Grouping by contiguous dates, ignoring weekends in SQL - sql

I'm attempting to group contiguous date ranges to show the minimum and maximum date for each range. So far I've used a solution similar to this one: http://www.sqlservercentral.com/articles/T-SQL/71550/ however I'm on SQL 2000 so I had to make some changes. This is my procedure so far:
create table #tmp
(
date smalldatetime,
rownum int identity
)
insert into #tmp
select distinct date from testDates order by date
select
min(date) as dateRangeStart,
max(date) as dateRangeEnd,
count(*) as dates,
dateadd(dd,-1*rownum, date) as GroupID
from #tmp
group by dateadd(dd,-1*rownum, date)
drop table #tmp
It works exactly how I want except for one issue: weekends. My data sets have no records for weekend dates, which means any group found is at most 5 days. For instance, in the results below, I would like the last 3 groups to show up as a single record, with a dateRangeStart of 10/6 and a dateRangeEnd of 10/20:
Is there some way I can set this up to ignore a break in the date range if that break is just a weekend?
Thanks for the help.

EDITED
I didn't like my previous idea very much. Here's a better one, I think:
Based on the first and the last dates from the set of those to be grouped, prepare the list of all the intermediate weekend dates.
Insert the working dates together with weekend dates, ordered, so they would all be assigned rownum values according to their normal order.
Use your method of finding contiguous ranges with the following modifications:
1) when calculating dateRangeStart, if it's a weekend date, pick the nearest following weekday;
2) accordingly for dateRangeEnd, if it's a weekend date, pick the nearest preceding weekday;
3) when counting dates for the group, pick only weekdays.
Select from the resulting set only those rows where dates > 0, thus eliminating the groups formed only of the weekends.
And here's an implementation of the method, where it is assumed, that a week starts on Sunday (DATEPART returns 1) and weekend days are Sunday and Saturday:
DECLARE #tmp TABLE (date smalldatetime, rownum int IDENTITY);
DECLARE #weekends TABLE (date smalldatetime);
DECLARE #minDate smalldatetime, #maxDate smalldatetime, #date smalldatetime;
/* #1 */
SELECT #minDate = MIN(date), #maxDate = MAX(date)
FROM testDates;
SET #date = #minDate - DATEPART(dw, #minDate) + 7;
WHILE #date < #maxDate BEGIN
INSERT INTO #weekends
SELECT #date UNION ALL
SELECT #date + 1;
SET #date = #date + 7;
END;
/* #2 */
INSERT INTO #tmp
SELECT date FROM testDates
UNION
SELECT date FROM #weekends
ORDER BY date;
/* #3 & #4 */
SELECT *
FROM (
SELECT
MIN(date + CASE DATEPART(dw, date) WHEN 1 THEN 1 WHEN 7 THEN 2 ELSE 0 END)
AS dateRangeStart,
MAX(date - CASE DATEPART(dw, date) WHEN 1 THEN 2 WHEN 7 THEN 1 ELSE 0 END)
AS dateRangeEnd,
COUNT(CASE WHEN DATEPART(dw, date) NOT IN (1, 7) THEN date END) AS dates,
DATEADD(d, -rownum, date) AS GroupID
FROM #tmp
GROUP BY DATEADD(d, -rownum, date)
) s
WHERE dates > 0;

