Doris的Routine Load方式消费Kafka数据进入Doris

假设kafka已有嵌套JSON数据格式为

复制代码

{
    "appId": "10000",
    "platform": "YY",
    "userId": "007",
    "userAgent": "6",
    "event": "login",
    "package": "org.apache.doris",
    "properties": {
        "phoneNumber": "13814516235",
        "actionTime": "1694928000",
        "deviceID": "device123",
        "deviceType": "smartphone",
        "appVersion": "1.0.0",
        "networkType": "WiFi",
        "os": "Android",
        "userUID": "user123",
        "nickname": "小王",
        "clientIp": "192.168.1.1"
    },
    "clientIp": "10.225.36.85",
    "timestamp": "1694928000",
    "source": "mobileApp",
    "sessionId": "12554122524422"
}

1、创建建表语句

复制代码

CREATE TABLE test_app_dwh.rt_ods_log_app_loginout (
    appId VARCHAR(20) NOT NULL COMMENT "应用ID",
    userId VARCHAR(20) NOT NULL COMMENT "用户ID",
    timestamp BIGINT COMMENT "时间戳",
    platform VARCHAR(20) NOT NULL COMMENT "平台",
    userAgent VARCHAR(20) NOT NULL COMMENT "用户代理",
    event VARCHAR(20) NOT NULL COMMENT "事件类型",
    package VARCHAR(100) NOT NULL COMMENT "包名",
    phoneNumber VARCHAR(20) COMMENT "电话号码",
    actionTime BIGINT COMMENT "动作时间戳",
    deviceID VARCHAR(50) COMMENT "设备ID",
    deviceType VARCHAR(20) COMMENT "设备类型",
    appVersion VARCHAR(20) COMMENT "应用版本",
    networkType VARCHAR(20) COMMENT "网络类型",
    os VARCHAR(20) COMMENT "操作系统",
    userUID VARCHAR(50) COMMENT "用户唯一标识",
    nickname VARCHAR(50) COMMENT "昵称",
    clientIp VARCHAR(20) COMMENT "客户端IP",
    source VARCHAR(20) COMMENT "来源",
    sessionId VARCHAR(50) COMMENT "会话ID"
)
DUPLICATE KEY(appId, userId, timestamp)
DISTRIBUTED BY HASH(appId) BUCKETS 1;

2、导入命令

复制代码

CREATE ROUTINE LOAD test_game_dwh.kafkajob_rt_ods_log_app_loginout ON rt_ods_log_app_loginout
COLUMNS(appId, userId, timestamp, platform, userAgent, event, package, phoneNumber, actionTime, deviceID, deviceType, appVersion, networkType, os, userUID, nickname, clientIp, source, sessionId)
PROPERTIES
(
    "desired_concurrent_number" = "1",
    "format" = "json",
    "strict_mode" = "false",
    "jsonpaths" = "[\"$.appId\",\"$.userId\",\"$.timestamp\",\"$.platform\",\"$.userAgent\",\"$.event\",\"$.package\",\"$.properties.phoneNumber\",\"$.properties.actionTime\",\"$.properties.deviceID\",\"$.properties.deviceType\",\"$.properties.appVersion\",\"$.properties.networkType\",\"$.properties.os\",\"$.properties.userUID\",\"$.properties.nickname\",\"$.properties.clientIp\",\"$.source\",\"$.sessionId\"]"
)
FROM KAFKA
(
    "kafka_broker_list" = "ip1:9092,ip2:9092,ip3:9092",
    "kafka_topic" = "loginout",
    "property.group.id" = "kafka_job",
    "property.kafka_default_offsets" = "OFFSET_BEGINNING"
);

最后kafka的数据就可以源源不断的存储到doris表里面了