Sql server ul当您写入xml文件时，验证它时会出现无效字符错误。这只需要一个小更改，Varchar（128）需要更大，因为存储了2个字符。我做的是Varchar（200）。在我的数据库中运行确实需要一些时间。我也很惊讶，一个范围不能用来简化这个过程。i、 e.像“%

---

ul当您写入xml文件时，验证它时会出现无效字符错误。

这只需要一个小更改，Varchar（128）需要更大，因为存储了2个字符。我做的是Varchar（200）。在我的数据库中运行确实需要一些时间。我也很惊讶，一个范围不能用来简化这个过程。i、 e.像“%[^ |-| ~]%”escape“|”一样，我试图让一个范围工作，但它没有返回正确的信息。我还将127更改为126。我不想要DEL这个角色。有趣的方法。出于我自己的好奇……我可以问一下，为什么需要在语句末尾的行“OPTION（MAXRECURSION 1000）”以及在这种情况下它会做什么吗？“OPTION（MAXRECURSION 1000）”是CTE所必需的，它递归地构建一组从1到1000的行，默认值是100（我认为）cte中的任何嵌套递归调用要超过默认值，都需要设置此选项。如果你有一个数字表，你就不需要CTE或这个“OPTION（MAXRECURSION 1000）”行注释了……在case语句版本中，我提到了一行中有多个列的值不正确。如果first_name和last_name的值都不正确……我认为case语句会找到first_name部分并正确显示，但会在那里结束，而不会正确显示last_name值。可能不是最佳解决方案……我文章底部的子查询版本将所有表的值合并为id、columnname、value格式，它似乎更具功能性，更易于遵循。这真的很有趣。您能解释一下这是如何工作的吗？Gerhard正在为PATINDEX函数提供一个正则表达式。正则表达式是[^！-~]。我不知道他为什么在那里包括感叹号字符，因为它正好在空格字符后面。关键是正则表达式查找不在空格Tilde（32-126）范围内的字符。值得注意的是，PATINDEX函数不接受任何正则表达式模式。它有自己的语法，在某些方面类似于正则表达式。简单快速。谢谢@很好的解决方案，喜欢它。这看起来不对。ASCII！=拉丁语1.虽然我有时会编辑答案，以包含被省略的分号，但在这里这样做是不对的，因为答案对于您使用的代码不再准确。但重要的是不要离开他们。见：见

select *
from Staging.APARMRE1 as ar
where ar.Line like '%[^!-~ ]%'

declare @str varchar(128);
declare @i int;
set @str = '';
set @i = 32;
while @i <= 127
    begin
    set @str = @str + '|' + char(@i);
    set @i = @i + 1;
    end;

select  col1
from    YourTable
where   col1 like '%[^' + @str + ']%' escape '|';

Select * from Staging.APARMRE1 ar
where udf_parsealpha(ar.last_name) <> ar.last_name

Select id, case when udf_parsealpha(ar.last_name) <> ar.last_name then 'last name'
when udf_parsealpha(ar.first_name) <> ar.first_name then 'first name'
when udf_parsealpha(ar.Address1) <> ar.last_name then 'Address1'
end, 
case when udf_parsealpha(ar.last_name) <> ar.last_name then ar.last_name
when udf_parsealpha(ar.first_name) <> ar.first_name then ar.first_name
when udf_parsealpha(ar.Address1) <> ar.last_name then ar.Address1
end
from Staging.APARMRE1 ar
where udf_parsealpha(ar.last_name) <> ar.last_name or
udf_parsealpha(ar.first_name) <> ar.first_name or
udf_parsealpha(ar.Address1) <> ar.last_name 

select id,fieldname,value from (
Select id,'last_name' as 'fieldname', last_name as 'value'
from Staging.APARMRE1 ar
Union
Select id,'first_name' as 'fieldname', first_name as 'value'
from Staging.APARMRE1 ar
---(and repeat unions for each field)
)
where udf_parsealpha(value) <> value

DECLARE @YourTable table (PK int, col1 varchar(20), col2 varchar(20), col3 varchar(20));
INSERT @YourTable VALUES (1, 'ok','ok','ok');
INSERT @YourTable VALUES (2, 'BA'+char(182)+'D','ok','ok');
INSERT @YourTable VALUES (3, 'ok',char(182)+'BAD','ok');
INSERT @YourTable VALUES (4, 'ok','ok','B'+char(182)+'AD');
INSERT @YourTable VALUES (5, char(182)+'BAD','ok',char(182)+'BAD');
INSERT @YourTable VALUES (6, 'BAD'+char(182),'B'+char(182)+'AD','BAD'+char(182)+char(182)+char(182));

