1 files changed, 34 insertions, 0 deletions

diff --git a/contrib/unaccent/sql/unaccent.sql b/contrib/unaccent/sql/unaccent.sql
new file mode 100644
index 0000000..3fc0c70
--- /dev/null
+++ b/contrib/unaccent/sql/unaccent.sql
@@ -0,0 +1,34 @@
+CREATE EXTENSION unaccent;
+
+-- must have a UTF8 database
+SELECT getdatabaseencoding();
+
+SET client_encoding TO 'UTF8';
+
+SELECT unaccent('foobar');
+SELECT unaccent('ёлка');
+SELECT unaccent('ЁЖИК');
+SELECT unaccent('˃˖˗˜');
+SELECT unaccent('À');  -- Remove combining diacritical 0x0300
+SELECT unaccent('℃℉'); -- degree signs
+SELECT unaccent('℗'); -- sound recording copyright
+
+SELECT unaccent('unaccent', 'foobar');
+SELECT unaccent('unaccent', 'ёлка');
+SELECT unaccent('unaccent', 'ЁЖИК');
+SELECT unaccent('unaccent', '˃˖˗˜');
+SELECT unaccent('unaccent', 'À');
+SELECT unaccent('unaccent', '℃℉');
+SELECT unaccent('unaccent', '℗');
+
+SELECT ts_lexize('unaccent', 'foobar');
+SELECT ts_lexize('unaccent', 'ёлка');
+SELECT ts_lexize('unaccent', 'ЁЖИК');
+SELECT ts_lexize('unaccent', '˃˖˗˜');
+SELECT ts_lexize('unaccent', 'À');
+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');