使用Flink-JDBC将数据同步到Doris

上海研博数据2025-01-14 19:22

在现代数据分析和处理环境中，数据同步是一个至关重要的环节。Apache Flink和Doris是两个强大的工具，分别用于实时数据处理和大规模并行处理（MPP）SQL数据库。本文将介绍如何使用Flink-JDBC连接器将数据同步到Doris。

一、背景介绍

1、Apache Flink：Flink是一个开源流处理框架，用于处理无界和有界数据流。它提供了高吞吐量、低延迟的数据处理能力，并支持复杂的状态管理和容错机制。

2、Doris：Doris（原百度Palo）是一个基于MPP架构的高性能、实时分析型数据库。它支持高并发查询和高吞吐量的复杂分析场景，具有亚秒级响应时间，并兼容MySQL协议。

3、JDBC：Java数据库连接（JDBC）是一种Java API，用于连接和操作数据库。Flink提供了JDBC连接器，允许从各种关系型数据库中读取和写入数据。

二、准备工作

1、安装Flink：确保你的环境中已经安装了Apache Flink。本文示例使用的是Flink 1.20.0版本。

2、安装Doris：确保你的环境中已经安装并配置了Doris。

3、准备相关测试数据集（excel）。

4、依赖库：使用flink-connector-jdbc和Doris的JDBC驱动。如果你使用的是Maven，可以在项目的pom.xml文件中添加以下依赖：

java 复制代码 
<dependencies>
  <!--    flink-->
  <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>${flink.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-base</artifactId>
    <version>${flink.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-kafka</artifactId>
    <version>${flink-kafka.version}</version>
  </dependency>
  <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-connector-jdbc -->
  <dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-jdbc</artifactId>
    <version>${flink-jdbc.version}</version>
  </dependency>

  <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-connector-files -->
  <dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-files</artifactId>
    <version>${flink.version}</version>
  </dependency>

  <!-- flink-doris-connector -->
  <dependency>
    <groupId>org.apache.doris</groupId>
    <artifactId>flink-doris-connector-1.16</artifactId>
    <version>${flink-doris.version}</version>
  </dependency>

  <!--    json处理-->
  <dependency>
    <groupId>com.alibaba.fastjson2</groupId>
    <artifactId>fastjson2</artifactId>
    <version>2.0.53</version>
  </dependency>
  <dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>easyexcel</artifactId>
    <version>4.0.3</version>
  </dependency>

  <dependency>
    <groupId>org.projectlombok</groupId>
    <artifactId>lombok</artifactId>
    <version>1.18.36</version>
  </dependency>
  <!-- https://mvnrepository.com/artifact/org.apache.logging.log4j/log4j-core -->
  <dependency>
    <groupId>org.apache.logging.log4j</groupId>
    <artifactId>log4j-core</artifactId>
    <version>2.24.3</version>
  </dependency>
  <dependency>
    <groupId>mysql</groupId>
    <artifactId>mysql-connector-java</artifactId>
    <version>8.0.27</version>
  </dependency>

  <dependency>
    <groupId>junit</groupId>
    <artifactId>junit</artifactId>
    <version>3.8.1</version>
    <scope>test</scope>
  </dependency>
</dependencies>

三、实现步骤

1.读取并解析excel中的测试数据集

java 复制代码 
package org.example.day20250105;

import com.alibaba.excel.EasyExcel;
import com.alibaba.excel.context.AnalysisContext;
import com.alibaba.excel.read.listener.ReadListener;
import com.alibaba.excel.support.ExcelTypeEnum;
import org.example.day20250105.domain.*;
import org.example.day20250105.flink.jdbc.OdsXwDetailDataWriteByFlink;

import java.util.ArrayList;
import java.util.List;

public class ExcelDataHandle {
    private static final String filePath = "src/main/resources/20250105/WW2216069019-循环-90-3-1-20230104110446.xlsx";
    /**
     * 每隔5条存储数据库，实际使用中可以100条，然后清理list ，方便内存回收
     */
    private static final int BATCH_COUNT = 1000;
    /**
     * 缓存的数据
     */
    private static List<OdsXwCycleData> odsXwCycleDataList = new ArrayList<>(BATCH_COUNT);
    private static List<OdsXwDetailData> odsXwDetailDataList = new ArrayList<>(BATCH_COUNT);
    private static List<OdsXwStepData> odsXwStepDataList = new ArrayList<>(BATCH_COUNT);
    private static List<OdsTestFlow> odsTestFlowList = new ArrayList<>(BATCH_COUNT);
    private static final OdsTestFlow finalFlow = new OdsTestFlow();

    public static void main(String[] args) {
        EasyExcel.read(filePath, OdsTestFlowDataFormat.class, new OdsTestFlowDataHandle()).sheet(1).doRead();
        System.out.println(odsTestFlowList.add(finalFlow));
        System.out.println(odsTestFlowList);

