Flink Java Table API & SQL 之 wordcount

最新推荐文章于 2023-03-26 09:34:40 发布

Lynn Gin

最新推荐文章于 2023-03-26 09:34:40 发布

阅读量161

点赞数

分类专栏： Flink 文章标签： java flink sql

本文链接：https://blog.csdn.net/weixin_46376562/article/details/125635530

版权

Flink 专栏收录该内容

19 篇文章 3 订阅

订阅专栏

Table API

package com.daidai.table;

import org.apache.flink.api.common.functions.MapFunction;
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.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;

import java.util.Arrays;

import static org.apache.flink.table.api.Expressions.$;

public class WordCountTable {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        DataStreamSource<String> source = env.fromCollection(Arrays.asList("hello", "word", "java", "scala", "java"));
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = source.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                return Tuple2.of(value, 1);
            }
        });

        Table table = tableEnv.fromDataStream(wordAndOne, $("word"), $("sum"));
        Table result = table.groupBy($("word"))
                .select($("word"), $("sum").sum().as("count"));

        tableEnv.toRetractStream(result, Row.class).print();

        env.execute();
    }
}

SQL

package com.daidai.table;

import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;

import java.util.Arrays;

import static org.apache.flink.table.api.Expressions.$;

public class WordCountSQL {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        DataStreamSource<String> source = env.fromCollection(Arrays.asList("hello", "word", "java", "scala", "java"));
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = source.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                return Tuple2.of(value, 1);
            }
        });

        Table table = tableEnv.fromDataStream(wordAndOne, $("word"), $("sum"));

        tableEnv.createTemporaryView("wc", table);

        Table result = tableEnv.sqlQuery("select word, sum(`sum`) from wc group by word");

        tableEnv.toRetractStream(result, Row.class).print();

        env.execute();
    }

}