuple t1 = new Tuple(schemaNoNulls);
    Tuple t2 = new Tuple(schemaNulls);

    t1.set(0, 0);
    t1.set(1, "nn");
    withTupleInput(input1, t1);

    Object tuples[][] = new Object[][] { new Object[] { 0, null }, new Object[] { 0, "n1" },
        new Object[] { null, "n2" } };
    for(Object[] tuple : tuples) {
      t2.set(0, tuple[0]);
      t2.set(1, tuple[1]);
      withTupleInput(input2, t2);
    }

    TupleMRBuilder builder = new TupleMRBuilder(getConf(), "test");
    builder.addTupleInput(new Path(input1), new IdentityTupleMapper());
    builder.addTupleInput(new Path(input2), new IdentityTupleMapper());

    builder.setTupleReducer(new TupleReducer<ITuple, NullWritable>() {
      @Override
      public void reduce(ITuple group, Iterable<ITuple> tuples, TupleMRContext context,
          Collector collector) throws IOException, InterruptedException, TupleMRException {
        int count = 0;
        for(ITuple tuple : tuples) {
          Tuple t = new Tuple(schemaNulls);
          t.set(0, tuple.get(0));
          t.set(1, tuple.get(1));
          collector.write(t, NullWritable.get());
          count++;
        }
        if(group.get(0) == null) {
          assertEquals(1, count);
        } else if(((Integer) group.get(0)) == 0) {
          assertEquals(3, count);
        }
      }
    });
    builder.addIntermediateSchema(schemaNoNulls);
    builder.addIntermediateSchema(schemaNulls);
    builder.setGroupByFields("f1");
    builder.setOrderBy(OrderBy.parse("f1:desc|null_smallest").addSchemaOrder(Criteria.Order.ASC));
    builder.setSpecificOrderBy("NoNulls", OrderBy.parse("f2:asc|null_biggest"));
    builder.setSpecificOrderBy("Nulls", OrderBy.parse("f2:asc|null_biggest"));
    builder.setTupleOutput(new Path(output), schemaNulls);

    Job job = builder.createJob();
    job.setNumReduceTasks(1);
    try {
      assertRun(job);
    } finally {
      builder.cleanUpInstanceFiles();
    }

    final Object expectedOutput[][] = new Object[][] { new Object[] { 0, "nn" },
        new Object[] { 0, "n1" }, new Object[] { 0, null }, new Object[] { null, "n2" } };

    boolean debug = false;
    if(debug) {
      readTuples(new Path(output + "/part-r-00000"), getConf(), new TupleVisitor() {
        @Override
        public void onTuple(ITuple t) {
          System.out.println(t);
        }
      });
    }

    readTuples(new Path(output + "/part-r-00000"), getConf(), new TupleVisitor() {
      int i = 0;

      @Override
      public void onTuple(ITuple t) {
        assertEqualsNull(expectedOutput[i][0], t.get(0));
        Object f2 = t.get(1);
        f2 = (f2 != null) ? f2.toString() : f2;
        assertEqualsNull(expectedOutput[i][1], f2);
        i++;
      }
    });
View Full Code Here
54
55
56
57
58
59
60
61
    public void setup(TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      Schema peopleSchema = context.getTupleMRConfig().getIntermediateSchema("user");
      Schema countrySchema = context.getTupleMRConfig().getIntermediateSchema("country");
      user = new Tuple(peopleSchema);
      country = new Tuple(countrySchema);
    }
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
    // Define the input and its associated mapper.
    // We'll just have a Mapper, reducer will be Identity
    job.addInput(new Path(input), new HadoopInputFormat(TextInputFormat.class),
        new TupleMapper<LongWritable, Text>() {

          Tuple tuple = new Tuple(schema);

          @Override
          public void map(LongWritable key, Text value, TupleMRContext context, Collector collector)
              throws IOException, InterruptedException {
            String[] fields = value.toString().split("\t");
            String language = fields[1];
            tuple.set("user_id", fields[0]);
            tuple.set("message", fields[2]);
            if(language.equals("en")) {
              // English -> write to main output
              collector.write(tuple);
            } else if(language.equals("fr")) {
              // French -> write to french index
View Full Code Here
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
137
138
139
140
141
142
    Schema targetSchema = Mutator.superSetOf(schema, cField, dField);
   
    Configuration conf = new Configuration();
    HadoopSerialization hadoopSerDe = new HadoopSerialization(conf);

    ITuple tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("b", 10);
   
    SimpleTupleSerializer ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    ser.open(bos);
   
    for(int i = 0; i < 100000; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
   
    bos.close();
    ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
   
    SimpleTupleDeserializer des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    ITuple targetTuple = new Tuple(targetSchema);
    long start = System.currentTimeMillis();
    for(int i = 0; i < 100000; i++) {
      des.deserialize(targetTuple);
    }
    long end = System.currentTimeMillis();
    System.out.println(end - start);
   
    assertEquals("foo", targetTuple.getString("a"));
    assertEquals(10, targetTuple.get("b"));
    assertEquals(100d, targetTuple.get("c"));
    assertEquals(1000l, targetTuple.get("d"));
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
  public static int assertOutput(String output, Configuration conf) throws NumberFormatException, IOException, InterruptedException {
    int validatedOutputLines = 0;

    Path outPath = new Path(output);
    TupleFile.Reader reader = new TupleFile.Reader(FileSystem.get(outPath.toUri(), conf), conf, outPath);
    Tuple tuple = new Tuple(reader.getSchema());

    while(reader.next(tuple)) {
      int topicId = (Integer) tuple.get("topic");
      String word = ((Utf8) tuple.get("word")).toString();
      int count   = (Integer) tuple.get("count");
      if(topicId == 1) {
        if(word.equals("bar") || word.equals("foo")) {
          assertEquals(2, count);
          validatedOutputLines++;
        } else if(word.equals("blah") || word.equals("bloh")) {
View Full Code Here
TOP

Related Classes of com.datasalt.pangool.io.Tuple

  • com.datasalt.pangool.examples.avro.AvroCustomSerializationJob$TokenizeMapper
  • com.datasalt.pangool.examples.avro.AvroTopicalWordCount$TokenizeMapper
  • com.datasalt.pangool.examples.avro.AvroTweetsJoin$RetweetsMapper
  • com.datasalt.pangool.examples.avro.AvroTweetsJoin$TweetsMapper
  • com.datasalt.pangool.examples.avro.TestAvroTopicalWordCount
  • com.datasalt.pangool.examples.gameoflife.GameOfLifeJob
  • com.datasalt.pangool.examples.movingaverage.MovingAverage$URLVisitsProcessor
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesClassifier
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate
  • com.datasalt.pangool.examples.secondarysort.SecondarySort$IProcessor
    • 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.