将逗号分隔的字符串变成单独的行

我有一个像这样的SQL表：

| SomeID         | OtherID     | Data
+----------------+-------------+-------------------
| abcdef-.....   | cdef123-... | 18,20,22
| abcdef-.....   | 4554a24-... | 17,19
| 987654-.....   | 12324a2-... | 13,19,20

是否有一个查询，我可以在其中执行这样的查询SELECT OtherID, SplitData WHERE SomeID = 'abcdef-.......'，该查询返回单个行，如下所示：

| OtherID     | SplitData
+-------------+-------------------
| cdef123-... | 18
| cdef123-... | 20
| cdef123-... | 22
| 4554a24-... | 17
| 4554a24-... | 19

基本上将逗号处的数据分成几行？

我知道将comma-separated字符串存储到关系数据库中听起来很愚蠢，但是在消费者应用程序中的正常使用案例确实很有帮助。

我不想在应用程序中进行拆分，因为我需要分页，因此我想在重构整个应用程序之前探索各种选项。

是SQL Server 2008（非R2）。

您可以使用SQL Server中出色的递归函数：

样表：

CREATE TABLE Testdata
(
    SomeID INT,
    OtherID INT,
    String VARCHAR(MAX)
)

INSERT Testdata SELECT 1,  9, '18,20,22'
INSERT Testdata SELECT 2,  8, '17,19'
INSERT Testdata SELECT 3,  7, '13,19,20'
INSERT Testdata SELECT 4,  6, ''
INSERT Testdata SELECT 9, 11, '1,2,3,4'

查询

;WITH tmp(SomeID, OtherID, DataItem, String) AS
(
    SELECT
        SomeID,
        OtherID,
        LEFT(String, CHARINDEX(',', String + ',') - 1),
        STUFF(String, 1, CHARINDEX(',', String + ','), '')
    FROM Testdata
    UNION all

    SELECT
        SomeID,
        OtherID,
        LEFT(String, CHARINDEX(',', String + ',') - 1),
        STUFF(String, 1, CHARINDEX(',', String + ','), '')
    FROM tmp
    WHERE
        String > ''
)

SELECT
    SomeID,
    OtherID,
    DataItem
FROM tmp
ORDER BY SomeID
-- OPTION (maxrecursion 0)
-- normally recursion is limited to 100. If you know you have very long
-- strings, uncomment the option

输出量

 SomeID | OtherID | DataItem 
--------+---------+----------
 1      | 9       | 18       
 1      | 9       | 20       
 1      | 9       | 22       
 2      | 8       | 17       
 2      | 8       | 19       
 3      | 7       | 13       
 3      | 7       | 19       
 3      | 7       | 20       
 4      | 6       |          
 9      | 11      | 1        
 9      | 11      | 2        
 9      | 11      | 3        
 9      | 11      | 4        

最后，SQL Server 2016的等待结束了。他们引入了Split string函数STRING_SPLIT：

select OtherID, cs.Value --SplitData
from yourtable
cross apply STRING_SPLIT (Data, ',') cs

所有其他用于拆分字符串的方法（例如XML，Tally表，while循环等）都已被该STRING_SPLIT函数吹走。

这是一篇出色的性能比较文章：性能惊奇和假设：STRING_SPLIT。

对于较旧的版本，这里使用计数表是一个拆分字符串函数（最佳方法）

CREATE FUNCTION [dbo].[DelimitedSplit8K]
        (@pString VARCHAR(8000), @pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
 RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
     -- enough to cover NVARCHAR(4000)
  WITH E1(N) AS (
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL 
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL 
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
                ),                          --10E+1 or 10 rows
       E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
       E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
 cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
                     -- for both a performance gain and prevention of accidental "overruns"
                 SELECT TOP (ISNULL(DATALENGTH(@pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
                ),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
                 SELECT 1 UNION ALL
                 SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(@pString,t.N,1) = @pDelimiter
                ),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
                 SELECT s.N1,
                        ISNULL(NULLIF(CHARINDEX(@pDelimiter,@pString,s.N1),0)-s.N1,8000)
                   FROM cteStart s
                )
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
 SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
        Item       = SUBSTRING(@pString, l.N1, l.L1)
   FROM cteLen l
;

