Server 2008和HashBytes

Question

我有一个相当大的nvarchar，我希望把它传递给HashBytes函数。我知道错误：

“字符串或二进制将被截断。无法将值NULL插入'colname‘、tbale’table‘列；列不允许空值。UPDATE失败。语句已终止。”

由于资源丰富，我发现这是由于HashBytes函数的最大限制为8000字节。进一步的搜索向我展示了一个“解决方案”，其中我的大型varchar将被分开并散列，然后与这个用户定义的函数组合在一起：

function [dbo].[udfLargeHashTable] (@algorithm nvarchar(4), @InputDataString varchar(MAX))
RETURNS varbinary(MAX)
AS
BEGIN
DECLARE
    @Index int,
    @InputDataLength int,
    @ReturnSum varbinary(max),
    @InputData varbinary(max)

SET @ReturnSum = 0
SET @Index = 1
SET @InputData = convert(binary,@InputDataString)
SET @InputDataLength = DATALENGTH(@InputData)

WHILE @Index <= @InputDataLength
BEGIN
    SET @ReturnSum = @ReturnSum + HASHBYTES(@algorithm, SUBSTRING(@InputData, @Index, 8000))
    SET @Index = @Index + 8000
END
RETURN @ReturnSum
END

我称之为：

set @ReportDefinitionHash=convert(int,dbo.[udfLargeHashTable]('SHA1',@ReportDefinitionForLookup))

其中@ReportDefinitionHash是int，@ReportDefinitionForLookup是varchar

通过一个简单的字符(如'test‘)，在我的UDF中产生一个与对HashBytes的正常调用不同的int。

在这个问题上有什么建议吗？

Answer 1

只需使用此函数(取自用用户定义的函数散列大型数据字符串)：

create function dbo.fn_hashbytesMAX
    ( @string  nvarchar(max)
    , @Algo    varchar(10)
    )
    returns varbinary(20)
as
/************************************************************
*
*    Author:        Brandon Galderisi
*    Last modified: 15-SEP-2009 (by Denis)
*    Purpose:       uses the system function hashbytes as well
*                   as sys.fn_varbintohexstr to split an 
*                   nvarchar(max) string and hash in 8000 byte 
*                   chunks hashing each 8000 byte chunk,,
*                   getting the 40 byte output, streaming each 
*                   40 byte output into a string then hashing 
*                   that string.
*
*************************************************************/
begin
     declare    @concat       nvarchar(max)
               ,@NumHash      int
               ,@HASH         varbinary(20)
     set @NumHash = ceiling((datalength(@string)/2)/(4000.0))
    /* HashBytes only supports 8000 bytes so split the string if it is larger */
    if @NumHash>1
    begin
                                                        -- # * 4000 character strings
          ;with a as (select 1 as n union all select 1) -- 2 
               ,b as (select 1 as n from a ,a a1)       -- 4
               ,c as (select 1 as n from b ,b b1)       -- 16
               ,d as (select 1 as n from c ,c c1)       -- 256
               ,e as (select 1 as n from d ,d d1)       -- 65,536
               ,f as (select 1 as n from e ,e e1)       -- 4,294,967,296 = 17+ TRILLION characters
               ,factored as (select row_number() over (order by n) rn from f)
               ,factors as (select rn,(rn*4000)+1 factor from factored)

          select @concat = cast((
          select right(sys.fn_varbintohexstr
                         (
                         hashbytes(@Algo, substring(@string, factor - 4000, 4000))
                         )
                      , 40) + ''
          from Factors
          where rn <= @NumHash
          for xml path('')
          ) as nvarchar(max))


          set @HASH = dbo.fn_hashbytesMAX(@concat ,@Algo)
    end
     else
     begin
          set @HASH = convert(varbinary(20), hashbytes(@Algo, @string))
     end

return @HASH
end

结果如下：

select 
 hashbytes('sha1', N'test') --native function with nvarchar input
,hashbytes('sha1', 'test') --native function with varchar input 
,dbo.fn_hashbytesMAX('test', 'sha1') --Galderisi's function which casts to nvarchar input
,dbo.fnGetHash('sha1', 'test') --your function

输出：

0x87F8ED9157125FFC4DA9E06A7B8011AD80A53FE1  
0xA94A8FE5CCB19BA61C4C0873D391E987982FBBD3  
0x87F8ED9157125FFC4DA9E06A7B8011AD80A53FE1   
0x00000000AE6DBA4E0F767D06A97038B0C24ED720662ED9F1

Answer 2

如果您不能创建一个函数，并且必须使用DB中已经存在的内容：

sys.fn_repl_hash_binary

可以使用以下语法使其工作：

sys.fn_repl_hash_binary(cast('some really long string' as varbinary(max)))

