postgresql/contrib/unaccent/expected/unaccent.out
Michael Paquier e1c1d5444e Update unaccent rules with release 34 of CLDR for Latin-ASCII.xml
This has required an update of the python script generating the rules,
as its format has changed in release 29.  This release has also added
new punctuation and symbols, and a new set of rules has been generated
to include them.  The way to find newest versions of Latin-ASCII gets
also more clearly documented.

Author: Hugh Ranalli, Michael Paquier
Discussion: https://postgr.es/m/15548-cef1b3f8de190d4f@postgresql.org
2019-01-10 14:10:21 +09:00

82 lines
1.1 KiB
Plaintext

CREATE EXTENSION unaccent;
-- must have a UTF8 database
SELECT getdatabaseencoding();
getdatabaseencoding
---------------------
UTF8
(1 row)
SET client_encoding TO 'UTF8';
SELECT unaccent('foobar');
unaccent
----------
foobar
(1 row)
SELECT unaccent('ёлка');
unaccent
----------
елка
(1 row)
SELECT unaccent('ЁЖИК');
unaccent
----------
ЕЖИК
(1 row)
SELECT unaccent('˃˖˗˜');
unaccent
----------
>+-~
(1 row)
SELECT unaccent('unaccent', 'foobar');
unaccent
----------
foobar
(1 row)
SELECT unaccent('unaccent', 'ёлка');
unaccent
----------
елка
(1 row)
SELECT unaccent('unaccent', 'ЁЖИК');
unaccent
----------
ЕЖИК
(1 row)
SELECT unaccent('unaccent', '˃˖˗˜');
unaccent
----------
>+-~
(1 row)
SELECT ts_lexize('unaccent', 'foobar');
ts_lexize
-----------
(1 row)
SELECT ts_lexize('unaccent', 'ёлка');
ts_lexize
-----------
{елка}
(1 row)
SELECT ts_lexize('unaccent', 'ЁЖИК');
ts_lexize
-----------
{ЕЖИК}
(1 row)
SELECT ts_lexize('unaccent', '˃˖˗˜');
ts_lexize
-----------
{>+-~}
(1 row)