分割/削除/結合手法も使用しました。
主なポイントは次のとおりです。
- これは、UDF ではなく、再帰的な CTEのペアを使用します。
- これは、すべての英語の文末で機能します:
.
または!
または?
- これにより、空白が削除されて「数字と従業員」の比較が行われるため、複数のスペースなどについて心配する必要がなくなります。
SqlFiddle demoとコードは次のとおりです。
-- Split descriptions into sentences (could use period, exclamation point, or question mark)
-- Delete any sentences that, without whitespace, are like '%[0-9]employ%'
-- Join sentences back into descriptions
;with Splitter as (
select ID
, ltrim(rtrim(Data)) as Data
, cast(null as varchar(max)) as Sentence
, 0 as SentenceNumber
from Descriptions -- Your table here
union all
select ID
, case when Data like '%[.!?]%' then right(Data, len(Data) - patindex('%[.!?]%', Data)) else null end
, case when Data like '%[.!?]%' then left(Data, patindex('%[.!?]%', Data)) else Data end
, SentenceNumber + 1
from Splitter
where Data is not null
), Joiner as (
select ID
, cast('' as varchar(max)) as Data
, 0 as SentenceNumber
from Splitter
group by ID
union all
select j.ID
, j.Data +
-- Don't want "digit+employ" sentences, remove whitespace to search
case when replace(replace(replace(replace(s.Sentence, char(9), ''), char(10), ''), char(13), ''), char(32), '') like '%[0-9]employ%' then '' else s.Sentence end
, s.SentenceNumber
from Joiner j
join Splitter s on j.ID = s.ID and s.SentenceNumber = j.SentenceNumber + 1
)
-- Final Select
select a.ID, a.Data
from Joiner a
join (
-- Only get max SentenceNumber
select ID, max(SentenceNumber) as SentenceNumber
from Joiner
group by ID
) b on a.ID = b.ID and a.SentenceNumber = b.SentenceNumber
order by a.ID, a.SentenceNumber