ci(forgejo): add forgejo actions

Problem: Crash when evaluating an XPath expression against a document
that has no root element.

Cause: mirror_node()’s DOCUMENT_NODE branch unconditionally mirrored
document.document_element(). But a document may lack a root element —
in which case, document_element() returns null.

Fix: Return null from mirror_node() when the document has no root
element. (The caller already maps a null mirror result to a failed
evaluation, and raises an error in that case.)

Fixes https://github.com/LadybirdBrowser/ladybird/issues/10004

.forgejo/workflows/build-ubuntu-24-04.yml

@@ -0,0 +1,112 @@
+name: Build Ladybird (Ubuntu 24.04)
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+  workflow_dispatch:
+
+env:
+  LADYBIRD_SOURCE_DIR: ${{ github.workspace }}
+  CCACHE_DIR: ${{ github.workspace }}/.ccache
+  VCPKG_ROOT: ${{ github.workspace }}/Build/vcpkg
+
+jobs:
+  build:
+    name: Build on Ubuntu 24.04
+    runs-on: ubuntu-latest
+    container:
+      image: ubuntu:24.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install system dependencies
+        run: |
+          apt-get update && apt-get install -y \
+            software-properties-common \
+            wget \
+            curl \
+            gpg \
+            lsb-release \
+            git
+          
+          # Install CMake 3.30+ from Kitware (since Ubuntu 24.04 has 3.28)
+          wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
+          echo "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ noble main" | tee /etc/apt/sources.list.d/kitware.list
+          
+          apt-get update && apt-get install -y \
+            autoconf \
+            autoconf-archive \
+            automake \
+            build-essential \
+            ccache \
+            cmake \
+            fonts-liberation2 \
+            glslang-tools \
+            libdrm-dev \
+            libgl1-mesa-dev \
+            libncurses-dev \
+            libtool \
+            nasm \
+            ninja-build \
+            pkg-config \
+            python3-venv \
+            qt6-base-dev \
+            qt6-tools-dev-tools \
+            qt6-wayland \
+            tar \
+            unzip \
+            zip \
+            libpulse-dev \
+            gcc-14 \
+            g++-14
+
+      - name: Configure compiler alternatives
+        run: |
+          update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100 \
+            --slave /usr/bin/g++ g++ /usr/bin/g++-14 \
+            --slave /usr/bin/gcov gcov /usr/bin/gcov-14
+
+      - name: Install Rust
+        run: |
+          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain 1.96.0
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+      - name: Configure Git Safe Directory
+        run: |
+          git config --global safe.directory '*'
+
+      - name: Bootstrap vcpkg
+        run: |
+          ./Meta/Utils/build_vcpkg.py
+
+      - name: Configure CMake
+        env:
+          CC: gcc-14
+          CXX: g++-14
+        run: |
+          cmake --preset Release -B Build \
+            -DCMAKE_C_COMPILER=gcc-14 \
+            -DCMAKE_CXX_COMPILER=g++-14 \
+            -DENABLE_CI_BASELINE_CPU=ON \
+            -DLADYBIRD_GUI_FRAMEWORK=Qt
+
+      - name: Build
+        run: |
+          cmake --build Build
+
+      - name: Install
+        run: |
+          cmake --install Build --strip --prefix dist
+
+      - name: Package Binaries
+        run: |
+          tar -czf ladybird-ubuntu-24.04.tar.gz -C dist .
+
+      - name: Upload Build Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: ladybird-ubuntu-24.04
+          path: ladybird-ubuntu-24.04.tar.gz

Libraries/LibTextCodec/Decoder.cpp

@@ -15,15 +15,8 @@
 
 namespace TextCodec {
 
-static constexpr u32 replacement_code_point = 0xfffd;
-
 namespace {
 
-enum class RemoveBOM {
-    No,
-    Yes,
-};
-
 class RustDecoder final : public Decoder {
 public:
     explicit RustDecoder(StringView encoding)
@@ -31,8 +24,7 @@ public:
     {
     }
 
