批处理
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
public class BatchWordCount {
public static void main(String[] args) throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSource<String> lineDataSource = env.readTextFile("input/words.txt");
FlatMapOperator<String, Tuple2<String, Long>> wordAndOneTuple = lineDataSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
String[] words = line.split(" ");
for (String word : words) {
out.collect(Tuple2.of(word, 1L));
}
}).returns(Types.TUPLE(Types.STRING, Types.LONG));
UnsortedGrouping<Tuple2<String, Long>> wordAndOneGroup = wordAndOneTuple.groupBy(0);
AggregateOperator<Tuple2<String, Long>> sum = wordAndOneGroup.sum(1);
sum.print();
}
}
![[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-VYrdmeoL-1650032968723)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220410165452008.png)]](https://img-blog.csdnimg.cn/3a3beb1a6d3043ba96064125738771c7.png)
有界流式处理
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
public class BoundedStreamWordCount {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStreamSource<String> lineDataStreamSource = env.readTextFile("input/words.txt");
SingleOutputStreamOperator<Tuple2<String, Long>> wordsAndOneTuple = lineDataStreamSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
String[] words = line.split(" ");
for (String word : words) {
out.collect(Tuple2.of(word, 1L));
}
}).returns(Types.TUPLE(Types.STRING, Types.LONG));
KeyedStream<Tuple2<String, Long>, String> wordAndOneKeyedStream = wordsAndOneTuple.keyBy(data -> data.f0);
SingleOutputStreamOperator<Tuple2<String, Long>> sum = wordAndOneKeyedStream.sum(1);
sum.print();
env.execute();
}
}
![在这里插入图片描述](https://img-blog.csdnimg.cn/c60da37471aa49ec8b93dd527b963e25.png)
无界流式处理
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
public class StreamWordCount {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStreamSource<String> lineDataStreamSource = env.socketTextStream("hadoop102", 7777);
SingleOutputStreamOperator<Tuple2<String, Long>> wordsAndOneTuple = lineDataStreamSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
String[] words = line.split(" ");
for (String word : words) {
out.collect(Tuple2.of(word, 1L));
}
}).returns(Types.TUPLE(Types.STRING, Types.LONG));
KeyedStream<Tuple2<String, Long>, String> wordAndOneKeyedStream = wordsAndOneTuple.keyBy(data -> data.f0);
SingleOutputStreamOperator<Tuple2<String, Long>> sum = wordAndOneKeyedStream.sum(1);
sum.print();
env.execute();
}
}
![在这里插入图片描述](https://img-blog.csdnimg.cn/389e39ddd9b047d198f115936245570e.png)