How to find all positions of a string within another string

Question

How can I find all the positions with patindex in a table or variable?

declare @name nvarchar(max)
set @name ='ali reza dar yek shabe barani ba yek  '
  + 'dokhtare khoshkel be disco raft va ali baraye'
  + ' 1 saat anja bud va sepas... ali...'
select patindex('%ali%',@name) as pos 

This returns 1 but I want all results, e.g.:

pos
===
  1
 74
113

Answer 1

declare @name nvarchar(max)
set @name ='ali reza dar yek shabe barani ba yek  dokhtare khoshkel be disco raft va ali baraye 1 saat anja bud va sepas... ali...'

Declare @a table (pos int)
Declare @pos int
Declare @oldpos int
Select @oldpos=0
select @pos=patindex('%ali%',@name) 
while @pos > 0 and @oldpos<>@pos
 begin
   insert into @a Values (@pos)
   Select @oldpos=@pos
   select @pos=patindex('%ali%',Substring(@name,@pos + 1,len(@name))) + @pos
end

Select * from @a

To make it reuseable you can use it in a table function to call it like:

Select * from  dbo.F_CountPats ('ali reza dar yek shabe barani ba yek  dokhtare khoshkel be disco raft va ali baraye 1 saat anja bud va sepas... ali...','%ali%')

The function could look like this

Create FUNCTION [dbo].[F_CountPats] 
(
@txt varchar(max),
@Pat varchar(max)
)
RETURNS 
@tab TABLE 
(
 ID int
)
AS
BEGIN
Declare @pos int
Declare @oldpos int
Select @oldpos=0
select @pos=patindex(@pat,@txt) 
while @pos > 0 and @oldpos<>@pos
 begin
   insert into @tab Values (@pos)
   Select @oldpos=@pos
   select @pos=patindex(@pat,Substring(@txt,@pos + 1,len(@txt))) + @pos
end

RETURN 
END

GO

Answer 2

I think this will be slightly more efficient than the looping method you've chosen (some evidence here), and definitely more efficient than the recursive CTE:

CREATE FUNCTION dbo.FindPatternLocation
(
    @string NVARCHAR(MAX),
    @term   NVARCHAR(255)
)
RETURNS TABLE
AS
    RETURN 
    (
      SELECT pos = Number - LEN(@term) 
      FROM (SELECT Number, Item = LTRIM(RTRIM(SUBSTRING(@string, Number, 
      CHARINDEX(@term, @string + @term, Number) - Number)))
      FROM (SELECT ROW_NUMBER() OVER (ORDER BY [object_id])
      FROM sys.all_objects) AS n(Number)
      WHERE Number > 1 AND Number <= CONVERT(INT, LEN(@string)+1)
      AND SUBSTRING(@term + @string, Number, LEN(@term)) = @term
    ) AS y);

Sample usage:

DECLARE @name NVARCHAR(MAX);

SET @name = N'ali reza dar yek shabe barani ba yek'
    + '  dokhtare khoshkel be disco raft va ali baraye '
    + '1 saat anja bud va sepas... ali...';

SELECT pos FROM dbo.FindPatternLocation(@name, 'ali');

Results:

pos
---
  1
 74
113

If your strings will be longer than 2K then use sys.all_columns instead of sys.all_objects. If longer than 8K then add a cross join.

Answer 3

--Recursive CTE

with cte as
(select 'ali reza dar yek shabe barani ba yek  dokhtare khoshkel be disco raft va ali baraye 1 saat anja bud va sepas... ali...' as name
), 
pos as
(select patindex('%ali%',name) pos, name from cte
union all
select pos+patindex('%ali%',substring(name, pos+1, len(name))) pos, name from pos
where patindex('%ali%',substring(name, pos+1, len(name)))>0
)
select pos from pos

Answer 4

I love Aaron Bertrand's answer. Although I don't understand it completely, it looks really elegant.

In the past I've ran into problems with permissions when using sys.objects. Combined with the need for me to troubleshoot the code, I've come up with a variation on Aaron's code, and added it below.

This is my procedure:

CREATE PROCEDURE dbo.FindPatternLocations
-- Params
@TextToSearch nvarchar (max),
@TextToFind nvarchar (255)

AS
BEGIN

    declare @Length int
    set @Length = (Select LEN(@TextToSearch))

    declare @LengthSearchString int
    set @LengthSearchString = (select LEN (@TextToFind))

    declare @Index int
    set @Index=1

    create table #Positions (
    [POSID] [int] IDENTITY(0,1) NOT FOR REPLICATION NOT NULL,
    POS int
    )

    insert into #Positions (POS) select 0 -- to return a row even if no findings occur

        set @Index = (select charindex(@TextToFind, @TextToSearch, @Index))
                    if @Index = 0 goto Ende -- TextToFind is not in TextToSearch

        insert into #Positions (POS) select @Index


        set @Index = @Index + @LengthSearchString

while @Index <= @Length - @LengthSearchString   
    Begin
            set @Index = (select charindex(@TextToFind, @TextToSearch, @Index) )
            if @Index = 0 goto Ende -- no findings anymore
            insert into #Positions (POS) select @Index
            set @Index = @Index + @LengthSearchString
    end
Ende:
if (select MAX(posid) from #Positions) > 0 delete from #Positions where POSID = 0 -- row is not needed if TextToFind occurs
select * from #Positions
END
GO

The MAX(posid) value is also the number of matches found.