-    virtual bool validate(StringView input) override;
+    virtual ErrorOr<String> to_utf8(StringView input, IgnoreBOM, ErrorMode) override;
-    virtual ErrorOr<String> to_utf8(StringView input) override;
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView input) override;
 
 private:
@@ -44,15 +36,13 @@ private:
 class UTF8Decoder final : public Decoder {
 public:
     virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
-    virtual bool validate(StringView) override;
+    virtual ErrorOr<String> to_utf8(StringView, IgnoreBOM, ErrorMode) override;
-    virtual ErrorOr<String> to_utf8(StringView) override;
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
 };
 
 class UTF16BEDecoder final : public Decoder {
 public:
-    virtual bool validate(StringView) override;
+    virtual ErrorOr<String> to_utf8(StringView, IgnoreBOM, ErrorMode) override;
-    virtual ErrorOr<String> to_utf8(StringView) override;
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
 
 private:
@@ -61,8 +51,7 @@ private:
 
 class UTF16LEDecoder final : public Decoder {
 public:
-    virtual bool validate(StringView) override;
+    virtual ErrorOr<String> to_utf8(StringView, IgnoreBOM, ErrorMode) override;
-    virtual ErrorOr<String> to_utf8(StringView) override;
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
 
 private:
@@ -72,7 +61,6 @@ private:
 class Latin1Decoder final : public Decoder {
 public:
     virtual ErrorOr<void> process(StringView, Function<ErrorOr<void>(u32)> on_code_point) override;
-    virtual bool validate(StringView) override { return true; }
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView) override;
 };
 
@@ -130,7 +118,7 @@ static void append_decoded_bytes(void* context, u8 const* data, size_t length)
     decode_context.result = decode_context.builder.try_append(StringView { data, length });
 }
 
-ErrorOr<String> rust_decode_to_utf8(StringView encoding, StringView input, RemoveBOM remove_bom)
+ErrorOr<String> rust_decode_to_utf8(StringView encoding, StringView input, IgnoreBOM ignore_bom, ErrorMode error_mode)
 {
     DecodeContext context { .builder = StringBuilder(input.length()) };
     auto succeeded = FFI::textcodec_rust_decode_to_utf8(
@@ -138,36 +126,27 @@ ErrorOr<String> rust_decode_to_utf8(StringView encoding, StringView input, Remov
         encoding.length(),
         reinterpret_cast<u8 const*>(input.characters_without_null_termination()),
         input.length(),
-        remove_bom == RemoveBOM::Yes,
+        ignore_bom == IgnoreBOM::No,
+        error_mode == ErrorMode::Fatal,
         &context,
         append_decoded_bytes);
     if (!succeeded)
-        return Error::from_errno(EINVAL);
+        return Error::from_string_literal("Failed to decode input");
     TRY(context.result);
     return context.builder.to_string_without_validation();
 }
 
-ErrorOr<void> rust_process(StringView encoding, StringView input, RemoveBOM remove_bom, Function<ErrorOr<void>(u32)> on_code_point)
+ErrorOr<void> rust_process(StringView encoding, StringView input, IgnoreBOM ignore_bom, Function<ErrorOr<void>(u32)> on_code_point)
 {
-    auto utf8 = TRY(rust_decode_to_utf8(encoding, input, remove_bom));
+    auto utf8 = TRY(rust_decode_to_utf8(encoding, input, ignore_bom, ErrorMode::Replacement));
     for (auto code_point : Utf8View { utf8 })
         TRY(on_code_point(code_point));
     return {};
 }
 
-bool rust_validate(StringView encoding, StringView input, RemoveBOM remove_bom)
+ErrorOr<size_t> rust_length_in_utf16_code_units(StringView encoding, StringView input, IgnoreBOM ignore_bom)
 {
-    return FFI::textcodec_rust_validate(
+    auto utf8 = TRY(rust_decode_to_utf8(encoding, input, ignore_bom, ErrorMode::Replacement));
-        reinterpret_cast<u8 const*>(encoding.characters_without_null_termination()),
-        encoding.length(),
-        reinterpret_cast<u8 const*>(input.characters_without_null_termination()),
-        input.length(),
-        remove_bom == RemoveBOM::Yes);
-}
-
-ErrorOr<size_t> rust_length_in_utf16_code_units(StringView encoding, StringView input, RemoveBOM remove_bom)
-{
-    auto utf8 = TRY(rust_decode_to_utf8(encoding, input, remove_bom));
     size_t length = 0;
     for (auto code_point : Utf8View { utf8 })
         length += code_point <= 0xffff ? 1 : 2;
@@ -188,7 +167,7 @@ Optional<StringView> get_static_encoding_name_from_rust(StringView label)
     return StringView { encoding_name, encoding_name_length };
 }
 
