From b50f472e65c0ffca5d485049325caa51298daa1a Mon Sep 17 00:00:00 2001 From: fab Date: Sun, 2 Dec 2018 00:46:46 +0000 Subject: 1 bug fix and sorting out my own confusion: uw_Basis_char is already a codepoint, NOT the "serialized" utf8 --- tests/utf8.ur | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tests') diff --git a/tests/utf8.ur b/tests/utf8.ur index 07ac9c3d..e7c7fd40 100644 --- a/tests/utf8.ur +++ b/tests/utf8.ur @@ -100,7 +100,10 @@ fun strcats () : transaction page = {test_cat_and_len 5 "àà" "áá" "ààáá" 4} {test_cat_and_len 6 "" "áá" "áá" 2} {test_cat_and_len 7 "àà" "" "àà" 2} - {test_cat_and_len 8 "函數" "ãã" "函數ãã" 4} + {test_cat_and_len 8 "函數" "ãã" "函數ãã" 4} + {test_cat_and_len 9 "ç" "ã" "çã" 2} + {test_cat_and_len 10 (show (strsub "ç" 0)) (show (strsub "ã" 0)) "çã" 2} + {test_cat_and_len 11 (show (chr 231)) (show (chr 227)) "çã" 2} end -- cgit v1.2.3