postgresql/contrib/unaccent/expected/unaccent.out
Jeff Davis f413941f41 Fix t_isspace(), etc., when datlocprovider=i and datctype=C.
Check whether the datctype is C to determine whether t_isspace() and
related functions use isspace() or iswspace().

Previously, t_isspace() checked whether the database default collation
was C; which is incorrect when the default collation uses the ICU
provider.

Discussion: https://postgr.es/m/79e4354d9eccfdb00483146a6b9f6295202e7890.camel@j-davis.com
Reviewed-by: Peter Eisentraut
Backpatch-through: 15
2023-03-17 12:08:46 -07:00

144 lines
2.0 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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('À'); -- Remove combining diacritical 0x0300
unaccent
----------
A
(1 row)
SELECT unaccent('℃℉'); -- degree signs
unaccent
----------
°C°F
(1 row)
SELECT unaccent('℗'); -- sound recording copyright
unaccent
----------
(P)
(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 unaccent('unaccent', 'À');
unaccent
----------
A
(1 row)
SELECT unaccent('unaccent', '℃℉');
unaccent
----------
°C°F
(1 row)
SELECT unaccent('unaccent', '℗');
unaccent
----------
(P)
(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)
SELECT ts_lexize('unaccent', 'À');
ts_lexize
-----------
{A}
(1 row)
SELECT ts_lexize('unaccent', '℃℉');
ts_lexize
-----------
{°C°F}
(1 row)
SELECT ts_lexize('unaccent', '℗');
ts_lexize
-----------
{(P)}
(1 row)
-- Controversial case. Black-Letter Capital H (U+210C) is translated by
-- Latin-ASCII.xml as 'x', but it should be 'H'.
SELECT unaccent('');
unaccent
----------
x
(1 row)