-ErrorOr<String> rust_streaming_decode_to_utf8(FFI::TextCodecRustStreamingDecoder* decoder, ReadonlyBytes input, bool last)
+ErrorOr<String> rust_streaming_decode_to_utf8(FFI::TextCodecRustStreamingDecoder* decoder, ReadonlyBytes input, bool last, ErrorMode error_mode)
 {
     DecodeContext context { .builder = StringBuilder(input.size()) };
     auto succeeded = FFI::textcodec_rust_streaming_decoder_decode_to_utf8(
@@ -196,10 +175,11 @@ ErrorOr<String> rust_streaming_decode_to_utf8(FFI::TextCodecRustStreamingDecoder
         input.data(),
         input.size(),
         last,
+        error_mode == ErrorMode::Fatal,
         &context,
         append_decoded_bytes);
     if (!succeeded)
-        return Error::from_errno(EINVAL);
+        return Error::from_string_literal("Failed to decode input");
     TRY(context.result);
     return context.builder.to_string_without_validation();
 }
@@ -367,7 +347,7 @@ ErrorOr<String> convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte
 
     // 3. Process a queue with an instance of encoding’s decoder, ioQueue, output, and "replacement".
     // FIXME: This isn't the exact same as the spec, which is written in terms of I/O queues.
-    auto output = TRY(actual_decoder->to_utf8(input));
+    auto output = TRY(actual_decoder->to_utf8(input, IgnoreBOM::No, ErrorMode::Replacement));
 
     // 4. Return output.
     return output;
@@ -410,18 +390,7 @@ StringView get_output_encoding(StringView encoding)
     return encoding;
 }
 
-bool Decoder::validate(StringView input)
+ErrorOr<String> Decoder::to_utf8(StringView input, IgnoreBOM, ErrorMode)
-{
-    auto result = this->process(input, [](auto code_point) -> ErrorOr<void> {
-        if (code_point == replacement_code_point)
-            return Error::from_errno(EINVAL);
-        return {};
-    });
-
-    return !result.is_error();
-}
-
-ErrorOr<String> Decoder::to_utf8(StringView input)
 {
     StringBuilder builder(input.length());
     TRY(process(input, [&builder](u32 c) { return builder.try_append_code_point(c); }));
@@ -453,24 +422,19 @@ ErrorOr<void> Decoder::process_code_points(StringView input, Function<ErrorOr<vo
     return process(input, move(on_code_point));
 }
 
-bool RustDecoder::validate(StringView input)
+ErrorOr<String> RustDecoder::to_utf8(StringView input, IgnoreBOM ignore_bom, ErrorMode error_mode)
 {
-    return rust_validate(m_encoding, input, RemoveBOM::No);
+    return rust_decode_to_utf8(m_encoding, input, ignore_bom, error_mode);
-}
-
-ErrorOr<String> RustDecoder::to_utf8(StringView input)
-{
-    return rust_decode_to_utf8(m_encoding, input, RemoveBOM::No);
 }
 
 ErrorOr<size_t> RustDecoder::length_in_utf16_code_units(StringView input)
 {
-    return rust_length_in_utf16_code_units(m_encoding, input, RemoveBOM::No);
+    return rust_length_in_utf16_code_units(m_encoding, input, IgnoreBOM::Yes);
 }
 
 ErrorOr<void> RustDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
 {
-    return rust_process(m_encoding, input, RemoveBOM::No, move(on_code_point));
+    return rust_process(m_encoding, input, IgnoreBOM::Yes, move(on_code_point));
 }
 
 ErrorOr<void> Latin1Decoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
@@ -485,12 +449,13 @@ ErrorOr<size_t> Latin1Decoder::length_in_utf16_code_units(StringView input)
     return input.length();
 }
 
-StreamingDecoder::StreamingDecoder(StringView encoding)
+StreamingDecoder::StreamingDecoder(StringView encoding, IgnoreBOM ignore_bom, ErrorMode error_mode)
+    : m_error_mode(error_mode)
 {
     m_decoder = FFI::textcodec_rust_streaming_decoder_new(
         reinterpret_cast<u8 const*>(encoding.characters_without_null_termination()),
         encoding.length(),
-        true);
+        ignore_bom == IgnoreBOM::No);
     VERIFY(m_decoder);
 }
 
@@ -501,72 +466,57 @@ StreamingDecoder::~StreamingDecoder()
 
 ErrorOr<String> StreamingDecoder::to_utf8(ReadonlyBytes input)
 {
-    return rust_streaming_decode_to_utf8(static_cast<FFI::TextCodecRustStreamingDecoder*>(m_decoder), input, false);
+    return rust_streaming_decode_to_utf8(static_cast<FFI::TextCodecRustStreamingDecoder*>(m_decoder), input, false, m_error_mode);
 }
 
