AK: Add Utf16View::find_code_unit_offset(_ignoring_case)

Author: https://github.com/gmta
Commit: cc0a28ee7d
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/5067
Reviewed-by: https://github.com/tcl3
Reviewed-by: https://github.com/trflynn89

AK/Utf16View.cpp

@@ -281,6 +281,32 @@ Utf16View Utf16View::unicode_substring_view(size_t code_point_offset, size_t cod
     VERIFY_NOT_REACHED();
 }
 
+Optional<size_t> Utf16View::find_code_unit_offset(Utf16View const& needle, size_t start_offset) const
+{
+    return m_code_units.index_of(needle.m_code_units, start_offset);
+}
+
+Optional<size_t> Utf16View::find_code_unit_offset_ignoring_case(Utf16View const& needle, size_t start_offset) const
+{
+    Checked maximum_offset { start_offset };
+    maximum_offset += needle.length_in_code_units();
+    if (maximum_offset.has_overflow() || maximum_offset.value() > length_in_code_units())
+        return {};
+
+    if (needle.is_empty())
+        return start_offset;
+
+    size_t index = start_offset;
+    while (index <= length_in_code_units() - needle.length_in_code_units()) {
+        Utf16View const slice { m_code_units.slice(index, needle.length_in_code_units()) };
+        if (slice.equals_ignoring_case(needle))
+            return index;
+        index += slice.begin().length_in_code_units();
+    }
+
+    return {};
+}
+
 bool Utf16View::starts_with(Utf16View const& needle) const
 {
     if (needle.is_empty())

AK/Utf16View.h

@@ -134,6 +134,9 @@ public:
     Utf16View unicode_substring_view(size_t code_point_offset, size_t code_point_length) const;
     Utf16View unicode_substring_view(size_t code_point_offset) const { return unicode_substring_view(code_point_offset, length_in_code_points() - code_point_offset); }
 
+    Optional<size_t> find_code_unit_offset(Utf16View const& needle, size_t start_offset = 0) const;
+    Optional<size_t> find_code_unit_offset_ignoring_case(Utf16View const& needle, size_t start_offset = 0) const;
+
     bool starts_with(Utf16View const&) const;
     bool is_code_unit_less_than(Utf16View const& other) const;
 

Tests/AK/TestUtf16.cpp

@@ -367,3 +367,36 @@ TEST_CASE(starts_with)
     EXPECT(!emoji.starts_with(u"a"));
     EXPECT(!emoji.starts_with(u"🙃"));
 }
+
+TEST_CASE(find_code_unit_offset)
+{
+    auto conversion_result = MUST(AK::utf8_to_utf16("😀foo😀bar"sv));
+    Utf16View const view { conversion_result };
+
+    EXPECT_EQ(0u, view.find_code_unit_offset(u"").value());
+    EXPECT_EQ(4u, view.find_code_unit_offset(u"", 4).value());
+    EXPECT(!view.find_code_unit_offset(u"", 16).has_value());
+
+    EXPECT_EQ(0u, view.find_code_unit_offset(u"😀").value());
+    EXPECT_EQ(5u, view.find_code_unit_offset(u"😀", 1).value());
+    EXPECT_EQ(2u, view.find_code_unit_offset(u"foo").value());
+    EXPECT_EQ(7u, view.find_code_unit_offset(u"bar").value());
+
+    EXPECT(!view.find_code_unit_offset(u"baz").has_value());
+}
+
+TEST_CASE(find_code_unit_offset_ignoring_case)
+{
+    auto conversion_result = MUST(AK::utf8_to_utf16("😀Foo😀Bar"sv));
+    Utf16View const view { conversion_result };
+
+    EXPECT_EQ(0u, view.find_code_unit_offset_ignoring_case(u"").value());
+    EXPECT_EQ(4u, view.find_code_unit_offset_ignoring_case(u"", 4).value());
+    EXPECT(!view.find_code_unit_offset_ignoring_case(u"", 16).has_value());
+
+    EXPECT_EQ(0u, view.find_code_unit_offset_ignoring_case(u"😀").value());
+    EXPECT_EQ(5u, view.find_code_unit_offset_ignoring_case(u"😀", 1).value());
+    EXPECT_EQ(2u, view.find_code_unit_offset_ignoring_case(u"foO").value());
+    EXPECT_EQ(7u, view.find_code_unit_offset_ignoring_case(u"baR").value());
+    EXPECT(!view.find_code_unit_offset_ignoring_case(u"baz").has_value());
+}