AK+LibUnicode: Provide Unicode-aware String case transformations

Since AK can't refer to LibUnicode directly, the strategy here is that
if you need case transformations, you can link LibUnicode and receive
them. If you try to use either of these methods without linking it, then
you'll of course get a linker error (note we don't do any fallbacks to
e.g. ASCII case transformations). If you don't need these methods, you
don't have to link LibUnicode.

AK/String.h

@@ -9,6 +9,7 @@
 #include <AK/Concepts.h>
 #include <AK/Format.h>
 #include <AK/Forward.h>
+#include <AK/Optional.h>
 #include <AK/RefCounted.h>
 #include <AK/Span.h>
 #include <AK/StringView.h>
@@ -43,6 +44,11 @@ public:
     // Creates a new String from a sequence of UTF-8 encoded code points.
     static ErrorOr<String> from_utf8(StringView);
 
+    // Creates a new String by transforming this String to lower- or uppercase. Using these methods
+    // require linking LibUnicode into your application.
+    ErrorOr<String> to_lowercase(Optional<StringView> const& locale = {}) const;
+    ErrorOr<String> to_uppercase(Optional<StringView> const& locale = {}) const;
+
     // Creates a substring with a deep copy of the specified data window.
     ErrorOr<String> substring_from_byte_offset(size_t start, size_t byte_count) const;
 

Meta/Lagom/CMakeLists.txt

@@ -558,6 +558,7 @@ if (BUILD_LAGOM)
         foreach(source ${AK_TEST_SOURCES})
             lagom_test(${source} WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/../../Tests/AK)
         endforeach()
+        target_link_libraries(TestString LibUnicode)
 
         # LibAudio
         file(GLOB LIBAUDIO_TEST_SOURCES CONFIGURE_DEPENDS "../../Tests/LibAudio/*.cpp")

Tests/AK/CMakeLists.txt

@@ -86,3 +86,5 @@ set(AK_TEST_SOURCES
 foreach(source IN LISTS AK_TEST_SOURCES)
     serenity_test("${source}" AK)
 endforeach()
+
+target_link_libraries(TestString PRIVATE LibUnicode)

Tests/AK/TestString.cpp

@@ -107,3 +107,41 @@ TEST_CASE(replace)
         EXPECT_EQ(result, "anon@courage:~"sv);
     }
 }
+
+TEST_CASE(to_lowercase)
+{
+    {
+        auto string = MUST(String::from_utf8("Aa"sv));
+        auto result = MUST(string.to_lowercase());
+        EXPECT_EQ(result, "aa"sv);
+    }
+    {
+        auto string = MUST(String::from_utf8("Ωω"sv));
+        auto result = MUST(string.to_lowercase());
+        EXPECT_EQ(result, "ωω"sv);
+    }
+    {
+        auto string = MUST(String::from_utf8("İi̇"sv));
+        auto result = MUST(string.to_lowercase());
+        EXPECT_EQ(result, "i̇i̇"sv);
+    }
+}
+
+TEST_CASE(to_uppercase)
+{
+    {
+        auto string = MUST(String::from_utf8("Aa"sv));
+        auto result = MUST(string.to_uppercase());
+        EXPECT_EQ(result, "AA"sv);
+    }
+    {
+        auto string = MUST(String::from_utf8("Ωω"sv));
+        auto result = MUST(string.to_uppercase());
+        EXPECT_EQ(result, "ΩΩ"sv);
+    }
+    {
+        auto string = MUST(String::from_utf8("ʼn"sv));
+        auto result = MUST(string.to_uppercase());
+        EXPECT_EQ(result, "ʼN"sv);
+    }
+}

Userland/Libraries/LibUnicode/CMakeLists.txt

@@ -5,6 +5,7 @@ set(SOURCES
     CurrencyCode.cpp
     Emoji.cpp
     Normalize.cpp
+    String.cpp
     UnicodeUtils.cpp
     ${UNICODE_DATA_SOURCES}
 )

Userland/Libraries/LibUnicode/String.cpp

@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2023, Tim Flynn <trflynn89@serenityos.org>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <AK/String.h>
+#include <AK/StringBuilder.h>
+#include <LibUnicode/UnicodeUtils.h>
+
+// This file contains definitions of AK::String methods which require UCD data.
+
+namespace AK {
+
+ErrorOr<String> String::to_lowercase(Optional<StringView> const& locale) const
+{
+    StringBuilder builder;
+    TRY(Unicode::Detail::build_lowercase_string(code_points(), builder, locale));
+    return builder.to_string();
+}
+
+ErrorOr<String> String::to_uppercase(Optional<StringView> const& locale) const
+{
+    StringBuilder builder;
+    TRY(Unicode::Detail::build_uppercase_string(code_points(), builder, locale));
+    return builder.to_string();
+}
+
+}