2

我有一个存储大量 XML 的数据库，其中包含有关安装我们公司产品的信息。没有为 XML 定义模式，也没有人拥有所有潜在标签的列表。

每条记录都有数百个这样的结构：

<array type="DWORD" name="m_somesetting.SMTPPorts" size="5"> 
   <set>19</set> 
   <set>1D0</set> 
   <set>14B</set> 
</array>

我被要求创建一个表格，显示每个可能的标签一个值以及我们数以万计的记录中有多少具有该特定设置的计数。

有谁知道我如何自动化这个？我对如何对 XML 进行查询有一个合理的理解，但我需要一些方法来首先获取存在的每个标记，然后获取存在的每个唯一值，最后获取包含该值的记录计数。

关于如何将每个可能的标签手动编码到查询中的任何想法？

4

2 回答 2

0

UDF 从 xml 创建表

SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[XMLTable](@x XML)  
RETURNS TABLE 
AS RETURN 
WITH cte AS (  
SELECT 
        1 AS lvl,  
        x.value('local-name(.)','NVARCHAR(MAX)') AS Name,  
        CAST(NULL AS NVARCHAR(MAX)) AS ParentName, 
        CAST(1 AS INT) AS ParentPosition, 
        CAST(N'Element' AS NVARCHAR(20)) AS NodeType,  
        x.value('local-name(.)','NVARCHAR(MAX)') AS FullPath,  
        x.value('local-name(.)','NVARCHAR(MAX)')  
        + N'[' 
        + CAST(ROW_NUMBER() OVER(ORDER BY (SELECT 1)) AS NVARCHAR)  
        + N']' AS XPath,  
        ROW_NUMBER() OVER(ORDER BY (SELECT 1)) AS Position, 
        x.value('local-name(.)','NVARCHAR(MAX)') AS Tree,  
        x.value('text()[1]','NVARCHAR(MAX)') AS Value,  
        x.query('.') AS this,         
        x.query('*') AS t,  
        CAST(CAST(1 AS VARBINARY(4)) AS VARBINARY(MAX)) AS Sort,  
        CAST(1 AS INT) AS ID  
FROM @x.nodes('/*') a(x)  
UNION ALL 
SELECT 
        p.lvl + 1 AS lvl,  
        c.value('local-name(.)','NVARCHAR(MAX)') AS Name,  
        CAST(p.Name AS NVARCHAR(MAX)) AS ParentName, 
    CAST(p.Position AS INT) AS ParentPosition, 
        CAST(N'Element' AS NVARCHAR(20)) AS NodeType,  
        CAST(p.FullPath + N'/' + c.value('local-name(.)','NVARCHAR(MAX)') AS NVARCHAR(MAX)) AS FullPath,  
        CAST(p.XPath + N'/'+ c.value('local-name(.)','NVARCHAR(MAX)')+ N'['+ CAST(ROW_NUMBER() OVER(PARTITION BY c.value('local-name(.)','NVARCHAR(MAX)') 
        ORDER BY (SELECT 1)) AS NVARCHAR)+ N']' AS NVARCHAR(MAX)) AS XPath,  
        ROW_NUMBER() OVER(PARTITION BY c.value('local-name(.)','NVARCHAR(MAX)')
        ORDER BY (SELECT 1)) AS Position, 
        CAST( SPACE(2 * p.lvl - 1) + N'|' + REPLICATE(N'-', 1) + c.value('local-name(.)','NVARCHAR(MAX)') AS NVARCHAR(MAX)) AS Tree,  
        CAST( c.value('text()[1]','NVARCHAR(MAX)') AS NVARCHAR(MAX) ) AS Value, c.query('.') AS this,  
        c.query('*') AS t,  
        CAST(p.Sort + CAST( (lvl + 1) * 1024 + (ROW_NUMBER() OVER(ORDER BY (SELECT 1)) * 2) AS VARBINARY(4)) AS VARBINARY(MAX) ) AS Sort,  
        CAST((lvl + 1) * 1024 + (ROW_NUMBER() OVER(ORDER BY (SELECT 1)) * 2) AS INT)  
FROM cte p  
CROSS APPLY p.t.nodes('*') b(c)), cte2 AS (  
                                            SELECT 
                                            lvl AS Depth,  
                                            Name AS NodeName,  
                                            ParentName, 
                                            ParentPosition, 
                                            NodeType,  
                                            FullPath,  
                                            XPath,  
                                            Position, 
                                            Tree AS TreeView,  
                                            Value,  
                                            this AS XMLData,  
                                            Sort, ID  
                                            FROM cte  
UNION ALL 
SELECT 
        p.lvl,  
        x.value('local-name(.)','NVARCHAR(MAX)'),  
        p.Name, 
        p.Position, 
        CAST(N'Attribute' AS NVARCHAR(20)),  
        p.FullPath + N'/@' + x.value('local-name(.)','NVARCHAR(MAX)'),  
        p.XPath + N'/@' + x.value('local-name(.)','NVARCHAR(MAX)'),  
        1, 
        SPACE(2 * p.lvl - 1) + N'|' + REPLICATE('-', 1)  
        + N'@' + x.value('local-name(.)','NVARCHAR(MAX)'),  
        x.value('.','NVARCHAR(MAX)'),  
        NULL,  
        p.Sort,  
        p.ID + 1  
FROM cte p  
CROSS APPLY this.nodes('/*/@*') a(x)  
)  
SELECT 
        ROW_NUMBER() OVER(ORDER BY Sort, ID) AS ID,  
        ParentName, ParentPosition,Depth, NodeName, Position,   
        NodeType, FullPath, XPath, TreeView, Value, XMLData 
FROM cte2
于 2014-03-05T18:46:47.927 回答
0

您应该能够相当轻松地从充满 XML 内容的表中提取所有不同的标签名称：

DECLARE @input TABLE (ID INT, XmlCOntent XML)

INSERT INTO @input VALUES(1, '<array type="DWORD" name="m_somesetting.SMTPPorts" size="5"> 
   <set>19</set> 
   <set>1D0</set> 
   <set>14B</set> 
</array>'), 
(2, '<array2 type="DWORD" name="m_somesetting.SMTPPorts" size="5"> 
   <set2>19</set2> 
   <set3>1D0</set3> 
   <set4>14B</set4> 
</array2>')

SELECT
    DISTINCT 
    Nodes.value('local-name(.)', 'varchar(50)')
FROM
    @input
CROSS APPLY 
    XmlContent.nodes('//*') AS Tbl(Nodes)

请注意：我说的很简单——不是很快。这将搅动很长一段时间！但它仍然比手动完成所有操作要好:-)

于 2012-10-28T13:12:58.323 回答