使用SQL Server,我如何分割一个字符串,以便我可以访问项目x?

拿一根“你好,约翰·史密斯”的绳子。我如何通过空格分割字符串并访问索引1应该返回“约翰”的项目?


当前回答

如果任何人只想获得分离文本的一部分,可以使用这个

select * from from splitstringsep ('Word1 word2 word3',' ')

CREATE function [dbo].[SplitStringSep] 
(
    @str nvarchar(4000), 
    @separator char(1)
)
returns table
AS
return (
    with tokens(p, a, b) AS (
        select 
        1, 
        1, 
        charindex(@separator, @str)
        union all
        select
            p + 1, 
            b + 1, 
            charindex(@separator, @str, b + 1)
        from tokens
        where b > 0
        )
        select
            p-1 zeroBasedOccurance,
            substring(
                @str, 
                a, 
                case when b > 0 then b-a ELSE 4000 end) 
            AS s
        from tokens
  )

其他回答

我一直在使用vzczc的答案使用递归cte的一段时间,但一直想更新它来处理可变长度分隔符,也处理字符串与前驱和滞后“分隔符”,如当你有一个csv文件的记录,如:

“鲍勃”,“史密斯”桑尼维尔”,“CA”

或者当你处理如下所示的六部分fqn时。我广泛地使用这些来记录subject_fqn的审计,错误处理等,parsename只处理四个部分:

[netbios_name].[machine_name].[instance].[database].[schema].[table].[column]

这是我的更新版本,感谢vzczc的原始帖子!

select * from [utility].[split_string](N'"this"."string"."gets"."split"."and"."removes"."leading"."and"."trailing"."quotes"', N'"."', N'"', N'"');

select * from [utility].[split_string](N'"this"."string"."gets"."split"."but"."leaves"."leading"."and"."trailing"."quotes"', N'"."', null, null);

select * from [utility].[split_string](N'[netbios_name].[machine_name].[instance].[database].[schema].[table].[column]', N'].[', N'[', N']');

create function [utility].[split_string] ( 
  @input       [nvarchar](max) 
  , @separator [sysname] 
  , @lead      [sysname] 
  , @lag       [sysname]) 
returns @node_list table ( 
  [index]  [int] 
  , [node] [nvarchar](max)) 
  begin 
      declare @separator_length [int]= len(@separator) 
              , @lead_length    [int] = isnull(len(@lead), 0) 
              , @lag_length     [int] = isnull(len(@lag), 0); 
      -- 
      set @input = right(@input, len(@input) - @lead_length); 
      set @input = left(@input, len(@input) - @lag_length); 
      -- 
      with [splitter]([index], [starting_position], [start_location]) 
           as (select cast(@separator_length as [bigint]) 
                      , cast(1 as [bigint]) 
                      , charindex(@separator, @input) 
               union all 
               select [index] + 1 
                      , [start_location] + @separator_length 
                      , charindex(@separator, @input, [start_location] + @separator_length) 
               from   [splitter] 
               where  [start_location] > 0) 
      -- 
      insert into @node_list 
                  ([index],[node]) 
        select [index] - @separator_length                   as [index] 
               , substring(@input, [starting_position], case 
                                                            when [start_location] > 0 
                                                                then 
                                                              [start_location] - [starting_position] 
                                                            else 
                                                              len(@input) 
                                                        end) as [node] 
        from   [splitter]; 
      -- 
      return; 
  end; 
go 

可以利用Number表进行字符串解析。

创建一个物理数字表:

    create table dbo.Numbers (N int primary key);
    insert into dbo.Numbers
        select top 1000 row_number() over(order by number) from master..spt_values
    go

创建具有1000000行的测试表

    create table #yak (i int identity(1,1) primary key, array varchar(50))

    insert into #yak(array)
        select 'a,b,c' from dbo.Numbers n cross join dbo.Numbers nn
    go

