解析数据将一个数据点

Question

我有一个讨厌的数据集：

+----+------------------------------------------------------------------------------+ 
| PK |         Medications         | 
+----+------------------------------------------------------------------------------+ 
| 1 | NAPROXEN, neurontin, DOCUSATE, HYDROCODONE, BACLOFEN, advil     | 
| 2 | celexa, lortab, lyrica, ambien, xanax          | 
| 3 | adipex                  | 
| 4 | opana, roxicodone               | 
| 5 | adderall                  | 
| 6 | hydrocodone/apap                | 
| 7 | NEXIUM, METOPROLOL, lipitor, VERAPAMIL, ASPIRIN, WARFARIN, ambien   | 
| 8 | prozac                  | 
| 9 | flexeril                  | 
| 10 | soma, LITHIUM, MULTI-VITAMIN, fentanyl patch, percocet, PROPANOLOL, tegretol | 
+----+------------------------------------------------------------------------------+ 

请记住，这仅仅是2列。

我想回到根本的不同medications 1列的列表在整个数据集：

NAPROXEN 
neurontin 
DOCUSATE 
HYDROCODONE 
BACLOFEN 
advil 
celexa 
lortab 
lyrica 
ambien 
xanax 
adipex 
opana 

什么是去了解这一点的最好方法是什么？

非常感谢您的指导。

Answer 1

DECLARE @Medications TABLE 
     (
      PK BIGINT PRIMARY KEY IDENTITY(1,1) 
      ,Medications NVARCHAR(4000) 
     ) 

    /* Populate the table with example records*/ 
    INSERT INTO @Medications(Medications) VALUES 
    ('NAPROXEN, neurontin, DOCUSATE, HYDROCODONE, BACLOFEN, advil') 
    ,('celexa, lortab, lyrica, ambien, xanax ') 
    ,('adipex') 
     ,('opana roxicodone') 
     ,('adderall') 
     ,('hydrocodone/apap') 
     ,('NEXIUM,METOPROLOL,lipitor,VERAPAMIL,ASPIRIN,WARFARIN,ambien') 
     ,('prozac') 
     ,('flexeril') 
     ,('soma,LITHIUM,MULTI-VITAMIN,fentanyl patch,percocet,PROPANOLOL,tegretol') 

选项1

select distinct Medication = ltrim(rtrim(O.splitdata)) 
from 
(
select *, 
cast('<X>'+replace(F.Medications,',','</X><X>')+'</X>' as XML) as xmlfilter 
from @Medications F 
)F1 
cross apply 
( 
select fdata.D.value('.','varchar(50)') as splitdata 
from f1.xmlfilter.nodes('X') as fdata(D)) O 
where O.splitdata <> '' 
group by O.splitdata 

选项2

SELECT DISTINCT display_term 
FROM @Medications 
CROSS APPLY sys.dm_fts_parser('"' + Medications + '"', 1033, 0,0) 
where display_term NOT LIKE 'nn%' 

选项3

SELECT DISTINCT 
    LTRIM(RTRIM(SUBSTRING(Medications, Number ,CHARINDEX(',', Medications + ',', Number) - Number))) AS Medication 
FROM @Medications 
JOIN master..spt_values ON Number <= DATALENGTH(Medications) + 1 AND type='P' 
AND SUBSTRING(',' + Medications, Number , 1) = ',' 

Answer 2

，如果你能输出到awk的

outputcommand | awk 'BEGIN{FS="|"}{print $3}'|awk 'BEGIN{RS=","}{print $0}' 

如果一个简单的文本文件，你可以使用cat filename为outputcommand或：

awk 'BEGIN{FS="|"}{print $3}' some_filename |awk 'BEGIN{RS=","}{print $0}' 

Answer 3

这可能是你正在寻找的解决方案：

;WITH SourceDate(PK,MedicationsXML) AS 
(
    SELECT PK 
      ,CAST(N'<r><![CDATA[' + REPLACE(Medications, ',', ']]></r><r><![CDATA[') + ']]></r>' AS XML) 
    FROM @Medications 
) 
SELECT DISTINCT Medicament 
FROM SourceDate 
CROSS APPLY (SELECT DISTINCT RTRIM(LTRIM(Tbl.Col.value('.', 'nvarchar(250)'))) AS Medicament FROM MedicationsXML.nodes('//r') Tbl(Col)) AS List 

这是一个完整的工作示例（我添加了重复记录以显示它只返回不同的值：

SET NOCOUNT ON 
GO 

    /* Declare table that holds the data*/ 
    DECLARE @Medications TABLE 
    (
     PK BIGINT PRIMARY KEY IDENTITY(1,1) 
     ,Medications NVARCHAR(4000) 
    ) 

    /* Populate the table with exmaple records*/ 
    INSERT INTO @Medications(Medications) 
    VALUES ('NAPROXEN, neurontin, DOCUSATE, HYDROCODONE, BACLOFEN, advil') 
      ,('celexa, lortab, lyrica, ambien, xanax ') 
      ,('adipex') 
      ,('opana, roxicodone') 
      ,('adderall') 
      ,('hydrocodone/apap') 
      ,('NEXIUM, METOPROLOL, lipitor, VERAPAMIL, ASPIRIN, WARFARIN, ambien') 
      ,('prozac') 
      ,('flexeril') 
      ,('soma, LITHIUM, MULTI-VITAMIN, fentanyl patch, percocet, PROPANOLOL, tegretol') 
      ,('NAPROXEN, neurontin, DOCUSATE, HYDROCODONE, BACLOFEN, advil') 
      ,('celexa, lortab, lyrica, ambien, xanax ') 
      ,('adipex') 
      ,('opana, roxicodone') 
      ,('adderall') 
      ,('hydrocodone/apap') 
      ,('NEXIUM, METOPROLOL, lipitor, VERAPAMIL, ASPIRIN, WARFARIN, ambien') 
      ,('prozac') 
      ,('flexeril') 
      ,('soma, LITHIUM, MULTI-VITAMIN, fentanyl patch, percocet, PROPANOLOL, tegretol') 

    ;WITH SourceDate(PK,MedicationsXML) AS 
    (
     SELECT PK 
       ,CAST(N'<r><![CDATA[' + REPLACE(Medications, ',', ']]></r><r><![CDATA[') + ']]></r>' AS XML) 
     FROM @Medications 
    ) 
    SELECT DISTINCT Medicament 
    FROM SourceDate 
    CROSS APPLY (SELECT DISTINCT RTRIM(LTRIM(Tbl.Col.value('.', 'nvarchar(250)'))) AS Medicament FROM MedicationsXML.nodes('//r') Tbl(Col)) AS List 


SET NOCOUNT OFF 
GO 

随时问任何问题。