Related

SQL query to find employee aniversary

I need to find anniversary date and anniversary year of employees and send email in every 14 days.But I have a problem with last week of December when using the following query if start date and end date are in different years.
Select * from Resource
where (DATEPART(dayofyear,JoinDate)
BETWEEN DATEPART(dayofyear,GETDATE())
AND DATEPART(dayofyear,DateAdd(DAY,14,GETDATE())))
Instead of comparing to a dayofyear (which resets to zero at jan 1st and is the reason your query breaks within 14 days of the end of the year) you could update the employee's joindate to be the current year for the purpose of the query and just compare to actual dates
Select * from Resource
-- Add the number of years difference between joinDate and the current year
where DATEADD(year,DATEDIFF(Year,joinDate,GetDate()),JoinDate)
-- compare to range "today"
BETWEEN GetDate()
-- to 14 days from today
AND DATEADD(Day,14,GetDate())
-- duplicate for following year
OR DATEADD(year,DATEDIFF(Year,joinDate,GetDate())+1,JoinDate) -- 2016-1-1
BETWEEN GetDate()
AND DATEADD(Day,14,GetDate())
Test query:
declare #joindate DATETIME='2012-1-1'
declare #today DATETIME = '2015-12-26'
SELECT #joinDate
where DATEADD(year,DATEDIFF(Year,#joinDate,#today),#JoinDate) -- 2015-1-1
BETWEEN #today -- 2015-12-26
AND DATEADD(Day,14,#today) -- 2016-01-09
OR DATEADD(year,DATEDIFF(Year,#joinDate,#today)+1,#JoinDate) -- 2016-1-1
BETWEEN #today -- 2015-12-26
AND DATEADD(Day,14,#today) -- 2016-01-09
(H/T #Damien_The_Unbeliever for a simple fix)
The above correctly selects the joinDate which is in the first week of Jan (note I've had to fudge #today as Ive not managed to invent time travel).
The above solution should also solve the issue with leap years that was hiding in your original solution.
Update
You expressed in comments the requirement to select AnniversaryDate and Years of service, you need to apply some CASE logic to determine whether to add 1 (year or date) to your select
select *,
CASE
WHEN DATEADD(YEAR,DATEDIFF(Year,JoinDate,GETDATE()),JoinDate) < GetDate()
THEN DATEDIFF(Year,JoinDate,GETDATE())+1
ELSE DATEDIFF(Year,JoinDate,GETDATE())
END as [Years],
CASE WHEN DATEADD(YEAR,DATEDIFF(Year,JoinDate,GETDATE()),JoinDate) < GetDate()
THEN DATEADD(YEAR,DATEDIFF(Year,JoinDate,GETDATE())+1,JoinDate)
ELSE DATEADD(YEAR,DATEDIFF(Year,JoinDate,GETDATE()),JoinDate)
end as [AnniversaryDate]
.... // etc
You could do this:
Select * from Resource
where DATEPART(dayofyear,JoinDate)
BETWEEN DATEPART(dayofyear,GETDATE())
AND DATEPART(dayofyear,DateAdd(DAY,14,GETDATE()))
OR
DATEPART(dayofyear,JoinDate)
BETWEEN (DATEPART(dayofyear,GETDATE()) + 365)
AND (DATEPART(dayofyear,DateAdd(DAY,14,GETDATE())) + 365)
Try this:
DECLARE #Today DATE = GETDATE() --'12/25/2013'
DECLARE #Duration INT = 14
;WITH Recur AS
(
SELECT #Today AS RecurDate
UNION ALL