Answer 5

This is a simple code based on Aaron's answer that:

• Not limited to the size of sys.all_objects
• Do not miss the last 'X'

CODE:

DECLARE @termToFind CHAR(1) = 'X'
DECLARE @string VARCHAR(40) = 'XX XXX  X   XX'

SET @string += '.' --Add any data here (different from the one searched) to get the position of the last character

DECLARE @stringLength BIGINT = len(@string)

SELECT pos = Number - LEN(@termToFind)
FROM (
    SELECT Number
        , Item = LTRIM(RTRIM(SUBSTRING(@string, Number, CHARINDEX(@termToFind, @string + @termToFind, Number) - Number)))
    FROM (
        --All numbers between 1 and the lengh of @string. Better than use sys.all_objects
        SELECT TOP (@stringLength) row_number() OVER (
                ORDER BY t1.number
                ) AS N
        FROM master..spt_values t1
        CROSS JOIN master..spt_values t2
        ) AS n(Number)
    WHERE Number > 1
        AND Number <= CONVERT(INT, LEN(@string))
        AND SUBSTRING(@termToFind + @string, Number, LEN(@termToFind)) = @termToFind
    ) AS y

RESULT

pos
--------------------
1
2
4
5
6
9
13
14

(8 row(s) affected)

Answer 6

Sorry guys to drop in so late, but I'd like to make things easier for people that want to expand on this. I was looking at each of these implementations, took the one that seemed the best to me (Aaron Bertrand), simplified it and here you go, you have the "template". Use it wisely.

CREATE FUNCTION dbo.CHARINDICES (
    @search_expression NVARCHAR(4000),
    @expression_to_be_searched NVARCHAR(MAX)
) RETURNS TABLE AS RETURN (
    WITH tally AS (
        SELECT Number = ROW_NUMBER() OVER (ORDER BY [object_id])
        FROM sys.all_objects)
    SELECT DISTINCT n = subIdx -- (4) if we don't perform distinct we'll get result for each searched substring, and we don't want that
    FROM 
        tally 
        CROSS APPLY (SELECT subIdx = CHARINDEX(@search_expression, @expression_to_be_searched, Number)) x -- (2) subIdx is found in the rest of the substring 
    WHERE 
        Number BETWEEN 1 AND LEN(@expression_to_be_searched) -- (1) run for each substring once
        AND SubIdx != 0  -- (3) we care only about the indexes we've found, 0 stands for "not found"
)

SELECT CHARINDEX('C', 'BACBABCBABBCBACBBABC')
SELECT * FROM dbo.CHARINDICES('C', 'BACBABCBABBCBACBBABC')

Just as a reference - you can derive other behaviors from this, like expand on PATINDEX():

CREATE FUNCTION dbo.PATINDICES (
    @search_expression NVARCHAR(4000) = '%[cS]%',
    @expression_to_be_searched NVARCHAR(MAX) = 'W3Schools.com'
) RETURNS TABLE AS RETURN (
    WITH tally AS (
        SELECT num = ROW_NUMBER() OVER (ORDER BY [object_id])
        FROM sys.all_objects)
    SELECT DISTINCT n = subIdx + num - 1
    FROM 
        tally 
        CROSS APPLY (SELECT numRev = LEN(@expression_to_be_searched) - num + 1) x
        CROSS APPLY (SELECT subExp = RIGHT(@expression_to_be_searched, numRev)) y
        CROSS APPLY (SELECT subIdx = PATINDEX(@search_expression, subExp)) z
    WHERE 
        num BETWEEN 1 AND LEN(@expression_to_be_searched)
        AND SubIdx != 0
)

SELECT PATINDEX('%[cS]%', 'W3Schools.com')
SELECT * FROM dbo.PATINDICES('%[cS]%', 'W3Schools.com')

Answer 7

Declare @search varchar(5)
    sET @search='a'
    Declare @name varchar(40)
    Set @name='AmitabhBachan'
    Declare @init int
    Set @init=1
    Declare @hold int
    Declare @table table (POSITION Int)
    While( @init<= LEn(@name))
    Begin
   Set @hold=(Select CHARINDEX(@search,@name,@init))
   If (@hold!=0)
   BEgin 
   --Print @hold
   Insert into @table
   Select @hold
   Set @init=@hold+1
   End 
   Else
   If (@hold=0)
   BEgin
   Break
   End
  End
  Select * from @table