--if you have a Numbers table use that, other wise make one using a CTE
WITH AllNumbers AS
(   SELECT 1 AS Number
    UNION ALL
    SELECT Number+1
        FROM AllNumbers
        WHERE Number<1000
)
SELECT 
    pk, 'Col1' BadValueColumn, CONVERT(varchar(20),col1) AS BadValue --make the XYZ in convert(varchar(XYZ), ...) the largest value of col1, col2, col3
    FROM @YourTable           y
        INNER JOIN AllNumbers n ON n.Number <= LEN(y.col1)
    WHERE ASCII(SUBSTRING(y.col1, n.Number, 1))<32 OR ASCII(SUBSTRING(y.col1, n.Number, 1))>127
UNION
SELECT 
    pk, 'Col2' BadValueColumn, CONVERT(varchar(20),col2) AS BadValue --make the XYZ in convert(varchar(XYZ), ...) the largest value of col1, col2, col3
    FROM @YourTable           y
        INNER JOIN AllNumbers n ON n.Number <= LEN(y.col2)
    WHERE ASCII(SUBSTRING(y.col2, n.Number, 1))<32 OR ASCII(SUBSTRING(y.col2, n.Number, 1))>127
UNION
SELECT 
    pk, 'Col3' BadValueColumn, CONVERT(varchar(20),col3) AS BadValue --make the XYZ in convert(varchar(XYZ), ...) the largest value of col1, col2, col3
    FROM @YourTable           y
        INNER JOIN AllNumbers n ON n.Number <= LEN(y.col3)
    WHERE ASCII(SUBSTRING(y.col3, n.Number, 1))<32 OR ASCII(SUBSTRING(y.col3, n.Number, 1))>127
order by 1
OPTION (MAXRECURSION 1000);

pk          BadValueColumn BadValue
----------- -------------- --------------------
2           Col1           BA¶D
3           Col2           ¶BAD
4           Col3           B¶AD
5           Col1           ¶BAD
5           Col3           ¶BAD
6           Col1           BAD¶
6           Col2           B¶AD
6           Col3           BAD¶¶¶

(8 row(s) affected)

select line,
  patindex('%[^ !-~]%' COLLATE Latin1_General_BIN,Line) as [Position],
  substring(line,patindex('%[^ !-~]%' COLLATE Latin1_General_BIN,Line),1) as [InvalidCharacter],
  ascii(substring(line,patindex('%[^ !-~]%' COLLATE Latin1_General_BIN,Line),1)) as [ASCIICode]
from  staging.APARMRE1
where patindex('%[^ !-~]%' COLLATE Latin1_General_BIN,Line) >0

create function [dbo].[udf_ContainsNonASCIIChars]
(
@string nvarchar(4000),
@checkExtendedCharset bit
)
returns bit
as
begin

    declare @pos int = 0;
    declare @char varchar(1);
    declare @return bit = 0;

    while @pos < len(@string)
    begin
        select @char = substring(@string, @pos, 1)
        if ascii(@char) < 32 or ascii(@char) > 126 
            begin
                if @checkExtendedCharset = 1
                    begin
                        if ascii(@char) not in (9,124,130,138,142,146,150,154,158,160,170,176,180,181,183,184,185,186,192,193,194,195,196,197,199,200,201,202,203,204,205,206,207,209,210,211,212,213,214,216,217,218,219,220,221,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,248,249,250,251,252,253,254,255)
                            begin
                                select @return = 1;
                                select @pos = (len(@string) + 1)
                            end
                        else
                            begin
                                select @pos = @pos + 1
                            end
                    end
                else
                    begin
                        select @return = 1;
                        select @pos = (len(@string) + 1)    
                    end
            end
        else
            begin
                select @pos = @pos + 1
            end
    end

    return @return;

end

select Address1 
from PropertyFile_English
where udf_ContainsNonASCIIChars(Address1, 1) = 1

select dodgyColumn from myTable fcc
WHERE  patindex('%[^ !-~]%' COLLATE Latin1_General_BIN,dodgyColumn ) >0

select dodgyColumn from myTable fcc
INNER JOIN dbo.Numbers32k dn ON dn.number<(len(fcc.dodgyColumn ))
WHERE ASCII(SUBSTRING(fcc.dodgyColumn , dn.Number, 1))<32 
    OR ASCII(SUBSTRING(fcc.dodgyColumn , dn.Number, 1))>127

select dodgyColumn 
from myTable 
where dbo.udf_test_ContainsNonASCIIChars(dodgyColumn , 1) = 1

declare @UnicodeData table (
     data nvarchar(500)
)
insert into 
    @UnicodeData
values 
    (N'Horse�')
    ,(N'Dog')
    ,(N'Cat')

select
    data
from
    @UnicodeData 
where
    data collate LATIN1_GENERAL_BIN != cast(data as varchar(max))

declare 
    @sql    varchar(max)    = ''
    ,@table sysname         = 'mytable' -- enter your table here

;with ColumnData as (
    select
        RowId               = row_number() over (order by c.COLUMN_NAME)
        ,c.COLUMN_NAME
        ,ColumnName         = '[' + c.COLUMN_NAME + ']'
        ,TableName          = '[' + c.TABLE_SCHEMA + '].[' + c.TABLE_NAME + ']' 
    from
        INFORMATION_SCHEMA.COLUMNS c
    where
        c.DATA_TYPE         = 'nvarchar'
        and c.TABLE_NAME    = @table
)
select
    @sql = @sql + 'select FieldName = ''' + c.ColumnName + ''',         InvalidCharacter = [' + c.COLUMN_NAME + ']  from ' + c.TableName + ' where ' + c.ColumnName + ' collate LATIN1_GENERAL_BIN != cast(' + c.ColumnName + ' as varchar(max)) '  +  case when c.RowId <> (select max(RowId) from ColumnData) then  ' union all ' else '' end + char(13)
from
    ColumnData c

-- check
-- print @sql
exec (@sql)

SELECT * FROM Staging.APARMRE1 FOR XML AUTO, TYPE

SELECT top 1 'char 31: '+char(31)+' (hex 0x1F)' field
from sysobjects
FOR XML AUTO, TYPE