[libc-commits] [libc] [libc] Wchar Stringconverter (PR #146388)

[via libc-commits]

================
@@ -0,0 +1,167 @@
+//===-- Unittests for StringConverter class -------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "hdr/errno_macros.h"
+#include "hdr/types/char32_t.h"
+#include "hdr/types/char8_t.h"
+#include "src/__support/error_or.h"
+#include "src/__support/wchar/mbstate.h"
+#include "src/__support/wchar/string_converter.h"
+#include "test/UnitTest/Test.h"
+
+TEST(LlvmLibcStringConverterTest, UTF8To32) {
+  // first 4 bytes are clown emoji, then next 3 are sigma symbol
+  const char *src = "\xF0\x9F\xA4\xA1\xE2\x88\x91";
+  LIBC_NAMESPACE::internal::mbstate state;
+  LIBC_NAMESPACE::internal::StringConverter<char8_t> sc(
+      reinterpret_cast<const char8_t *>(src), &state);
+
+  auto res = sc.popUTF32();
+  ASSERT_TRUE(res.has_value());
+  ASSERT_EQ(static_cast<int>(res.value()), 0x1f921);
+
+  res = sc.popUTF32();
+  ASSERT_TRUE(res.has_value());
+  ASSERT_EQ(static_cast<int>(res.value()), 0x2211);
+
+  res = sc.popUTF32();
+  ASSERT_TRUE(res.has_value());
+  ASSERT_EQ(static_cast<int>(res.value()), 0);
+
+  res = sc.popUTF32();
+  ASSERT_FALSE(res.has_value());
+  ASSERT_EQ(res.error(), -1);
+}
+
+TEST(LlvmLibcStringConverterTest, UTF32To8) {
+  const wchar_t *src = L"\x1f921\x2211";
----------------
sribee8 wrote:

what are these wide characters

https://github.com/llvm/llvm-project/pull/146388