SELECT DATEADD(DAY, 1, RecurDate)
FROM Recur
WHERE DATEDIFF(DAY, #Today, RecurDate)+1 < #Duration
)
SELECT
r.*
FROM
Resource r
JOIN Recur
ON CONVERT(VARCHAR(5), JoinDate, 101) = CONVERT(VARCHAR(5), RecurDate, 101)
WHERE JoinDate < #Today
You can use the SQL DATEADD() function with week number parameter
Here is how you can use it:
DECLARE #date date = getdate()
Select * from Resource
where
JoinDate BETWEEN #date AND DATEADD(ww,2,#date)

SQL Current status for given day (FOR loop)

For simplicity lets assume that I have a view with three fields
date_in (date)
Container (varchar)
date_out (date)
Now, the container is IN if the date_in is lesser or equal to given date and date_out is null or greater than given date. Now I am trying to count the containers for given time period. In pseudocode between two values STARTDATE and ENDDATE it would be something like
FOR X =STARTDATE, X<= ENDDADE, X++ {
if date_in <=X and date_out>x
count (container)
}
or closer to SQL:
declare #startdate date,
#d date;
set #startdate = '1/01/2014'
set #d = #startdate
"FOR on the #d variable would go here" {
select #d as SNAP_DATE, count (container) where date_in <#d
and (date_out is null or date_out> #d)
}
It might be simple - I guess I could make a new table and manually do multiple SELECT INTO (and later query from this new table) but its not very elegant solution.
Edit: just to precise - in the end I'd like to have something like:
DATE Count
1/02/2014 10
2/02/2014 15
...
7/03/2014 19
You could do this procedurally as follows:
Use a while loop to loop from start to end date.
Use a table variable to store each date-count pair.
Select from the table variable to get the summarised result.
declare #start date = '1/01/2014'
declare #end date = '7/03/2014'
declare #tbl table(Date date, Count int)
while(#start < #end)
begin
insert into #tbl
select #start, count(*)
from your_view
where (in_date < #start)
and ((out_date is null) or (out_date > #start))
set #start = dateadd(day, 1, #start)
end
select * from #tbl
You might be able to do something like the following. It uses a numbers table, which can be a real or derived table. It contains rows of integers. You need a table that begins with 0 and has enough values to cover your date range. Check here for more information on a numbers table.
DECLARE #StartDate DATE = '1/2/2014'
DECLARE #EndDate DATE = '1/4/2014'
SELECT DATEADD(d, n.num, #StartDate) AS DATE, COUNT(*) AS COUNT
FROM Numbers n
JOIN MyView mv ON mv.date_in < DATEADD(d, n.num, #StartDate)
AND (mv.date_out IS NULL OR mv.date_out > DATEADD(d, n.num, #StartDate))
WHERE DATEADD(d, n.num, #StartDate) BETWEEN #StartDate AND #EndDate
GROUP BY DATEADD(d, n.num, #StartDate)
ORDER BY DATEADD(d, n.num, #StartDate)
The numbers in the numbers table are converted to the list of dates between the date range. Each date is joined to your view based on the criteria you need.