 ErrorOr<String> StreamingDecoder::finish()
 {
-    return rust_streaming_decode_to_utf8(static_cast<FFI::TextCodecRustStreamingDecoder*>(m_decoder), {}, true);
+    return rust_streaming_decode_to_utf8(static_cast<FFI::TextCodecRustStreamingDecoder*>(m_decoder), {}, true, m_error_mode);
 }
 
 ErrorOr<void> UTF8Decoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
 {
-    return rust_process("UTF-8"sv, input, RemoveBOM::No, move(on_code_point));
+    return rust_process("UTF-8"sv, input, IgnoreBOM::Yes, move(on_code_point));
 }
 
-bool UTF8Decoder::validate(StringView input)
+ErrorOr<String> UTF8Decoder::to_utf8(StringView input, IgnoreBOM ignore_bom, ErrorMode error_mode)
 {
-    return rust_validate("UTF-8"sv, input, RemoveBOM::No);
+    return rust_decode_to_utf8("UTF-8"sv, input, ignore_bom, error_mode);
-}
-
-ErrorOr<String> UTF8Decoder::to_utf8(StringView input)
-{
-    return rust_decode_to_utf8("UTF-8"sv, input, RemoveBOM::Yes);
 }
 
 ErrorOr<size_t> UTF8Decoder::length_in_utf16_code_units(StringView input)
 {
-    return rust_length_in_utf16_code_units("UTF-8"sv, input, RemoveBOM::Yes);
+    return rust_length_in_utf16_code_units("UTF-8"sv, input, IgnoreBOM::No);
-}
-
-bool UTF16BEDecoder::validate(StringView input)
-{
-    return rust_validate("UTF-16BE"sv, input, RemoveBOM::No);
 }
 
 ErrorOr<void> UTF16BEDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
 {
-    return rust_process("UTF-16BE"sv, input, RemoveBOM::Yes, move(on_code_point));
+    return rust_process("UTF-16BE"sv, input, IgnoreBOM::No, move(on_code_point));
 }
 
-ErrorOr<String> UTF16BEDecoder::to_utf8(StringView input)
+ErrorOr<String> UTF16BEDecoder::to_utf8(StringView input, IgnoreBOM ignore_bom, ErrorMode error_mode)
 {
-    return rust_decode_to_utf8("UTF-16BE"sv, input, RemoveBOM::Yes);
+    return rust_decode_to_utf8("UTF-16BE"sv, input, ignore_bom, error_mode);
 }
 
 ErrorOr<size_t> UTF16BEDecoder::length_in_utf16_code_units(StringView input)
 {
-    return rust_length_in_utf16_code_units("UTF-16BE"sv, input, RemoveBOM::Yes);
+    return rust_length_in_utf16_code_units("UTF-16BE"sv, input, IgnoreBOM::No);
-}
-
-bool UTF16LEDecoder::validate(StringView input)
-{
-    return rust_validate("UTF-16LE"sv, input, RemoveBOM::No);
 }
 
 ErrorOr<void> UTF16LEDecoder::process(StringView input, Function<ErrorOr<void>(u32)> on_code_point)
 {
-    return rust_process("UTF-16LE"sv, input, RemoveBOM::Yes, move(on_code_point));
+    return rust_process("UTF-16LE"sv, input, IgnoreBOM::No, move(on_code_point));
 }
 
-ErrorOr<String> UTF16LEDecoder::to_utf8(StringView input)
+ErrorOr<String> UTF16LEDecoder::to_utf8(StringView input, IgnoreBOM ignore_bom, ErrorMode error_mode)
 {
-    return rust_decode_to_utf8("UTF-16LE"sv, input, RemoveBOM::Yes);
+    return rust_decode_to_utf8("UTF-16LE"sv, input, ignore_bom, error_mode);
 }
 
 ErrorOr<size_t> UTF16LEDecoder::length_in_utf16_code_units(StringView input)
 {
-    return rust_length_in_utf16_code_units("UTF-16LE"sv, input, RemoveBOM::Yes);
+    return rust_length_in_utf16_code_units("UTF-16LE"sv, input, IgnoreBOM::No);
 }
 
