SQL Server 2008和HashBytes

Question

我有一个很大的nvarchar，我希望传递给HashBytes函数。 我收到错误：

  

“字符串或二进制文件将被截断。   无法将值NULL插入   列'colname'，tbale'table';   列不允许空值。 UPDATE   失败。声明一直如此   终止“。

由于资源充足，我发现这是由于HashBytes函数的最大限制为8000字节。进一步搜索向我展示了一个“解决方案”，我的大型varchar将被分开并单独进行散列，然后再与此用户定义的函数结合使用：

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

我打电话给：

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

其中@ReportDefinitionHash是int，而@ReportDefinitionForLookup是varchar

传递像'test'这样的简单char会产生与我的UDF不同的int，而不是对HashBytes的正常调用。

有关此问题的任何建议吗？

Answer 1

如果您无法创建功能并且必须使用数据库中已存在的内容：

sys.fn_repl_hash_binary

可以使用以下语法使

工作：

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

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

Answer 2

只需使用此功能（取自Hashing large data strings with a User Defined Function）：

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 3

我已经接受了接受的答案，并通过以下改进进行了一些修改：

1. 不再具有递归功能
2. 现在架构绑定
3. 不再依赖未记录的存储过程
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，根据使用的算法将其转换为最终用户。这允许函数支持具有更大数据返回的未来算法。

通过这些更改，现在可以在持久计算列中使用这些函数，因为它们在创建时现在标记为确定性。

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;

Answer 4

您可以编写SQL CLR函数：

[Microsoft.SqlServer.Server.SqlFunction]
public static SqlBinary BigHashBytes(SqlString algorithm, SqlString data)
{
    var algo = HashAlgorithm.Create(algorithm.Value);

    var bytes = Encoding.UTF8.GetBytes(data.Value);

    return new SqlBinary(algo.ComputeHash(bytes));
}

然后可以在SQL中调用它：

--these return the same value
select HASHBYTES('md5', 'test stuff')
select dbo.BigHashBytes('md5', 'test stuff')

仅当长度超过8k时才需要BigHashBytes。

Answer 5

测试和工作 选择master.sys.fn_repl_hash_binary（someVarbinaryMaxValue） 而且并不复杂：）

Answer 6

这也可以用作功能体：

DECLARE @A NVARCHAR(MAX) = N'test'

DECLARE @res VARBINARY(MAX) = 0x
DECLARE @position INT = 1
        ,@len INT = DATALENGTH(@A)

WHILE 1 = 1
BEGIN
    SET @res = @res + HASHBYTES('SHA2_256', SUBSTRING(@A, @position, 4000))
    SET @position = @position+4000
    IF @Position > @len 
        BREAK
END

SELECT HASHBYTES('SHA2_256',@res)

HASH 4000字符串NVARCHAR(MAX)部分的HASH概念，并将结果连接起来。然后到{{1}}后一个结果。

Answer 7

似乎最简单的解决方案是编写一个递归哈希算法，将输入文本值解析为子varchar(8000)段。 我随意选择将输入字符串切片为7500个字符段 散列算法返回varbinary(20)，可以轻松转换为varchar(20)

ALTER FUNCTION [dbo].[BigHash]
(   
    @TextValue nvarchar(max)
)

RETURNS varbinary(20)

AS
BEGIN

    if @TextValue = null
        return hashbytes('SHA1', 'null')


    Declare @FirstPart as varchar(7500)
    Declare @Remainder as varchar(max)

    Declare @RemainderHash as varbinary(20)
    Declare @BinaryValue as varbinary(20)

    Declare @TextLength as integer


    Set @TextLength = len(@TextValue)

    if @TextLength > 7500
        Begin
            Set @FirstPart = substring(@TextValue, 1, 7500)         

            Set @Remainder = substring(@TextValue, 7501, @TextLength - 7500)        

            Set @RemainderHash = dbo.BigHash(@Remainder)

            Set @BinaryValue = hashbytes('SHA1', @FirstPart + convert( varchar(20), @RemainderHash, 2 ))

            return @BinaryValue

        End
    else
        Begin
            Set @FirstPart = substring(@TextValue, 1, @TextLength)                      
            Set @BinaryValue = hashbytes('SHA1', @FirstPart)

            return @BinaryValue
        End


    return null

END