datax离线同步oracle表到clickhouse实践1-编程知识

时间：2024.01

目录
1、安装启动 oracle19c 容器
2、rpm包安装clickhouse
3、datax安装
4、datax同步
目标库根据要同步的表，按照clickhouse建表规范建表
编写json文件
编写增量同步shell脚本，加入 crond 定时任务

1、安装启动 oracle19c 容器

二、拉取镜像
docker pull registry.cn-hangzhou.aliyuncs.com/zhuyijun/oracle

三. 创建Oracle 19c镜像的容器

3.1创建目录
[root@docker ~]# mkdir /opt/oradata
[root@docker ~]# chmod -R 777 /opt/oradata/
[root@docker ~]# mkdir /opt/to_oracle

3.2 创建实例
docker run -d -it --name oracle19c -p 11521:1521 -p 5500:5500 \
-v /opt/oradata:/opt/oracle/oradata \
-v /opt/to_oracle:/home/oracle/to_oracle \
registry.cn-hangzhou.aliyuncs.com/zhuyijun/oracle:latest

3.3 查看日志
docker logs -f oracle19c

四、修改密码
# 系统默认的system密码修改成oracle
docker exec oracle19c ./setPassword.sh oracle

5.1 进入容器
docker exec -it oracle19c /bin/bash

5.2 登录数据库
sqlplus sys/oracle@localhost:1521/ORCLCDB as sysdba
show pdbs;
alter session set container=ORCLPDB1;

5.4 查看数据文件位置
select file_name from dba_data_files;

5.6 创建数据表空间
create tablespace bigdata datafile '/opt/oracle/oradata/ORCLCDB/ORCLPDB1/bigdata.dbf' size 10G autoextend on;

5.7 创建用户，指定默认表空间
create user bigdata identified by bigdata default tablespace bigdata;

5.8 用户授权
grant connect,resource,dba to bigdata;

5.3 连接可拔插数据库
sqlplus /nolog
conn bigdata/bigdata@ORCLPDB1

建表、插入数据
把 create.sql insert.sql 放在 /opt/to_oracle/

SQL> @/home/oracle/to_oracle/create.sql
文件内容

create table TDBA_TEST01
(TID          number primary key,TSN          varchar2(40),TNO          number,TAMT         number(15,2),CREATE_DATE  date not null,UPDATE_DATE  date,UPDATE_TIME  date
);

SQL> @/home/oracle/to_oracle/insert.sql
文件内容

INSERT INTO TDBA_TEST01 VALUES(1,'SN001',1,1.01,TO_DATE('2020-02-01','YYYY-MM-DD'),TO_DATE('2020-02-01','YYYY-MM-DD'),TO_DATE('2020-02-01 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(2,'SN002',2,2.12,TO_DATE('2020-02-02','YYYY-MM-DD'),TO_DATE('2020-02-02','YYYY-MM-DD'),TO_DATE('2020-02-02 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(3,'SN003',3,3.23,TO_DATE('2020-02-03','YYYY-MM-DD'),TO_DATE('2020-02-03','YYYY-MM-DD'),TO_DATE('2020-02-03 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(4,'SN004',4,4.34,TO_DATE('2020-02-04','YYYY-MM-DD'),TO_DATE('2020-02-04','YYYY-MM-DD'),TO_DATE('2020-02-04 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(5,'SN005',5,5.45,TO_DATE('2020-02-05','YYYY-MM-DD'),TO_DATE('2020-02-05','YYYY-MM-DD'),TO_DATE('2020-02-05 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(6,'SN006',6,6,TO_DATE('2020-02-06','YYYY-MM-DD'),TO_DATE('2020-02-06','YYYY-MM-DD'),TO_DATE('2020-02-06 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(7,'SN007',7,7.67,TO_DATE('2020-02-07','YYYY-MM-DD'),TO_DATE('2020-02-07','YYYY-MM-DD'),TO_DATE('2020-02-07 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(8,'SN008',8,8.78,TO_DATE('2020-02-08','YYYY-MM-DD'),TO_DATE('2020-02-08','YYYY-MM-DD'),TO_DATE('2020-02-08 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(9,'SN009',9,9,TO_DATE('2020-02-09','YYYY-MM-DD'),TO_DATE('2024-01-09','YYYY-MM-DD'),TO_DATE('2020-02-09 01:01:01','YYYY-MM-DD HH24:MI:SS'));
INSERT INTO TDBA_TEST01 VALUES(9,'SN009',9,9,TO_DATE('2020-02-09','YYYY-MM-DD'),TO_DATE('2024-01-09','YYYY-MM-DD'),TO_DATE('2020-02-09 01:01:01','YYYY-MM-DD HH24:MI:SS'));

2、rpm包安装clickhouse

[root@conda ~]# mkdir clickhouse22.3
[root@conda ~]# cd clickhouse22.3

下载clickhouse的rpm包
https://packages.clickhouse.com/rpm/stable/clickhouse-client-22.3.2.2-2.noarch.rpm
https://packages.clickhouse.com/rpm/stable/clickhouse-common-static-22.3.2.2-2.x86_64.rpm
https://packages.clickhouse.com/rpm/stable/clickhouse-common-static-dbg-22.3.2.2-2.x86_64.rpm
https://packages.clickhouse.com/rpm/stable/clickhouse-server-22.3.2.2-2.noarch.rpm

[root@conda clickhouse22.3]# ll
total 929924
-rw-r--r--. 1 root root 46748 Sep 22 2022 clickhouse-client-22.3.2.2-2.noarch.rpm
-rw-r--r--. 1 root root 178362876 Sep 22 2022 clickhouse-common-static-22.3.2.2-2.x86_64.rpm
-rw-r--r--. 1 root root 773751886 Sep 22 2022 clickhouse-common-static-dbg-22.3.2.2-2.x86_64.rpm
-rw-r--r--. 1 root root 72089 Sep 22 2022 clickhouse-server-22.3.2.2-2.noarch.rpm

[root@conda clickhouse22.3]# rpm -ivh *.rpm

自定义设置密码
bigdata

[root@conda clickhouse22.3]# clickhouse start

[root@conda clickhouse22.3]# clickhouse status
/var/run/clickhouse-server/clickhouse-server.pid file exists and contains pid = 10792.
The process with pid = 10792 is running.

[root@conda clickhouse22.3]# clickhouse-client --password bigdata -m
ClickHouse client version 22.3.2.1.
Connecting to localhost:9000 as user default.
Connected to ClickHouse server version 22.3.2 revision 54455.

conda :)

create table TEST01
(TID          UInt32,TSN          String,TNO          UInt16,TAMT         Decimal(15,2),CREATE_DATE  Date,UPDATE_DATE  Date,UPDATE_TIME  DateTime
) ENGINE = MergeTree(CREATE_DATE, (TID), 8192)

3、datax安装

System Requirements
JDK(1.8以上，推荐1.8)
Python(推荐Python2.6.X) 我使用的CentOS7自带的 Python 2.7.5

直接下载DataX工具包：
DataX下载地址（http://datax-opensource.oss-cn-hangzhou.aliyuncs.com/datax.tar.gz）

datax_ck.tar.gz
datax_ck.tar.gz下载https://www.123pan.com/s/VTMXjv-pfA6v.html
提取码:xxxx