How can I generate a temporary table filled with dates in SQL Server 2000?

I need to make a temporary table that holds of range of dates, as well as a couple of columns that hold placeholder values (0) for future use. The dates I need are the first day of each month between $startDate and $endDate where these variables can be several years apart.
My original sql statement looked like this:
select dbo.FirstOfMonth(InsertDate) as Month, 0 as Trials, 0 as Sales
into #dates
from customer
group by dbo.FirstOfMonth(InsertDate)
"FirstOfMonth" is a user-defined function I made that pretty much does what it says, returning the first day of the month for the provided date with the time at exactly midnight.
This produced almost exactly what I needed until I discovered there were occasionally gaps in my dates where I had a few months were there were no records insert dates. Since my result must still have the missing months I need a different approach.
I have added the following declarations to the stored procedure anticipating their need for the range of the dates I need ...
declare $startDate set $startDate = select min(InsertDate) from customer
declare $endDate set $endDate = select max(InsertDate) from customer
... but I have no idea what to do from here.
I know this question is similar to this question but, quite frankly, that answer is over my head (I don't often work with SQL and when I do it tends to be on older versions of SQL Server) and there are a few minor differences that are throwing me off.
I needed something similar, but all DAYS instead of all MONTHS.
Using the code from MatBailie as a starting point, here's the SQL for creating a permanent table with all dates from 2000-01-01 to 2099-12-31:
CREATE TABLE _Dates (
d DATE,
PRIMARY KEY (d)
)
DECLARE #dIncr DATE = '2000-01-01'
DECLARE #dEnd DATE = '2100-01-01'
WHILE ( #dIncr < #dEnd )
BEGIN
INSERT INTO _Dates (d) VALUES( #dIncr )
SELECT #dIncr = DATEADD(DAY, 1, #dIncr )
END
This will quickly populate a table with 170 years worth of dates.
CREATE TABLE CalendarMonths (
date DATETIME,
PRIMARY KEY (date)
)
DECLARE
#basedate DATETIME,
#offset INT
SELECT
#basedate = '01 Jan 2000',
#offset = 1
WHILE (#offset < 2048)
BEGIN
INSERT INTO CalendarMonths SELECT DATEADD(MONTH, #offset, date) FROM CalendarMonths
SELECT #offset = #offset + #offset
END
You can then use it by LEFT joining on to that table, for the range of dates you require.
I would probably use a Calendar table. Create a permanent table in your database and fill it with all of the dates. Even if you covered a 100 year range, the table would still only have ~36,525 rows in it.
CREATE TABLE dbo.Calendar (
calendar_date DATETIME NOT NULL,
is_weekend BIT NOT NULL,
is_holiday BIT NOT NULL,
CONSTRAINT PK_Calendar PRIMARY KEY CLUSTERED (calendar_date)
)
Once the table is created, just populate it once in a loop, so that it's always out there and available to you.
Your query then could be something like this:
SELECT
C.calendar_date,
0 AS trials,
0 AS sales
FROM
dbo.Calendar C
WHERE
C.calendar_date BETWEEN #start_date AND #end_date AND
DAY(C.calendar_date) = 1
You can join in the Customers table however you need to, outer joining on FirstOfMonth(InsertDate) = C.calendar_date if that's what you want.
You can also include a column for day_of_month if you want which would avoid the overhead of calling the DAY() function, but that's fairly trivial, so it probably doesn't matter one way or another.
This of course will not work in SQL-Server 2000 but in a modern database where you don't want to create a permanent table. You can use a table variable instead creating a table so you can left join the data try this. Change the DAY to HOUR etc to change the increment type.
declare #CalendarMonths table (date DATETIME, PRIMARY KEY (date)
)
DECLARE
#basedate DATETIME,
#offset INT
SELECT
#basedate = '01 Jan 2014',
#offset = 1
INSERT INTO #CalendarMonths SELECT #basedate
WHILE ( DATEADD(DAY, #offset, #basedate) < CURRENT_TIMESTAMP)
BEGIN
INSERT INTO #CalendarMonths SELECT DATEADD(HOUR, #offset, date) FROM #CalendarMonths where DATEADD(DAY, #offset, date) < CURRENT_TIMESTAMP
SELECT #offset = #offset + #offset
END
A starting point of a useful kludge to specify a range or specific list of dates:
SELECT *
FROM
(SELECT CONVERT(DateTime,'2017-1-1')+number AS [Date]
FROM master..spt_values WHERE type='P' AND number<370) AS DatesList
WHERE DatesList.Date IN ('2017-1-1','2017-4-14','2017-4-17','2017-12-25','2017-12-26')
You can get 0 to 2047 out of master..spt_values WHERE type='P', so that's five and a half year's worth of dates if you need it!
