词的排列组合

Question

跟进问题

我有以下数据：

我有以下用于排列和组合的示例数据。

create table tbltest
(
    name varchar(50),
    addres varchar(100)
);

insert into tbltest values('Sam Mak John','Street 1 HNo 101 USA');
insert into tbltest values('Donatella Nobatti','HNo 101 UK');
insert into tbltest values('Sam Buca','Main Road B Block UAE');
insert into tbltest values('Juan Soponatime','Hight Street CA');
insert into tbltest values('Aaron Spacemuseum','HNo A10 100 feet Road A Block ');
insert into tbltest values('Nasir Ahmed Amir Ahmed Mehendy','UAE High Street');

以预期结果为例：

name
----------------
John Mak Sam
John Sam Mak
Mak John Sam
Mak Sam John
Sam John Mak
Sam Mak John
....
....

尝试了上一个问题的解决方案：

--To store Words 
CREATE TABLE dbo.NameParts
(
  ID int NOT NULL,
  NamePart varchar(30) NOT NULL
);

--Table variable to identity column for each words
DECLARE @Inter TABLE (id int identity(1,1), names varchar(max));

--Insert into table variable
INSERT INTO @Inter(names) SELECT name from TblTest;

--Query to insert into NameParts table
;WITH splitdata 
AS 
(
    SELECT id,splitname 
    FROM   
    (
        SELECT *,Cast('<X>' + Replace(F.Names, ' ', '</X><X>') + '</X>' AS XML) AS  xmlfilter 
        FROM   @Inter F
    )F1 
    CROSS apply 
    (
        SELECT fdata.d.value('.', 'varchar(50)') AS splitName 
        FROM   f1.xmlfilter.nodes('X') AS fdata(d)
    ) O
) 
INSERT INTO dbo.NameParts
SELECT * 
FROM splitdata;

排列组合查询：

--Query for Permutation and Combination
;WITH
  permutations AS
  (
    SELECT
      ID = t.ID,
      FullNameVariation = CAST(t.NamePart AS varchar(500)),
      Level = COUNT(*) OVER (PARTITION BY t.ID)
    FROM
      dbo.NameParts AS t
    UNION ALL
    SELECT
      ID = t.ID,
      FullNameVariation = CAST(p.FullNameVariation + ' ' + t.NamePart AS varchar(500)),
      Level = p.Level - 1
    FROM
      dbo.NameParts AS t
      INNER JOIN permutations AS p ON t.ID = p.ID
    WHERE 1=1
      AND p.Level > 1
      AND ' ' + p.FullNameVariation + ' ' NOT LIKE '% ' + t.NamePart + ' %'
  )
SELECT
  ID,
  FullNameVariation
FROM
  permutations
WHERE
  Level = 1
ORDER BY
  ID,
  FullNameVariation 
OPTION (MAXRECURSION 5100);

注意：上述查询工作正常，但无法在结果集中获得以下记录：

Nasir Ahmed Amir Ahmed Mehendy

那是因为这个条件：

' ' + p.FullNameVariation + ' ' NOT LIKE '% ' + t.NamePart + ' %'

单词Ahmed重复，不满足上述条件。

Answer 1

扩展Andriy M的原始答案，我们可以在插入阶段使用虚拟字符（在我的情况下我使用 ~）统一字符串，然后删除该字符。

在这种情况下，我选择使用 REPLICATE 传递虚拟字符 '~' 和 ROW_NUMBER 函数作为要复制的实例数。这应该确保所有字符串都是唯一的。

数据库小提琴

完整代码

create table tbltest
(
    name varchar(50),
    addres varchar(100)
);

insert into tbltest values('Sam Mak John','Street 1 HNo 101 USA');
insert into tbltest values('Donatella Nobatti','HNo 101 UK');
insert into tbltest values('Sam Buca','Main Road B Block UAE');
insert into tbltest values('Juan Soponatime','Hight Street CA');
insert into tbltest values('Aaron Spacemuseum','HNo A10 100 feet Road A Block ');
insert into tbltest values('Nasir Ahmed Amir Ahmed Mehendy','UAE High Street');
GO

CREATE TABLE dbo.NameParts
(
  ID int NOT NULL,
  NamePart varchar(30) NOT NULL
);

--Table variable to identity column for each words
DECLARE @Inter TABLE (id int identity(1,1), names varchar(max));

--Insert into table variable
INSERT INTO @Inter(names) SELECT name from TblTest;

--Query to insert into NameParts table
;WITH splitdata 
AS 
(
    SELECT id,splitname 
    FROM   
    (
        SELECT *,Cast('<X>' + Replace(F.Names, ' ', '</X><X>') + '</X>' AS XML) AS  xmlfilter 
        FROM   @Inter F
    )F1 
    CROSS apply 
    (
        SELECT fdata.d.value('.', 'varchar(50)') AS splitName 
        FROM   f1.xmlfilter.nodes('X') AS fdata(d)
    ) O
) 
INSERT INTO dbo.NameParts
SELECT id,[splitdata].[splitName] + REPLICATE('~',(ROW_NUMBER() OVER (PARTITION BY [splitdata].[id] ORDER BY [splitdata].[splitName] ASC))
FROM splitdata;
GO

;WITH
  permutations AS
  (
    SELECT
      ID = t.ID,
      FullNameVariation = CAST(t.NamePart AS varchar(500)),
      Level = COUNT(*) OVER (PARTITION BY t.ID)
    FROM
      dbo.NameParts AS t
    UNION ALL
    SELECT
      ID = t.ID,
      FullNameVariation = CAST(p.FullNameVariation + ' ' + t.NamePart AS varchar(500)),
      Level = p.Level - 1
    FROM
      dbo.NameParts AS t
      INNER JOIN permutations AS p ON t.ID = p.ID
    WHERE 1=1
      AND p.Level > 1
      AND ' ' + p.FullNameVariation + ' ' NOT LIKE '% ' + t.NamePart + ' %'
  )
SELECT
  ID,
  REPLACE(FullNameVariation,'~','')
FROM
  permutations
WHERE 1=1 AND
  Level = 1
ORDER BY
  ID,
  FullNameVariation 
OPTION (MAXRECURSION 5100);

DROP TABLE [dbo].[tbltest]
DROP TABLE [dbo].[NameParts]