mirror of
https://github.com/postgres/postgres.git
synced 2025-07-30 11:03:19 +03:00
Add combining characters to unaccent.rules.
Strip certain classes of combining characters, so that accents encoded this way are removed. Author: Hugh Ranalli Discussion: https://postgr.es/m/15548-cef1b3f8de190d4f%40postgresql.org
This commit is contained in:
@ -31,6 +31,12 @@ SELECT unaccent('˃˖˗˜');
|
||||
>+-~
|
||||
(1 row)
|
||||
|
||||
SELECT unaccent('À'); -- Remove combining diacritical 0x0300
|
||||
unaccent
|
||||
----------
|
||||
A
|
||||
(1 row)
|
||||
|
||||
SELECT unaccent('unaccent', 'foobar');
|
||||
unaccent
|
||||
----------
|
||||
@ -55,6 +61,12 @@ SELECT unaccent('unaccent', '˃˖˗˜');
|
||||
>+-~
|
||||
(1 row)
|
||||
|
||||
SELECT unaccent('unaccent', 'À');
|
||||
unaccent
|
||||
----------
|
||||
A
|
||||
(1 row)
|
||||
|
||||
SELECT ts_lexize('unaccent', 'foobar');
|
||||
ts_lexize
|
||||
-----------
|
||||
@ -79,3 +91,9 @@ SELECT ts_lexize('unaccent', '˃˖˗˜');
|
||||
{>+-~}
|
||||
(1 row)
|
||||
|
||||
SELECT ts_lexize('unaccent', 'À');
|
||||
ts_lexize
|
||||
-----------
|
||||
{A}
|
||||
(1 row)
|
||||
|
||||
|
Reference in New Issue
Block a user