1 Project dependencies
My Scala version is 2.12, where Flink's dependency should correspond to the Scala version
<properties>
<java.version>1.8</java.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_2.12</artifactId>
<version>1.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>1.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_2.12</artifactId>
<version>1.12.0</version>
</dependency>
</dependencies>
2 Local operation
2.1 function passed as a parameter
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
public class WordCountSourceDataStream {
public static void main(String[] args) throws Exception {
// 1. 构建环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// 2. 设置运行模式
env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);
// 3. 准备数据并接收
DataStream<String> linesDS = env.fromElements("hadoop,hdfs,flink,spark", "hadoop,hdfs,flink", "hadoop,hdfs", "hadoop,spark");
// 4. 处理数据
// 4.1 每行按照逗号分割组成集合
DataStream<String> wordsDS = linesDS.flatMap(new FlatMapFunction<String, String>() {
@Override
public void flatMap(String value, Collector<String> out) throws Exception {
// value是一行单词
String[] words = value.split(",");
for (String word : words) {
// 收集每个word
out.collect(word);
}
}
});
// 4.2 将每个单词记为1,并组成元组返回
DataStream<Tuple2<String, Integer>> word_1 = wordsDS.map(new MapFunction<String, Tuple2<String, Integer>>() {
@Override
public Tuple2<String, Integer> map(String value) throws Exception {
return Tuple2.of(value, 1);
}
});
// 4.3 对数据按照单词分组
KeyedStream<Tuple2<String, Integer>, String> word_1_group = word_1.keyBy(tuple2 -> tuple2.f0);
// 4.4 把分组的数据按照索引聚合
DataStream<Tuple2<String, Integer>> result = word_1_group.sum(1);
// 5. 输出结果
result.print();
// 6. 执行
env.execute();
}
}
2.2 Lambda anonymous function
Modified 4.1 and 4.2 of the above code
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.typeinfo.TypeHint;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
import java.util.Arrays;
public class WordCountSourceDataStreamL {
public static void main(String[] args) throws Exception {
// 1. 构建环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// 2. 设置运行模式
env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);
// 3. 准备数据并接收
DataStream<String> linesDS = env.fromElements("hadoop,hdfs,flink,spark", "hadoop,hdfs,flink", "hadoop,hdfs", "hadoop,spark");
// 4. 处理数据
// 4.1 每行按照逗号分割组成集合
DataStream<String> wordsDS = linesDS.flatMap(
(String value, Collector<String> out) -> Arrays.asList(value.split(",")).forEach(out::collect)
).returns(Types.STRING);
// 4.2 将每个单词记为1,并组成元组返回
DataStream<Tuple2<String, Integer>> word_1 = wordsDS.map(
(String value) -> Tuple2.of(value, 1)
).returns(TypeInformation.of(new TypeHint<Tuple2<String, Integer>>(){
}));
// 4.3 对数据按照单词分组
KeyedStream<Tuple2<String, Integer>, String> word_1_group = word_1.keyBy(tuple2 -> tuple2.f0);
// 4.4 把分组的数据按照索引聚合
DataStream<Tuple2<String, Integer>> result = word_1_group.sum(1);
// 5. 输出结果
result.print();
// 6. 执行
env.execute();
}
}
Console output:
3 Submit to run on Yarn
Modified 5 of the 2.2 code
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.typeinfo.TypeHint;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
import java.util.Arrays;
public class WordCountSourceDataStreamYarn {
public static void main(String[] args) throws Exception {
// 1. 构建环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// 2. 设置运行模式
env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);
// 3. 准备数据并接收
DataStream<String> linesDS = env.fromElements("hadoop,hdfs,flink,spark", "hadoop,hdfs,flink", "hadoop,hdfs", "hadoop,spark");
// 4. 处理数据
// 4.1 每行按照逗号分割组成集合
DataStream<String> wordsDS = linesDS.flatMap(
(String value, Collector<String> out) -> Arrays.asList(value.split(",")).forEach(out::collect)
).returns(Types.STRING);
// 4.2 将每个单词记为1,并组成元组返回
DataStream<Tuple2<String, Integer>> word_1 = wordsDS.map(
(String value) -> Tuple2.of(value, 1)
).returns(TypeInformation.of(new TypeHint<Tuple2<String, Integer>>(){
}));
// 4.3 对数据按照单词分组
KeyedStream<Tuple2<String, Integer>, String> word_1_group = word_1.keyBy(tuple2 -> tuple2.f0);
// 4.4 把分组的数据按照索引聚合
DataStream<Tuple2<String, Integer>> result = word_1_group.sum(1);
// 5. 写入结果
result.writeAsText("hdfs://localhost:9000/user/hadoop/flink/wordcount/output_"+System.currentTimeMillis());
// 6. 执行
env.execute();
}
}
Turn on HDFS and cluster:
start-dfs.sh
start-cluster.sh
Submit to run:
flink run -c WordCountSourceDataStreamYarn ~/IdeaProjects/FlinkStudy/target/FlinkStudy-1.0-SNAPSHOT.jar
operation result:
4 Error and solutions
Error:
Could not find a file system implementation for scheme ‘hdfs’
Solution:
https://blog.csdn.net/Tiezhu_Wang/article/details/114977487