一、同步MySQL数据到HDFS案例
案例要求：同步gmall数据库中base_province表数据到HDFS的/base_province目录
需求分析：要实现该功能，需选用MySQLReader和HDFSWriter，MySQLReader具有两种模式分别是TableMode和QuerySQLMode，前者使用table，column，where等属性声明需要同步的数据；后者使用一条SQL查询语句声明需要同步的数据。
因为需要使用到MySQL和HDFS，需要确保MySQL服务和HDFS进程都成功启动。
1.MySQLReader之TableMode
1.1 编写配置文件
（1）创建配置文件base_province.json
vim /opt/module/datax/job/base_province.json
（2）配置文件内容如下
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"column": [
"id",
"name",
"region_id",
"area_code",
"iso_code",
"iso_3166_2",
"create_time",
"operate_time"
],
"where": "id>=3",
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
],
"table": [
"base_province"
]
}
],
"password": "000000",
"splitPk": "",
"username": "root"
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "region_id",
"type": "string"
},
{
"name": "area_code",
"type": "string"
},
{
"name": "iso_code",
"type": "string"
},
{
"name": "iso_3166_2",
"type": "string"
},
{
"name": "create_time",
"type": "string"
},
{
"name": "operate_time",
"type": "string"
}
],
"compress": "gzip",
"defaultFS": "hdfs://hadoop102:8020",
"fieldDelimiter": "\t",
"fileName": "base_province",
"fileType": "text",
"path": "/base_province",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": 1
}
}
}
}
配置文件说明
（1）Reader参数说明
"reader": {
"name": "mysqlreader", #使用MySQL读取器
"parameter": {
"column": [ "id","name", "region_id", "area_code", "iso_code","iso_3166_2",
"create_time","operate_time" ],
"where": "id>=3", # where过滤条件，只同步id>3的数据
"connection": [
{
"jdbcUrl": [ #数据库JDBC URL
"jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
],
"table": [
"base_province" #需要同步的表名
]
}
],
"password": "******", #数据库密码
"splitPk": "", #分片字段，如果指定该字段，则DataX会启动多个Taask同步数据；若未指定，则只会有单个Task。该参数只在TableMode模式下有效，QueryMode只会有单个Task。
"username": "root" #数据库用户名
}
}
(2)Writer参数说明
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [ #列信息
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "region_id",
"type": "string"
},
{
"name": "area_code",
"type": "string"
},
{
"name": "iso_code",
"type": "string"
},
{
"name": "iso_3166_2",
"type": "string"
},
{
"name": "create_time",
"type": "string"
},
{
"name": "operate_time",
"type": "string"
}
],
"compress": "gzip", #HDFS压缩类型
"defaultFS": "hdfs://hadoop102:8020", #HDFS文件系统给namenode节点地址
"fieldDelimiter": "\t", #HDFS文件字段分隔符
"fileName": "base_province", #HDFS文件名前缀
"fileType": "text", #HDFS文件类型，支持“text”或“orc”
"path": "/base_province", #HDFS文件系统目标路径
"writeMode": "append" #数据写入格式
}
}
（3）Setting参数说明
"setting": {
"speed": { #传输速度配置
"channel": 1 #并发数
}
}
HFDS Writer并未提供nullFormat参数：也就是用户并不能自定义null值写到HFDS文件中的存储格式。默认情况下，HFDS Writer会将null值存储为空字符串（''），而Hive默认的null值存储格式为\N。所以后期将DataX同步的文件导入Hive表就会出现问题。
解决该问题的方案有两个：
一是修改DataX HDFS Writer的源码，增加自定义null值存储格式的逻辑，可参考记Datax3.0解决MySQL抽数到HDFSNULL变为空字符的问题_datax nullformat-CSDN博客。
二是在Hive中建表时指定null值存储格式为空字符串（''），例如：
CREATE EXTERNAL TABLE base_province
(
`id` STRING COMMENT '编号',
`name` STRING COMMENT '省份名称',
`region_id` STRING COMMENT '地区ID',
`area_code` STRING COMMENT '地区编码',
`iso_code` STRING COMMENT '旧版ISO-3166-2编码，供可视化使用',
`iso_3166_2` STRING COMMENT '新版IOS-3166-2编码，供可视化使用'
) COMMENT '省份表'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
NULL DEFINED AS ''
LOCATION '/base_province/';
1.2 提交任务
1）在HDFS创建base_province目录
使用DataX向HDFS同步数据时，需确保目标路径已存在
hadoop fs -mkdir /base_province
2）进入DataX根目录
cd /opt/module/datax
3）开始同步
python bin/datax.py job/base_province.json
4）查看同步完成后的结果
查看HDFS文件
hadoop fs -cat /base_province/* | zcat
内容如下：
2. MySQLReader之QuerySQLMode
2.1 编写配置文件
（1）创建并修改配置文件base_province_sql.json
vim /opt/module/datax/job/base_province_sql.json
（2）配置文件内容如下
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
],
"querySql": [
"select id,name,region_id,area_code,iso_code,iso_3166_2,create_time,operate_time from base_province where id>=3"
]
}
],
"password": "000000",
"username": "root"
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "region_id",
"type": "string"
},
{
"name": "area_code",
"type": "string"
},
{
"name": "iso_code",
"type": "string"
},
{
"name": "iso_3166_2",
"type": "string"
},
{
"name": "create_time",
"type": "string"
},
{
"name": "operate_time",
"type": "string"
}
],
"compress": "gzip",
"defaultFS": "hdfs://hadoop102:8020",
"fieldDelimiter": "\t",
"fileName": "base_province",
"fileType": "text",
"path": "/base_province",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": 1
}
}
}
}
配置文件说明
（1）Reader参数说明
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": [ #数据JDBC URL
"jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
],
"querySql": [ #SQL查询语句。查询base_province表中id>3的数据
"select id,name,region_id,area_code,iso_code,iso_3166_2,create_time,operate_time from base_province where id>=3"
]
}
],
"password": "000000", #数据库密码
"username": "root" #数据库用户名
}
}
2.2 提交任务
1）清空历史数据
hadoop fs -rm -r -f /base_province/*
2）进入DataX根目录
cd /opt/module/datax
3）开始同步
python bin/datax.py job/base_province_sql.json
4）查看结果
查看HDFS文件
hadoop fs -cat /base_province/* | zcat
3. DataX传参
通常情况下，离线数据同步任务需要每日定时重复执行，故HDFS上的目标路径通常会包含一层日期，以对每日同步的数据加以区分，也就是说每日同步数据的目标路径不是固定不变的，因此DataX配置文件中HDFS Writer的path参数的值应该是动态的。为实现这一效果，就需要使用DataX传参的功能。
DataX传参的用法如下，在JSON配置文件中使用${param}引用参数，在提交任务时使用-p"-Dparam=value"传入参数值。
3.1 修改配置文件
1）修改配置文件base_province.json
vim /opt/module/datax/job/base_province.json
配置文件内容如下
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
],
"querySql": [
"select id,name,region_id,area_code,iso_code,iso_3166_2,create_time,operate_time from base_province where id>=3"
]
}
],
"password": "000000",
"username": "root"
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "region_id",
"type": "string"
},
{
"name": "area_code",
"type": "string"
},
{
"name": "iso_code",
"type": "string"
},
{
"name": "iso_3166_2",
"type": "string"
},
{
"name": "create_time",
"type": "string"
},
{
"name": "operate_time",
"type": "string"
}
],
"compress": "gzip",
"defaultFS": "hdfs://hadoop102:8020",
"fieldDelimiter": "\t",
"fileName": "base_province",
"fileType": "text",
"path": "/base_province/${dt}",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": 1
}
}
}
}
3.2 提交任务
1）创建目标路径
hadoop fs -mkdir /base_province/2022-06-08
2）进入DataX目录
cd /opt/module/datax
3）开始
python bin/datax.py -p"-Ddt=2022-06-08" job/base_province.json
3.3 查看结果
二、同步HDFS数据到MySQL案例
案例要求：同步HDFS上的/base_province目录下的数据到MySQL gmall数据库下的test_province表。
需求分析：要实现该功能，需选用HDFSReader和MySQLWriter。
1.编写配置文件
1）创建配置文件test_province.json
vim /opt/module/datax/job/test_province.json
配置文件内容如下
{
"job": {
"content": [
{
"reader": {
"name": "hdfsreader",
"parameter": {
"defaultFS": "hdfs://hadoop102:8020",
"path": "/base_province/2022-06-08",
"column": [
"*"
],
"fileType": "text",
"compress": "gzip",
"encoding": "UTF-8",
"nullFormat": "\\N",
"fieldDelimiter": "\t",
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"username": "root",
"password": "000000",
"connection": [
{
"table": [
"test_province"
],
"jdbcUrl": "jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
}
],
"column": [
"id",
"name",
"region_id",
"area_code",
"iso_code",
"iso_3166_2",
"create_time",
"operate_time"
],
"writeMode": "replace"
}
}
}
],
"setting": {
"speed": {
"channel": 1
}
}
}
}
配置文件说明
（1）Reader参数说明
"reader": {
"name": "hdfsreader",
"parameter": {
"defaultFS": "hdfs://hadoop102:8020", #HDFS文件系统namenode地址
"path": "/base_province", #文件所在路径
"column": [ #需要同步的列，*标识所有列
"*"
],
"fileType": "text", #文件类型
"compress": "gzip", #压缩类型
"encoding": "UTF-8", #文件编码
"nullFormat": "\\N", #null值存储格式
"fieldDelimiter": "\t", #字段分隔符
}
}
（2）Writer参数说明
"writer": {
"name": "mysqlwriter",
"parameter": {
"username": "root", #数据库用户名
"password": "000000", #数据库密码
"connection": [
{
"table": [
"test_province/2022-06-08" #目标表
],
"jdbcUrl": "jdbc:mysql://hadoop102:3306/gmall?useUnicode=true&allowPublicKeyRetrieval=true&characterEncoding=utf-8"
}
],
"column": [ #目标列
"id",
"name",
"region_id",
"area_code",
"iso_code",
"iso_3166_2",
"create_time",
"operate_time"
],
"writeMode": "replace" #写入方式
}
}
}
//column：需要同步的列。可以使用索引选择所需列，例如：[{"index":0,"type":"数据类型"}，{"index":1,"type":"数据类型"}]标识前两列；或者直接使用属性名选择，例如：["id","name"]； * 可以标识所有列。
写入方式：控制写入数据到目标表采用insert into(insert)或者replace into(replace) 或者 ON DUPLICATE KEY UPDATE(update)语句。
2. 提交任务
1）在MySQL的gmall数据库中创建test_province表
DROP TABLE IF EXISTS `test_province`;
CREATE TABLE `test_province` (
`id` bigint(20) NOT NULL,
`name` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`region_id` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`area_code` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`iso_code` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`iso_3166_2` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`create_time` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
`operate_time` varchar(20) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
PRIMARY KEY (`id`)
) ENGINE = InnoDB CHARACTER SET = utf8 COLLATE = utf8_general_ci ROW_FORMAT = Dynamic;2）进入DataX根目录
cd /opt/module/datax
3）开始同步
python bin/datax.py job/test_province.json
4）查看结果
查看MySQL目标表数据
