import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class WordCount {

    public static void main(String[] args) throws Exception {

        // StreamExecutionEnvironment 생성
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 데이터 소스 생성
        DataStream<String> text = env.fromElements(
		        "Apache Flink is a framework for stream processing and batch processing.",
		        "It is designed to run on all common cluster environments.");

        // 단어별로 분리하고 카운트하기
        DataStream<Tuple2<String, Integer>> counts = text
                .flatMap(new Tokenizer())
                .keyBy(0)
                .sum(1);

        // 결과 출력
        counts.print();

        // 스트리밍 애플리케이션 실행
        env.execute("WordCount");
    }

    public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
            // 문장을 단어로 분리하여 출력
            for (String word : value.split(" ")) {
                out.collect(new Tuple2<>(word, 1));
            }
        }
    }
}