nathanmarz

(use 'cascalog.playground) (bootstrap)

(require '[clojure.set :as set])
(require '[cascalog.vars :as v])

(defn all-syms [form]
  (if (coll? form)
    (reduce (fn [curr elem] (set/union curr (all-syms elem)))
            #{}
            form)

nathanmarz

FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
               new Values("the cow jumped over the moon"),
               new Values("the man went to the store and bought some candy"),
               new Values("four score and seven years ago"),
               new Values("how many apples can you eat"),
spout.setCycle(true);

nathanmarz

TridentTopology topology = new TridentTopology();        
TridentState wordCounts =
     topology.newStream("spout1", spout)
       .each(new Fields("sentence"), new Split(), new Fields("word"))
       .groupBy(new Fields("word"))
       .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))                
       .parallelismHint(6);

nathanmarz

public class Split extends BaseFunction {
   public void execute(TridentTuple tuple, TridentCollector collector) {
       String sentence = tuple.getString(0);
       for(String word: sentence.split(" ")) {
           collector.emit(new Values(word));                
       }
   }
}

nathanmarz

.persistentAggregate(MemcachedState.transactional(serverLocations), new Count(), new Fields("count"))

nathanmarz

DRPCClient client = new DRPCClient("drpc.server.location", 3772);
System.out.println(client.execute("words", "cat dog the man");
// prints the JSON-encoded result, e.g.: "[[5078]]"

nathanmarz

topology.newDRPCStream("words")
       .each(new Fields("args"), new Split(), new Fields("word"))
       .groupBy(new Fields("word"))
       .stateQuery(wordCounts, new Fields("word"), new MapGet(), new Fields("count"))
       .each(new Fields("count"), new FilterNull())
       .aggregate(new Fields("count"), new Sum(), new Fields("sum"));

nathanmarz

TridentState urlToTweeters =
       topology.newStaticState(getUrlToTweetersState());
TridentState tweetersToFollowers =
       topology.newStaticState(getTweeterToFollowersState());

topology.newDRPCStream("reach")
       .stateQuery(urlToTweeters, new Fields("args"), new MapGet(), new Fields("tweeters"))
       .each(new Fields("tweeters"), new ExpandList(), new Fields("tweeter"))
       .shuffle()
       .stateQuery(tweetersToFollowers, new Fields("tweeter"), new MapGet(), new Fields("followers"))

nathanmarz

public class One implements CombinerAggregator<Integer> {
   public Integer init(TridentTuple tuple) {
       return 1;
   }

   public Integer combine(Integer val1, Integer val2) {
       return 1;
   }

   public Integer zero() {

nathanmarz

stream.each(new Fields("y"), new MyFilter())