use of org.apache.flink.runtime.operators.testutils.DiscardingOutputCollector in project flink by apache.
the class NonReusingHashJoinIteratorITCase method testBuildFirstAndBuildSideOuterJoin.
@Test
public void testBuildFirstAndBuildSideOuterJoin() {
try {
TupleGenerator generator1 = new TupleGenerator(SEED1, 500, 4096, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
TupleGenerator generator2 = new TupleGenerator(SEED2, 1000, 2048, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
final TestData.TupleGeneratorIterator input1 = new TestData.TupleGeneratorIterator(generator1, INPUT_1_SIZE);
final TestData.TupleGeneratorIterator input2 = new TestData.TupleGeneratorIterator(generator2, INPUT_2_SIZE);
// collect expected data
final Map<Integer, Collection<TupleMatch>> expectedMatchesMap = leftOuterJoinTuples(collectTupleData(input1), collectTupleData(input2));
final TupleMatchRemovingJoin matcher = new TupleMatchRemovingJoin(expectedMatchesMap);
final Collector<Tuple2<Integer, String>> collector = new DiscardingOutputCollector<>();
// reset the generators
generator1.reset();
generator2.reset();
input1.reset();
input2.reset();
// compare with iterator values
NonReusingBuildFirstHashJoinIterator<Tuple2<Integer, String>, Tuple2<Integer, String>, Tuple2<Integer, String>> iterator = new NonReusingBuildFirstHashJoinIterator<>(input1, input2, this.recordSerializer, this.record1Comparator, this.recordSerializer, this.record2Comparator, this.recordPairComparator, this.memoryManager, ioManager, this.parentTask, 1.0, false, true, false);
iterator.open();
while (iterator.callWithNextKey(matcher, collector)) ;
iterator.close();
// assert that each expected match was seen
for (Entry<Integer, Collection<TupleMatch>> entry : expectedMatchesMap.entrySet()) {
if (!entry.getValue().isEmpty()) {
Assert.fail("Collection for key " + entry.getKey() + " is not empty");
}
}
} catch (Exception e) {
e.printStackTrace();
Assert.fail("An exception occurred during the test: " + e.getMessage());
}
}
use of org.apache.flink.runtime.operators.testutils.DiscardingOutputCollector in project flink by apache.
the class NonReusingHashJoinIteratorITCase method testBuildSecond.
@Test
public void testBuildSecond() {
try {
TupleGenerator generator1 = new TupleGenerator(SEED1, 500, 4096, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
TupleGenerator generator2 = new TupleGenerator(SEED2, 500, 2048, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
final TestData.TupleGeneratorIterator input1 = new TestData.TupleGeneratorIterator(generator1, INPUT_1_SIZE);
final TestData.TupleGeneratorIterator input2 = new TestData.TupleGeneratorIterator(generator2, INPUT_2_SIZE);
// collect expected data
final Map<Integer, Collection<TupleMatch>> expectedMatchesMap = joinTuples(collectTupleData(input1), collectTupleData(input2));
final TupleMatchRemovingJoin matcher = new TupleMatchRemovingJoin(expectedMatchesMap);
final Collector<Tuple2<Integer, String>> collector = new DiscardingOutputCollector<>();
// reset the generators
generator1.reset();
generator2.reset();
input1.reset();
input2.reset();
// compare with iterator values
NonReusingBuildSecondHashJoinIterator<Tuple2<Integer, String>, Tuple2<Integer, String>, Tuple2<Integer, String>> iterator = new NonReusingBuildSecondHashJoinIterator<>(input1, input2, this.recordSerializer, this.record1Comparator, this.recordSerializer, this.record2Comparator, this.recordPairComparator, this.memoryManager, ioManager, this.parentTask, 1.0, false, false, true);
iterator.open();
while (iterator.callWithNextKey(matcher, collector)) ;
iterator.close();
// assert that each expected match was seen
for (Entry<Integer, Collection<TupleMatch>> entry : expectedMatchesMap.entrySet()) {
if (!entry.getValue().isEmpty()) {
Assert.fail("Collection for key " + entry.getKey() + " is not empty");
}
}
} catch (Exception e) {
e.printStackTrace();
Assert.fail("An exception occurred during the test: " + e.getMessage());
}
}
use of org.apache.flink.runtime.operators.testutils.DiscardingOutputCollector in project flink by apache.
the class NonReusingHashJoinIteratorITCase method testBuildFirst.
@Test
public void testBuildFirst() {
try {
TupleGenerator generator1 = new TupleGenerator(SEED1, 500, 4096, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
TupleGenerator generator2 = new TupleGenerator(SEED2, 500, 2048, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
final TestData.TupleGeneratorIterator input1 = new TestData.TupleGeneratorIterator(generator1, INPUT_1_SIZE);
final TestData.TupleGeneratorIterator input2 = new TestData.TupleGeneratorIterator(generator2, INPUT_2_SIZE);
// collect expected data
final Map<Integer, Collection<TupleMatch>> expectedMatchesMap = joinTuples(collectTupleData(input1), collectTupleData(input2));
final TupleMatchRemovingJoin matcher = new TupleMatchRemovingJoin(expectedMatchesMap);
final Collector<Tuple2<Integer, String>> collector = new DiscardingOutputCollector<Tuple2<Integer, String>>();
// reset the generators
generator1.reset();
generator2.reset();
input1.reset();
input2.reset();
// compare with iterator values
NonReusingBuildFirstHashJoinIterator<Tuple2<Integer, String>, Tuple2<Integer, String>, Tuple2<Integer, String>> iterator = new NonReusingBuildFirstHashJoinIterator<>(input1, input2, this.recordSerializer, this.record1Comparator, this.recordSerializer, this.record2Comparator, this.recordPairComparator, this.memoryManager, ioManager, this.parentTask, 1.0, false, false, true);
iterator.open();
// noinspection StatementWithEmptyBody
while (iterator.callWithNextKey(matcher, collector)) ;
iterator.close();
// assert that each expected match was seen
for (Entry<Integer, Collection<TupleMatch>> entry : expectedMatchesMap.entrySet()) {
if (!entry.getValue().isEmpty()) {
Assert.fail("Collection for key " + entry.getKey() + " is not empty");
}
}
} catch (Exception e) {
e.printStackTrace();
Assert.fail("An exception occurred during the test: " + e.getMessage());
}
}
use of org.apache.flink.runtime.operators.testutils.DiscardingOutputCollector in project flink by apache.
the class NonReusingHashJoinIteratorITCase method testBuildSecondWithHighNumberOfCommonKeys.
@Test
public void testBuildSecondWithHighNumberOfCommonKeys() {
// the size of the left and right inputs
final int INPUT_1_SIZE = 200;
final int INPUT_2_SIZE = 100;
final int INPUT_1_DUPLICATES = 10;
final int INPUT_2_DUPLICATES = 2000;
final int DUPLICATE_KEY = 13;
try {
TupleGenerator generator1 = new TupleGenerator(SEED1, 500, 4096, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
TupleGenerator generator2 = new TupleGenerator(SEED2, 500, 2048, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
final TestData.TupleGeneratorIterator gen1Iter = new TestData.TupleGeneratorIterator(generator1, INPUT_1_SIZE);
final TestData.TupleGeneratorIterator gen2Iter = new TestData.TupleGeneratorIterator(generator2, INPUT_2_SIZE);
final TestData.TupleConstantValueIterator const1Iter = new TestData.TupleConstantValueIterator(DUPLICATE_KEY, "LEFT String for Duplicate Keys", INPUT_1_DUPLICATES);
final TestData.TupleConstantValueIterator const2Iter = new TestData.TupleConstantValueIterator(DUPLICATE_KEY, "RIGHT String for Duplicate Keys", INPUT_2_DUPLICATES);
final List<MutableObjectIterator<Tuple2<Integer, String>>> inList1 = new ArrayList<>();
inList1.add(gen1Iter);
inList1.add(const1Iter);
final List<MutableObjectIterator<Tuple2<Integer, String>>> inList2 = new ArrayList<>();
inList2.add(gen2Iter);
inList2.add(const2Iter);
MutableObjectIterator<Tuple2<Integer, String>> input1 = new UnionIterator<>(inList1);
MutableObjectIterator<Tuple2<Integer, String>> input2 = new UnionIterator<>(inList2);
// collect expected data
