基于层次结构的数据透视表
Pivot Data Based on Hierarchy
我有一个分层数据，其结构可能会发生变化。这些关系在单个 table 中维护，通过两列（节点 ID 和父 ID）上的自引用来标识。我希望能够 运行 一个查询来对数据进行透视，以便每一行代表节点的最低单位。
例如：
如果我有一个看起来像这样的 table...
我希望能够做到这一点...
我试过多次连接，试图让所有内容都在同一行上...
SELECT L1.NAME AS CITY, L2.NAME AS COUNTY, L3.NAME AS STATE, L4.NAME AS
COUNTRY
FROM TABLENAME L1
LEFT JOIN TABLENAME AS L2 ON L1.PARENT_NODE_ID = L2.NODE_ID
LEFT JOIN TABLENAME AS L3 ON L2.PARENT_NODE_ID = L3.NODE_ID
LEFT JOIN TABLENAME AS L4 ON L3.PARENT_NODE_ID = L4.NODE_ID
WHERE L1.Type = City
这里是问题的核心：我可能并不总是知道层次结构。因此我需要一个可以处理变化的解决方案。假设业务逻辑的维护者决定我们需要在国家之上添加半球。或州以上的地区（西海岸、中部、东海岸）。然而，城市将始终是最低节点。我需要一些可以独立于层次结构而存在的东西。
更新
我原来的问题我用了一个简单的例子。在我的实际解决方案中，我必须利用多个连接来获得我需要的层次结构。我正在处理下面的查询，但截至目前，我希望填充的每一列都为 returns null。最有可能是 case 语句的问题？
;WITH ALLORGS AS( --All Orgs
SELECT ORGS.ID, ORGS.ORG_NAME
, HIER.ID_PARENTORG, TYP.ORG_TYPE_DESCR
FROM ORGANIATIONS AS ORGS
FULL OUTER JOIN HIERARCHYTABLE AS HIER ON ORGS.ID = HIER.ID_ORG
FULL OUTER JOIN ORGANIZATION_TYPES AS TYP ON ORGS.ID_ORG_TYPE = TYP.ID
), CTE AS (
SELECT ID
, ID_PARENTORG
, L1.ORG_NAME
--, ORG_TYPE_DESCR
, CAST('' as varchar(100)) AS UNIT
, CAST('' as varchar(100)) AS REGION
, CAST('' as varchar(100)) AS DDA_POOL
, CAST('' as varchar(100)) AS COUNTY
, CAST('' as varchar(100)) AS STATE
, CAST('' as varchar(100)) AS BUSINESS_UNIT
, CAST('' as varchar(100)) AS PROEPRTY
, CAST('' as varchar(100)) AS DISTRICT
, 1 AS FLAG
FROM ALLORGS L1
WHERE L1.ORG_TYPE_DESCR = 'COST CENTER'
UNION ALL
SELECT T1.ID
,L2.ID_PARENTORG
,T1.ORG_NAME AS COSTCNTR
--, T.ORG_TYPE_DESCR
,CASE WHEN L2.ORG_TYPE_DESCR = 'UNIT' THEN L2.ORG_NAME ELSE NULL END AS UNIT
,CASE WHEN L2.ORG_TYPE_DESCR = 'REGION' THEN L2.ORG_NAME ELSE NULL END AS REGION
,CASE WHEN L2.ORG_TYPE_DESCR = 'DDA_POOL' THEN L2.ORG_NAME ELSE NULL END AS DDA_POOL
,CASE WHEN L2.ORG_TYPE_DESCR = 'COUNTRY' THEN L2.ORG_NAME ELSE NULL END AS COUNTRY
,CASE WHEN L2.ORG_TYPE_DESCR = 'STATE' THEN L2.ORG_NAME ELSE NULL END AS STATE
,CASE WHEN L2.ORG_TYPE_DESCR = 'BUSINESS_UNIT' THEN L2.ORG_NAME ELSE NULL END AS BUSINESS_UNIT
,CASE WHEN L2.ORG_TYPE_DESCR = 'PROPERTY' THEN L2.ORG_NAME ELSE NULL END AS PROPERTY
,CASE WHEN L2.ORG_TYPE_DESCR = 'DISTRICT' THEN L2.ORG_NAME ELSE NULL END AS DISTRICT
,T1.FLAG + 1 AS FLAG
FROM CTE AS T1
INNER JOIN ALLORGS AS L2 ON T1.ID_PARENTORG = L2.ID
)
SELECT a.ID
,a.ORG_NAME AS COSTCNTR
,UNIT
,REGION
,DDA_POOL
,COUNTY
,STATE
,BUSINESS_UNIT
,PROEPRTY
,DISTRICT
FROM CTE AS a
INNER JOIN (SELECT ID, MAX(FLAG) FLAG FROM CTE GROUP BY ID) b ON a.ID = b.ID AND a.FLAG = b.FLAG
试试这个...
