Package storm.trident

Examples of storm.trident.TridentTopology.newStream()

37
38
39
40
41
42
43
44
45
46
47
    public static StormTopology buildTopology(TransactionalTridentKafkaSpout spout) throws IOException {

        TridentTopology topology = new TridentTopology();
        TridentState count =
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("text", "content", "user"))
                .project(new Fields("content", "user"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("user"), new OnlyEnglish())
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
    public static StormTopology buildTopology(TransactionalTridentKafkaSpout spout) throws IOException {

        TridentTopology topology = new TridentTopology();
        TridentState count =
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("text", "content", "user"))
                .project(new Fields("content", "user"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("user"), new OnlyEnglish())
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
         * As a first thing, we need a stream of tweets which we can parse and extract
         * only the text and its id. As you will notice, we're going to store the stream
         * using the {@link ElasticSearchState} implementation using its {@link StateUpdater}.
         * Check their implementations for details.
         */
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("text", "content", "user"))
                .each(new Fields("text", "content"), new TweetIdExtractor(), new Fields("tweetId"))
                .project(new Fields("tweetId", "text"))
                .each(new Fields("tweetId", "text"), new Print())
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
    public static StormTopology buildTopology(TransactionalTridentKafkaSpout spout) throws IOException {

        TridentTopology topology = new TridentTopology();
        TridentState count =
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("status", "content", "user"))
                .project(new Fields("content", "user", "status"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("status"), new OnlyGeo())
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
        /**
         * First, grab the tweets stream. We're going to use it in two different places
         * and then, we'll going to join them.
         *
         */
        Stream contents = topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("text", "content", "user"));

        /**
         * Now, let's select and project only hashtags for each tweet.
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
    public static StormTopology buildTopology(TransactionalTridentKafkaSpout spout) throws IOException {

        TridentTopology topology = new TridentTopology();
        TridentState count =
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new ParseTweet(), new Fields("text", "content", "user"))
                .project(new Fields("content", "user"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("user"), new OnlyEnglish())
View Full Code Here
24
25
26
27
28
29
30
31
32
33
34
*/
public class Skeleton {
    private static final Logger log = LoggerFactory.getLogger(Skeleton.class);
    public static StormTopology buildTopology(TransactionalTridentKafkaSpout spout) throws IOException {
        TridentTopology topology = new TridentTopology();
        topology
                .newStream("tweets", spout)
                .each(new Fields("str"), new Print())
        ;

        topology
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
        FakeTweetsBatchSpout fakeTweets = new FakeTweetsBatchSpout(10);

        TridentTopology topology = new TridentTopology();
        TridentState countState =
                topology
                        .newStream("spout", fakeTweets)
                        .groupBy(new Fields("actor"))
                        .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"));

        topology
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
        TridentTopology topology = new TridentTopology();

        // What if we want more than one aggregation? For that, we can use "chained" aggregations.
        // Note how we calculate count and sum.
        // The aggregated values can then be processed further, in this case into mean
        topology
                .newStream("aggregation", spout)
                .groupBy(new Fields("city"))
                .chainedAgg()
                .aggregate(new Count(), new Fields("count"))
                .aggregate(new Fields("age"), new Sum(), new Fields("age_sum"))
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
                .each(new Fields("city", "mean_age"), new Print())
        ;

        // What if we want to persist results of an aggregation, but want to further process these
        // results? You can use "newValuesStream" for that
        topology
                .newStream("further",spout)
                .groupBy(new Fields("city"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
                .newValuesStream()
                .each(new Fields("city", "count"), new Print());
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.