Examples of org.apache.pig.builtin.Distinct$Initial

org.apache.pig.builtin.Distinct
Find the distinct set of tuples in a bag. This is a blocking operator. All the input is put in the hashset implemented in DistinctDataBag which also provides the other DataBag interfaces.

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));
        
        Integer[] exp = new Integer[inputSize/2];
        for(int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));
        
        Integer[] exp = new Integer[inputSize/2];
        for(int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));
        
        Integer[] exp = new Integer[inputSize/2];
        for(int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));
        
        Integer[] exp = new Integer[inputSize/2];
        for(int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

    @Test
    public void testDistinctIsNullSafe() throws Exception {
        DataBag empty = bagFactory.newDefaultBag();
        Tuple tupleOfNull = tupleFactory.newTuple(1);
        Tuple tupleOfEmpty = tupleFactory.newTuple(empty);
        assertEquals(empty, new Distinct().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Initial().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Intermediate().exec(tupleOfNull));
        assertEquals(empty, new Distinct.Final().exec(tupleOfNull));
    }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));


        Integer[] exp = new Integer[inputSize/2];
        for (int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

    @Test
    public void testDistinctIsNullSafe() throws Exception {
        DataBag empty = bagFactory.newDefaultBag();
        Tuple tupleOfNull = tupleFactory.newTuple(1);
        Tuple tupleOfEmpty = tupleFactory.newTuple(empty);
        assertEquals(empty, new Distinct().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Initial().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Intermediate().exec(tupleOfNull));
        assertEquals(empty, new Distinct.Final().exec(tupleOfNull));
    }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));


        Integer[] exp = new Integer[inputSize/2];
        for (int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

    @Test
    public void testDistinctIsNullSafe() throws Exception {
        DataBag empty = bagFactory.newDefaultBag();
        Tuple tupleOfNull = tupleFactory.newTuple(1);
        Tuple tupleOfEmpty = tupleFactory.newTuple(empty);
        assertEquals(empty, new Distinct().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Initial().exec(tupleOfNull));
        assertEquals(tupleOfEmpty, new Distinct.Intermediate().exec(tupleOfNull));
        assertEquals(empty, new Distinct.Final().exec(tupleOfNull));
    }

View Full Code Here

            inp[i] = i/2;
            inp[i+1] = i/2;
        }


        DataBag inputBag = Util.createBagOfOneColumn(inp);
        EvalFunc<DataBag> distinct = new Distinct();
        DataBag result = distinct.exec(tupleFactory.newTuple(inputBag));


        Integer[] exp = new Integer[inputSize/2];
        for(int j = 0; j < inputSize/2; ++j) {
            exp[j] = j;
        }

View Full Code Here

0 1

TOP

Related Classes of org.apache.pig.builtin.Distinct$Initial

org.apache.hadoop.util.bloom.BloomFilter

org.apache.hadoop.util.bloom.Key

org.apache.pig.data.DataAtom

org.apache.pig.data.DataBag

org.apache.pig.data.DataByteArray

org.apache.pig.data.InternalDistinctBag

org.apache.pig.data.SingleTupleBag

org.apache.pig.data.Tuple

org.apache.pig.test.TestBuiltin

org.joda.time.DateTime

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.