sql - 将文本解析为多列

Question

我有一个提要，它用统计信息填充表格中的单个文本字段。我需要将此数据拉入另一个表中的多个字段但是奇怪的格式使得自动导入变得困难。

文件格式为纯文本，示例如下:

08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12

实际上它由以下部分组成:

[timestamp] [Field1 name]=[Field1 value],[Field2 name]=[Field2 value],[Field4 name]=[Field4 value]...[CR]

所有字段的顺序始终相同，但并不总是存在。列总数可以在 5 到 30 之间。

我已经尝试了下面的函数来翻译它，它似乎大部分工作但似乎随机跳过字段:

解析数据:

(SELECT [Data].[dbo].[GetFromTextString] ( 'Checksum=' ,',' ,RAWTEXT)) AS RowCheckSum,
(SELECT [Data].[dbo].[GetFromTextString] ( 'TicketType=' ,',' ,RAWTEXT)) AS TicketType,

和功能:

CREATE FUNCTION [dbo].[GetFromTextString]
-- Input start and end and return value.
   (@uniqueprefix VARCHAR(100),
    @commonsuffix VARCHAR(100),
    @datastring VARCHAR(MAX) )
RETURNS VARCHAR(MAX) -- Picked Value.
AS
BEGIN

    DECLARE @ADJLEN INT = LEN(@uniqueprefix)

    SET @datastring = @datastring + @commonsuffix

   RETURN ( 
    CASE WHEN (CHARINDEX(@uniqueprefix,@datastring) > 0) 
         AND (CHARINDEX(@uniqueprefix + @commonsuffix,@datastring) = 0)
    THEN SUBSTRING(@datastring, PATINDEX('%' + @uniqueprefix + '%',@datastring)+@ADJLEN, CHARINDEX(@commonsuffix,@datastring,PATINDEX('%' + @uniqueprefix + '%',@datastring))- PATINDEX('%' + @uniqueprefix + '%',@datastring)-@ADJLEN) ELSE NULL END
)
END

谁能建议一种更好/更干净的方法来去除数据，或者有人能弄清楚为什么这个公式会跳过行？

非常感谢任何帮助。

Answer 1

注意 - 第一个解决方案是垃圾。由于历史原因，我保留了它，但下面包含了更好的解决方案

我什至不确定这是否会比您当前的方法更快，但这是我处理问题的方式(如果我被迫采用仅 SQL 的解决方案)。首先需要的是一个表值函数，它将执行拆分函数:

CREATE FUNCTION dbo.Split (@TextToSplit VARCHAR(MAX), @Delimiter VARCHAR(MAX))
RETURNS @Values TABLE (Position INT IDENTITY(1, 1) NOT NULL, TextValues VARCHAR(MAX) NOT NULL)
AS
BEGIN
    WHILE CHARINDEX(@Delimiter, @TextToSplit) > 0
        BEGIN
            INSERT @Values 
            SELECT  LEFT(@TextToSplit, CHARINDEX(@Delimiter, @TextToSplit) - 1)
            SET @TextToSplit = SUBSTRING(@TextToSplit, CHARINDEX(@Delimiter, @TextToSplit) + 1, LEN(@TextToSplit))

        END
        INSERT @Values VALUES (@TextToSplit) 
    RETURN
END

在我的示例中，我使用临时表 @Worklist 工作，您可能需要相应地调整您的临时表，或者您可以将相关数据插入我使用虚拟数据的 @Worklist 中:

DECLARE @WorkList TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
INSERT @WorkList
SELECT  '08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12'
UNION
SELECT  '08:34:52 Checksum=180957249,TicketType=5,InitialUserType=H,InitialUserID=521,CommunicationType=Outgoing,Date=27-03-2012,Time=14:27:00,Service=ST,Duration=00:15:12,Cost=0.37'

查询的主要部分在这里完成。它很长，所以我试着尽可能地评论它。如果需要进一步说明，我可以添加更多评论。

DECLARE @Output TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
DECLARE @KeyPairs TABLE (WorkListID INT NOT NULL, KeyField VARCHAR(MAX), ValueField VARCHAR(MAX))

-- STORE TIMESTAMP DATA - THIS ASSUMES THE FIRST SPACE IS THE END OF THE TIMESTAMP
INSERT @KeyPairs 
SELECT  ID, 'TimeStamp', LEFT(TextField, CHARINDEX(' ', TextField))
FROM    @WorkList

-- CLEAR THE TIMESTAMP FROM THE WORKLIST
UPDATE  @WorkList
SET     TextField = SUBSTRING(TextField, CHARINDEX(' ', TextField) + 1, LEN(TextField))

DECLARE @ID INT = (SELECT MIN(ID) FROM @WorkList)
WHILE @ID IS NOT NULL 
    BEGIN
        -- SPLIT THE STRING FIRST INTO ALL THE PAIRS (e.g. Checksum=180957248)
        INSERT @Output
        SELECT  TextValues
        FROM    dbo.Split((SELECT TextField FROM @WorkList WHERE ID = @ID), ',')

