完全外部连接行为
full outer join behavior
HIVE SQL - 我有 2 个表。 survey and survey_comments 结构如下图：
create external table if not exists survey(
id string,
category_name string,
subcategory_name string)
STORED AS parquet;
insert into survey(id, category_name, subcategory_name)
values ('1', 'Engine', 'Engine problem other than listed');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Exterior Body', 'Color match of painted parts');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Exterior Body', 'Tail lights');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Transmission', 'Rough shifting');
create external table if not exists survey_comments(
id string,
category_name_txt string,
subcategory_name_txt string,
comments string)
STORED AS parquet;
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Exterior Body', 'Tail lights', 'Moisture in lower portion of rear tail lights along with leaves etc.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up', 'Small amount of fog low on front windshield during/after rain.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Miscellaneous', 'General problem other than listed', 'When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Miscellaneous', 'General problem other than listed', 'Touch-up paint too red, not same red as on the car.');
现在我的全外连接如下图所示：
select b.id, b.category_name, b.subcategory_name, a.category_name_txt, a.sub_category_name_txt, a.comments
from survey b full outer join survey_comments a
on (
b.id = a.id and
b.category_name = a.category_name_txt and b.subcategory_name = a.sub_category_name_txt
)
我没有得到 survey_comment_txt 中 category_name 作为 'Miscellaneous' 的行。我需要调查中的非匹配行和 survey_comments 作为单独的行和匹配行。我做错了什么。
使用 CTE 进行测试，发现了两个问题。 1st: 您要在 survey_comments 中插入四列，但只命名了三列。 2nd:在查询列名中应该是subcategory_name_txt，而不是sub_category_name_txt.
修复后测试：
with survey as (
select stack(5,
'1', 'Engine', 'Engine problem other than listed',
'1', 'Exterior Body', 'Color match of painted parts',
'1', 'Exterior Body', 'Tail lights',
'1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up',
'1', 'Transmission', 'Rough shifting') as (id, category_name, subcategory_name)
),
survey_comments as (
select stack(4,
'1', 'Exterior Body', 'Tail lights', 'Moisture in lower portion of rear tail lights along with leaves etc.',
'1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up', 'Small amount of fog low on front windshield during/after rain.',
'1', 'Miscellaneous', 'General problem other than listed', 'When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.',
'1', 'Miscellaneous', 'General problem other than listed', 'Touch-up paint too red, not same red as on the car.') as (id, category_name_txt, subcategory_name_txt,comments)
)
select b.id, b.category_name, b.subcategory_name, a.category_name_txt, a.subcategory_name_txt, a.comments
from survey b full outer join survey_comments a
on (
b.id = a.id and
b.category_name = a.category_name_txt and b.subcategory_name = a.subcategory_name_txt
)
Returns:
b.id b.category_name b.subcategory_name a.category_name_txt a.subcategory_name_txt a.comments
1 Engine Engine problem other than listed NULL NULL NULL
1 Exterior Body Color match of painted parts NULL NULL NULL
1 Exterior Body Tail lights Exterior Body Tail lights Moisture in lower portion of rear tail lights along with leaves etc.
1 Heating/Ventilation and Cooling Front windshield fogs up Heating/Ventilation and Cooling Front windshield fogs up Small amount of fog low on front windshield during/after rain.
NULL NULL NULL Miscellaneous General problem other than listed Touch-up paint too red, not same red as on the car.
NULL NULL NULL Miscellaneous General problem other than listed When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.
1 Transmission Rough shifting NULL NULL NULL
返回 Miscellaneous。
HIVE SQL - 我有 2 个表。 survey and survey_comments 结构如下图：
create external table if not exists survey(
id string,
category_name string,
subcategory_name string)
STORED AS parquet;
insert into survey(id, category_name, subcategory_name)
values ('1', 'Engine', 'Engine problem other than listed');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Exterior Body', 'Color match of painted parts');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Exterior Body', 'Tail lights');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up');
insert into survey(id, category_name, subcategory_name)
values ('1', 'Transmission', 'Rough shifting');
create external table if not exists survey_comments(
id string,
category_name_txt string,
subcategory_name_txt string,
comments string)
STORED AS parquet;
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Exterior Body', 'Tail lights', 'Moisture in lower portion of rear tail lights along with leaves etc.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up', 'Small amount of fog low on front windshield during/after rain.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Miscellaneous', 'General problem other than listed', 'When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.');
insert into survey_comments(id, category_name_txt, subcategory_name_txt)
values ('1', 'Miscellaneous', 'General problem other than listed', 'Touch-up paint too red, not same red as on the car.');
现在我的全外连接如下图所示：
select b.id, b.category_name, b.subcategory_name, a.category_name_txt, a.sub_category_name_txt, a.comments
from survey b full outer join survey_comments a
on (
b.id = a.id and
b.category_name = a.category_name_txt and b.subcategory_name = a.sub_category_name_txt
)
我没有得到 survey_comment_txt 中 category_name 作为 'Miscellaneous' 的行。我需要调查中的非匹配行和 survey_comments 作为单独的行和匹配行。我做错了什么。
使用 CTE 进行测试，发现了两个问题。 1st: 您要在 survey_comments 中插入四列，但只命名了三列。 2nd:在查询列名中应该是subcategory_name_txt，而不是sub_category_name_txt.
修复后测试：
with survey as (
select stack(5,
'1', 'Engine', 'Engine problem other than listed',
'1', 'Exterior Body', 'Color match of painted parts',
'1', 'Exterior Body', 'Tail lights',
'1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up',
'1', 'Transmission', 'Rough shifting') as (id, category_name, subcategory_name)
),
survey_comments as (
select stack(4,
'1', 'Exterior Body', 'Tail lights', 'Moisture in lower portion of rear tail lights along with leaves etc.',
'1', 'Heating/Ventilation and Cooling', 'Front windshield fogs up', 'Small amount of fog low on front windshield during/after rain.',
'1', 'Miscellaneous', 'General problem other than listed', 'When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.',
'1', 'Miscellaneous', 'General problem other than listed', 'Touch-up paint too red, not same red as on the car.') as (id, category_name_txt, subcategory_name_txt,comments)
)
select b.id, b.category_name, b.subcategory_name, a.category_name_txt, a.subcategory_name_txt, a.comments
from survey b full outer join survey_comments a
on (
b.id = a.id and
b.category_name = a.category_name_txt and b.subcategory_name = a.subcategory_name_txt
)
Returns:
b.id b.category_name b.subcategory_name a.category_name_txt a.subcategory_name_txt a.comments
1 Engine Engine problem other than listed NULL NULL NULL
1 Exterior Body Color match of painted parts NULL NULL NULL
1 Exterior Body Tail lights Exterior Body Tail lights Moisture in lower portion of rear tail lights along with leaves etc.
1 Heating/Ventilation and Cooling Front windshield fogs up Heating/Ventilation and Cooling Front windshield fogs up Small amount of fog low on front windshield during/after rain.
NULL NULL NULL Miscellaneous General problem other than listed Touch-up paint too red, not same red as on the car.
NULL NULL NULL Miscellaneous General problem other than listed When filling vehicle with gas; the pumps fill the gas line too quickly, had to hold the pump handle only 1/2 way on.
1 Transmission Rough shifting NULL NULL NULL
Miscellaneous。