关于 SQL Server：SQL Server – 查询按计数拆分时间(重叠办公室)

SQL Server - Query to split time by count (overlapping offices)

我正在寻找一些关于我应该采取的查询方法的建议。我有一张表 (EMP)，其中存储了今年的员工详细信息和工作时间(每周 40 小时)。另外 2 个表存储员工所属的主要和次要办公室。由于员工可以在办公室之间移动，因此这些都与日期一起存储。

我希望返回员工在办公室期间的工作小时数。如果员工的主要办公室与次要办公室重叠，则小时数应仅按重叠期间的重叠办公室数量进行划分。

我在下面附上了示例 DDL。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120

-- Employee Table with hours for year 2014

CREATE TABLE [dbo].[EMP](
[EMP_ID] [INT] NOT NULL,
[EMP_NAME] [VARCHAR](255) NULL,
[EMP_FYHOURS] [FLOAT] NULL,
CONSTRAINT [PK_EMP] PRIMARY KEY CLUSTERED
(
[EMP_ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON, FILLFACTOR = 80) ON [PRIMARY]
) ON [PRIMARY]

GO

-- Employees and their primary offices

CREATE TABLE [dbo].[OFFICEPRIMARY](
[OFFICEPRIMARY_ID] [INT] NOT NULL,
[OFFICEPRIMARY_NAME] [VARCHAR](255) NULL,
[OFFICEPRIMARY_EMP_ID] [INT] NOT NULL,
[OFFICEPRIMARY_START] [datetime] NULL,
[OFFICEPRIMARY_END] [datetime] NULL,
CONSTRAINT [PK_OFFICEPRIMARY] PRIMARY KEY CLUSTERED
(
[OFFICEPRIMARY_ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON, FILLFACTOR = 80) ON [PRIMARY]
) ON [PRIMARY]

GO

SET ANSI_PADDING OFF
GO

ALTER TABLE [dbo].[OFFICEPRIMARY] WITH CHECK ADD CONSTRAINT [FK_OFFICEPRIMARY_FK1] FOREIGN KEY([OFFICEPRIMARY_EMP_ID])
REFERENCES [dbo].[EMP] ([EMP_ID])
ON DELETE CASCADE
GO

ALTER TABLE [dbo].[OFFICEPRIMARY] CHECK CONSTRAINT [FK_OFFICEPRIMARY_FK1]
GO

-- Employees and their secondary offices

CREATE TABLE [dbo].[OFFICESECONDARY](
[OFFICESECONDARY_ID] [INT] NOT NULL,
[OFFICESECONDARY_NAME] [VARCHAR](255) NULL,
[OFFICESECONDARY_EMP_ID] [INT] NOT NULL,
[OFFICESECONDARY_START] [datetime] NULL,
[OFFICESECONDARY_END] [datetime] NULL,
CONSTRAINT [PK_OFFICESECONDARY] PRIMARY KEY CLUSTERED
(
[OFFICESECONDARY_ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON, FILLFACTOR = 80) ON [PRIMARY]
) ON [PRIMARY]

GO

SET ANSI_PADDING OFF
GO

ALTER TABLE [dbo].[OFFICESECONDARY] WITH CHECK ADD CONSTRAINT [FK_OFFICESECONDARY_FK1] FOREIGN KEY([OFFICESECONDARY_EMP_ID])
REFERENCES [dbo].[EMP] ([EMP_ID])
ON DELETE CASCADE
GO

ALTER TABLE [dbo].[OFFICESECONDARY] CHECK CONSTRAINT [FK_OFFICESECONDARY_FK1]
GO

-- Insert sample data

INSERT INTO EMP (EMP_ID, EMP_NAME, EMP_FYHOURS)
VALUES (1, 'John Smith', 2080);

INSERT INTO EMP (EMP_ID, EMP_NAME, EMP_FYHOURS)
VALUES (2, 'Jane Doe', 2080);

GO

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (1, 'London', 1, '2014-01-01', '2014-05-31')

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (2, 'Berlin', 1, '2014-06-01', '2014-08-31')

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (3, 'New York', 1, '2014-09-01', '2014-12-31')

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (4, 'New York', 2, '2014-01-01', '2014-04-15')

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (5, 'Paris', 2, '2014-04-16', '2014-09-30')

INSERT INTO OFFICEPRIMARY (OFFICEPRIMARY_ID, OFFICEPRIMARY_NAME, OFFICEPRIMARY_EMP_ID, OFFICEPRIMARY_START, OFFICEPRIMARY_END)
VALUES (6, 'London', 2, '2014-10-01', '2014-12-31')

GO

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (1, 'Paris', 1, '2014-01-01', '2014-03-31')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (2, 'Lyon', 1, '2014-04-01', '2014-05-15')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (3, 'Berlin', 1, '2014-05-16', '2014-09-30')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (4, 'Chicago', 1, '2014-10-01', '2015-02-22')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (5, 'Chicago', 2, '2013-11-21', '2014-04-10')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (6, 'Berlin', 2, '2014-04-11', '2014-09-16')

INSERT INTO OFFICESECONDARY (OFFICESECONDARY_ID, OFFICESECONDARY_NAME, OFFICESECONDARY_EMP_ID, OFFICESECONDARY_START, OFFICESECONDARY_END)
VALUES (7, 'Amsterdam', 2, '2014-09-17', '2015-03-31')

GO

感谢您的指点。我调整了您的查询，使其呈现主要和次要办公室的联合。

剩下的就是计算办公室之间重叠时段的工作时间。例如，

约翰·史密斯，纽约，2014 年 1 月 4 日，2014 年 10 月 8 日

约翰·史密斯，伦敦，2014 年 1 月 8 日，2014 年 12 月 31 日

对于 2014 年 1 月 8 日至 2014 年 8 月 10 日这两个办公室之间的重叠时间段，我预计工作时间将平均分配。如果有 3 个重叠的办公室，那么它将被分成 3 路。

1
2
3
4
5
6
7
8

SELECT 'Primary' AS Office, e.EMP_NAME, op.OFFICEPRIMARY_NAME, op.OFFICEPRIMARY_START, op.OFFICEPRIMARY_END, datediff(wk,OFFICEPRIMARY_START,OFFICEPRIMARY_END) * 40 AS HoursWorkedPrimary
FROM EMP e
INNER JOIN OFFICEPRIMARY op ON op.OFFICEPRIMARY_EMP_ID = e.EMP_ID
UNION ALL
SELECT 'Secondary' AS Office, e.EMP_NAME, os.OFFICESECONDARY_NAME, os.OFFICESECONDARY_START, os.OFFICESECONDARY_END, datediff(wk,OFFICESECONDARY_START,OFFICESECONDARY_END) * 40 AS HoursWorkedSecondary
FROM EMP e
INNER JOIN OFFICESECONDARY os ON os.OFFICESECONDARY_EMP_ID = e.EMP_ID
ORDER BY e.EMP_NAME

如果我理解正确，您希望看到的最终结果是每个员工和办公室的总工作小时数？

我想出了这个：

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73

-- generate date table
DECLARE @MinDate datetime, @MaxDate datetime
SET @MinDate = (SELECT MIN(d) FROM (SELECT d = OFFICEPRIMARY_START FROM dbo.OFFICEPRIMARY UNION SELECT OFFICESECONDARY_START FROM dbo.OFFICESECONDARY) a)
SET @MaxDate = (SELECT MAX(d) FROM (SELECT d = OFFICEPRIMARY_END FROM dbo.OFFICEPRIMARY UNION SELECT OFFICESECONDARY_END FROM dbo.OFFICESECONDARY) a)

SELECT
d = DATEADD(DAY, NUMBER, @MinDate)
INTO
#tmp_dates
FROM
(SELECT DISTINCT NUMBER FROM master.dbo.spt_values WHERE name IS NULL) n
WHERE
DATEADD(DAY, NUMBER, @MinDate) < @MaxDate

;WITH CTE AS
(
SELECT
d.d
,o.OfficeType
,o.OfficeID
,o.OfficeName
,o.EmpID
,EmpName = e.EMP_NAME
,HoursWorked = 8 / (COUNT(1) OVER (PARTITION BY EmpID, d))
FROM
(
SELECT
OfficeType = 1
,OfficeID = op.OFFICEPRIMARY_ID
,OfficeName = op.OFFICEPRIMARY_NAME
,EmpID = op.OFFICEPRIMARY_EMP_ID
,StartDate = op.OFFICEPRIMARY_START
,EndDate = op.OFFICEPRIMARY_END
FROM
dbo.OFFICEPRIMARY op

UNION

SELECT
OfficeType = 2
,OfficeID = os.OFFICESECONDARY_ID
,OfficeName = os.OFFICESECONDARY_NAME
,EmpID = os.OFFICESECONDARY_EMP_ID
,StartDate = os.OFFICESECONDARY_START
,EndDate = os.OFFICESECONDARY_END
FROM
dbo.OFFICESECONDARY os
) o

INNER JOIN
dbo.EMP e ON e.EMP_ID = o.EmpID
INNER JOIN
#tmp_dates d ON o.StartDate<=d.d AND o.EndDate>=d.d
)

SELECT
EmpID
,EmpName
,OfficeType
,OfficeName
,TotalHoursWorked = SUM(HoursWorked)
FROM
CTE
GROUP BY
EmpID
,EmpName
,OfficeType
,OfficeID
,OfficeName
ORDER BY
EmpID
,OfficeName

我首先生成一个临时表，其中包含最小日期和最大日期之间的日期。

然后我合并两个办公室表(为什么你有 2 个表？)，我得到一个 CTE，它返回关于员工、日期、办公室和在这个办公室工作的小时数的数据(8 除以员工所在办公室的数量)这一天上班)。

然后我将这些数据相加，得到按员工和办公室分组的小时总和。

也许有一个更简单的解决方案。这是我想到的第一个解决方案。

下面的链接应该可以帮助您指出正确的方向，以确定日期如何重叠。

计算日期范围内可能重叠的排除天数

这应该会给你一个良好的开端：

1
2
3
4
5
6
7
8

SELECT datediff(wk,OFFICEPRIMARY_START,OFFICEPRIMARY_END) * 40 AS HoursWorkedPrimary
,datediff(wk,OFFICESECONDARY_START,OFFICESECONDARY_END) * 40 AS HoursWorkedSecondary
,EMP_NAME
,OFFICEPRIMARY_NAME,OFFICEPRIMARY_START,OFFICEPRIMARY_END
,OFFICESECONDARY_NAME,OFFICESECONDARY_START,OFFICESECONDARY_END
FROM [EMP]
INNER JOIN OFFICEPRIMARY AS op ON op.OFFICEPRIMARY_EMP_ID = EMP.EMP_ID
INNER JOIN OFFICESECONDARY AS os ON os.OFFICESECONDARY_EMP_ID = EMP.EMP_ID