1.增加字段后直接查看文件有值,但是hsq查出来就没有值,但是impala查询是有值的
hive建表语句
CREATE EXTERNAL TABLE nretail_ability_order.retail_report (
sub_order_no STRING COMMENT '订单号',
order_source STRING COMMENT '订单来源:1.T销客 2.方舟 3.方舟移动端 8.T云店',
company_name STRING COMMENT '开单客户商务中心',
customer_code STRING COMMENT '开单客户编码',
customer_name STRING COMMENT '开单客户名称',
create_time STRING COMMENT '开单时间',
product_line STRING COMMENT '产品线',
sku STRING COMMENT '产品skuNo',
commodity_name STRING COMMENT '商品名称',
product_model STRING COMMENT '产品型号',
spec STRING COMMENT '规格',
sort STRING COMMENT '分类',
quantity INT COMMENT '购买数量',
total_price STRING COMMENT '总金额',
NAME STRING COMMENT '收货人',
telephone STRING COMMENT '收货人手机号',
receiving_address STRING COMMENT '收货地址',
uuid STRING COMMENT '商品'
) PARTITIONED BY ( dt STRING COMMENT '时间' ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\u0001' WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'serialization.format' = '\u0001' ) STORED AS TEXTFILE LOCATION 'hdfs://nameservice1/user/hive/warehouse/nretail_ability_order.db/retail_report' TBLPROPERTIES ( 'last_modified_by' = 'root', 'last_modified_time' = '1640658557' )
增加字段的语句
Alter table retail_report add column buy_proof_img STRING comment '购机凭证图片URL';
查看文件里面是有值的
hdfs dfs -text /user/hive/warehouse/nretail_ability_order.db/retail_order_detail/dt=2021-12-23/part-m-00000.snappy
impala查询是有值的
直接hive查询就都是null
2.解决方案
直接删除表、重新建表,将新增字段在建表的时候就增加上来
CREATE EXTERNAL TABLE nretail_ability_order.retail_report (
sub_order_no STRING COMMENT '订单号',
order_source STRING COMMENT '订单来源:1.T销客 2.方舟 3.方舟移动端 8.T云店',
company_name STRING COMMENT '开单客户商务中心',
customer_code STRING COMMENT '开单客户编码',
customer_name STRING COMMENT '开单客户名称',
create_time STRING COMMENT '开单时间',
product_line STRING COMMENT '产品线',
sku STRING COMMENT '产品skuNo',
commodity_name STRING COMMENT '商品名称',
product_model STRING COMMENT '产品型号',
spec STRING COMMENT '规格',
sort STRING COMMENT '分类',
quantity INT COMMENT '购买数量',
total_price STRING COMMENT '总金额',
NAME STRING COMMENT '收货人',
telephone STRING COMMENT '收货人手机号',
receiving_address STRING COMMENT '收货地址',
uuid STRING COMMENT '商品',
buy_proof_img STRING COMMENT '购机凭证图片URL'
) PARTITIONED BY ( dt STRING COMMENT '时间' ) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\u0001' WITH SERDEPROPERTIES ( 'field.delim' = '\u0001', 'serialization.format' = '\u0001' ) STORED AS TEXTFILE LOCATION 'hdfs://nameservice1/user/hive/warehouse/nretail_ability_order.db/retail_report' TBLPROPERTIES ( 'last_modified_by' = 'root', 'last_modified_time' = '1640658557' )
这样数据load上来以后就能和mysql保持一致。hive也能查出来。impala也能查出来, 如果关联以后的中间表用的这个字段,也需要提前将表重新建了。否则也会出现查不出来的情况