2011-02-13 20:06:41 -05:00
|
|
|
|
CREATE EXTENSION unaccent;
|
2009-08-18 06:34:39 -04:00
|
|
|
|
|
2009-08-18 12:00:50 -04:00
|
|
|
|
-- must have a UTF8 database
|
|
|
|
|
|
SELECT getdatabaseencoding();
|
|
|
|
|
|
|
2019-01-02 12:36:05 -05:00
|
|
|
|
SET client_encoding TO 'UTF8';
|
2009-08-18 06:34:39 -04:00
|
|
|
|
|
|
|
|
|
|
SELECT unaccent('foobar');
|
2019-01-02 12:36:05 -05:00
|
|
|
|
SELECT unaccent('ёлка');
|
|
|
|
|
|
SELECT unaccent('ЁЖИК');
|
2019-01-10 00:10:21 -05:00
|
|
|
|
SELECT unaccent('˃˖˗˜');
|
2019-02-01 09:23:01 -05:00
|
|
|
|
SELECT unaccent('À'); -- Remove combining diacritical 0x0300
|
2022-07-05 03:17:51 -04:00
|
|
|
|
SELECT unaccent('℃℉'); -- degree signs
|
|
|
|
|
|
SELECT unaccent('℗'); -- sound recording copyright
|
2009-08-18 06:34:39 -04:00
|
|
|
|
|
|
|
|
|
|
SELECT unaccent('unaccent', 'foobar');
|
2019-01-02 12:36:05 -05:00
|
|
|
|
SELECT unaccent('unaccent', 'ёлка');
|
|
|
|
|
|
SELECT unaccent('unaccent', 'ЁЖИК');
|
2019-01-10 00:10:21 -05:00
|
|
|
|
SELECT unaccent('unaccent', '˃˖˗˜');
|
2019-02-01 09:23:01 -05:00
|
|
|
|
SELECT unaccent('unaccent', 'À');
|
2022-07-05 03:17:51 -04:00
|
|
|
|
SELECT unaccent('unaccent', '℃℉');
|
|
|
|
|
|
SELECT unaccent('unaccent', '℗');
|
2009-08-18 06:34:39 -04:00
|
|
|
|
|
|
|
|
|
|
SELECT ts_lexize('unaccent', 'foobar');
|
2019-01-02 12:36:05 -05:00
|
|
|
|
SELECT ts_lexize('unaccent', 'ёлка');
|
|
|
|
|
|
SELECT ts_lexize('unaccent', 'ЁЖИК');
|
2019-01-10 00:10:21 -05:00
|
|
|
|
SELECT ts_lexize('unaccent', '˃˖˗˜');
|
2019-02-01 09:23:01 -05:00
|
|
|
|
SELECT ts_lexize('unaccent', 'À');
|
2022-07-05 03:17:51 -04:00
|
|
|
|
SELECT ts_lexize('unaccent', '℃℉');
|
|
|
|
|
|
SELECT ts_lexize('unaccent', '℗');
|
|
|
|
|
|
|
|
|
|
|
|
-- Controversial case. Black-Letter Capital H (U+210C) is translated by
|
|
|
|
|
|
-- Latin-ASCII.xml as 'x', but it should be 'H'.
|
|
|
|
|
|
SELECT unaccent('ℌ');
|