请在使用前使用更多示例数据对其进行测试。
Table 脚本和样本数据
CREATE TABLE [TableName](
[ParentNodeID] [int] NULL,
[NodeID] [int] NULL,
[Type] [nvarchar](50) NULL,
[Name] [nvarchar](50) NULL
)
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (NULL, 1, N'Country', N'US')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (1, 2, N'State', N'Texas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (2, 3, N'County', N'Dallas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (3, 4, N'City', N'Dallas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (NULL, 1, N'Country', N'US')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (5, 6, N'State', N'Massachusetts')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (7, 8, N'County', N'Suffolk')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (9, 10, N'City', N'Boston')
查询
DECLARE @cols AS NVARCHAR(max) = Stuff((SELECT DISTINCT ',' + Quotename([Type])
FROM TableName
FOR xml path(''), type).value('.', 'NVARCHAR(MAX)'), 1, 1, '');
DECLARE @query AS NVARCHAR(max) = 'SELECT max(NodeID) AS NodeID
,max([Country]) AS Country
,max([State]) AS STATE
,max([County]) AS County
,max([City]) AS City
FROM (
SELECT *, Row_Number() OVER (PARTITION BY Type ORDER BY NodeID) rn
FROM TableName
) sq
pivot(max([Name]) FOR [Type] IN ('+ @cols +') ) pvt
GROUP BY rn';
EXECUTE(@query)
输出
+--------+---------+---------------+---------+--------+
| NodeID | Country | STATE | County | City |
+--------+---------+---------------+---------+--------+
| 4 | US | Texas | Dallas | Dallas |
| 10 | US | Massachusetts | Suffolk | Boston |
+--------+---------+---------------+---------+--------+
我也实现了同样的情况，我没有测试这个，因为我现在只用我的phone，但我使用的逻辑几乎是这样的，使用递归的CTE，希望这也有效
WITH CTE AS (
--Put Initial Value '' to be filled later
SELECT NODE_ID, PARENT_ID, L1.NAME AS CITY, '' AS COUNTY, '' AS STATE, '' AS COUNTRY,
--add hemisphere
'' AS HEMISPHERE,
1 AS FLAG --Only for indication of looping
FROM TABLENAME L1
WHERE L1.TYPE = 'CITY'
UNION ALL
SELECT T1.NODE_ID, L2.PARENT_ID,
T1.NAME AS CITY,
(CASE WHEN L2.TYPE = 'COUNTY' THEN L2.NAME ELSE T1.NAME) AS COUNTY,
(CASE WHEN L2.TYPE = 'STATE' THEN L2.NAME ELSE T1.NAME) AS STATE,
(CASE WHEN L2.TYPE = 'COUNTRY' THEN L2.NAME ELSE T1.NAME) AS COUNTRY
--and can add some more columns here, in case if there is additional column for Hemisphere
(CASE WHEN L2.TYPE = 'Hemisphere' THEN L2.NAME ELSE T1.NAME) AS Hemisphere
T1.FLAG + 1 AS FLAG -- add +1 for n reccuring, only for indication of looping
FROM CTE T1
INNER JOIN TABLENAME L2 ON T1.PARENT_ID =
L2.NODE_ID
)
SELECT a.NODE_ID, CITY, COUNTY, STATE, COUNTRY
FROM CTE a
--to get the last loop which has completely filled data
INNER JOIN (SELECT NODE_ID, MAX(FLAG) FLAG FROM CTE GROUP BY NODE_ID ) b ON a.NODE_ID = b.NODE_ID AND a.FLAG = b.FLAG
我有一个分层数据，其结构可能会发生变化。这些关系在单个 table 中维护，通过两列（节点 ID 和父 ID）上的自引用来标识。我希望能够 运行 一个查询来对数据进行透视，以便每一行代表节点的最低单位。
例如：
如果我有一个看起来像这样的 table...