由Tally OH推荐！改进的SQL 8K“ CSV拆分器”功能

检查一下

 SELECT A.OtherID,  
     Split.a.value('.', 'VARCHAR(100)') AS Data  
 FROM  
 (
     SELECT OtherID,  
         CAST ('<M>' + REPLACE(Data, ',', '</M><M>') + '</M>' AS XML) AS Data  
     FROM  Table1
 ) AS A CROSS APPLY Data.nodes ('/M') AS Split(a); 

select t.OtherID,x.Kod
    from testData t
    cross apply (select Code from dbo.Split(t.Data,',') ) x

从2014年2月开始-请参阅TALLY表示例-从2014年2月开始，很有可能跑赢我下面的TVF。

在上面的示例中，我不太喜欢重复的代码。而且我不喜欢CTE和XML的性能。同样，一个显式的Id，以便特定于订单的使用者可以指定一个ORDER BY子句。

CREATE FUNCTION dbo.Split
(
    @Line nvarchar(MAX),
    @SplitOn nvarchar(5) = ','
)
RETURNS @RtnValue table
(
    Id INT NOT NULL IDENTITY(1,1) PRIMARY KEY CLUSTERED,
    Data nvarchar(100) NOT NULL
)
AS
BEGIN
    IF @Line IS NULL RETURN

    DECLARE @split_on_len INT = LEN(@SplitOn)
    DECLARE @start_at INT = 1
    DECLARE @end_at INT
    DECLARE @data_len INT

    WHILE 1=1
    BEGIN
        SET @end_at = CHARINDEX(@SplitOn,@Line,@start_at)
        SET @data_len = CASE @end_at WHEN 0 THEN LEN(@Line) ELSE @end_at-@start_at END
        INSERT INTO @RtnValue (data) VALUES( SUBSTRING(@Line,@start_at,@data_len) );
        IF @end_at = 0 BREAK;
        SET @start_at = @end_at + @split_on_len
    END

    RETURN
END

很高兴看到它已在2016版本中解决，但是对于所有未在其中发布的版本，以下是上述方法的两个广义和简化版本。

XML方法较短，但是当然需要使用字符串来允许xml技巧（没有“坏”字符）。

XML方法：

create function dbo.splitString(@input Varchar(max), @Splitter VarChar(99)) returns table as
Return
    SELECT Split.a.value('.', 'VARCHAR(max)') AS Data FROM
    ( SELECT CAST ('<M>' + REPLACE(@input, @Splitter, '</M><M>') + '</M>' AS XML) AS Data 
    ) AS A CROSS APPLY Data.nodes ('/M') AS Split(a); 

递归方法：

create function dbo.splitString(@input Varchar(max), @Splitter Varchar(99)) returns table as
Return
  with tmp (DataItem, ix) as
   ( select @input  , CHARINDEX('',@Input)  --Recu. start, ignored val to get the types right
     union all
     select Substring(@input, ix+1,ix2-ix-1), ix2
     from (Select *, CHARINDEX(@Splitter,@Input+@Splitter,ix+1) ix2 from tmp) x where ix2<>0
   ) select DataItem from tmp where ix<>0

发挥作用

Create table TEST_X (A int, CSV Varchar(100));
Insert into test_x select 1, 'A,B';
Insert into test_x select 2, 'C,D';

Select A,data from TEST_X x cross apply dbo.splitString(x.CSV,',') Y;