Tested below and it works, though it's a bit convoluted.
I assigned arbitrary values to the dates for the test.
DECLARE #SD smalldatetime,
#ED smalldatetime,
#FD smalldatetime,
#LD smalldatetime,
#Mct int,
#currct int = 0
SET #SD = '1/15/2011'
SET #ED = '2/02/2012'
SET #FD = (DATEADD(dd, -1*(Datepart(dd, #SD)-1), #sd))
SET #LD = (DATEADD(dd, -1*(Datepart(dd, #ED)-1), #ED))
SET #Mct = DATEDIFF(mm, #FD, #LD)
CREATE TABLE #MyTempTable (FoM smalldatetime, Trials int, Sales money)
WHILE #currct <= #Mct
BEGIN
INSERT INTO #MyTempTable (FoM, Trials, Sales)
VALUES
(DATEADD(MM, #currct, #FD), 0, 0)
SET #currct = #currct + 1
END
SELECT * FROM #MyTempTable
DROP TABLE #MyTempTable
For SQL Server 2000, this stackoverflow post looks promising for a way to temporarily generate dates calculated off of a start and end date. It's not exactly the same but quite similar. This post has a very in-depth answer on truncating dates, if needed.
In case anyone stumbles on this question and is working in PostgreSQL instead of SQL Server 2000, here is how you might do it there...
PostgreSQL has a nifty series generating function. For your example, you could use this series of all days instead of generating an entire calendar table, and then do groupings and matchups from there.
SELECT current_date + s.a AS dates FROM generate_series(0,14,7) AS s(a);
dates
------------
2004-02-05
2004-02-12
2004-02-19
(3 rows)
SELECT * FROM generate_series('2008-03-01 00:00'::timestamp,
'2008-03-04 12:00', '10 hours');
generate_series
---------------------
2008-03-01 00:00:00
2008-03-01 10:00:00
2008-03-01 20:00:00
2008-03-02 06:00:00
2008-03-02 16:00:00
2008-03-03 02:00:00
2008-03-03 12:00:00
2008-03-03 22:00:00
2008-03-04 08:00:00
(9 rows)
I would also look into date_trunc from PostgreSQL using 'month' for the truncator field to maybe refactor your original query to easily match with a date_trunc version of the calendar series.
select top (datediff(D,#start,#end)) dateadd(D,id-1,#start)
from BIG_TABLE_WITH_NO_JUMPS_IN_ID
declare #start datetime
set #start = '2016-09-01'
declare #end datetime
set #end = '2016-09-30'
create table #Date
(
table_id int identity(1,1) NOT NULL,
counterDate datetime NULL
);
insert into #Date select top (datediff(D,#start,#end)) NULL from SOME_TABLE
update #Date set counterDate = dateadd(D,table_id - 1, #start)
The code above should populate the table with all the dates between the start and end. You would then just join on this table to get all of the dates needed. If you only needed a certain day of each month, you could dateadd a month instead.
SELECT P.Id
, DATEADD ( DD, -P.Id, P.Date ) AS Date
FROM (SELECT TOP 1000 ROW_NUMBER () OVER (ORDER BY (SELECT NULL)) AS Id, CAST(GETDATE () AS DATE) AS Date FROM master.dbo.spt_values) AS P
This query returns a table calendar for the last 1000 days or so. It can be put in a temporary or other table.
Create a table variable containing a date for each month in a year:
declare #months table (reportMonth date, PRIMARY KEY (reportMonth));
declare #start date = '2018', #month int = 0; -- base 0 month
while (#month < 12)
begin
insert into #months select dateAdd(month, #month, #start);
select #month = #month + 1;
end
--verify
select * from #months;
This is by far the quickest method I have found (much quicker than inserting rows 1 by 1 in a WHILE loop):
DECLARE #startDate DATE = '1900-01-01'
DECLARE #endDate DATE = '2050-01-01'
SELECT DATEADD(DAY, sequenceNumber, #startDate) AS TheDate
INTO #TheDates
FROM (
SELECT ones.n + 10*tens.n + 100*hundreds.n + 1000*thousands.n + 10000*tenthousands.n AS sequenceNumber
FROM
(VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) ones(n),
(VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) tens(n),
(VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) hundreds(n),
(VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) thousands(n),
(VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) tenthousands(n)
WHERE ones.n + 10*tens.n + 100*hundreds.n + 1000*thousands.n + 10000*tenthousands.n <= DATEDIFF(day, #startDate, #endDate)
) theNumbers
SELECT *
FROM #TheDates
ORDER BY TheDate
The recursive answer:
DECLARE #startDate AS date = '20220315';
DECLARE #endDate AS date = '20230316'; -- inclusive
WITH cte_minutes(dt)
AS (
SELECT
DATEFROMPARTS(YEAR(#startDate), MONTH(#startDate), 1)
UNION ALL
SELECT
DATEADD(month, 1, dt)
FROM
cte_minutes
WHERE DATEADD(month, 1, dt) < #endDate
)
SELECT
dt
into #dates
FROM
cte_minutes
WHERE
dt >= #startDate
AND
dt <= #endDate
OPTION (MAXRECURSION 2000);
DROP TABLE dbo.#dates