我希望能够做到这一点...
我试过多次连接，试图让所有内容都在同一行上...
SELECT L1.NAME AS CITY, L2.NAME AS COUNTY, L3.NAME AS STATE, L4.NAME AS
COUNTRY
FROM TABLENAME L1
LEFT JOIN TABLENAME AS L2 ON L1.PARENT_NODE_ID = L2.NODE_ID
LEFT JOIN TABLENAME AS L3 ON L2.PARENT_NODE_ID = L3.NODE_ID
LEFT JOIN TABLENAME AS L4 ON L3.PARENT_NODE_ID = L4.NODE_ID
WHERE L1.Type = City
这里是问题的核心：我可能并不总是知道层次结构。因此我需要一个可以处理变化的解决方案。假设业务逻辑的维护者决定我们需要在国家之上添加半球。或州以上的地区（西海岸、中部、东海岸）。然而，城市将始终是最低节点。我需要一些可以独立于层次结构而存在的东西。
更新 我原来的问题我用了一个简单的例子。在我的实际解决方案中，我必须利用多个连接来获得我需要的层次结构。我正在处理下面的查询，但截至目前，我希望填充的每一列都为 returns null。最有可能是 case 语句的问题？
;WITH ALLORGS AS( --All Orgs
SELECT ORGS.ID, ORGS.ORG_NAME
, HIER.ID_PARENTORG, TYP.ORG_TYPE_DESCR
FROM ORGANIATIONS AS ORGS
FULL OUTER JOIN HIERARCHYTABLE AS HIER ON ORGS.ID = HIER.ID_ORG
FULL OUTER JOIN ORGANIZATION_TYPES AS TYP ON ORGS.ID_ORG_TYPE = TYP.ID
), CTE AS (
SELECT ID
, ID_PARENTORG
, L1.ORG_NAME
--, ORG_TYPE_DESCR
, CAST('' as varchar(100)) AS UNIT
, CAST('' as varchar(100)) AS REGION
, CAST('' as varchar(100)) AS DDA_POOL
, CAST('' as varchar(100)) AS COUNTY
, CAST('' as varchar(100)) AS STATE
, CAST('' as varchar(100)) AS BUSINESS_UNIT
, CAST('' as varchar(100)) AS PROEPRTY
, CAST('' as varchar(100)) AS DISTRICT
, 1 AS FLAG
FROM ALLORGS L1
WHERE L1.ORG_TYPE_DESCR = 'COST CENTER'
UNION ALL
SELECT T1.ID
,L2.ID_PARENTORG
,T1.ORG_NAME AS COSTCNTR
--, T.ORG_TYPE_DESCR
,CASE WHEN L2.ORG_TYPE_DESCR = 'UNIT' THEN L2.ORG_NAME ELSE NULL END AS UNIT
,CASE WHEN L2.ORG_TYPE_DESCR = 'REGION' THEN L2.ORG_NAME ELSE NULL END AS REGION
,CASE WHEN L2.ORG_TYPE_DESCR = 'DDA_POOL' THEN L2.ORG_NAME ELSE NULL END AS DDA_POOL
,CASE WHEN L2.ORG_TYPE_DESCR = 'COUNTRY' THEN L2.ORG_NAME ELSE NULL END AS COUNTRY
,CASE WHEN L2.ORG_TYPE_DESCR = 'STATE' THEN L2.ORG_NAME ELSE NULL END AS STATE
,CASE WHEN L2.ORG_TYPE_DESCR = 'BUSINESS_UNIT' THEN L2.ORG_NAME ELSE NULL END AS BUSINESS_UNIT
,CASE WHEN L2.ORG_TYPE_DESCR = 'PROPERTY' THEN L2.ORG_NAME ELSE NULL END AS PROPERTY
,CASE WHEN L2.ORG_TYPE_DESCR = 'DISTRICT' THEN L2.ORG_NAME ELSE NULL END AS DISTRICT
,T1.FLAG + 1 AS FLAG
FROM CTE AS T1
INNER JOIN ALLORGS AS L2 ON T1.ID_PARENTORG = L2.ID
)
SELECT a.ID
,a.ORG_NAME AS COSTCNTR
,UNIT
,REGION
,DDA_POOL
,COUNTY
,STATE
,BUSINESS_UNIT
,PROEPRTY
,DISTRICT
FROM CTE AS a
INNER JOIN (SELECT ID, MAX(FLAG) FLAG FROM CTE GROUP BY ID) b ON a.ID = b.ID AND a.FLAG = b.FLAG
试试这个... 请在使用前使用更多示例数据对其进行测试。
Table 脚本和样本数据
CREATE TABLE [TableName](
[ParentNodeID] [int] NULL,
[NodeID] [int] NULL,
[Type] [nvarchar](50) NULL,
[Name] [nvarchar](50) NULL
)