Drop table TEST_X

XML-METHOD 2：Unicode友好😀（由Max Hodges提供） create function dbo.splitString(@input nVarchar(max), @Splitter nVarchar(99)) returns table as Return SELECT Split.a.value('.', 'NVARCHAR(max)') AS Data FROM ( SELECT CAST ('<M>' + REPLACE(@input, @Splitter, '</M><M>') + '</M>' AS XML) AS Data ) AS A CROSS APPLY Data.nodes ('/M') AS Split(a);

请参考下面的TSQL。STRING_SPLIT函数仅在兼容级别130及更高版本下可用。

TSQL：

DECLARE @stringValue NVARCHAR(400) = 'red,blue,green,yellow,black'  
DECLARE @separator CHAR = ','

SELECT [value]  As Colour
FROM STRING_SPLIT(@stringValue, @separator); 

结果：

颜色

红色蓝色绿色黄色黑色

很晚了，但是尝试一下：

SELECT ColumnID, Column1, value  --Do not change 'value' name. Leave it as it is.
FROM tbl_Sample  
CROSS APPLY STRING_SPLIT(Tags, ','); --'Tags' is the name of column containing comma separated values

所以我们有了这个：tbl_Sample：

ColumnID|   Column1 |   Tags
--------|-----------|-------------
1       |   ABC     |   10,11,12    
2       |   PQR     |   20,21,22

运行此查询后：

ColumnID|   Column1 |   value
--------|-----------|-----------
1       |   ABC     |   10
1       |   ABC     |   11
1       |   ABC     |   12
2       |   PQR     |   20
2       |   PQR     |   21
2       |   PQR     |   22

谢谢！

DECLARE @id_list VARCHAR(MAX) = '1234,23,56,576,1231,567,122,87876,57553,1216'
DECLARE @table TABLE ( id VARCHAR(50) )
DECLARE @x INT = 0
DECLARE @firstcomma INT = 0
DECLARE @nextcomma INT = 0

SET @x = LEN(@id_list) - LEN(REPLACE(@id_list, ',', '')) + 1 -- number of ids in id_list

WHILE @x > 0
    BEGIN
        SET @nextcomma = CASE WHEN CHARINDEX(',', @id_list, @firstcomma + 1) = 0
                              THEN LEN(@id_list) + 1
                              ELSE CHARINDEX(',', @id_list, @firstcomma + 1)
                         END
        INSERT  INTO @table
        VALUES  ( SUBSTRING(@id_list, @firstcomma + 1, (@nextcomma - @firstcomma) - 1) )
        SET @firstcomma = CHARINDEX(',', @id_list, @firstcomma + 1)
        SET @x = @x - 1
    END

SELECT  *
FROM    @table

;WITH tmp(SomeID, OtherID, DataItem, Data) as (
    SELECT SomeID, OtherID, LEFT(Data, CHARINDEX(',',Data+',')-1),
        STUFF(Data, 1, CHARINDEX(',',Data+','), '')
FROM Testdata
WHERE Data > ''
)
SELECT SomeID, OtherID, Data
FROM tmp
ORDER BY SomeID

只需对上述查询进行少量修改...

使用这种方法时，必须确保所有值都不包含非法的XML – user1151923

我总是使用XML方法。确保使用VALID XML。我有两个函数可以在有效的XML和文本之间进行转换。（我倾向于去除回车，因为我通常不需要它们。

CREATE FUNCTION dbo.udf_ConvertTextToXML (@Text varchar(MAX)) 
    RETURNS varchar(MAX)
AS
    BEGIN
        SET @Text = REPLACE(@Text,CHAR(10),'')
        SET @Text = REPLACE(@Text,CHAR(13),'')
        SET @Text = REPLACE(@Text,'<','&lt;')
        SET @Text = REPLACE(@Text,'&','&amp;')
        SET @Text = REPLACE(@Text,'>','&gt;')
        SET @Text = REPLACE(@Text,'''','&apos;')
        SET @Text = REPLACE(@Text,'"','&quot;')
    RETURN @Text
END


