sqlite/ext/fts5/test/fts5umlaut.test
dan e89feee5c3 Add the "remove_diacritics=2" option to the unicode61 tokenizer in both FTS5
and FTS3/4.

FossilOrigin-Name: 06177f3f114b5d804b84c27ac843740282e2176fdf0f7a999feda0e1b624adec
2018-12-03 16:14:49 +00:00

66 lines
1.6 KiB
Plaintext

# 2014 June 17
#
# The author disclaims copyright to this source code. In place of
# a legal notice, here is a blessing:
#
# May you do good and not evil.
# May you find forgiveness for yourself and forgive others.
# May you share freely, never taking more than you give.
#
#*************************************************************************
# This file implements regression tests for SQLite library. The
# focus of this script is testing the FTS5 module.
#
source [file join [file dirname [info script]] fts5_common.tcl]
set testprefix fts5umlaut
# If SQLITE_ENABLE_FTS5 is not defined, omit this file.
ifcapable !fts5 {
finish_test
return
}
do_execsql_test 1.0 {
CREATE VIRTUAL TABLE t1 USING fts5(x);
CREATE VIRTUAL TABLE t2 USING fts5(
x,
tokenize="unicode61 remove_diacritics 2"
);
}
foreach {tn q res1 res2} {
1 "Hà Nội" 0 1
2 "Hà Noi" 1 1
3 "Ha Noi" 1 1
4 "Ha N\u1ed9i" 0 1
5 "Ha N\u006fi" 1 1
6 "Ha N\u006f\u0302i" 1 1
7 "Ha N\u006f\u0323\u0302i" 1 1
} {
do_execsql_test 1.$tn.1 {
DELETE FROM t1;
INSERT INTO t1(rowid, x) VALUES (1, 'Ha Noi');
SELECT count(*) FROM t1($q)
} $res1
do_execsql_test 1.$tn.2 {
DELETE FROM t1;
INSERT INTO t1(rowid, x) VALUES (1, $q);
SELECT count(*) FROM t1('Ha Noi')
} $res1
do_execsql_test 1.$tn.2 {
DELETE FROM t2;
INSERT INTO t2(rowid, x) VALUES (1, 'Ha Noi');
SELECT count(*) FROM t2($q)
} $res2
do_execsql_test 1.$tn.2 {
DELETE FROM t2;
INSERT INTO t2(rowid, x) VALUES (1, $q);
SELECT count(*) FROM t2('Ha Noi')
} $res2
}
finish_test