 // https://infra.spec.whatwg.org/#isomorphic-decode

Libraries/LibTextCodec/Decoder.h

@@ -19,10 +19,20 @@
 
 namespace TextCodec {
 
+enum class IgnoreBOM {
+    Yes,
+    No,
+};
+
+// https://encoding.spec.whatwg.org/#concept-encoding-error-mode
+enum class ErrorMode {
+    Replacement,
+    Fatal,
+};
+
 class TEXTCODEC_API Decoder {
 public:
-    virtual bool validate(StringView);
+    virtual ErrorOr<String> to_utf8(StringView, IgnoreBOM, ErrorMode);
-    virtual ErrorOr<String> to_utf8(StringView);
     virtual ErrorOr<Utf16String> to_utf16(StringView);
     virtual ErrorOr<size_t> length_in_utf16_code_units(StringView);
     ErrorOr<void> process_code_points(StringView, Function<ErrorOr<void>(u32)>);
@@ -36,13 +46,14 @@ class TEXTCODEC_API StreamingDecoder final {
     AK_MAKE_NONCOPYABLE(StreamingDecoder);
 
 public:
-    explicit StreamingDecoder(StringView encoding);
+    StreamingDecoder(StringView encoding, IgnoreBOM, ErrorMode);
     ~StreamingDecoder();
 
     ErrorOr<String> to_utf8(ReadonlyBytes);
     ErrorOr<String> finish();
 
 private:
+    ErrorMode m_error_mode { ErrorMode::Replacement };
     void* m_decoder { nullptr };
 };
 

Libraries/LibTextCodec/Rust/src/lib.rs

@@ -93,6 +93,7 @@ pub unsafe extern "C" fn textcodec_rust_decode_to_utf8(
     input: *const u8,
     input_len: usize,
     remove_bom: bool,
+    fatal: bool,
     ctx: *mut c_void,
     on_bytes: FfiBytesFn,
 ) -> bool {
@@ -108,60 +109,20 @@ pub unsafe extern "C" fn textcodec_rust_decode_to_utf8(
                 return false;
             };
 
-            let (output, _) = if remove_bom {
+            let (output, had_errors) = if remove_bom {
                 encoding.decode_with_bom_removal(input)
             } else {
                 encoding.decode_without_bom_handling(input)
             };
+            if fatal && had_errors {
+                return false;
+            }
             on_bytes(ctx, output.as_bytes().as_ptr(), output.len());
             true
         })
     }
 }
 
-/// # Safety
-/// - `encoding_label`/`encoding_label_len` and `input`/`input_len` must be valid byte slices.
-#[unsafe(no_mangle)]
-pub unsafe extern "C" fn textcodec_rust_validate(
-    encoding_label: *const u8,
-    encoding_label_len: usize,
-    input: *const u8,
-    input_len: usize,
-    remove_bom: bool,
-) -> bool {
-    unsafe {
-        abort_on_panic(|| {
-            let Some(label) = bytes_from_raw(encoding_label, encoding_label_len) else {
-                return false;
-            };
-            let Some(input) = bytes_from_raw(input, input_len) else {
-                return false;
-            };
-            let Some(encoding) = Encoding::for_label(label) else {
-                return false;
-            };
-
-            let input = if remove_bom {
-                if encoding == encoding_rs::UTF_8 && input.starts_with(b"\xEF\xBB\xBF") {
-                    &input[3..]
-                } else if (encoding == encoding_rs::UTF_16LE && input.starts_with(b"\xFF\xFE"))
-                    || (encoding == encoding_rs::UTF_16BE && input.starts_with(b"\xFE\xFF"))
-                {
-                    &input[2..]
-                } else {
-                    input
-                }
-            } else {
-                input
-            };
-
-            encoding
-                .decode_without_bom_handling_and_without_replacement(input)
-                .is_some()
-        })
-    }
-}
-
 /// # Safety
 /// - `encoding_label`/`encoding_label_len` must be a valid byte slice.
 /// - The returned pointer must be freed with `textcodec_rust_streaming_decoder_free`.
@@ -212,6 +173,7 @@ pub unsafe extern "C" fn textcodec_rust_streaming_decoder_decode_to_utf8(
     input: *const u8,
     input_len: usize,
     last: bool,
+    fatal: bool,
     ctx: *mut c_void,
     on_bytes: FfiBytesFn,
 ) -> bool {
@@ -230,7 +192,10 @@ pub unsafe extern "C" fn textcodec_rust_streaming_decoder_decode_to_utf8(
             };
             let mut output = String::with_capacity(output_capacity);
 