What is a good way to find gaps in a set of datespans?

What is a way to find gaps in a set of date spans?
For example, I have these date spans:
1/ 1/11 - 1/10/11
1/13/11 - 1/15/11
1/20/11 - 1/30/11
Then I have a start and end date of 1/7/11 and 1/14/11.
I want to be able to tell that between 1/10/11 and 1/13/11 there is a gap so the start and end date is not possible. Or I want to return only the datespans up to the first gap encountered.
If this can be done in SQL server that would be good.
I was thinking to go through each date to find out if it lands in a datespan... if it does not then there's a gap on that day.
Jump to 2nd last code block for: *I want to be able to tell that
between 1/10/11 and 1/13/11 there is
a gap so the start and end date is*
not possible.
Jump to last code block for: *I want to return only
the datespans up to the first gap
encountered.*
First of all, here's a virtual table to discuss
create table spans (date1 datetime, date2 datetime);
insert into spans select '20110101', '20110110';
insert into spans select '20110113', '20110115';
insert into spans select '20110120', '20110130';
This is a query that will list, individually, all the dates in the calendar
declare #startdate datetime, #enddate datetime
select #startdate = '20110107', #enddate = '20110114'
select distinct a.date1+v.number
from spans A
inner join master..spt_values v
on v.type='P' and v.number between 0 and datediff(d, a.date1, a.date2)
-- we don't care about spans that don't intersect with our range
where A.date1 <= #enddate
and #startdate <= A.date2
Armed with this query, we can now test to see if there are any gaps, by
counting the days in the calendar against the expected number of days
declare #startdate datetime, #enddate datetime
select #startdate = '20110107', #enddate = '20110114'
select case when count(distinct a.date1+v.number)
= datediff(d,#startdate, #enddate) + 1
then 'No gaps' else 'Gap' end
from spans A
inner join master..spt_values v
on v.type='P' and v.number between 0 and datediff(d, a.date1, a.date2)
-- we don't care about spans that don't intersect with our range
where A.date1 <= #enddate
and #startdate <= A.date2
-- count only those dates within our range
and a.date1 + v.number between #startdate and #enddate
Another way to do this is to just build the calendar from #start
to #end up front and look to see if there is a span with this date
declare #startdate datetime, #enddate datetime
select #startdate = '20110107', #enddate = '20110114'
-- startdate+v.number is a day on the calendar
select #startdate + v.number
from master..spt_values v
where v.type='P' and v.number between 0
and datediff(d, #startdate, #enddate)
-- run the part above this line alone to see the calendar
-- the condition checks for dates that are not in any span (gap)
and not exists (
select *
from spans
where #startdate + v.number between date1 and date2)
The query returns ALL dates that are gaps in the date range #start - #end
A TOP 1 can be added to just see if there are gaps
To return all records that are before the gap, use the query as a
derived table in a larger query
declare #startdate datetime, #enddate datetime
select #startdate = '20110107', #enddate = '20110114'
select *
from spans
where date1 <= #enddate and #startdate <= date2 -- overlaps
and date2 < ( -- before the gap
select top 1 #startdate + v.number
from master..spt_values v
where v.type='P' and v.number between 0
and datediff(d, #startdate, #enddate)
and not exists (
select *
from spans
where #startdate + v.number between date1 and date2)
order by 1 ASC
)
Assuming MySQL, something like this would work:
select #olddate := null;
select start_date, end_date, datediff(end_date, #olddate) as diff, #olddate:=enddate
from table
order by start_date asc, end_date asc
having diff > 1;
Basically: cache the previous row's end_date in the #olddate variable, and then do a diff on that "old" value with the currel enddate. THe having clause will return only the records where the difference between two rows is greater than a day.
disclaimer: Haven't tested this, but the basic query construct should work.
I want to be able to tell that between
1/10/11 and 1/13/11 there is a gap so
the start and end date is not
possible.
I think you're asking this question: does the data in your table have a gap between the start date and the end date?
I created a one-column table, date_span, and inserted your date spans into it.
You can identify a gap by counting the number of days between start date and end date, and comparing that the the number of rows in date_span for the same range.
select
date '2011-01-14' - date '2011-01-07' + 1 as elapsed_days,
count(*) from date_span
where cal_date between '2011-01-07' and '2011-01-14';
returns
elapsed_days count
-- --
8 6
Since they're not equal, there's a gap in the table "date_span" between 2011-01-07 and 2011-01-14. I'll stop there for now, because I'm really not certain what you're trying to do.