    }

    public static List<OdsXwCycleData> readCycleData() {
        EasyExcel.read(filePath, OdsXwCycleData.class, new OdsXwCycleDataHandle()).sheet(2).doRead();
        return odsXwCycleDataList;
    }

    public static List<OdsTestFlow> readTestFlowData(){
        EasyExcel.read(filePath, OdsTestFlowDataFormat.class, new OdsTestFlowDataHandle()).sheet(1).doRead();
        return odsTestFlowList;
    }
    public static List<OdsXwStepData> readStepData() {
        EasyExcel.read(filePath, OdsXwStepData.class, new OdsXwStepDataHandle()).excelType(ExcelTypeEnum.XLSX).sheet(3).doRead();
        return odsXwStepDataList;
    }

    public static List<OdsXwDetailData> readDetailData() {
        EasyExcel.read(filePath, OdsXwDetailData.class, new OdsXwDetailDataHandle()).sheet(4).doRead();
        return odsXwDetailDataList;
    }

    /**
     * 新威原始测试流程数据   sheet 1
     */
    public static class OdsTestFlowDataHandle implements ReadListener<OdsTestFlowDataFormat> {
        private static int rowCount = 0;

        @Override
        public void invoke(OdsTestFlowDataFormat format, AnalysisContext analysisContext) {
            if (rowCount > 5) {
                return;
            }
            if (rowCount == 0) {
                finalFlow.setStartStepNo(format.getV1());
                finalFlow.setVoltageUpperLimit(format.getV2());
                finalFlow.setBatteryBatchNumber(format.getV3());
            } else if (rowCount == 1) {
                finalFlow.setCycleTimes(format.getV1());
                finalFlow.setVoltageLowerLimit(format.getV2());
                finalFlow.setCreator(format.getV3());
            } else if (rowCount == 2) {
                finalFlow.setRecordCondition(format.getV1());
                finalFlow.setCurrentUpperLimit(format.getV2());
                finalFlow.setRemark(format.getV3());
            } else if (rowCount == 3) {
                finalFlow.setVoltageRange(format.getV1());
                finalFlow.setCurrentLowerLimit(format.getV2());
            } else if (rowCount == 4) {
                finalFlow.setCurrentRange(format.getV1());
                finalFlow.setStartDatetime(format.getV2());
                finalFlow.setTestBarcode(format.getV3());
            } else if (rowCount == 5) {
                finalFlow.setActiveSubstances(format.getV1());
                finalFlow.setNominalCapacity(format.getV2());
            }
            rowCount++;
        }

        @Override
        public void doAfterAllAnalysed(AnalysisContext analysisContext) {
            odsTestFlowList.add(finalFlow);
        }
    }

    /**
     * 循环数据处理   sheet 2
     */
    public static class OdsXwCycleDataHandle implements ReadListener<OdsXwCycleData> {
        @Override
        public void invoke(OdsXwCycleData odsXwCycleData, AnalysisContext analysisContext) {
            odsXwCycleDataList.add(odsXwCycleData);
//            if (odsXwCycleDataList.size() >= BATCH_COUNT) {
//                // 存储完成清理 list
//                odsXwCycleDataList.clear();
//            }
        }

        @Override
        public void doAfterAllAnalysed(AnalysisContext analysisContext) {

        }
    }

    /**
     * 新威原始详情数据 sheet 4
     */
    public static class OdsXwDetailDataHandle implements ReadListener<OdsXwDetailData> {
        @Override
        public void invoke(OdsXwDetailData odsXwDetailData, AnalysisContext analysisContext) {
            odsXwDetailDataList.add(odsXwDetailData);
            if (odsXwDetailDataList.size() >= BATCH_COUNT) {
                //每1000条去调用存储方法一次
                OdsXwDetailDataWriteByFlink.save(odsXwDetailDataList);
                // 存储完成清理 list
                odsXwDetailDataList.clear();
            }
        }

        @Override
        public void doAfterAllAnalysed(AnalysisContext analysisContext) {

        }
    }

    /**
     * 新威原始工步数据 sheet 3
     */
    public static class OdsXwStepDataHandle implements ReadListener<OdsXwStepData> {
        @Override
        public void invoke(OdsXwStepData odsXwStepData, AnalysisContext analysisContext) {
            odsXwStepDataList.add(odsXwStepData);
        }

        @Override
        public void doAfterAllAnalysed(AnalysisContext analysisContext) {

        }
    }
}

2.通过filnk-jdbc写入到doris中

java 复制代码 
package org.example.day20250105.flink;

public interface DorisConstant {
   public static final String FE_NODE_URL = "192.168.12.244:18030";
    String BE_NODE_URL = "192.168.12.244:18030";

    String DORIS_JDBC_URL = "jdbc:mysql://192.168.12.244:19030/test_db_czq";

    String USERNAME = "root";
    String PASSWORD = "*******";
    String DB_NAMME = "test_db_czq";

    String DRIVER_CLASS_NAME = "com.mysql.cj.jdbc.Driver";
}


package org.example.day20250105.flink.jdbc;

import org.apache.flink.connector.jdbc.JdbcConnectionOptions;
import org.apache.flink.connector.jdbc.JdbcSink;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.example.day20250105.ExcelDataHandle;
import org.example.day20250105.flink.DorisConstant;

/**
 * INSERT INTO `test_db_czq`.`ods_xw_step_data` (`cycle_id`, `step_id`, `step_no`, `step_type`, `step_time`, `start_absolute_time`, `end_absolute_time`, `capacity`, `specific_capacity`, `charge_capacity`, `charge_specific_capacity`, `discharge_capacity`, `discharge_specific_capacity`, `net_discharge_capacity`, `energy`, `specific_energy`, `charge_energy`, `charge_specific_energy`, `discharge_energy`, `discharge_specific_energy`, `net_discharge_energy`, `super_capacitor`, `initial_voltage`, `charge_initial_voltage`, `discharge_initial_voltage`, `end_voltage`, `charge_end_voltage`, `discharge_end_voltage`, `charge_median_voltage`, `discharge_median_voltage`, `initial_current`, `end_current`, `dcir`, `t1_start_temperature`, `t1_end_temperature`, `t1_max_temperature`, `t1_min_temperature`, `v1_start_voltage`, `v1_end_voltage`, `v1_max_voltage`, `v1_min_voltage`, `file_name`) VALUES ('5', '30', '45', '恒流放电', '02:00:19', '2023-01-03 03:47:37', '2023-01-03 05:47:56', '4.0266', '4026648', '0', '0', '4.0266', '4026648', '4.0266', '12.858', '12857977.78', '0', '0', '12.858', '12857977.78', '12.858', '10407.4004', '3.4573', '0', '3.4573', '1.9993', '0', '1.9993', '0', '3.2285', '0', '-2.0089', '0', '25.3', '25.5', '25.6', '25.2', '-0.0003', '-0.0003', '-0.0001', '-0.0003', NULL);
 */
public class OdsXwStepDataWriteByFlink {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        env.fromData(ExcelDataHandle.readStepData())
                .addSink(JdbcSink.sink(
                        "INSERT INTO `test_db_czq`.`ods_xw_step_data` " +
                                "(`cycle_id`, `step_id`, `step_no`, `step_type`, `step_time`, `start_absolute_time`, " +
                                "`end_absolute_time`, `capacity`, `specific_capacity`, `charge_capacity`, `charge_specific_capacity`," +
                                " `discharge_capacity`, `discharge_specific_capacity`, `net_discharge_capacity`, `energy`, `specific_energy`, " +
                                "`charge_energy`, `charge_specific_energy`, `discharge_energy`, `discharge_specific_energy`, `net_discharge_energy`, " +
                                "`super_capacitor`, `initial_voltage`, `charge_initial_voltage`, `discharge_initial_voltage`, `end_voltage`, `charge_end_voltage`," +
                                " `discharge_end_voltage`, `charge_median_voltage`, `discharge_median_voltage`, `initial_current`, `end_current`, `dcir`, " +
                                "`t1_start_temperature`, `t1_end_temperature`, `t1_max_temperature`, `t1_min_temperature`, `v1_start_voltage`, `v1_end_voltage`, " +
                                "`v1_max_voltage`, `v1_min_voltage`, `file_name`) " +
                                "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?,?, ?, ?, ?, ?, ?, ?, ?, ?, ?,?, ?, ?, ?, ?, ?, ?, ?, ?, ?,?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?);",
                        (ps, data) -> {
                            ps.setString(1, data.getCycle_id());
                            ps.setString(2, data.getStep_id());
                            ps.setString(3, data.getStep_no());
                            ps.setString(4, data.getStep_type());
                            ps.setString(5, data.getStep_time());
                            ps.setString(6, data.getStart_absolute_time());
                            ps.setString(7, data.getEnd_absolute_time());
                            ps.setString(8, data.getCapacity());
                            ps.setString(9, data.getSpecific_capacity());
                            ps.setString(10, data.getCharge_capacity());
                            ps.setString(11, data.getCharge_specific_capacity());
                            ps.setString(12, data.getDischarge_capacity());
                            ps.setString(13, data.getDischarge_specific_capacity());
                            ps.setString(14, data.getNet_discharge_capacity());
                            ps.setString(15, data.getEnergy());
                            ps.setString(16, data.getSpecific_energy());
                            ps.setString(17, data.getCharge_energy());
                            ps.setString(18, data.getCharge_specific_energy());
                            ps.setString(19, data.getDischarge_energy());
                            ps.setString(20, data.getDischarge_specific_energy());
                            ps.setString(21, data.getNet_discharge_energy());
                            ps.setString(22, data.getSuper_capacitor());
                            ps.setString(23, data.getInitial_voltage());
                            ps.setString(24, data.getCharge_initial_voltage());
                            ps.setString(25, data.getDischarge_initial_voltage());
                            ps.setString(26, data.getEnd_voltage());
                            ps.setString(27, data.getCharge_end_voltage());
                            ps.setString(28, data.getDischarge_end_voltage());
                            ps.setString(29, data.getCharge_median_voltage());
                            ps.setString(30, data.getDischarge_median_voltage());
                            ps.setString(31, data.getInitial_current());
                            ps.setString(32, data.getEnd_current());
                            ps.setString(33, data.getDcir());
                            ps.setString(34, data.getT1_start_temperature());
                            ps.setString(35, data.getT1_end_temperature());
                            ps.setString(36, data.getT1_max_temperature());
                            ps.setString(37, data.getT1_min_temperature());
                            ps.setString(38, data.getV1_start_voltage());
                            ps.setString(39, data.getV1_end_voltage());
                            ps.setString(40, data.getV1_max_voltage());
                            ps.setString(41, data.getV1_min_voltage());
                            ps.setString(42, data.getFile_name());
                        },
                        new JdbcConnectionOptions.JdbcConnectionOptionsBuilder()
                                .withUsername(DorisConstant.USERNAME)
                                .withPassword(DorisConstant.PASSWORD)
                                .withDriverName(DorisConstant.DRIVER_CLASS_NAME)
                                .withUrl(DorisConstant.DORIS_JDBC_URL)
                                .build()
                ));
        env.execute();
    }
}
复制代码