-            let (result, _, _) = decoder.decoder.decode_to_string(input, &mut output, last);
+            let (result, _, had_errors) = decoder.decoder.decode_to_string(input, &mut output, last);
+            if fatal && had_errors {
+                return false;
+            }
             if !output.is_empty() {
                 on_bytes(ctx, output.as_ptr(), output.len());
             }

Libraries/LibWeb/CSS/Parser/RustTokenizer.cpp

@@ -36,7 +36,7 @@ static String decode_and_filter_code_points(StringView input, StringView encodin
                 input = input.substring_view(3);
             return String::from_utf8_without_validation(input.bytes());
         }
-        return MUST(decoder->to_utf8(input));
+        return MUST(decoder->to_utf8(input, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement));
     }();
 
     // OPTIMIZATION: If the input doesn't contain any filterable characters, we can skip the filtering

Libraries/LibWeb/CSS/Parser/Tokenizer.cpp

@@ -175,7 +175,7 @@ Vector<Token> Tokenizer::tokenize(StringView input, StringView encoding, Tokeniz
                     input = input.substring_view(3);
                 return String::from_utf8_without_validation(input.bytes());
             }
-            return MUST(decoder->to_utf8(input));
+            return MUST(decoder->to_utf8(input, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement));
         }();
 
         // OPTIMIZATION: If the input doesn't contain any filterable characters, we can skip the filtering

Libraries/LibWeb/DOM/DocumentLoading.cpp

@@ -73,11 +73,12 @@ bool build_xml_document(DOM::Document& document, ByteBuffer const& data, Optiona
     }
     VERIFY(decoder.has_value());
     // Well-formed XML documents contain only properly encoded characters
-    if (!decoder->validate(data)) {
+    auto source_or_error = decoder->to_utf8(data, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal);
+    if (source_or_error.is_error()) {
         convert_to_xml_error_document(document, "XML Document contains improperly-encoded characters"_utf16);
         return false;
     }
-    auto source = decoder->to_utf8(data).release_value_but_fixme_should_propagate_errors();
+    auto source = source_or_error.release_value();
     XML::Parser parser(source, { .resolve_named_html_entity = resolve_named_html_entity });
     XMLDocumentBuilder builder { document };
     auto result = parser.parse_with_listener(builder);
@@ -198,13 +199,7 @@ static WebIDL::ExceptionOr<GC::Ref<DOM::Document>> load_xml_document(HTML::Navig
         }
         VERIFY(decoder.has_value());
         // Well-formed XML documents contain only properly encoded characters
-        if (!decoder->validate(data)) {
+        auto source = decoder->to_utf8(data, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal);
-            // FIXME: Insert error message into the document.
-            dbgln("XML Document contains improperly-encoded characters");
-            convert_to_xml_error_document(document, "XML Document contains improperly-encoded characters"_utf16);
-            return;
-        }
-        auto source = decoder->to_utf8(data);
         if (source.is_error()) {
             // FIXME: Insert error message into the document.
             dbgln("Failed to decode XML document: {}", source.error());

Libraries/LibWeb/Encoding/TextDecoder.cpp

@@ -18,7 +18,7 @@ namespace Web::Encoding {
 GC_DEFINE_ALLOCATOR(TextDecoder);
 
 // https://encoding.spec.whatwg.org/#dom-textdecoder
-WebIDL::ExceptionOr<GC::Ref<TextDecoder>> TextDecoder::construct_impl(JS::Realm& realm, FlyString label, Optional<Bindings::TextDecoderOptions> const& options)
+WebIDL::ExceptionOr<GC::Ref<TextDecoder>> TextDecoder::construct_impl(JS::Realm& realm, StringView label, Bindings::TextDecoderOptions const& options)
 {
     auto& vm = realm.vm();
 
@@ -35,10 +35,10 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoder>> TextDecoder::construct_impl(JS::Realm&
     auto lowercase_encoding_name = encoding.value().to_ascii_lowercase_string();
 
     // 4. If options["fatal"] is true, then set this’s error mode to "fatal".
-    auto error_mode = options.value_or({}).fatal ? ErrorMode::Fatal : ErrorMode::Replacement;
+    auto error_mode = options.fatal ? TextCodec::ErrorMode::Fatal : TextCodec::ErrorMode::Replacement;
 
     // 5. Set this’s ignore BOM to options["ignoreBOM"].
-    auto ignore_bom = options.value_or({}).ignore_bom;
+    auto ignore_bom = options.ignore_bom;
 
