From 6524748e66c87ec899b6e24d02508ddd31265c17 Mon Sep 17 00:00:00 2001 From: Urban Müller Date: Mon, 13 Jul 2026 14:44:41 +0200 Subject: combining chars not well defined after blanks and cause more trouble after word split --- test/it.t | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'test') diff --git a/test/it.t b/test/it.t index dc60727..d4225f4 100755 --- a/test/it.t +++ b/test/it.t @@ -437,8 +437,6 @@ is(it::substr_replace('abc', 'xyz', 0, 2), substr_replace('abc', 'xyz', 0, 2), ' is(it::substr_replace('abc', 'xyz', 0, 10), substr_replace('abc', 'xyz', 0, 10), 'it::substr_replace replacing past end of haystack'); is(it::substr_replace('abcdefgh', 'xyz', 10, 4), substr_replace('abcdefgh', 'xyz', 10, 4), 'it::substr_replace outside of string'); -is(grapheme_strlen("\xc1"), null, "need grapheme_strlen side effect for any2utf8"); - is(it::any2utf8('Meier'), 'Meier', "it::any2utf8 ascii input"); is(it::any2utf8('Müller'), 'Müller', "it::any2utf8 utf8 input"); is(it::any2utf8('Aslı'), 'Aslı', "it::any2utf8 utf8 non-latin1 input"); @@ -481,6 +479,8 @@ foreach ([ 'a' => 'ä', 'e' => 'ë', 'i' => 'ï', 'o' => 'ö', 'u' => 'ü' ] as } is(it::any2utf8("\x65\xcc\x81"), "é", "it::any2utf8 convert to normal form C"); +is(it::any2utf8("\xcc\xb8x"), "x", "bad (un-nomalizable) combining char"); +is(it::any2utf8(" \xcc\xb8x"), " x", "bad (un-normalizable) combining char"); foreach ([$dummy, false, true, null, 1, "a", "Ä", "/", []] as $var) is(it::json_decode(it::json_encode($var)), $var); -- cgit v1.2.3