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (NULL, 1, N'Country', N'US')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (1, 2, N'State', N'Texas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (2, 3, N'County', N'Dallas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (3, 4, N'City', N'Dallas')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (NULL, 1, N'Country', N'US')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (5, 6, N'State', N'Massachusetts')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (7, 8, N'County', N'Suffolk')
INSERT [TableName] ([ParentNodeID], [NodeID], [Type], [Name]) VALUES (9, 10, N'City', N'Boston')
查询
DECLARE @cols AS NVARCHAR(max) = Stuff((SELECT DISTINCT ',' + Quotename([Type])
FROM TableName
FOR xml path(''), type).value('.', 'NVARCHAR(MAX)'), 1, 1, '');
DECLARE @query AS NVARCHAR(max) = 'SELECT max(NodeID) AS NodeID
,max([Country]) AS Country
,max([State]) AS STATE
,max([County]) AS County
,max([City]) AS City
FROM (
SELECT *, Row_Number() OVER (PARTITION BY Type ORDER BY NodeID) rn
FROM TableName
) sq
pivot(max([Name]) FOR [Type] IN ('+ @cols +') ) pvt
GROUP BY rn';
EXECUTE(@query)
输出
+--------+---------+---------------+---------+--------+
| NodeID | Country | STATE | County | City |
+--------+---------+---------------+---------+--------+
| 4 | US | Texas | Dallas | Dallas |
| 10 | US | Massachusetts | Suffolk | Boston |
+--------+---------+---------------+---------+--------+
我也实现了同样的情况，我没有测试这个，因为我现在只用我的phone，但我使用的逻辑几乎是这样的，使用递归的CTE，希望这也有效
WITH CTE AS (
--Put Initial Value '' to be filled later
SELECT NODE_ID, PARENT_ID, L1.NAME AS CITY, '' AS COUNTY, '' AS STATE, '' AS COUNTRY,
--add hemisphere
'' AS HEMISPHERE,
1 AS FLAG --Only for indication of looping
FROM TABLENAME L1
WHERE L1.TYPE = 'CITY'
UNION ALL
SELECT T1.NODE_ID, L2.PARENT_ID,
T1.NAME AS CITY,
(CASE WHEN L2.TYPE = 'COUNTY' THEN L2.NAME ELSE T1.NAME) AS COUNTY,
(CASE WHEN L2.TYPE = 'STATE' THEN L2.NAME ELSE T1.NAME) AS STATE,
(CASE WHEN L2.TYPE = 'COUNTRY' THEN L2.NAME ELSE T1.NAME) AS COUNTRY
--and can add some more columns here, in case if there is additional column for Hemisphere
(CASE WHEN L2.TYPE = 'Hemisphere' THEN L2.NAME ELSE T1.NAME) AS Hemisphere
T1.FLAG + 1 AS FLAG -- add +1 for n reccuring, only for indication of looping
FROM CTE T1
INNER JOIN TABLENAME L2 ON T1.PARENT_ID =
L2.NODE_ID
)
SELECT a.NODE_ID, CITY, COUNTY, STATE, COUNTRY
FROM CTE a
--to get the last loop which has completely filled data
INNER JOIN (SELECT NODE_ID, MAX(FLAG) FLAG FROM CTE GROUP BY NODE_ID ) b ON a.NODE_ID = b.NODE_ID AND a.FLAG = b.FLAG