四、实现结果

登录Doris后台可以看到数据已经同步到了ods_xw_step_data表中

相关推荐
码界筑梦坊43 分钟前
基于Flask的京东商品信息可视化分析系统的设计与实现
大数据·python·信息可视化·flask·毕业设计
专注API从业者4 小时前
分布式电商系统中的API网关架构设计
大数据·数据仓库·分布式·架构
viperrrrrrrrrr75 小时前
大数据学习(49) - Flink按键分区状态（Keyed State）
大数据·学习·flink
狮歌~资深攻城狮6 小时前
未来已来：HBase的新功能与发展趋势展望
大数据·wpf·hbase
weixin_307779136 小时前
PySpark实现MERGE INTO的数据合并功能
大数据·python·spark
vx1530278236211 小时前
CDGA|企业数据治理实战：从疏通“信息河”到打造优质“数据湖”
java·大数据·人工智能·cdga·数据治理
AIRIOT12 小时前
AIRIOT智慧消防管理解决方案
大数据
哔哩哔哩技术13 小时前
ClickHouse BSI与字典服务在B站商业化DMP中的应用实践
大数据
想做富婆14 小时前
数仓搭建(hive):DM搭建(数据集市层)
大数据·数仓搭建
热门推荐
01本地部署DeepSeek教程（Mac版本）02如何在WPS和Word/Excel中直接使用DeepSeek功能03DeepSeek本地部署详细指南04DeepSeek各版本说明与优缺点分析05本地化部署AI知识库：基于Ollama+DeepSeek+AnythingLLM保姆级教程06DeepSeek r1本地安装全指南07太炸裂了！清华大学deepseek从入门到精通使用手册又出第三版了，《普通人如何抓住DeepSeek红利》（无套路，直接下载）08DeepSeek R1本地化部署 Ollama + Chatbox 打造最强 AI 工具09在Windows下安装Ollama并体验DeepSeek r1大模型10Page Assist - 本地Deepseek模型 Web UI 的安装和使用