（五）Flink Table API 编程

首先：flink根据使用的便捷性提供了三种API，自下而上是：

Table API & SQL

1、声明行：用户只关心做什么，不用关心怎么做

2、高性能：支持性能优化，可以获取更好的执行性能

3、流批统一：相同的统计逻辑，既可以流模式运行，也可以批模式运行

4、性能稳定：语义遵循SQL标准，不易变动

5、易理解：语义明确，所见即所得

Table API：tab.groupBy("word").select("word,count(1) as count")

SQL:SELECT word,COUNT(*) as cnt FROM MyTable GROUP BY word

Table API 特点：

1、Table API使得多声明的数据处理起来比较容易

　　例如：我们把a大于10的数据存xxx的外部表，同时需要把a小于10的数据插入到外部表yyy，我们是使用TableAPI很方便。

　　　　Table.filter(a>10).insertInto("xxx")

　　　　Table.filter(a<10).insertInto("yyy")

2、TableAPI使得扩展标准SQL更容易（当且仅当需要的时候）

Table API 编程：

1、WordCount示例：

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.api.java.StreamTableEnvironment;
import org.apache.flink.table.descriptors.FileSystem;
import org.apache.flink.table.descriptors.OldCsv;
import org.apache.flink.table.descriptors.Schema;
import org.apache.flink.types.Row;

public class JavaStreamWordCount {

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tEnv = TableEnvironment.getTableEnvironment(env);

        String path = JavaStreamWordCount.class.getClassLoader().getResource("words.txt").getPath();
        tEnv.connect(new FileSystem().path(path))
            .withFormat(new OldCsv().field("word", Types.STRING).lineDelimiter("\n"))
            .withSchema(new Schema().field("word", Types.STRING))
            .inAppendMode()
            .registerTableSource("fileSource");

        Table result = tEnv.scan("fileSource")
            .groupBy("word")
            .select("word, count(1) as count");

        tEnv.toRetractStream(result, Row.class).print();
        env.execute();
    }
}

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.api.java.StreamTableEnvironment;
import org.apache.flink.table.descriptors.FileSystem;
import org.apache.flink.table.descriptors.OldCsv;
import org.apache.flink.table.descriptors.Schema;
import org.apache.flink.types.Row;

public class JavaStreamWordCount {

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tEnv = TableEnvironment.getTableEnvironment(env);

        String path = JavaStreamWordCount.class.getClassLoader().getResource("words.txt").getPath();
        tEnv.connect(new FileSystem().path(path))
            .withFormat(new OldCsv().field("word", Types.STRING).lineDelimiter("\n"))
            .withSchema(new Schema().field("word", Types.STRING))
            .inAppendMode()
            .registerTableSource("fileSource");

        Table result = tEnv.scan("fileSource")
            .groupBy("word")
            .select("word, count(1) as count");

        tEnv.toRetractStream(result, Row.class).print();
        env.execute();
    }
}

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.java.BatchTableEnvironment;
import org.apache.flink.table.descriptors.FileSystem;
import org.apache.flink.table.descriptors.OldCsv;
import org.apache.flink.table.descriptors.Schema;
import org.apache.flink.types.Row;

public class JavaBatchWordCount {

    public static void main(String[] args) throws Exception {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        BatchTableEnvironment tEnv = BatchTableEnvironment.create(env);

        String path = JavaBatchWordCount.class.getClassLoader().getResource("words.txt").getPath();
        tEnv.connect(new FileSystem().path(path))
            .withFormat(new OldCsv().field("word", Types.STRING).lineDelimiter("\n"))
            .withSchema(new Schema().field("word", Types.STRING))
            .registerTableSource("fileSource");

        Table result = tEnv.scan("fileSource")
            .groupBy("word")
            .select("word, count(1) as count");

        tEnv.toDataSet(result, Row.class).print();
    }
}