摘自：http://www.sqlnotes.info/2012/01/16/generate-md5-value-from-big-data/

Answer 3

我接受了公认的答案，并对其进行了以下改进：

1. 不再是递归函数
2. 现在模式绑定
3. 不再依赖无文档的存储过程
4. 两个版本:一个用于nvarchar，一个用于varchar。
5. 返回与HASHBYTES相同的数据大小，由最终用户根据所使用的算法将其转换为更小的数据。这使得函数能够支持具有更大数据返回量的未来算法。

通过这些更改，这些函数现在可以在持久化计算列中使用，因为它们在创建时被标记为确定性。

CREATE FUNCTION dbo.fnHashBytesNVARCHARMAX
(
    @Algorithm VARCHAR(10),
    @Text NVARCHAR(MAX)
)
RETURNS VARBINARY(8000)
WITH SCHEMABINDING
AS
BEGIN
    DECLARE @NumHash INT;
    DECLARE @HASH VARBINARY(8000);
    SET @NumHash = CEILING(DATALENGTH(@Text) / (8000.0));
    /* HashBytes only supports 8000 bytes so split the string if it is larger */
    WHILE @NumHash > 1
    BEGIN
        -- # * 4000 character strings
        WITH a AS
        (SELECT 1 AS n UNION ALL SELECT 1), -- 2 
        b AS
        (SELECT 1 AS n FROM a, a a1),       -- 4
        c AS
        (SELECT 1 AS n FROM b, b b1),       -- 16
        d AS
        (SELECT 1 AS n FROM c, c c1),       -- 256
        e AS
        (SELECT 1 AS n FROM d, d d1),       -- 65,536
        f AS
        (SELECT 1 AS n FROM e, e e1),       -- 4,294,967,296 = 17+ TRILLION characters
        factored AS
        (SELECT ROW_NUMBER() OVER (ORDER BY n) rn FROM f),
        factors AS
        (SELECT rn, (rn * 4000) + 1 factor FROM factored)
        SELECT  @Text = CAST
            (
                (
                    SELECT  CONVERT(VARCHAR(MAX), HASHBYTES(@Algorithm, SUBSTRING(@Text, factor - 4000, 4000)), 1)
                    FROM    factors
                    WHERE   rn <= @NumHash
                    FOR XML PATH('')
                ) AS NVARCHAR(MAX)
            );

        SET @NumHash = CEILING(DATALENGTH(@Text) / (8000.0));
    END;
    SET @HASH = CONVERT(VARBINARY(8000), HASHBYTES(@Algorithm, @Text));
    RETURN @HASH;
END;

CREATE FUNCTION dbo.fnHashBytesVARCHARMAX
(
    @Algorithm VARCHAR(10),
    @Text VARCHAR(MAX)
)
RETURNS VARBINARY(8000)
WITH SCHEMABINDING
AS
BEGIN
    DECLARE @NumHash INT;
    DECLARE @HASH VARBINARY(8000);
    SET @NumHash = CEILING(DATALENGTH(@Text) / (8000.0));
    /* HashBytes only supports 8000 bytes so split the string if it is larger */
    WHILE @NumHash > 1
    BEGIN
        -- # * 4000 character strings
        WITH a AS
        (SELECT 1 AS n UNION ALL SELECT 1), -- 2 
        b AS
        (SELECT 1 AS n FROM a, a a1),       -- 4
        c AS
        (SELECT 1 AS n FROM b, b b1),       -- 16
        d AS
        (SELECT 1 AS n FROM c, c c1),       -- 256
        e AS
        (SELECT 1 AS n FROM d, d d1),       -- 65,536
        f AS
        (SELECT 1 AS n FROM e, e e1),       -- 4,294,967,296 = 17+ TRILLION characters
        factored AS
        (SELECT ROW_NUMBER() OVER (ORDER BY n) rn FROM f),
        factors AS
        (SELECT rn, (rn * 8000) + 1 factor FROM factored)
        SELECT  @Text = CAST
        (
            (
                SELECT  CONVERT(VARCHAR(MAX), HASHBYTES(@Algorithm, SUBSTRING(@Text, factor - 8000, 8000)), 1)
                FROM    factors
                WHERE   rn <= @NumHash
                FOR XML PATH('')
            ) AS NVARCHAR(MAX)
        );

        SET @NumHash = CEILING(DATALENGTH(@Text) / (8000.0));
    END;
    SET @HASH = CONVERT(VARBINARY(8000), HASHBYTES(@Algorithm, @Text));
    RETURN @HASH;
END;