app_user_cert_info.ini 1.5 KB

1234567891011121314151617181920212223242526272829303132
  1. ; DataX 同步配置:PG public.app_user_cert_info → Hive test.raw_usr_app_user_cert_info_inc_d
  2. ;
  3. ; 源 datasource:datasource/postgresql/dev-poyee-xiaoxu.ini
  4. ; 目标 datasource:datasource/hdfs/prd-hdfs-ha.ini(HA 集群,nameservice1)
  5. ; 时间锚点:create_time
  6. ; 敏感字段:
  7. ; - user_cert_data / cert_no / cert_real_name:column/querySql 都不查
  8. ; - cert_birthday:querySql 里 TO_CHAR 截到月粒度,PG 端执行完成脱敏(敏感原值不出业务库)
  9. ;
  10. ; 注:key = value 不对齐——parse_ddl 的 grep "path =" 要求字面子串,多空格对齐会破匹配
  11. [reader]
  12. dataSource = postgresql/dev-poyee-xiaoxu
  13. database = hs_sync_data
  14. table = public.app_user_cert_info
  15. column = id,user_id,cert_birthday,cert_sex,cert_province,cert_city,version,status,del_flag,create_time,update_time
  16. columnType =
  17. where =
  18. querySql = SELECT id, user_id, TO_CHAR(cert_birthday, 'YYYY-MM') AS cert_birthday, cert_sex, cert_province, cert_city, version, status, del_flag, create_time, update_time FROM public.app_user_cert_info WHERE create_time >= '${start_date}' AND create_time < '${stop_date}'
  19. splitPk = id
  20. fetchSize = 1000
  21. [writer]
  22. dataSource = hdfs/prd-hdfs-ha
  23. path = /user/hive/warehouse/test.db/raw_usr_app_user_cert_info_inc_d/dt=${dt}/
  24. column = id,user_id,cert_birthday,cert_sex,cert_province,cert_city,version,status,del_flag,create_time,update_time
  25. columnType =
  26. fileType = orc
  27. fileName = raw_usr_app_user_cert_info_inc_d
  28. encoding = UTF-8
  29. writeMode = truncate
  30. fieldDelimiter = \t