LibWeb: Make the atob JS function compliant with the spec

It is specified to use the "forgiving-base64" decoder instead of the
regular base64 decoder, which is slightly different
This commit is contained in:
Arda Cinar 2022-12-28 12:23:10 +03:00 committed by Andreas Kling
parent bbaf86fb46
commit 598fcfca26
Notes: sideshowbarker 2024-07-17 04:03:27 +09:00

View File

@ -1394,19 +1394,33 @@ JS_DEFINE_NATIVE_FUNCTION(Window::cancel_idle_callback)
return JS::js_undefined(); return JS::js_undefined();
} }
// https://html.spec.whatwg.org/multipage/webappapis.html#dom-atob-dev
JS_DEFINE_NATIVE_FUNCTION(Window::atob) JS_DEFINE_NATIVE_FUNCTION(Window::atob)
{ {
if (!vm.argument_count()) if (!vm.argument_count())
return vm.throw_completion<JS::TypeError>(JS::ErrorType::BadArgCountOne, "atob"); return vm.throw_completion<JS::TypeError>(JS::ErrorType::BadArgCountOne, "atob");
auto string = TRY(vm.argument(0).to_string(vm)); auto deprecated_string = TRY(vm.argument(0).to_string(vm));
auto decoded = decode_base64(StringView(string)); auto string = String::from_utf8(deprecated_string).release_value_but_fixme_should_propagate_errors();
// must throw an "InvalidCharacterError" DOMException if data contains any character whose code point is greater than U+00FF
for (auto code_point : string.code_points()) {
if (code_point > 0x00FF)
return throw_completion(WebIDL::InvalidCharacterError::create(*vm.current_realm(), "Data contains characters outside the range U+0000 and U+00FF"));
}
// Otherwise, the user agent must convert data to a byte sequence whose nth byte is the eight-bit representation of the nth code point of data
// and then must apply forgiving-base64 encode to that byte sequence and return the result.
auto decoded = AK::decode_forgiving_base64(StringView(deprecated_string));
if (decoded.is_error()) if (decoded.is_error())
return vm.throw_completion<JS::TypeError>(JS::ErrorType::InvalidFormat, "Base64"); return vm.throw_completion<JS::TypeError>(JS::ErrorType::InvalidFormat, "Base64");
// decode_base64() returns a byte string. LibJS uses UTF-8 for strings. Use Latin1Decoder to convert bytes 128-255 to UTF-8. // The bytes object might contain bytes greater than 128, encode them in UTF8
auto decoder = TextCodec::decoder_for("windows-1252"); // NOTE: Any 8-bit encoding -> utf-8 decoder will work for this
VERIFY(decoder); auto text_decoder = TextCodec::decoder_for("windows-1252");
return JS::PrimitiveString::create(vm, decoder->to_utf8(decoded.value())); VERIFY(text_decoder);
auto text = text_decoder->to_utf8(decoded.release_value());
return JS::PrimitiveString::create(vm, DeprecatedString(text));
} }
JS_DEFINE_NATIVE_FUNCTION(Window::btoa) JS_DEFINE_NATIVE_FUNCTION(Window::btoa)