     // NOTE: This should happen in decode(), but we don't support streaming yet and share decoders across calls.
     auto decoder = TextCodec::decoder_for_exact_name(encoding.value());
@@ -48,7 +48,7 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoder>> TextDecoder::construct_impl(JS::Realm&
 }
 
 // https://encoding.spec.whatwg.org/#dom-textdecoder
-TextDecoder::TextDecoder(JS::Realm& realm, TextCodec::Decoder& decoder, FlyString encoding, ErrorMode error_mode, bool ignore_bom)
+TextDecoder::TextDecoder(JS::Realm& realm, TextCodec::Decoder& decoder, FlyString encoding, TextCodec::ErrorMode error_mode, bool ignore_bom)
     : PlatformObject(realm)
     , TextDecoderCommonMixin(decoder, move(encoding), error_mode, ignore_bom)
 {
@@ -65,18 +65,23 @@ void TextDecoder::initialize(JS::Realm& realm)
 // https://encoding.spec.whatwg.org/#dom-textdecoder-decode
 WebIDL::ExceptionOr<String> TextDecoder::decode(Optional<WebIDL::BufferSourceVariant> input, Optional<Bindings::TextDecodeOptions> const&) const
 {
-    if (!input.has_value())
+    auto ignore_bom = m_ignore_bom ? TextCodec::IgnoreBOM::Yes : TextCodec::IgnoreBOM::No;
-        return TRY_OR_THROW_OOM(vm(), m_decoder.to_utf8({}));
+    if (!input.has_value()) {
+        auto result = m_decoder.to_utf8({}, ignore_bom, m_error_mode);
+        if (result.is_error() && result.error().code() != ENOMEM)
+            return WebIDL::SimpleException { WebIDL::SimpleExceptionType::TypeError, "Decoding failed"sv };
+        return TRY_OR_THROW_OOM(vm(), move(result));
+    }
 
     // FIXME: Implement the streaming stuff.
     auto data_buffer_or_error = WebIDL::get_buffer_source_copy(*input);
     if (data_buffer_or_error.is_error())
         return WebIDL::OperationError::create(realm(), "Failed to copy bytes from ArrayBuffer"_utf16);
     auto& data_buffer = data_buffer_or_error.value();
-    auto result = TRY_OR_THROW_OOM(vm(), m_decoder.to_utf8({ data_buffer.data(), data_buffer.size() }));
+    auto result = m_decoder.to_utf8({ data_buffer.data(), data_buffer.size() }, ignore_bom, m_error_mode);
-    if (this->fatal() && result.contains(0xfffd))
+    if (result.is_error() && result.error().code() != ENOMEM)
         return WebIDL::SimpleException { WebIDL::SimpleExceptionType::TypeError, "Decoding failed"sv };
-    return result;
+    return TRY_OR_THROW_OOM(vm(), move(result));
 }
 
 }

Libraries/LibWeb/Encoding/TextDecoder.h

@@ -27,14 +27,14 @@ class TextDecoder
     GC_DECLARE_ALLOCATOR(TextDecoder);
 
 public:
-    static WebIDL::ExceptionOr<GC::Ref<TextDecoder>> construct_impl(JS::Realm&, FlyString encoding, Optional<Bindings::TextDecoderOptions> const& options = {});
+    static WebIDL::ExceptionOr<GC::Ref<TextDecoder>> construct_impl(JS::Realm&, StringView label, Bindings::TextDecoderOptions const&);
 
     virtual ~TextDecoder() override;
 
     WebIDL::ExceptionOr<String> decode(Optional<WebIDL::BufferSourceVariant>, Optional<Bindings::TextDecodeOptions> const& options = {}) const;
 
 private:
-    TextDecoder(JS::Realm&, TextCodec::Decoder&, FlyString encoding, ErrorMode error_mode, bool ignore_bom);
+    TextDecoder(JS::Realm&, TextCodec::Decoder&, FlyString encoding, TextCodec::ErrorMode error_mode, bool ignore_bom);
 
     virtual void initialize(JS::Realm&) override;
 };

Libraries/LibWeb/Encoding/TextDecoderCommon.cpp

@@ -8,7 +8,7 @@
 
 namespace Web::Encoding {
 
-TextDecoderCommonMixin::TextDecoderCommonMixin(TextCodec::Decoder& decoder, FlyString encoding, ErrorMode error_mode, bool ignore_bom)
+TextDecoderCommonMixin::TextDecoderCommonMixin(TextCodec::Decoder& decoder, FlyString encoding, TextCodec::ErrorMode error_mode, bool ignore_bom)
     : m_decoder(decoder)
     , m_encoding(move(encoding))
     , m_error_mode(error_mode)

