AK: Add Utf8View::code_point_offset_of()

Author: https://github.com/gmta
Commit: 6f926e6977
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/5067
Reviewed-by: https://github.com/tcl3
Reviewed-by: https://github.com/trflynn89

AK/Utf8View.cpp

@@ -30,6 +30,18 @@ Utf8CodePointIterator Utf8View::iterator_at_byte_offset_without_validation(size_
     return Utf8CodePointIterator { reinterpret_cast<u8 const*>(m_string.characters_without_null_termination()) + byte_offset, m_string.length() - byte_offset };
 }
 
+size_t Utf8View::code_point_offset_of(size_t byte_offset) const
+{
+    VERIFY(byte_offset < byte_length());
+    size_t code_point_offset = 0;
+    for (auto it = begin(); !it.done(); ++it) {
+        if (it.m_ptr > begin_ptr() + byte_offset)
+            break;
+        ++code_point_offset;
+    }
+    return code_point_offset - 1;
+}
+
 size_t Utf8View::byte_offset_of(size_t code_point_offset) const
 {
     size_t byte_offset = 0;

AK/Utf8View.h

@@ -96,6 +96,8 @@ public:
     unsigned char const* bytes() const { return begin_ptr(); }
     size_t byte_length() const { return m_string.length(); }
 
+    size_t code_point_offset_of(size_t code_unit_offset) const;
+
     [[nodiscard]] size_t byte_offset_of(Utf8CodePointIterator const& it) const
     {
         VERIFY(it.m_ptr >= begin_ptr());

Tests/AK/TestUtf8.cpp

@@ -333,3 +333,16 @@ TEST_CASE(for_each_split_view)
     EXPECT_EQ(gather(SplitBehavior::KeepEmpty | SplitBehavior::KeepTrailingSeparator),
         Vector({ "."sv, "."sv, "."sv, "Well."sv, "."sv, "hello."sv, "friends!."sv, "."sv, "."sv, ""sv }));
 }
+
+TEST_CASE(code_point_offset_of)
+{
+    Utf8View view { "😭foo"sv };
+
+    EXPECT_EQ(0u, view.code_point_offset_of(0));
+    EXPECT_EQ(0u, view.code_point_offset_of(1));
+    EXPECT_EQ(0u, view.code_point_offset_of(2));
+    EXPECT_EQ(0u, view.code_point_offset_of(3));
+    EXPECT_EQ(1u, view.code_point_offset_of(4));
+    EXPECT_EQ(2u, view.code_point_offset_of(5));
+    EXPECT_EQ(3u, view.code_point_offset_of(6));
+}