SQL select 不同于串联列
SQL select distinct from a concatenated column
这个查询几乎可以满足我的要求
SELECT staging.dbo.ITEM_CODES.ITEM_CODE, MAX(dbo.OC_VDAT_AUX.UDL40) AS SAMPLEDATE,
CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) as LinkID
FROM dbo.OC_VDATA
INNER JOIN dbo.OC_VDAT_AUX ON dbo.OC_VDATA.PARTNO = dbo.OC_VDAT_AUX.PARTNOAUX AND dbo.OC_VDATA.DATETIME = dbo.OC_VDAT_AUX.DATETIMEAUX
INNER JOIN stagingPLM.dbo.ITEM_CODES ON LEFT(dbo.OC_VDATA.PARTNO, 12) = staging.dbo.ITEM_CODES.SPEC_NO
AND LEFT(dbo.OC_VDAT_AUX.PARTNOAUX, 12) = stagingPLM.dbo.ITEM_CODES.SPEC_NO
INNER JOIN stagingPLM.dbo.PLANTS ON dbo.OC_VDATA.UDL1 = staging.dbo.PLANTS.PLANT_CODE
WHERE (CONVERT(DATETIME, dbo.OC_VDAT_AUX.UDL40) > DATEADD(day, - 30, GETDATE()))
GROUP BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)),staging.dbo.ITEM_CODES.ITEM_CODE
样本 Table 由查询生成:
我试图实现的最终结果是每个唯一 LinkID 的最新 ITEM_CODE 请注意 table 中的第一行和最后一行。最后一行不应被查询拉出。
我如何修改此查询以实现此目的?
我在 select 和 where 语句中尝试了 DISTINCT 和子查询的各种放置。
我会用 ROW_NUMBER
window 函数和 CTE
.
解决方法可以这样:
WITH FilterCTE AS
(
SELECT staging.dbo.ITEM_CODES.ITEM_CODE, MAX(dbo.OC_VDAT_AUX.UDL40) AS SAMPLEDATE,
CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) AS LinkID,
ROW_NUMBER() OVER (PARTITION BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) ORDER BY MAX(dbo.OC_VDAT_AUX.UDL40)) AS RowNumber
FROM dbo.OC_VDATA
INNER JOIN dbo.OC_VDAT_AUX ON dbo.OC_VDATA.PARTNO = dbo.OC_VDAT_AUX.PARTNOAUX AND dbo.OC_VDATA.DATETIME = dbo.OC_VDAT_AUX.DATETIMEAUX
INNER JOIN stagingPLM.dbo.ITEM_CODES ON LEFT(dbo.OC_VDATA.PARTNO, 12) = staging.dbo.ITEM_CODES.SPEC_NO
AND LEFT(dbo.OC_VDAT_AUX.PARTNOAUX, 12) = stagingPLM.dbo.ITEM_CODES.SPEC_NO
INNER JOIN stagingPLM.dbo.PLANTS ON dbo.OC_VDATA.UDL1 = staging.dbo.PLANTS.PLANT_CODE
WHERE (CONVERT(DATETIME, dbo.OC_VDAT_AUX.UDL40) > DATEADD(day, - 30, GETDATE()))
GROUP BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)),staging.dbo.ITEM_CODES.ITEM_CODE
)
SELECT *
FROM FilterCTE
WHERE RowNumber = 1
这个查询几乎可以满足我的要求
SELECT staging.dbo.ITEM_CODES.ITEM_CODE, MAX(dbo.OC_VDAT_AUX.UDL40) AS SAMPLEDATE,
CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) as LinkID
FROM dbo.OC_VDATA
INNER JOIN dbo.OC_VDAT_AUX ON dbo.OC_VDATA.PARTNO = dbo.OC_VDAT_AUX.PARTNOAUX AND dbo.OC_VDATA.DATETIME = dbo.OC_VDAT_AUX.DATETIMEAUX
INNER JOIN stagingPLM.dbo.ITEM_CODES ON LEFT(dbo.OC_VDATA.PARTNO, 12) = staging.dbo.ITEM_CODES.SPEC_NO
AND LEFT(dbo.OC_VDAT_AUX.PARTNOAUX, 12) = stagingPLM.dbo.ITEM_CODES.SPEC_NO
INNER JOIN stagingPLM.dbo.PLANTS ON dbo.OC_VDATA.UDL1 = staging.dbo.PLANTS.PLANT_CODE
WHERE (CONVERT(DATETIME, dbo.OC_VDAT_AUX.UDL40) > DATEADD(day, - 30, GETDATE()))
GROUP BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)),staging.dbo.ITEM_CODES.ITEM_CODE
样本 Table 由查询生成:
我试图实现的最终结果是每个唯一 LinkID 的最新 ITEM_CODE 请注意 table 中的第一行和最后一行。最后一行不应被查询拉出。 我如何修改此查询以实现此目的? 我在 select 和 where 语句中尝试了 DISTINCT 和子查询的各种放置。
我会用 ROW_NUMBER
window 函数和 CTE
.
解决方法可以这样:
WITH FilterCTE AS
(
SELECT staging.dbo.ITEM_CODES.ITEM_CODE, MAX(dbo.OC_VDAT_AUX.UDL40) AS SAMPLEDATE,
CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) AS LinkID,
ROW_NUMBER() OVER (PARTITION BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)) ORDER BY MAX(dbo.OC_VDAT_AUX.UDL40)) AS RowNumber
FROM dbo.OC_VDATA
INNER JOIN dbo.OC_VDAT_AUX ON dbo.OC_VDATA.PARTNO = dbo.OC_VDAT_AUX.PARTNOAUX AND dbo.OC_VDATA.DATETIME = dbo.OC_VDAT_AUX.DATETIMEAUX
INNER JOIN stagingPLM.dbo.ITEM_CODES ON LEFT(dbo.OC_VDATA.PARTNO, 12) = staging.dbo.ITEM_CODES.SPEC_NO
AND LEFT(dbo.OC_VDAT_AUX.PARTNOAUX, 12) = stagingPLM.dbo.ITEM_CODES.SPEC_NO
INNER JOIN stagingPLM.dbo.PLANTS ON dbo.OC_VDATA.UDL1 = staging.dbo.PLANTS.PLANT_CODE
WHERE (CONVERT(DATETIME, dbo.OC_VDAT_AUX.UDL40) > DATEADD(day, - 30, GETDATE()))
GROUP BY CONCAT(RTRIM(dbo.OC_VDATA.UDL1), RTRIM(dbo.OC_VDATA.UDL6)),staging.dbo.ITEM_CODES.ITEM_CODE
)
SELECT *
FROM FilterCTE
WHERE RowNumber = 1