Created
September 19, 2022 16:40
-
-
Save yssymmt/463716c7a358940038b8ce359d6871f8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
drop table jumbo.aud06_mecab_vertical; | |
create table jumbo.aud06_mecab_vertical ( | |
docid integer, | |
seqno integer, | |
word varchar(10) character set unicode, | |
pos varchar(10) character set unicode, | |
norm varchar(10) character set unicode | |
) primary index(docid) | |
; | |
insert into jumbo.aud06_mecab_vertical | |
with src as ( | |
/*改行コードで別行にする*/ | |
select | |
outkey as docid, | |
token_nbr as seqno, | |
result_string | |
from table ( | |
regexp_split_to_table | |
(jumbo.aud04_mecab.docid, jumbo.aud04_mecab.docdesc, '\n','c') | |
returns (outkey integer, token_nbr integer, result_string varchar(1000) character set unicode) | |
) a1 | |
) | |
/*49文字: select max(char_length(result_string)) as aaa from src*/ | |
/*タブとカンマで列分解する*/ | |
select | |
docid, | |
seqno, | |
strtok(result_string, ' ',1) as word, | |
strtok((strtok(result_string, ' ', 2)), ',', 1) as pos, | |
/*strtok(result_string, ',', 3) as n3, */ | |
/*strtok(result_string, ',', 4) as n4, */ | |
/*strtok(result_string, ',', 5) as n5, */ | |
/*strtok(result_string, ',', 6) as n6, */ | |
strtok(result_string, ',', 7) as norm | |
/*strtok(result_string, ',', 8) as n8, */ | |
/*strtok(result_string, ',', 9) as n9, */ | |
from src | |
where result_string<>'EOS' | |
; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment