在使用分析功能方面需要帮助
Need help in using Analytical function
sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';') within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within group(order by apn_nbr)
END as apn_nbr
FROM (SELECT max(f1.pid) as pid,f1.id,apn_nbr,date
FROM table_1 f1
JOIN table_2 d1
ON f1.process_id = d1.process_id
WHERE apn_nbr is not null
and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr)
group by id,pid
当我 运行 上述查询时，我得到的结果如下所述：
ID PID APN_NBR
220247111 64306012133 228887143,130050106,220247111,220247143
220247111 57558164496 105450046,105450314,136010476,136150077,184060007,186930609
对于一个 ID，我得到 PID 和 APN_NBR 列的不同值。我需要在结果中显示最后的 NOT NULL 记录。
当我尝试使用
QUALIFY rank() over (partition by ID, pid order by datedesc) = 1，我没有得到逗号分隔的 listagg 值。我只得到一条记录（即 APN_NBR 列的第一条记录）
谁能指导我这个逻辑？
提前致谢:)
示例记录：
ID PID APN_NBR
30247521 5533433057558 130050044,130050106,195050142,960109430,960228707,960542787,960542788
30247521 5533433059643 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915
34690213 1594308114486 960513957,970020828
34690213 5943081144866
我只想为每个订单显示一行。即我想为每个订单显示第二行。
请看看这是否有帮助-
Data-set 使用 -
select column1,column2,column3 from
values
(30247521,5533433057558,'130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521,5533433059643,'105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,97
0010915'),
(34690213,1594308114486,'960513957,970020828'),
(34690213,5943081144866,NULL);
+----------+---------------+-------------------------------------------------------------------------------------------+
| COLUMN1 | COLUMN2 | COLUMN3 |
|----------+---------------+-------------------------------------------------------------------------------------------|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
| 34690213 | 5943081144866 | NULL |
+----------+---------------+-------------------------------------------------------------------------------------------+
查询得到结果 -
select column1,column2,nvl2(column3, column3,lag(column3) over (order by column1))
as column3 from
values
(30247521,5533433057558,'130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521,5533433059643,'105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,97
0010915'),
(34690213,1594308114486,'960513957,970020828'),
(34690213,5943081144866,NULL) ;
+----------+---------------+-------------------------------------------------------------------------------------------+
| COLUMN1 | COLUMN2 | COLUMN3 |
|----------+---------------+-------------------------------------------------------------------------------------------|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
| 34690213 | 5943081144866 | 960513957,970020828 |
+----------+---------------+-------------------------------------------------------------------------------------------+
因此，如果您有上次 table 中的数据。
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR);
ID
PID
APN_NBR
30247521
5533433057558
130050044,130050106,195050142,960109430,960228707,960542787,960542788
30247521
5533433059643
105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915
34690213
1594308114486
960513957,970020828
34690213
5943081144866
null
并且您希望删除所有带有 APN_NBR 的 NULL 行，然后使用 WHERE 子句消除它们：
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR)
WHERE APN_NBR IS NOT NULL;
给出：
ID
PID
APN_NBR
30247521
5533433057558
130050044,130050106,195050142,960109430,960228707,960542787,960542788
30247521
5533433059643
105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915
34690213
1594308114486
960513957,970020828
现在，这些结果可以被 p运行 编辑为每个 ID 唯一的一个结果，并通过 运行 的 QUALIFY 将首选顺序分配给较大的 PID ]s 在 WHERE 子句之后有 运行。你应该在这里使用 ROW_NUMBER 而不是 RANK，虽然我说过你可以使用 RANK，因为如果行相等，RANK 可以有 2 个第一（你可能确实想要）。但另一方面，ROW_NUMBER 将静默选择 1 行，这可能会因执行而异。
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR)
WHERE APN_NBR IS NOT NULL
QUALIFY row_number() over (partition by ID order by PID desc) = 1;
ID
PID
APN_NBR
34690213
1594308114486
960513957,970020828
30247521
5533433059643
105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915
现在这些可能正是您想要的结果，但这是使用 WHERE 和 QUALIFY/ROW_NUMBER 过滤、排序和限制显示结果的方法。如果您尝试使用小型玩具数据集（如上面提供的），并内化此功能的工作原理。您应该能够将它们应用于您拥有的数据，以及您想要应用的转换。
鉴于您在外部 SELECT 中有一个分组，您可以使用 HAVING 应用 post GROUPING 过滤器，如下所示：
sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';') within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within group(order by apn_nbr)
END as apn_nbr
FROM (SELECT max(f1.pid) as pid,f1.id,apn_nbr,date
FROM table_1 f1
JOIN table_2 d1
ON f1.process_id = d1.process_id
WHERE apn_nbr is not null
and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr)
group by id,pid
HAVING APN_NBR IS NOT NULL
QUALIFY row_number() over (partition by ID order by PID desc) = 1;
或者您可以添加另一层选择以应用显示的模式：
SELECT id,pid,apn_nbr FROM(sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';')
within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within
group(order by apn_nbr) END as apn_nbr
FROM(SELECT max(f1.pid) as pid,f1.id,apn_nbr,
date FROM table_1 f1 JOIN table_2 d1 ON
f1.process_id = d1.process_id WHERE
apn_nbr is not null and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr) group by id,pid)
WHERE APN_NBR IS NOT NULL QUALIFY
row_number() over (partition by ID order
by PID desc) = 1;
sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';') within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within group(order by apn_nbr)