        DECLARE @ID2 INT = (SELECT MIN(ID) FROM @Output)

        -- FOR ALL THE PAIRS SPLIT THEM INTO A KEY AND A VALUE (USING THE POSITION OF THE SPLIT FUNCTION)
        WHILE @ID2 IS NOT NULL
            BEGIN
                INSERT @KeyPairs
                SELECT  @ID, 
                        MAX(CASE WHEN Position = 1 THEN TextValues ELSE '' END),
                        MAX(CASE WHEN Position = 2 THEN TextValues ELSE '' END)
                FROM    dbo.Split((SELECT TextField FROM @Output WHERE ID = @ID2), '=')

                DELETE  @Output
                WHERE   ID = @ID2

                SET @ID2 = (SELECT MIN(ID) FROM @Output)
            END

        DELETE  @WorkList
        WHERE   ID = @ID

        SET @ID = (SELECT MIN(ID) FROM @WorkList)
    END

-- WE NOW HAVE A TABLE CONTAINING EAV MODEL STYLE DATA. THIS NEEDS TO BE PIVOTED INTO THE CORRECT FORMAT
-- ENSURE COLUMNS ARE LISTED IN THE ORDER YOU WANT THEM TO APPEAR
SELECT  *
FROM    @KeyPairs p
        PIVOT
        (   MAX(ValueField)
            FOR KeyField IN 
                (   [TimeStamp], [Checksum], [TicketType], [InitialUserType], 
                    [InitialUserID], [CommunicationType], [Date], [Time],
                    [Service], [Duration], [Cost]
                )
        ) AS PivotTable;

---

编辑(4 年后)

最近的一次投票引起了我的注意，我有点讨厌自己以目前的形式发布这个答案。

更好的分割函数是:

CREATE FUNCTION dbo.Split
(
   @List       NVARCHAR(MAX),
   @Delimiter  NVARCHAR(255)
)
RETURNS TABLE
WITH SCHEMABINDING AS
RETURN
(   WITH N1 AS (SELECT N FROM (VALUES (1),(1),(1),(1),(1),(1),(1),(1),(1), (1)) n (N)),
    N2(N) AS (SELECT 1 FROM N1 a CROSS JOIN N1 b),
    N3(N) AS (SELECT 1 FROM N2 a CROSS JOIN N2 b),
    N4(N) AS (SELECT 1 FROM N3 a CROSS JOIN N3 b),
    cteTally(N) AS 
    (   SELECT 0 UNION ALL 
        SELECT TOP (DATALENGTH(ISNULL(@List,1))) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) 
        FROM n4
    ),
    cteStart(N1) AS 
    (   SELECT t.N+1 
        FROM cteTally t
        WHERE (SUBSTRING(@List,t.N,1) = @Delimiter OR t.N = 0)
    )
    SELECT Item = SUBSTRING(@List, s.N1, ISNULL(NULLIF(CHARINDEX(@Delimiter,@List,s.N1),0)-s.N1,8000)), 
            Position = s.N1,
            ItemNumber = ROW_NUMBER() OVER(ORDER BY s.N1)
    FROM cteStart s
);

然后根本不需要循环，您只需通过两次调用 split 函数来获取您的 EAV 样式数据集，就可以得到一个基于集合的正确解决方案:

DECLARE @WorkList TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
INSERT @WorkList
SELECT  '08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12'
UNION
SELECT  '08:34:52 Checksum=180957249,TicketType=5,InitialUserType=H,InitialUserID=521,CommunicationType=Outgoing,Date=27-03-2012,Time=14:27:00,Service=ST,Duration=00:15:12,Cost=0.37';

WITH KeyPairs AS
(   SELECT  w.ID, 
            [Timestamp] = LEFT(w.TextField, CHARINDEX(' ', w.TextField)),
            KeyField = MAX(CASE WHEN v.ItemNumber = 1 THEN v.Item END),
            ValueField = MAX(CASE WHEN v.ItemNumber = 2 THEN v.Item END)
    FROM    @WorkList AS w
            CROSS APPLY dbo.Split(SUBSTRING(TextField, CHARINDEX(' ', TextField) + 1, LEN(TextField)), ',') AS kp
            CROSS APPLY dbo.Split(kp.Item, '=') AS v
    GROUP BY w.ID, kp.ItemNumber,w.TextField
)
SELECT  *
FROM   KeyPairs AS kp
        PIVOT
        (   MAX(ValueField)
            FOR KeyField IN 
                (   [Checksum], [TicketType], [InitialUserType], 
                    [InitialUserID], [CommunicationType], [Date], [Time],
                    [Service], [Duration], [Cost]
                )
        ) AS pvt;