CREATE FUNCTION dbo.udf_ConvertTextFromXML (@Text VARCHAR(MAX)) 
    RETURNS VARCHAR(max)
AS
    BEGIN
        SET @Text = REPLACE(@Text,'&lt;','<')
        SET @Text = REPLACE(@Text,'&amp;','&')
        SET @Text = REPLACE(@Text,'&gt;','>')
        SET @Text = REPLACE(@Text,'&apos;','''')
        SET @Text = REPLACE(@Text,'&quot;','"')
    RETURN @Text
END

功能

CREATE FUNCTION dbo.SplitToRows (@column varchar(100), @separator varchar(10))
RETURNS @rtnTable TABLE
  (
  ID int identity(1,1),
  ColumnA varchar(max)
  )
 AS
BEGIN
    DECLARE @position int = 0
    DECLARE @endAt int = 0
    DECLARE @tempString varchar(100)

    set @column = ltrim(rtrim(@column))

    WHILE @position<=len(@column)
    BEGIN       
        set @endAt = CHARINDEX(@separator,@column,@position)
            if(@endAt=0)
            begin
            Insert into @rtnTable(ColumnA) Select substring(@column,@position,len(@column)-@position)
            break;
            end
        set @tempString = substring(ltrim(rtrim(@column)),@position,@endAt-@position)

        Insert into @rtnTable(ColumnA) select @tempString
        set @position=@endAt+1;
    END
    return
END

用例

select * from dbo.SplitToRows('T14; p226.0001; eee; 3554;', ';')

或者只是选择多个结果集

DECLARE @column varchar(max)= '1234; 4748;abcde; 324432'
DECLARE @separator varchar(10) = ';'
DECLARE @position int = 0
DECLARE @endAt int = 0
DECLARE @tempString varchar(100)

set @column = ltrim(rtrim(@column))

WHILE @position<=len(@column)
BEGIN       
    set @endAt = CHARINDEX(@separator,@column,@position)
        if(@endAt=0)
        begin
        Select substring(@column,@position,len(@column)-@position)
        break;
        end
    set @tempString = substring(ltrim(rtrim(@column)),@position,@endAt-@position)

    select @tempString
    set @position=@endAt+1;
END

下面适用于sql server 2008

select *, ROW_NUMBER() OVER(order by items) as row# 
from 
( select 134 myColumn1, 34 myColumn2, 'd,c,k,e,f,g,h,a' comaSeperatedColumn) myTable
    cross apply 
SPLIT (rtrim(comaSeperatedColumn), ',') splitedTable -- gives 'items'  column 

将获得所有带有原始表列以及拆分表“项”的笛卡尔乘积。

您可以使用以下功能提取数据

CREATE FUNCTION [dbo].[SplitString]
(    
    @RowData NVARCHAR(MAX),
    @Delimeter NVARCHAR(MAX)
)
RETURNS @RtnValue TABLE 
(
    ID INT IDENTITY(1,1),
    Data NVARCHAR(MAX)
) 
AS
BEGIN 
    DECLARE @Iterator INT
    SET @Iterator = 1

    DECLARE @FoundIndex INT
    SET @FoundIndex = CHARINDEX(@Delimeter,@RowData)

    WHILE (@FoundIndex>0)
    BEGIN
        INSERT INTO @RtnValue (data)
        SELECT 
            Data = LTRIM(RTRIM(SUBSTRING(@RowData, 1, @FoundIndex - 1)))

        SET @RowData = SUBSTRING(@RowData,
                @FoundIndex + DATALENGTH(@Delimeter) / 2,
                LEN(@RowData))

        SET @Iterator = @Iterator + 1
        SET @FoundIndex = CHARINDEX(@Delimeter, @RowData)
    END

    INSERT INTO @RtnValue (Data)
    SELECT Data = LTRIM(RTRIM(@RowData))

    RETURN
END