From fc4547b412e28164af1bf8981234c6af959ccc0b Mon Sep 17 00:00:00 2001
From: Joel Klinghed <the_jk@spawned.biz>
Date: Tue, 13 Jun 2023 10:07:16 +0200
Subject: WIP

---
 utf/inc/utf8.hh | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 utf/inc/utf8.hh

(limited to 'utf/inc/utf8.hh')

diff --git a/utf/inc/utf8.hh b/utf/inc/utf8.hh
new file mode 100644
index 0000000..a3ea84a
--- /dev/null
+++ b/utf/inc/utf8.hh
@@ -0,0 +1,22 @@
+#ifndef UTF_UTF8_HH
+#define UTF_UTF8_HH
+
+#include "macros.hh"
+
+#include <cstdint>
+#include <string_view>
+
+namespace utf {
+
+/* Read one unicode codepoint from UTF-8 encoded data if possible.
+ * If successfull offset is incremented to point to next codepoint.
+ * Will fail:
+ * - not enough data is left in data given offset, returns NEED_MORE.
+ * - data is not valid UTF-8, this includes overlong encodings and
+ *   invalid unicode code points, returns INVALID.
+ */
+uint32_t HIDDEN read8(std::string_view data, std::size_t& offset);
+
+}  // namespace utf
+
+#endif  // UTF_UTF8_HH
-- 
cgit v1.2.3-70-g09d2