LibWebView: Add a helper to sanitize a user-provided URL

We currently implement several forms of this method across the Ladybird
chromes. As such, we see commits to add special URL handling that only
affects a single chrome. Instead, let's consolidate all special handling
in a single location for all chromes to make use of.

This method can handle resolving file:// URLs, falling back to a search
engine query, and validation against the Public Suffix List. These cases
were gathered from the various chromes.

Userland/Libraries/LibWebView/CMakeLists.txt

@@ -9,6 +9,7 @@ set(SOURCES
     RequestServerAdapter.cpp
     SourceHighlighter.cpp
     StylePropertiesModel.cpp
+    URL.cpp
     UserAgent.cpp
     ViewImplementation.cpp
     WebContentClient.cpp
@@ -40,7 +41,7 @@ set(GENERATED_SOURCES
 )
 
 serenity_lib(LibWebView webview)
-target_link_libraries(LibWebView PRIVATE LibCore LibGfx LibGUI LibIPC LibProtocol LibJS LibWeb LibSQL)
+target_link_libraries(LibWebView PRIVATE LibCore LibFileSystem LibGfx LibGUI LibIPC LibProtocol LibPublicSuffix LibJS LibWeb LibSQL)
 
 if (SERENITYOS)
     target_link_libraries(LibWebView PRIVATE LibFileSystemAccessClient)

Userland/Libraries/LibWebView/URL.cpp

@@ -0,0 +1,48 @@
+/*
+ * Copyright (c) 2023, Tim Flynn <trflynn89@serenityos.org>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <LibCore/System.h>
+#include <LibFileSystem/FileSystem.h>
+#include <LibPublicSuffix/URL.h>
+#include <LibWebView/URL.h>
+
+namespace WebView {
+
+Optional<URL> sanitize_url(StringView url, Optional<StringView> search_engine, AppendTLD append_tld)
+{
+    if (FileSystem::exists(url)) {
+        auto path = FileSystem::real_path(url);
+        if (path.is_error())
+            return {};
+
+        return URL::create_with_file_scheme(path.value().to_deprecated_string());
+    }
+
+    auto format_search_engine = [&]() -> Optional<URL> {
+        if (!search_engine.has_value())
+            return {};
+
+        return MUST(String::formatted(*search_engine, URL::percent_decode(url)));
+    };
+
+    String url_buffer;
+
+    if (append_tld == AppendTLD::Yes) {
+        // FIXME: Expand the list of top level domains.
+        if (!url.ends_with(".com"sv) && !url.ends_with(".net"sv) && !url.ends_with(".org"sv)) {
+            url_buffer = MUST(String::formatted("{}.com", url));
+            url = url_buffer;
+        }
+    }
+
+    auto result = PublicSuffix::absolute_url(url);
+    if (result.is_error())
+        return format_search_engine();
+
+    return result.release_value();
+}
+
+}

Userland/Libraries/LibWebView/URL.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (c) 2023, Tim Flynn <trflynn89@serenityos.org>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#pragma once
+
+#include <AK/Optional.h>
+#include <AK/StringView.h>
+#include <AK/URL.h>
+
+namespace WebView {
+
+enum class AppendTLD {
+    No,
+    Yes,
+};
+
+Optional<URL> sanitize_url(StringView, Optional<StringView> search_engine = {}, AppendTLD = AppendTLD::No);
+
+}