AK+LibUnicode: Add Unicode::create_unicode_url

This is a workaround for the fact that AK::URLParser can't call into
LibUnicode directly.

AK/URLParser.cpp

@@ -603,7 +603,8 @@ static Optional<URL::Host> parse_host(StringView input, bool is_opaque = false)
     // FIXME: 4. Let domain be the result of running UTF-8 decode without BOM on the percent-decoding of input.
     auto domain = URL::percent_decode(input);
 
-    // FIXME: 5. Let asciiDomain be the result of running domain to ASCII on domain.
+    // NOTE: This is handled in Unicode::create_unicode_url, to work around the fact that we can't call into LibUnicode here
+    // FIXME: 5. Let asciiDomain be the result of running domain to ASCII with domain and false.
     // FIXME: 6. If asciiDomain is failure, then return failure.
     auto ascii_domain_or_error = String::from_deprecated_string(domain);
     if (ascii_domain_or_error.is_error())

Userland/Libraries/LibUnicode/CMakeLists.txt

@@ -10,6 +10,7 @@ set(SOURCES
     Segmentation.cpp
     String.cpp
     UnicodeUtils.cpp
+    URL.cpp
     ${UNICODE_DATA_SOURCES}
 )
 set(GENERATED_SOURCES ${CURRENT_LIB_GENERATED})

Userland/Libraries/LibUnicode/URL.cpp

@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2023, Simon Wanner <simon@skyrising.xyz>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <LibUnicode/IDNA.h>
+#include <LibUnicode/URL.h>
+
+namespace Unicode {
+
+// https://url.spec.whatwg.org/#concept-domain-to-ascii
+static ErrorOr<String> domain_to_ascii(StringView domain, bool be_strict)
+{
+    // 1. Let result be the result of running Unicode ToASCII with domain_name set to domain, UseSTD3ASCIIRules set to beStrict, CheckHyphens set to false, CheckBidi set to true, CheckJoiners set to true, Transitional_Processing set to false, and VerifyDnsLength set to beStrict. [UTS46]
+    // 2. If result is a failure value, domain-to-ASCII validation error, return failure.
+    Unicode::IDNA::ToAsciiOptions const options {
+        Unicode::IDNA::CheckHyphens::No,
+        Unicode::IDNA::CheckBidi::Yes,
+        Unicode::IDNA::CheckJoiners::Yes,
+        be_strict ? Unicode::IDNA::UseStd3AsciiRules::Yes : Unicode::IDNA::UseStd3AsciiRules::No,
+        Unicode::IDNA::TransitionalProcessing::No,
+        be_strict ? Unicode::IDNA::VerifyDnsLength::Yes : Unicode::IDNA::VerifyDnsLength::No
+    };
+    auto result = TRY(Unicode::IDNA::to_ascii(Utf8View(domain), options));
+
+    // 3. If result is the empty string, domain-to-ASCII validation error, return failure.
+    if (result.is_empty())
+        return Error::from_string_literal("Empty domain");
+
+    // 4. Return result.
+    return result;
+}
+
+// https://url.spec.whatwg.org/#concept-host-parser
+ErrorOr<URL> create_unicode_url(String const& url_string)
+{
+    // NOTE: 1.-4. are implemented in URLParser::parse_host
+
+    URL url = url_string;
+    if (!url.is_valid() || !url.host().has<String>())
+        return url;
+
+    auto& domain = url.host().get<String>();
+    if (domain.is_empty())
+        return url;
+
+    // 5. Let asciiDomain be the result of running domain to ASCII with domain and false.
+    // 6. If asciiDomain is failure, then return failure.
+    auto ascii_domain = TRY(domain_to_ascii(domain.bytes_as_string_view(), false));
+
+    // FIXME: Reimplement 7. or call into URLParser::parse_host using ascii_domain (8. & 9. do not apply)
+    url.set_host(ascii_domain);
+    return url;
+}
+
+}

Userland/Libraries/LibUnicode/URL.h

@@ -0,0 +1,16 @@
+/*
+ * Copyright (c) 2023, Simon Wanner <simon@skyrising.xyz>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#pragma once
+
+#include <AK/String.h>
+#include <AK/URL.h>
+
+namespace Unicode {
+
+ErrorOr<URL> create_unicode_url(String const&);
+
+}