Ce n'est pas une solution, mais une solution de contournement de modélisation de données
- divisez les URL en composants {protocol,hostname,pathname}.
- Vous pouvez désormais utiliser des correspondances exactes pour joindre la partie du nom d'hôte, en évitant le % de tête dans la correspondance de regex.
- la vue est destinée à démontrer que la full_url peut être reconstruite si nécessaire.
La mise à jour peut probablement prendre quelques minutes.
SET search_path='tmp';
DROP TABLE urls CASCADE;
CREATE TABLE urls
( id SERIAL NOT NULL PRIMARY KEY
, full_url varchar
, proto varchar
, hostname varchar
, pathname varchar
);
INSERT INTO urls(full_url) VALUES
( 'ftp://www.myhost.com/secret.tgz' )
,( 'http://www.myhost.com/robots.txt' )
,( 'http://www.myhost.com/index.php' )
,( 'https://www.myhost.com/index.php' )
,( 'http://www.myhost.com/subdir/index.php' )
,( 'https://www.myhost.com/subdir/index.php' )
,( 'http://www.hishost.com/index.php' )
,( 'https://www.hishost.com/index.php' )
,( 'http://www.herhost.com/index.php' )
,( 'https://www.herhost.com/index.php' )
;
UPDATE urls
SET proto = split_part(full_url, '://' , 1)
, hostname = split_part(full_url, '://' , 2)
;
UPDATE urls
SET pathname = substr(hostname, 1+strpos(hostname, '/' ))
, hostname = split_part(hostname, '/' , 1)
;
-- the full_url field is now redundant: we can drop it
ALTER TABLE urls
DROP column full_url
;
-- and we could always reconstruct the full_url from its components.
CREATE VIEW vurls AS (
SELECT id
, proto || '://' || hostname || '/' || pathname AS full_url
, proto
, hostname
, pathname
FROM urls
);
SELECT * FROM urls;
;
SELECT * FROM vurls;
;
SORTIE :
INSERT 0 10
UPDATE 10
UPDATE 10
ALTER TABLE
CREATE VIEW
id | proto | hostname | pathname
----+-------+-----------------+------------------
1 | ftp | www.myhost.com | secret.tgz
2 | http | www.myhost.com | robots.txt
3 | http | www.myhost.com | index.php
4 | https | www.myhost.com | index.php
5 | http | www.myhost.com | subdir/index.php
6 | https | www.myhost.com | subdir/index.php
7 | http | www.hishost.com | index.php
8 | https | www.hishost.com | index.php
9 | http | www.herhost.com | index.php
10 | https | www.herhost.com | index.php
(10 rows)
id | full_url | proto | hostname | pathname
----+-----------------------------------------+-------+-----------------+------------------
1 | ftp://www.myhost.com/secret.tgz | ftp | www.myhost.com | secret.tgz
2 | http://www.myhost.com/robots.txt | http | www.myhost.com | robots.txt
3 | http://www.myhost.com/index.php | http | www.myhost.com | index.php
4 | https://www.myhost.com/index.php | https | www.myhost.com | index.php
5 | http://www.myhost.com/subdir/index.php | http | www.myhost.com | subdir/index.php
6 | https://www.myhost.com/subdir/index.php | https | www.myhost.com | subdir/index.php
7 | http://www.hishost.com/index.php | http | www.hishost.com | index.php
8 | https://www.hishost.com/index.php | https | www.hishost.com | index.php
9 | http://www.herhost.com/index.php | http | www.herhost.com | index.php
10 | https://www.herhost.com/index.php | https | www.herhost.com | index.php
(10 rows)