Examples with Pipeline com.google.cloud.dataflow.sdk.Pipeline used on opensource projects

Example 16 with Pipeline

use of com.google.cloud.dataflow.sdk.Pipeline in project spark-dataflow by cloudera.

the class DoFnOutputTest method test.

@Test
public void test() throws Exception {
    SparkPipelineOptions options = SparkPipelineOptionsFactory.create();
    options.setRunner(SparkPipelineRunner.class);
    Pipeline pipeline = Pipeline.create(options);
    PCollection<String> strings = pipeline.apply(Create.of("a"));
    // Test that values written from startBundle() and finishBundle() are written to
    // the output
    PCollection<String> output = strings.apply(ParDo.of(new DoFn<String, String>() {

        @Override
        public void startBundle(Context c) throws Exception {
            c.output("start");
        }

        @Override
        public void processElement(ProcessContext c) throws Exception {
            c.output(c.element());
        }

        @Override
        public void finishBundle(Context c) throws Exception {
            c.output("finish");
        }
    }));
    DataflowAssert.that(output).containsInAnyOrder("start", "a", "finish");
    EvaluationResult res = SparkPipelineRunner.create().run(pipeline);
    res.close();
}

Example 17 with Pipeline

use of com.google.cloud.dataflow.sdk.Pipeline in project spark-dataflow by cloudera.

the class EmptyInputTest method test.

@Test
public void test() throws Exception {
    SparkPipelineOptions options = SparkPipelineOptionsFactory.create();
    Pipeline p = Pipeline.create(options);
    List<String> empty = Collections.emptyList();
    PCollection<String> inputWords = p.apply(Create.of(empty)).setCoder(StringUtf8Coder.of());
    PCollection<String> output = inputWords.apply(Combine.globally(new ConcatWords()));
    EvaluationResult res = SparkPipelineRunner.create().run(p);
    assertEquals("", Iterables.getOnlyElement(res.get(output)));
    res.close();
}

Example 18 with Pipeline

use of com.google.cloud.dataflow.sdk.Pipeline in project spark-dataflow by cloudera.

the class MultiOutputWordCountTest method testRun.

@Test
public void testRun() throws Exception {
    Pipeline p = Pipeline.create(PipelineOptionsFactory.create());
    PCollection<String> regex = p.apply(Create.of("[^a-zA-Z']+"));
    PCollection<String> w1 = p.apply(Create.of("Here are some words to count", "and some others"));
    PCollection<String> w2 = p.apply(Create.of("Here are some more words", "and even more words"));
    PCollectionList<String> list = PCollectionList.of(w1).and(w2);
    PCollection<String> union = list.apply(Flatten.<String>pCollections());
    PCollectionView<String> regexView = regex.apply(View.<String>asSingleton());
    CountWords countWords = new CountWords(regexView);
    PCollectionTuple luc = union.apply(countWords);
    PCollection<Long> unique = luc.get(lowerCnts).apply(ApproximateUnique.<KV<String, Long>>globally(16));
    EvaluationResult res = SparkPipelineRunner.create().run(p);
    Iterable<KV<String, Long>> actualLower = res.get(luc.get(lowerCnts));
    Assert.assertEquals("are", actualLower.iterator().next().getKey());
    Iterable<KV<String, Long>> actualUpper = res.get(luc.get(upperCnts));
    Assert.assertEquals("Here", actualUpper.iterator().next().getKey());
    Iterable<Long> actualUniqCount = res.get(unique);
    Assert.assertEquals(9, (long) actualUniqCount.iterator().next());
    int actualTotalWords = res.getAggregatorValue("totalWords", Integer.class);
    Assert.assertEquals(18, actualTotalWords);
    int actualMaxWordLength = res.getAggregatorValue("maxWordLength", Integer.class);
    Assert.assertEquals(6, actualMaxWordLength);
    AggregatorValues<Integer> aggregatorValues = res.getAggregatorValues(countWords.getTotalWordsAggregator());
    Assert.assertEquals(18, Iterables.getOnlyElement(aggregatorValues.getValues()).intValue());
    res.close();
}

Example 19 with Pipeline

use of com.google.cloud.dataflow.sdk.Pipeline in project spark-dataflow by cloudera.

the class KafkaStreamingTest method testRun.

@Test
public void testRun() throws Exception {
    // test read from Kafka
    SparkStreamingPipelineOptions options = SparkStreamingPipelineOptionsFactory.create();
    options.setAppName(this.getClass().getSimpleName());
    options.setRunner(SparkPipelineRunner.class);
    // run for one interval
    options.setTimeout(TEST_TIMEOUT_MSEC);
    Pipeline p = Pipeline.create(options);
    Map<String, String> kafkaParams = ImmutableMap.of("metadata.broker.list", EMBEDDED_KAFKA_CLUSTER.getBrokerList(), "auto.offset.reset", "smallest");
    PCollection<KV<String, String>> kafkaInput = p.apply(KafkaIO.Read.from(StringDecoder.class, StringDecoder.class, String.class, String.class, Collections.singleton(TOPIC), kafkaParams));
    PCollection<KV<String, String>> windowedWords = kafkaInput.apply(Window.<KV<String, String>>into(FixedWindows.of(Duration.standardSeconds(1))));
    PCollection<String> formattedKV = windowedWords.apply(ParDo.of(new FormatKVFn()));
    DataflowAssert.thatIterable(formattedKV.apply(View.<String>asIterable())).containsInAnyOrder(EXPECTED);
    EvaluationResult res = SparkPipelineRunner.create(options).run(p);
    res.close();
    DataflowAssertStreaming.assertNoFailures(res);
}

Example 20 with Pipeline

use of com.google.cloud.dataflow.sdk.Pipeline in project spark-dataflow by cloudera.

the class CombineGloballyTest method test.

@Test
public void test() throws Exception {
    SparkPipelineOptions options = SparkPipelineOptionsFactory.create();
    Pipeline p = Pipeline.create(options);
    PCollection<String> inputWords = p.apply(Create.of(WORDS)).setCoder(StringUtf8Coder.of());
    PCollection<String> output = inputWords.apply(Combine.globally(new WordMerger()));
    EvaluationResult res = SparkPipelineRunner.create().run(p);
    assertEquals("hi there,hi,hi sue bob,hi sue,,bob hi", Iterables.getOnlyElement(res.get(output)));
    res.close();
}