助力工业物联网，工业大数据之其他维度：组织机构【十五】

select empid,empcode,empname,userid from org_employee;

select empid,positionid from org_empposition;

select positionid,posicode,posiname,orgid from org_position;

select orgid,orgcode,orgname from org_organization;

-- 创建组织机构维度表，组织机构人员是经常变动的，所以按照日期分区
create external table if not exists one_make_dws.dim_emporg(
    empid string comment '人员id'   
    , empcode string comment '人员编码(erp对应的账号id)'
    , empname string comment '人员姓名'
    , userid string comment '用户系统id（登录用户名）'
    , posid string comment '岗位id'
    , posicode string comment '岗位编码'
    , posiname string comment '岗位名称'
    , orgid string comment '部门id'
    , orgcode string comment '部门编码'
    , orgname string comment '部门名称'
) comment '组织机构维度表'
partitioned by (dt string)
stored as orc
location '/data/dw/dws/one_make/dim_emporg';

-- 先根据dwd层的表进行关联，然后分别把数据取出来
insert overwrite table one_make_dws.dim_emporg partition(dt='20210101')
select
    emp.empid as empid
    , emp.empcode as empcode
    , emp.empname as empname
    , emp.userid as userid
    , pos.positionid as posid
    , pos.posicode as posicode
    , pos.posiname as posiname
    , org.orgid as orgid
    , org.orgcode as orgcode
    , org.orgname as orgname
from  one_make_dwd.org_employee emp
left join one_make_dwd.org_empposition emppos
    on emp.empid = emppos.empid and emp.dt = '20210101' and emppos.dt = '20210101'
left join one_make_dwd.org_position pos
    on emppos.positionid = pos.positionid and pos.dt = '20210101'
left join one_make_dwd.org_organization org
    on pos.orgid = org.orgid and org.dt = '20210101';

-- 仓库维度表
create external table if not exists one_make_dws.dim_warehouse(
    code string comment '仓库编码'
    , name string comment '仓库名称'
    , company_id string comment '所属公司'
    , company string comment '公司名称'
    , srv_station_id string comment '所属服务网点ID'
    , srv_station_name string comment '所属服务网点名称'
)comment '仓库维度表'
partitioned by (dt string)
stored as orc
location '/data/dw/dws/one_make/dim_warehouse';

insert overwrite table one_make_dws.dim_warehouse partition(dt='20210101')
select
    warehouse.code as code
    , warehouse.name as name
    , warehouse.company as company_id
    , cmp.compmay as compmay
    , station.id as srv_station_id
    , station.name as srv_station_name
from
    one_make_dwd.ciss_base_warehouse warehouse
-- 关联公司信息表
left join (
     select
           ygcode as company_id, max(companyname) as compmay
     from one_make_dwd.ciss_base_baseinfo where dt='20210101'
     -- 需要对company信息进行分组去重，里面有一些重复数据 
     group by ygcode) cmp
     on warehouse.dt = '20210101' and cmp.company_id = warehouse.company
-- 关联服务网点和仓库关系表
left join one_make_dwd.ciss_r_serstation_warehouse station_r_warehouse
     on station_r_warehouse.dt = '20210101' and station_r_warehouse.warehouse_code = warehouse.code
-- 关联服务网点表 
left join one_make_dwd.ciss_base_servicestation station
     on station.dt = '20210101' and station.id = station_r_warehouse.service_station_id;

-- 物流维度表(和服务属性表类似)
create external table if not exists one_make_dws.dim_logistics(
    prop_name string comment '字典名称'
    , type_id string comment '属性id'
    , type_name string comment '属性名称'
)comment '物流维度表'
partitioned by (dt string)
stored as orc
location '/data/dw/dws/one_make/dim_logistics';

insert overwrite table one_make_dws.dim_logistics partition(dt = '20210101')
select
    dict_t.dicttypename as prop_name
    , dict_e.dictid as type_id
    , dict_e.dictname as type_name
from  one_make_dwd.eos_dict_type dict_t
inner join one_make_dwd.eos_dict_entry dict_e
    on dict_t.dt = '20210101'
        and dict_e.dt = '20210101'
        and dict_t.dicttypeid = dict_e.dicttypeid
        and dict_t.dicttypename in (
            '物流公司'
            , '物流类型'
        )
order by dict_t.dicttypename, dict_e.dictid;

insert overwrite table one_make_dws.dim_logistics partition (dt = '20210101')
select dict_t.dicttypename as prop_name
     , dict_e.dictid       as type_id
     , dict_e.dictname     as type_name
from one_make_dwd.eos_dict_type dict_t
        inner join one_make_dwd.eos_dict_entry dict_e on dict_t.dt = '20210101'
        and dict_e.dt = '20210101'
        and dict_t.dicttypeid = dict_e.dicttypeid   -- 通过状态字符串进行关联
        and dict_t.dicttypename in ('物流公司', '物流类型') -- 通过和物流相关的字样进行过滤
order by prop_name, type_id;

Exception in thread "main" org.apache.spark.sql.AnalysisException: Detected implicit cartesian product for INNER join between logical plans.Use the CROSS JOIN syntax to allow cartesian products between these relations

Error: org.apache.spark.sql.AnalysisException: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to move source hdfs://hadoop.bigdata.cn:9000/data/dw/dws/one_make/dim_warehouse/.hive-staging_hive_2020-12-23_04-26-01_363_5663538019799519260-16/-ext-10000/part-00000-63069107-6405-4e31-a55a-6bdeefcd7d9b-c000 to destination hdfs://hadoop.bigdata.cn:9000/data/dw/dws/one_make/dim_warehouse/dt=20210101/part-00000-63069107-6405-4e31-a55a-6bdeefcd7d9b-c000; (state=,code=0)