Flink导入StarRocks

1、pom依赖

powershell 复制代码
  <properties>
    <maven.compiler.source>8</maven.compiler.source>
    <maven.compiler.target>8</maven.compiler.target>
    <flink.version>1.13.6</flink.version>
    <scala.binary.version>2.12</scala.binary.version>
  </properties>

  <dependencies>
    <!-- Apache Flink 的依赖, 这些依赖项,生产环境可以不打包到JAR文件中. -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-java</artifactId>
      <version>${flink.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
      <version>${flink.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
      <version>${flink.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-table-planner_${scala.binary.version}</artifactId>
      <version>${flink.version}</version>
    </dependency>
    <!-- flink-connector-starrocks -->
    <dependency>
      <groupId>com.starrocks</groupId>
      <artifactId>flink-connector-starrocks</artifactId>
      <version>1.2.5_flink-1.13_2.12</version>
    </dependency>
  </dependencies>

2、代码编写

java 复制代码
public class LoadJsonRecords {
    public static void main(String[] args) throws Exception {
        // To run the example, you should prepare in the following steps
        // 1. create a primary key table in your StarRocks cluster. The DDL is
        //  CREATE DATABASE `test`;
        //    CREATE TABLE `test`.`score_board`
        //    (
        //        `id` int(11) NOT NULL COMMENT "",
        //        `name` varchar(65533) NULL DEFAULT "" COMMENT "",
        //        `score` int(11) NOT NULL DEFAULT "0" COMMENT ""
        //    )
        //    ENGINE=OLAP
        //    PRIMARY KEY(`id`)
        //    COMMENT "OLAP"
        //    DISTRIBUTED BY HASH(`id`)
        //    PROPERTIES(
        //        "replication_num" = "1"
        //    );
        //
        // 2. replace the connector options "jdbc-url" and "load-url" with your cluster configurations
        MultipleParameterTool params = MultipleParameterTool.fromArgs(args);
        String jdbcUrl = params.get("jdbcUrl", "jdbc:mysql://fe-ip:9030");
        String loadUrl = params.get("loadUrl", "be-ip:8040;be-ip:8040;be-ip:8040");

        //String jdbcUrl = params.get("jdbcUrl", "jdbc:mysql://fe-ip:9030");
        //String loadUrl = params.get("loadUrl", "be-ip:8040;be-ip:8040;be-ip:8040");

        //String jdbcUrl = params.get("jdbcUrl", "jdbc:mysql://fe-ip:9030");
        //String loadUrl = params.get("loadUrl", "be-ip:8040,be-ip:8040,be-ip:8040");

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // Generate json-format records. Each record has three fields correspond to
        // the columns `id`, `name`, and `score` in StarRocks table.
        String[] records = new String[]{
                "{\"id\":1111, \"name\":\"starrocks-json\", \"score\":100}",
                "{\"id\":2222, \"name\":\"flink-json\", \"score\":100}",
        };
        DataStream<String> source = env.fromElements(records);

        // Configure the connector with the required properties, and you also need to add properties
        // "sink.properties.format" and "sink.properties.strip_outer_array" to tell the connector the
        // input records are json-format.
        StarRocksSinkOptions options = StarRocksSinkOptions.builder()
                .withProperty("jdbc-url", jdbcUrl)
                .withProperty("load-url", loadUrl)
                .withProperty("database-name", "tmp")
                .withProperty("table-name", "score_board")
                .withProperty("username", "")
                .withProperty("password", "")
                .withProperty("sink.properties.format", "json")
                .withProperty("sink.properties.strip_outer_array", "true")
                .withProperty("sink.parallelism","1")
                //.withProperty("sink.version","V1")
                .build();
        // Create the sink with the options
        SinkFunction<String> starRockSink = StarRocksSink.sink(options);
        source.addSink(starRockSink);

        env.execute("LoadJsonRecords");
    }
}
相关推荐
阿里云大数据AI技术1 天前
鹰角网络基于阿里云 EMR Serverless StarRocks 的实时分析工程实践
starrocks·clickhouse·阿里云·emr·实时分析
小Tomkk3 天前
StarRocks不能启动 ,StarRocksFe节点不能启动问题 处理
starrocks·log满了
jakeswang18 天前
去哪儿StarRocks实践
starrocks·后端
鸿乃江边鸟18 天前
Starrocks中的 Query Profile以及explain analyze及trace命令中的区别
大数据·starrocks·sql
鸿乃江边鸟20 天前
Starrocks ShortCircuit短路径的调度
大数据·starrocks·sql
镜舟科技21 天前
什么是列存储(Columnar Storage)?深度解析其原理与应用场景
starrocks·数据分析·列存储·行存储·mpp分布式架构
大数据狂人24 天前
深入剖析 StarRocks 与 Hive 的区别、使用场景及协同方案实践
大数据·starrocks·hive·数仓
StarRocks_labs1 个月前
Lakehouse x AI ,打造智能 BI 新体验
大数据·starrocks·人工智能·iceberg·lakehouse·智能bi·湖仓分析
StarRocks_labs1 个月前
StarRocks × MinIO:打造灵活高效的存算分离方案
数据库·starrocks·数据查询·存算分离·minlo