END as apn_nbr
FROM (SELECT max(f1.pid) as pid,f1.id,apn_nbr,date
FROM table_1 f1
JOIN table_2 d1
ON f1.process_id = d1.process_id
WHERE apn_nbr is not null
and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr)
group by id,pid
当我 运行 上述查询时，我得到的结果如下所述：
ID PID APN_NBR
220247111 64306012133 228887143,130050106,220247111,220247143
220247111 57558164496 105450046,105450314,136010476,136150077,184060007,186930609
对于一个 ID，我得到 PID 和 APN_NBR 列的不同值。我需要在结果中显示最后的 NOT NULL 记录。
当我尝试使用
QUALIFY rank() over (partition by ID, pid order by datedesc) = 1，我没有得到逗号分隔的 listagg 值。我只得到一条记录（即 APN_NBR 列的第一条记录）
谁能指导我这个逻辑？
提前致谢:)
示例记录：
ID PID APN_NBR
30247521 5533433057558 130050044,130050106,195050142,960109430,960228707,960542787,960542788
30247521 5533433059643 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915
34690213 1594308114486 960513957,970020828
34690213 5943081144866
我只想为每个订单显示一行。即我想为每个订单显示第二行。
请看看这是否有帮助-
Data-set 使用 -
select column1,column2,column3 from
values
(30247521,5533433057558,'130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521,5533433059643,'105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,97
0010915'),
(34690213,1594308114486,'960513957,970020828'),
(34690213,5943081144866,NULL);
+----------+---------------+-------------------------------------------------------------------------------------------+
| COLUMN1 | COLUMN2 | COLUMN3 |
|----------+---------------+-------------------------------------------------------------------------------------------|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
| 34690213 | 5943081144866 | NULL |
+----------+---------------+-------------------------------------------------------------------------------------------+
查询得到结果 -
select column1,column2,nvl2(column3, column3,lag(column3) over (order by column1))
as column3 from
values
(30247521,5533433057558,'130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521,5533433059643,'105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,97
0010915'),
(34690213,1594308114486,'960513957,970020828'),
(34690213,5943081144866,NULL) ;
+----------+---------------+-------------------------------------------------------------------------------------------+
| COLUMN1 | COLUMN2 | COLUMN3 |
|----------+---------------+-------------------------------------------------------------------------------------------|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
| 34690213 | 5943081144866 | 960513957,970020828 |
+----------+---------------+-------------------------------------------------------------------------------------------+
因此，如果您有上次 table 中的数据。
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR);
| ID | PID | APN_NBR |
|---|---|---|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
| 34690213 | 5943081144866 | null |
并且您希望删除所有带有 APN_NBR 的 NULL 行，然后使用 WHERE 子句消除它们：
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR)
WHERE APN_NBR IS NOT NULL;
给出：
| ID | PID | APN_NBR |
|---|---|---|
| 30247521 | 5533433057558 | 130050044,130050106,195050142,960109430,960228707,960542787,960542788 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
| 34690213 | 1594308114486 | 960513957,970020828 |
现在，这些结果可以被 p运行 编辑为每个 ID 唯一的一个结果，并通过 运行 的 QUALIFY 将首选顺序分配给较大的 PID ]s 在 WHERE 子句之后有 运行。你应该在这里使用 ROW_NUMBER 而不是 RANK，虽然我说过你可以使用 RANK，因为如果行相等，RANK 可以有 2 个第一（你可能确实想要）。但另一方面，ROW_NUMBER 将静默选择 1 行，这可能会因执行而异。
select ID, PID, APN_NBR
from values
(30247521, 5533433057558, '130050044,130050106,195050142,960109430,960228707,960542787,960542788'),
(30247521, 5533433059643, '105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915'),
(34690213, 1594308114486, '960513957,970020828'),
(34690213, 5943081144866, NULL)
t(ID, PID, APN_NBR)
WHERE APN_NBR IS NOT NULL
QUALIFY row_number() over (partition by ID order by PID desc) = 1;
| ID | PID | APN_NBR |
|---|---|---|
| 34690213 | 1594308114486 | 960513957,970020828 |
| 30247521 | 5533433059643 | 105450046,105450314,136010476,136150077,184060007,186930609,196051036,960113678,970010915 |
现在这些可能正是您想要的结果，但这是使用 WHERE 和 QUALIFY/ROW_NUMBER 过滤、排序和限制显示结果的方法。如果您尝试使用小型玩具数据集（如上面提供的），并内化此功能的工作原理。您应该能够将它们应用于您拥有的数据，以及您想要应用的转换。
鉴于您在外部 SELECT 中有一个分组，您可以使用 HAVING 应用 post GROUPING 过滤器，如下所示：
sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';') within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within group(order by apn_nbr)
END as apn_nbr
FROM (SELECT max(f1.pid) as pid,f1.id,apn_nbr,date
FROM table_1 f1
JOIN table_2 d1
ON f1.process_id = d1.process_id
WHERE apn_nbr is not null
and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr)
group by id,pid
HAVING APN_NBR IS NOT NULL
QUALIFY row_number() over (partition by ID order by PID desc) = 1;
或者您可以添加另一层选择以应用显示的模式：
SELECT id,pid,apn_nbr FROM(sELECT id, pid,
case WHEN listagg(DISTINCT apn_nbr, ';')
within GROUP(ORDER BY apn_nbr)= '' THEN 'null'
ELSE listagg(distinct apn_nbr,',') within
group(order by apn_nbr) END as apn_nbr
FROM(SELECT max(f1.pid) as pid,f1.id,apn_nbr,
date FROM table_1 f1 JOIN table_2 d1 ON
f1.process_id = d1.process_id WHERE
apn_nbr is not null and id=1234576
// AND pid='5812900'
GROUP BY id,apn_nbr) group by id,pid)
WHERE APN_NBR IS NOT NULL QUALIFY
row_number() over (partition by ID order
by PID desc) = 1;