+0
日增长
26,473
stars
14,184
forks
896
watchers
29,939
prs
0
issues
0
releases

README

Apache Flink

Apache Flink is an open source stream processing framework with powerful stream- and batch-processing capabilities.

Learn more about Flink at https://flink.apache.org/


 Features

 A streaming-first runtime that supports both batch processing and data streaming programs

 Elegant and fluent APIs in Java

 A runtime that supports very high throughput and low event latency at the same time

 Support for event time and out-of-order processing in the DataStream API, based on the Dataflow Model

 Flexible windowing (time, count, sessions, custom triggers) across different time semantics (event time, processing time)

 Fault-tolerance with exactly-once processing guarantees

 Natural back-pressure in streaming programs

 Libraries for Graph processing (batch), Machine Learning (batch), and Complex Event Processing (streaming)

 Custom memory management for efficient and robust switching between in-memory and out-of-core data processing algorithms

 Compatibility layers for Apache Hadoop MapReduce

 Integration with YARN, HDFS, HBase, and other components of the Apache Hadoop ecosystem


 Streaming Example
java
// pojo class WordWithCount
public class WordWithCount {
    public String word;
    public int count;

    public WordWithCount() {}
    
    public WordWithCount(String word, int count) {
        this.word = word;
        this.count = count;
    }
}

// main method
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStreamSource text = env.socketTextStream(host, port);
DataStream windowCounts = text
    .flatMap(
        (FlatMapFunction) (line, collector) 
            - Arrays.stream(line.split("\\s")).forEach(collector::collect)
    ).returns(String.class)
    .map(word - new WordWithCount(word, 1)).returns(TypeInformation.of(WordWithCount.class))
    .keyBy(wordWithCnt - wordWithCnt.word)
    .window(TumblingProcessingTimeWindows.of(Duration.ofSeconds(5)))
    .sum("count").returns(TypeInformation.of(WordWithCount.class));

windowCounts.print();
env.execute();
}


 Batch Example
java
// pojo class WordWithCount
public class WordWithCount {
    public String word;
    public int count;

    public WordWithCount() {}

    public WordWithCount(String word, int count) {
        this.word = word;
        this.count = count;
    }
}

// main method
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setRuntimeMode(RuntimeExecutionMode.BATCH);
FileSource source = FileSource.forRecordStreamFormat(new TextLineInputFormat(), new Path("MyInput.txt")).build();
DataStreamSource text = env.fromSource(source, WatermarkStrategy.noWatermarks(), "MySource");
DataStream windowCounts = text
        .flatMap((FlatMapFunction) (line, collector) - Arrays
                .stream(line.split("\\s"))
                .forEach(collector::collect)).returns(String.class)
        .map(word - new WordWithCount(word, 1)).returns(TypeInformation.of(WordWithCount.class))
        .keyB

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON