使用 Flink SQL 读取本地csv文件，建表并输出到控制台（Java实现）

data.csv内容:

1,Tom,15
2,Lily,13
3,Mike,21
4,John,20
5,Emma,18
6,Sophia,19
7,David,22
8,James,16
9,Olivia,17
10,Robert,23
11,Emily,14
12,Daniel,25
13,Amelia,24

代码1（直接输出结果）

package com.auguigu.demo;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;

import java.nio.file.Paths;

public class TextSql {

    public static void main(String[] args) throws Exception {

        // 相对路径
        String csvFilePath = "input/data.csv";
        // 转换为绝对路径
        String absoluteCsvFilePath = Paths.get(csvFilePath).toAbsolutePath().toString();

        // 创建流式执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        // 注册 CSV 表
        tableEnv.executeSql(
                "CREATE TABLE csv_source (" +
                        "  `uid` INT," +
                        "  `name` STRING," +
                        "  `age` INT" +
                        ") WITH (" +
                        "  'connector' = 'filesystem'," +
                        "  'path' = '" + absoluteCsvFilePath + "'," +
                        "  'format' = 'csv'," +
                        "  'csv.field-delimiter' = ','," +
                        "  'csv.ignore-parse-errors' = 'true'" +
                        ")"
        );

        // 执行查询，打印结果
        tableEnv.executeSql("select name,uid from csv_source").print();
    }
}

代码1结果

+----+--------------------------------+-------------+
| op |                           name |         uid |
+----+--------------------------------+-------------+
| +I |                            Tom |           1 |
| +I |                           Lily |           2 |
| +I |                           Mike |           3 |
| +I |                           John |           4 |
| +I |                           Emma |           5 |
| +I |                         Sophia |           6 |
| +I |                          David |           7 |
| +I |                          James |           8 |
| +I |                         Olivia |           9 |
| +I |                         Robert |          10 |
| +I |                          Emily |          11 |
| +I |                         Daniel |          12 |
| +I |                         Amelia |          13 |
+----+--------------------------------+-------------+
13 rows in set

Process finished with exit code 0

代码2（使用DataStream输出结果）：

package com.xxx.demo;

import org.apache.flink.streaming.api.datastream.DataStream;
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.nio.file.Paths;

public class TextSql {

    public static void main(String[] args) throws Exception {

        // 相对路径
        String csvFilePath = "input/data.csv";
        // 转换为绝对路径
        String absoluteCsvFilePath = Paths.get(csvFilePath).toAbsolutePath().toString();

        // 创建流式执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        // 注册 CSV 表
        tableEnv.executeSql(
                "CREATE TABLE csv_source (" +
                        "  `uid` INT," +
                        "  `name` STRING," +
                        "  `age` INT" +
                        ") WITH (" +
                        "  'connector' = 'filesystem'," +
                        "  'path' = '" + absoluteCsvFilePath + "'," +
                        "  'format' = 'csv'," +
                        "  'csv.field-delimiter' = ','," +
                        "  'csv.ignore-parse-errors' = 'true'" +
                        ")"
        );

        // 执行查询
        Table result = tableEnv.sqlQuery("select name,uid from csv_source");
        // 将查询结果转换为DataStream
        DataStream<Row> stream = tableEnv.toDataStream(result, Row.class);
        // 控制台输出
        stream.print();

        // 执行任务
        env.execute();
    }
}

代码2输出结果

+I[Tom, 1]
+I[Lily, 2]
+I[Mike, 3]
+I[John, 4]
+I[Emma, 5]
+I[Sophia, 6]
+I[David, 7]
+I[James, 8]
+I[Olivia, 9]
+I[Robert, 10]
+I[Emily, 11]
+I[Daniel, 12]
+I[Amelia, 13]

Process finished with exit code 0

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.example</groupId>
    <artifactId>flink-demo1</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <java.version>11</java.version>
        <flink.version>1.17.2</flink.version>
        <maven.compiler.source>${java.version}</maven.compiler.source>
        <maven.compiler.target>${java.version}</maven.compiler.target>


    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-api-java-bridge</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner-loader</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-runtime</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka</artifactId>
            <version>${flink.version}</version>
        </dependency>


        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-files</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-csv</artifactId>
            <version>${flink.version}</version>
        </dependency>

    </dependencies>

</project>