大数据之Hive：get_json_object函数使用

1.数据

[{"name":"大郎","sex":"男","age":"25"},{"name":"西门庆","sex":"男","age":"47"}]

2.取出第一个json对象

hive (gmall)>
select get_json_object('[{"name":"大郎","sex":"男","age":"25"},{"name":"西门庆","sex":"男","age":"47"}]','$[0]');
结果是：{"name":"大郎","sex":"男","age":"25"}

3.取出第一个json的age字段的值

hive (gmall)>
SELECT get_json_object('[{"name":"大郎","sex":"男","age":"25"},{"name":"西门庆","sex":"男","age":"47"}]',"$[0].age");
结果是：25

4.复杂案例

1）建表语句

hive (gmall)>
drop table if exists dwd_start_log;
CREATE EXTERNAL TABLE dwd_start_log(
    `area_code` string COMMENT '地区编码',
    `brand` string COMMENT '手机品牌', 
    `channel` string COMMENT '渠道', 
    `model` string COMMENT '手机型号', 
    `mid_id` string COMMENT '设备id', 
    `os` string COMMENT '操作系统', 
    `user_id` string COMMENT '会员id', 
    `version_code` string COMMENT 'app版本号', 
    `entry` string COMMENT ' icon手机图标  notice 通知   install 安装后启动',
    `loading_time` bigint COMMENT '启动加载时间',
    `open_ad_id` string COMMENT '广告页ID ',
    `open_ad_ms` bigint COMMENT '广告总共播放时间', 
    `open_ad_skip_ms` bigint COMMENT '用户跳过广告时点', 
    `ts` bigint COMMENT '时间'
) COMMENT '启动日志表'
PARTITIONED BY (dt string) -- 按照时间创建分区
stored as parquet -- 采用parquet列式存储
LOCATION '/warehouse/gmall/dwd/dwd_start_log' -- 指定在HDFS上存储位置
TBLPROPERTIES('parquet.compression'='lzo') -- 采用LZO压缩
;

2）数据导入

hive (gmall)> 
SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
insert overwrite table dwd_start_log partition(dt='2021-03-20')
select 
    get_json_object(line,'$.common.ar'),
    get_json_object(line,'$.common.ba'),
    get_json_object(line,'$.common.ch'),
    get_json_object(line,'$.common.md'),
    get_json_object(line,'$.common.mid'),
    get_json_object(line,'$.common.os'),
    get_json_object(line,'$.common.uid'),
    get_json_object(line,'$.common.vc'),
    get_json_object(line,'$.start.entry'),
    get_json_object(line,'$.start.loading_time'),
    get_json_object(line,'$.start.open_ad_id'),
    get_json_object(line,'$.start.open_ad_ms'),
    get_json_object(line,'$.start.open_ad_skip_ms'),
    get_json_object(line,'$.ts')
from ods_log
where dt='2021-03-20'
and get_json_object(line,'$.start') is not null;