LibWeb: Implement ASCII case-insensitive matching

While DeprecatedString and StringView use ASCII case-insensitivity when
matching, String uses the Unicode rules, so in order to match the spec,
we need to *not* use `String::equals_ignoring_case()`.

This function needs to be used everywhere that the spec refers to
an "ASCII case-insensitive match".

2 files changed, 28 insertions, 0 deletions

diff --git a/Userland/Libraries/LibWeb/Infra/Strings.cpp b/Userland/Libraries/LibWeb/Infra/Strings.cpp
index 9a95fb9750..3f381c8426 100644
--- a/Userland/Libraries/LibWeb/Infra/Strings.cpp
+++ b/Userland/Libraries/LibWeb/Infra/Strings.cpp
@@ -2,10 +2,12 @@
  * Copyright (c) 2022, Linus Groh <linusg@serenityos.org>
  * Copyright (c) 2022, networkException <networkexception@serenityos.org>
  * Copyright (c) 2023, Kenneth Myhra <kennethmyhra@serenityos.org>
+ * Copyright (c) 2023, Sam Atkins <atkinssj@serenityos.org>
  *
  * SPDX-License-Identifier: BSD-2-Clause
  */
 
+#include <AK/CharacterTypes.h>
 #include <AK/DeprecatedString.h>
 #include <AK/Utf16View.h>
 #include <AK/Utf8View.h>
@@ -14,6 +16,30 @@
 
 namespace Web::Infra {
 
+// https://infra.spec.whatwg.org/#ascii-case-insensitive
+bool is_ascii_case_insensitive_match(StringView a, StringView b)
+{
+    // A string A is an ASCII case-insensitive match for a string B,
+    // if the ASCII lowercase of A is the ASCII lowercase of B.
+
+    Utf8View a_view { a };
+    Utf8View b_view { b };
+
+    if (a_view.length() != b_view.length())
+        return false;
+
+    auto b_iterator = b_view.begin();
+    for (auto a_char : a_view) {
+        auto b_char = *b_iterator;
+        ++b_iterator;
+
+        if (to_ascii_lowercase(a_char) != to_ascii_lowercase(b_char))
+            return false;
+    }
+
+    return true;
+}
+
 // https://infra.spec.whatwg.org/#strip-and-collapse-ascii-whitespace
 DeprecatedString strip_and_collapse_whitespace(StringView string)
 {
diff --git a/Userland/Libraries/LibWeb/Infra/Strings.h b/Userland/Libraries/LibWeb/Infra/Strings.h
index a3f6fa3d8f..f44f6d9865 100644
--- a/Userland/Libraries/LibWeb/Infra/Strings.h
+++ b/Userland/Libraries/LibWeb/Infra/Strings.h
@@ -2,6 +2,7 @@
  * Copyright (c) 2022, Linus Groh <linusg@serenityos.org>
  * Copyright (c) 2022, networkException <networkexception@serenityos.org>
  * Copyright (c) 2023, Kenneth Myhra <kennethmyhra@serenityos.org>
+ * Copyright (c) 2023, Sam Atkins <atkinssj@serenityos.org>
  *
  * SPDX-License-Identifier: BSD-2-Clause
  */
@@ -12,6 +13,7 @@
 
 namespace Web::Infra {
 
+bool is_ascii_case_insensitive_match(StringView a, StringView b);
 DeprecatedString strip_and_collapse_whitespace(StringView string);
 bool is_code_unit_prefix(StringView potential_prefix, StringView input);
 ErrorOr<String> convert_to_scalar_value_string(StringView string);