源代码：跨数据库通用“字段级”数据血缘解析与图形化(2/3:标注信息的拆解、检验、保存)

drop table sql_table_struct_info
;
create table sql_table_struct_info
(
  table_name_hash     bigint       COMMENT '表名生成的哈希值'
, table_name          varchar(200) COMMENT '表名'
, column_seq          int          COMMENT '字段顺序'
, column_name         varchar(200) COMMENT '表字段名'
, column_data_type    varchar(200) COMMENT '表字段类型'
, column_comment      varchar(200) COMMENT '表字段注释'
)
DEFAULT CHARSET=utf8
partition by hash(table_name_hash)
partitions 197
;


drop table sql_table2table_info
;
create table sql_table2table_info
(
  file_name_hash            bigint         COMMENT 'SQL文件名生成的哈希值'
, file_name                 varchar(200)   COMMENT 'SQL文件名'
, sql_seq                   int            COMMENT 'SQL语句顺序'
, sql_type                  varchar(50)    COMMENT 'SQL类型'
, target_table              varchar(200)   COMMENT 'SQL语句目标表'
, source_table              varchar(200)   COMMENT 'SQL加工源表' 
, source_table_seq          int            COMMENT 'SQL源表顺序' 
, source_table_join_type    varchar(50)    COMMENT 'SQL加工源表关联方式' 
, source_table_other_name   varchar(200)   COMMENT 'SQL加工源表别名' 
, source_table_condition    varchar(10000) COMMENT 'SQL源表条件' 
, src_tab_seqs_of_cdt_join  varchar(100)   COMMENT '关联条件的源表顺序'
)
DEFAULT CHARSET=utf8
partition by hash(file_name_hash) 
partitions 197
;

drop table sql_table2column_info
;
create table sql_table2column_info
(
  file_name_hash          bigint         COMMENT 'SQL文件名生成的哈希值'
, file_name               varchar(200)   COMMENT 'SQL文件名'
, sql_seq                 int            COMMENT 'SQL语句顺序'
, target_table            varchar(200)   COMMENT 'SQL语句目标表'
, column_name             varchar(200)   COMMENT '目标表字段名'
, column_logic            varchar(10000) COMMENT '字段逻辑'
, source_table_column     varchar(4000)  COMMENT '字段逻辑涉及到的源表和字段' 
)
DEFAULT CHARSET=utf8
partition by hash(file_name_hash)
partitions 197
;

DROP TABLE IF EXISTS bi_dw.dw_omc_sales_detail_f_tmp
;
CREATE TABLE bi_dw.dw_omc_sales_detail_f_tmp
(
company_wid int4,
org_id      int4 COMMENT'机构ID',
org_code  varchar(255) COMMENT'机构code',
org_name  varchar(255),
customer_wid  int4,
cust_account_id int4
)
distributed randomly
;

--ALTER TABLE bi_dw.dw_omc_sales_detail_f_tmp ADD PRIMARY KEY(invoice_number);
GRANT ALL PRIVILEGES ON bi_dw.dw_omc_sales_detail_f_tmp TO gkht_yibai;

set optimizer = off;
insert into bi_dw.dw_omc_sales_detail_f_tmp
(
company_wid,
org_id,
org_code,
org_name,
customer_wid,
cust_account_id
)
select 
123 as company_wid,
ifnull(T.org_id, '9999') org_id,
T.org_code as org_code,
T.org_name,
T.customer_wid,
T.cust_account_id
FROM bi_dw.dw_om_sales_detail_f_data_tmp T
where 1=1
;

reset optimizer;

python  col_lvl_data_lineage_reader.py  2-codefile.sql > log.log