Calculating in SQL the first working day of a given month

I have to calculate all the invoices which have been paid in the first 'N' days of a month. I have two tables
. INVOICE: it has the invoice information. The only field which does matter is called 'datePayment'
. HOLYDAYS: It is a one column table. Entries at this table are of the form "2009-01-01",
2009-05-01" and so on.
I should consider also Saturdays and Sundays
(this might be not a problem because I could insert those days at the Hollidays table in order to consider them as hollidays if neccesary)
The problem is to calculate which is the 'payment limit'.
select count(*) from invoice
where datePayment < PAYMENTLIMIT
My question is how to calculate this PAYMENTLIMIT. Where PAYMENTLIMIT is 'the fifth working day of every month'.
The query should be run under Mysql and Oracle therefore standard SQL should be used.
Any hint?
EDIT
In order to be consistent with the title of the question the pseudo-query should the read as follows:
select count(*) from invoice
where datePayment < FIRST_WORKING_DAY + N
then the question can be reduced to calculate the FIRST_WORKING_DAY of every month.
You could look for the first date in a month, where the date is not in the holiday table and the date is not a weekend:
select min(datePayment), datepart(mm, datePayment)
from invoices
where datepart(dw, datePayment) not in (1,7) --day of week
and not exists (select holiday from holidays where holiday = datePayment)
group by datepart(mm, datePayment) --monthnr
Something like this might work:
create function dbo.GetFirstWorkdayOfMonth(#Year INT, #Month INT)
returns DATETIME
as begin
declare #firstOfMonth VARCHAR(20)
SET #firstOfMonth = CAST(#Year AS VARCHAR(4)) + '-' + CAST(#Month AS VARCHAR) + '-01'
declare #currDate DATETIME
set #currDate = CAST(#firstOfMonth as DATETIME)
declare #weekday INT
set #weekday = DATEPART(weekday, #currdate)
-- 7 = saturday, 1 = sunday
while #weekday = 1 OR #weekday = 7
begin
set #currDate = DATEADD(DAY, 1, #currDate)
set #weekday = DATEPART(weekday, #currdate)
end
return #currdate
end
I'm not 100% sure about whether the "weekday" numbers are fixed or might depend on your locale on your SQL Server. Check it out!
Marc
Rather than a Holidays table of days to exclude, we use the calendar table approach: one row for every day the application will ever need (thirty years spans a modest 11K rows). So not only does it have an is_weekday column, it has other things relevant to the enterprise e.g. julianized_date. This way, every possible date would have a ready-prepared value for first_working_day_this_month and finding it involves a simple lookup (which SQL products tend to be optimized for!) rather than 'calculating' it each time on the fly.
We have dates table in our application (filled with all dates and date parts for some tens of years), what allows various "missing" date manipulations, like (in pseudo-sql):
select min(ourdates.datevalue)
from ourdates
where ourdates.year=<given year> and ourdates.month=<given month>
and ourdates.isworkday
and not exists (
select * from holidays
where holidays.datevalue=ourdates.datevalue
)
Ok, at a first stab, you could put the following code into a UDF and pass in the Year and Month as variables. It can then return TestDate which is the first working day of the month.
DECLARE #Month INT
DECLARE #Year INT
SELECT #Month = 5
SELECT #Year = 2009
DECLARE #FirstDate DATETIME
SELECT #FirstDate = CONVERT(varchar(4), #Year) + '-' + CONVERT(varchar(2), #Month) + '-' + '01 00:00:00.000'
DROP TABLE #HOLIDAYS
CREATE TABLE #HOLIDAYS (HOLIDAY DateTime)
INSERT INTO #HOLIDAYS VALUES('2009-01-01 00:00:00.000')
INSERT INTO #HOLIDAYS VALUES('2009-05-01 00:00:00.000')
DECLARE #DateFound BIT
SELECT #DateFound = 0
WHILE(#DateFound = 0)
BEGIN
IF(
DATEPART(dw, #FirstDate) = 1
OR
DATEPART(dw, #FirstDate) = 1
OR
EXISTS(SELECT * FROM #HOLIDAYS WHERE HOLIDAY = #FirstDate)
)
BEGIN
SET #FirstDate = DATEADD(dd, 1, #FirstDate)
END
ELSE
BEGIN
SET #DateFound = 1
END
END
SELECT #FirstDate
The things I don`t like with this solution though are, if your holidays table contains all days of the month there will be an infinite loop. (You could check the loop is still looking at the right month) It relies upon the dates being equal, eg all at time 00:00:00. Finally, the way I calculate the 1st of the month past in using string concatenation was a short cut. There are much better ways of finding the actual first day of the month.
Gets the first N working days of each month of year 2009:
select * from invoices as x
where
datePayment between '2009-01-01' and '2009-12-31'
and exists
(
select
1
from invoices
where
-- exclude holidays and sunday saturday...
(
datepart(dw, datePayment) not in (1,7) -- day of week
/*
-- Postgresql and Oracle have programmer-friendly IN clause
and
(datepart(yyyy,datePayment), datepart(mm,datePayment))
not in (select hyear, hday from holidays)
*/
-- this is the MSSQL equivalent of programmer-friendly IN
and
not exists
(
select * from holidays
where
hyear = datepart(yyyy,datePayment)
and hmonth = datepart(mm, datePayment)
)
)
-- ...exclude holidays and sunday saturday
-- get the month of x datePayment
and
(datepart(yyyy, datePayment) = datepart(yyyy, x.datePayment)
and datepart(mm, datePayment) = datepart(mm, x.datePayment))
group by
datepart(yyyy, datePayment), datepart(mm, datePayment)
having
x.datePayment < MIN(datePayment) + #N -- up to N working days
)
Returns the first Monday of the current month
SELECT DATEADD(
WEEK,
DATEDIFF( --x weeks between 1900-01-01 (Monday) and inner result
WEEK,
0, --1900-01-01
DATEADD( --inner result
DAY,
6 - DATEPART(DAY, GETDATE()),
GETDATE()
)
),
0 --1900-01-01 (Monday)
)
SELECT DATEADD(day, DATEDIFF (day, 0, DATEADD (month, DATEDIFF (month, 0, GETDATE()), 0) -1)/7*7 + 7, 0);
select if(weekday('yyyy-mm-01') < 5,'yyyy-mm-01',if(weekday('yyyy-mm-02') < 5,'yyyy-mm-02','yyyy-mm-03'))
Saturdays and Sundays are 5, 6 so you only need two checks to get the first working day