final Map<Integer, Collection<TupleMatch>> expectedMatchesMap = joinTuples(collectTupleData(input1), collectTupleData(input2));
// re-create the whole thing for actual processing
// reset the generators and iterators
generator1.reset();
generator2.reset();
const1Iter.reset();
const2Iter.reset();
gen1Iter.reset();
gen2Iter.reset();
inList1.clear();
inList1.add(gen1Iter);
inList1.add(const1Iter);
inList2.clear();
inList2.add(gen2Iter);
inList2.add(const2Iter);
input1 = new UnionIterator<>(inList1);
input2 = new UnionIterator<>(inList2);
final TupleMatchRemovingJoin matcher = new TupleMatchRemovingJoin(expectedMatchesMap);
final Collector<Tuple2<Integer, String>> collector = new DiscardingOutputCollector<>();
NonReusingBuildSecondHashJoinIterator<Tuple2<Integer, String>, Tuple2<Integer, String>, Tuple2<Integer, String>> iterator = new NonReusingBuildSecondHashJoinIterator<>(input1, input2, this.recordSerializer, this.record1Comparator, this.recordSerializer, this.record2Comparator, this.recordPairComparator, this.memoryManager, ioManager, this.parentTask, 1.0, false, false, true);
iterator.open();
while (iterator.callWithNextKey(matcher, collector)) ;
iterator.close();
// assert that each expected match was seen
for (Entry<Integer, Collection<TupleMatch>> entry : expectedMatchesMap.entrySet()) {
if (!entry.getValue().isEmpty()) {
Assert.fail("Collection for key " + entry.getKey() + " is not empty");
}
}
} catch (Exception e) {
e.printStackTrace();
Assert.fail("An exception occurred during the test: " + e.getMessage());
}
}
use of org.apache.flink.runtime.operators.testutils.DiscardingOutputCollector in project flink by apache.
the class NonReusingHashJoinIteratorITCase method testBuildSecondAndBuildSideOuterJoin.
@Test
public void testBuildSecondAndBuildSideOuterJoin() {
try {
TupleGenerator generator1 = new TupleGenerator(SEED1, 1000, 4096, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
TupleGenerator generator2 = new TupleGenerator(SEED2, 500, 2048, KeyMode.RANDOM, ValueMode.RANDOM_LENGTH);
final TestData.TupleGeneratorIterator input1 = new TestData.TupleGeneratorIterator(generator1, INPUT_1_SIZE);
final TestData.TupleGeneratorIterator input2 = new TestData.TupleGeneratorIterator(generator2, INPUT_2_SIZE);
// collect expected data
final Map<Integer, Collection<TupleMatch>> expectedMatchesMap = rightOuterJoinTuples(collectTupleData(input1), collectTupleData(input2));
final TupleMatchRemovingJoin matcher = new TupleMatchRemovingJoin(expectedMatchesMap);
final Collector<Tuple2<Integer, String>> collector = new DiscardingOutputCollector<>();
// reset the generators
generator1.reset();
generator2.reset();
input1.reset();
input2.reset();
// compare with iterator values
NonReusingBuildSecondHashJoinIterator<Tuple2<Integer, String>, Tuple2<Integer, String>, Tuple2<Integer, String>> iterator = new NonReusingBuildSecondHashJoinIterator<>(input1, input2, this.recordSerializer, this.record1Comparator, this.recordSerializer, this.record2Comparator, this.recordPairComparator, this.memoryManager, ioManager, this.parentTask, 1.0, false, true, false);
iterator.open();
while (iterator.callWithNextKey(matcher, collector)) ;
iterator.close();
// assert that each expected match was seen
for (Entry<Integer, Collection<TupleMatch>> entry : expectedMatchesMap.entrySet()) {
if (!entry.getValue().isEmpty()) {
Assert.fail("Collection for key " + entry.getKey() + " is not empty");
}
}
} catch (Exception e) {
e.printStackTrace();
Assert.fail("An exception occurred during the test: " + e.getMessage());
}
}
Aggregations