创建函数

    create function [dbo].[ufn_ParseArray]
        (   @Input      nvarchar(4000), 
            @Delimiter  char(1) = ',',
            @BaseIdent  int
        )
    returns table as
    return  
        (   select  row_number() over (order by n asc) + (@BaseIdent - 1) [i],
                    substring(@Input, n, charindex(@Delimiter, @Input + @Delimiter, n) - n) s
            from    dbo.Numbers
            where   n <= convert(int, len(@Input)) and
                    substring(@Delimiter + @Input, n, 1) = @Delimiter
        )
    go

使用情况(在我的笔记本电脑上40秒内输出3mil行)

    select * 
    from #yak 
    cross apply dbo.ufn_ParseArray(array, ',', 1)

清理

    drop table dbo.Numbers;
    drop function  [dbo].[ufn_ParseArray]

这里的性能并不惊人,但在100万行表上调用函数并不是最好的主意。如果将字符串拆分到多行,我会避免使用该函数。

Aaron Bertrand的回答很好,但也有缺陷。它不能准确地将空格作为分隔符处理(就像最初问题中的示例一样),因为长度函数将空格带在后面。

下面是他的代码,稍微调整了一下,允许使用空格分隔符:

CREATE FUNCTION [dbo].[SplitString]
(
    @List NVARCHAR(MAX),
    @Delim VARCHAR(255)
)
RETURNS TABLE
AS
    RETURN ( SELECT [Value] FROM 
      ( 
        SELECT 
          [Value] = LTRIM(RTRIM(SUBSTRING(@List, [Number],
          CHARINDEX(@Delim, @List + @Delim, [Number]) - [Number])))
        FROM (SELECT Number = ROW_NUMBER() OVER (ORDER BY name)
          FROM sys.all_objects) AS x
          WHERE Number <= LEN(@List)
          AND SUBSTRING(@Delim + @List, [Number], LEN(@Delim+'x')-1) = @Delim
      ) AS y
    );

我知道已经晚了,但我最近有了这个需求,并提出了下面的代码。我没有选择使用用户定义的函数。希望这能有所帮助。

SELECT 
    SUBSTRING(
                SUBSTRING('Hello John Smith' ,0,CHARINDEX(' ','Hello John Smith',CHARINDEX(' ','Hello John Smith')+1)
                        ),CHARINDEX(' ','Hello John Smith'),LEN('Hello John Smith')
            )

试试这个:

CREATE function [SplitWordList]
(
 @list varchar(8000)
)
returns @t table 
(
 Word varchar(50) not null,
 Position int identity(1,1) not null
)
as begin
  declare 
    @pos int,
    @lpos int,
    @item varchar(100),
    @ignore varchar(100),
    @dl int,
    @a1 int,
    @a2 int,
    @z1 int,
    @z2 int,
    @n1 int,
    @n2 int,
    @c varchar(1),
    @a smallint
  select 
    @a1 = ascii('a'),
    @a2 = ascii('A'),
    @z1 = ascii('z'),
    @z2 = ascii('Z'),
    @n1 = ascii('0'),
    @n2 = ascii('9')
  set @ignore = '''"'
  set @pos = 1
  set @dl = datalength(@list)
  set @lpos = 1
  set @item = ''
  while (@pos <= @dl) begin
    set @c = substring(@list, @pos, 1)
    if (@ignore not like '%' + @c + '%') begin
      set @a = ascii(@c)
      if ((@a >= @a1) and (@a <= @z1))  
        or ((@a >= @a2) and (@a <= @z2))
        or ((@a >= @n1) and (@a <= @n2))
      begin
        set @item = @item + @c
      end else if (@item > '') begin
        insert into @t values (@item)
        set @item = ''
      end
    end 
    set @pos = @pos + 1
  end
  if (@item > '') begin
    insert into @t values (@item)
  end
  return
end

像这样测试它:

select * from SplitWordList('Hello John Smith')