From 918d015302a004755ce0cf4968793cdf6a61bca8 Mon Sep 17 00:00:00 2001 From: Roland Reichwein Date: Mon, 25 Jan 2021 18:54:25 +0100 Subject: Add first working conversion UTF-8 -> UTF-16 --- src/test-unicode.cpp | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'src') diff --git a/src/test-unicode.cpp b/src/test-unicode.cpp index 4576d06..41fcd20 100644 --- a/src/test-unicode.cpp +++ b/src/test-unicode.cpp @@ -4,14 +4,23 @@ #include -//#include +#include BOOST_AUTO_TEST_CASE(utf8_to_utf16) { std::u8string u8{u8"ascii string1"}; - //std::u16string u16{unicode::utf8_to_utf16(u8)}; + std::u16string u16{unicode::utf8_to_utf16(u8)}; - //BOOST_CHECK_EQUAL(u16, u"ascii string1"); + BOOST_CHECK(u16 == u"ascii string1"); } +// TODO: +// invalid bytes +// an unexpected continuation byte +// a non-continuation byte before the end of the character +// the string ending before the end of the character (which can happen in simple string truncation) +// an overlong encoding +// a sequence that decodes to an invalid code point +// +// high and low surrogate halves used by UTF-16 (U+D800 through U+DFFF) and code points not encodable by UTF-16 (those after U+10FFFF) -- cgit v1.2.3