postgresql/contrib/unaccent/expected/unaccent.out

182 lines
2.5 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.

/*
* This test must be run in a database with UTF-8 encoding,
* because other encodings don't support all the characters used.
*/
SELECT getdatabaseencoding() <> 'UTF8'
AS skip_test \gset
\if :skip_test
\quit
\endif
CREATE EXTENSION unaccent;
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('1½'); -- math expression with whitespace
unaccent
----------
1 1/2
(1 row)
SELECT unaccent('〝'); -- quote
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 unaccent('unaccent', 'À');
unaccent
----------
A
(1 row)
SELECT unaccent('unaccent', '℃℉');
unaccent
----------
°C°F
(1 row)
SELECT unaccent('unaccent', '℗');
unaccent
----------
(P)
(1 row)
SELECT unaccent('unaccent', '1½');
unaccent
----------
1 1/2
(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)
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)
SELECT ts_lexize('unaccent', '1½');
ts_lexize
-----------
{"1 1/2"}
(1 row)
SELECT ts_lexize('unaccent', '〝');
ts_lexize
-----------
{"\""}
(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)