Libraries/LibWeb/Encoding/TextDecoderCommon.h

@@ -7,7 +7,7 @@
 #pragma once
 
 #include <AK/FlyString.h>
-#include <LibTextCodec/Forward.h>
+#include <LibTextCodec/Decoder.h>
 
 namespace Web::Encoding {
 
@@ -20,19 +20,13 @@ public:
     FlyString const& encoding() const { return m_encoding; }
 
     // https://encoding.spec.whatwg.org/#dom-textdecoder-fatal
-    bool fatal() const { return m_error_mode == ErrorMode::Fatal; }
+    bool fatal() const { return m_error_mode == TextCodec::ErrorMode::Fatal; }
 
     // https://encoding.spec.whatwg.org/#dom-textdecoder-ignorebom
     bool ignore_bom() const { return m_ignore_bom; }
 
 protected:
-    // https://encoding.spec.whatwg.org/#concept-encoding-error-mode
+    TextDecoderCommonMixin(TextCodec::Decoder& decoder, FlyString encoding, TextCodec::ErrorMode error_mode, bool ignore_bom);
-    enum class ErrorMode {
-        Replacement,
-        Fatal,
-    };
-
-    TextDecoderCommonMixin(TextCodec::Decoder& decoder, FlyString encoding, ErrorMode error_mode, bool ignore_bom);
 
     // https://encoding.spec.whatwg.org/#textdecodercommon-decoder
     TextCodec::Decoder& m_decoder;
@@ -41,13 +35,10 @@ protected:
     FlyString m_encoding;
 
     // https://encoding.spec.whatwg.org/#textdecoder-error-mode
-    ErrorMode m_error_mode { ErrorMode::Replacement };
+    TextCodec::ErrorMode m_error_mode { TextCodec::ErrorMode::Replacement };
 
     // https://encoding.spec.whatwg.org/#textdecoder-ignore-bom-flag
     bool m_ignore_bom { false };
-
-    // https://encoding.spec.whatwg.org/#textdecoder-bom-seen-flag
-    bool m_bom_seen { false };
 };
 
 }

Libraries/LibWeb/Encoding/TextDecoderStream.cpp

@@ -15,6 +15,7 @@
 #include <LibWeb/Bindings/TextDecoder.h>
 #include <LibWeb/Bindings/TextDecoderStream.h>
 #include <LibWeb/Encoding/TextDecoderStream.h>
+#include <LibWeb/HTML/Scripting/TemporaryExecutionContext.h>
 #include <LibWeb/Streams/TransformStream.h>
 #include <LibWeb/Streams/TransformStreamOperations.h>
 #include <LibWeb/WebIDL/AbstractOperations.h>
@@ -38,7 +39,7 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoderStream>> TextDecoderStream::construct_imp
     auto lowercase_encoding_name = encoding.value().to_ascii_lowercase_string();
 
     // 4. If options["fatal"] is true, then set this’s error mode to "fatal".
-    auto error_mode = options.fatal ? ErrorMode::Fatal : ErrorMode::Replacement;
+    auto error_mode = options.fatal ? TextCodec::ErrorMode::Fatal : TextCodec::ErrorMode::Replacement;
 
     // 5. Set this’s ignore BOM to options["ignoreBOM"].
     auto ignore_bom = options.ignore_bom;
@@ -59,6 +60,7 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoderStream>> TextDecoderStream::construct_imp
     //    algorithm with this and chunk.
     auto transform_algorithm = GC::create_function(realm.heap(), [stream](JS::Value chunk) -> GC::Ref<WebIDL::Promise> {
         auto& realm = stream->realm();
+        HTML::TemporaryExecutionContext execution_context { realm };
         if (auto result = stream->decode_and_enqueue_chunk(chunk); result.is_error())
             return WebIDL::create_rejected_promise_from_exception(realm, result.release_error());
         return WebIDL::create_resolved_promise(realm, JS::js_undefined());
@@ -67,6 +69,7 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoderStream>> TextDecoderStream::construct_imp
     // 8. Let flushAlgorithm be an algorithm which takes no arguments and runs the flush and enqueue algorithm with this.
     auto flush_algorithm = GC::create_function(realm.heap(), [stream]() -> GC::Ref<WebIDL::Promise> {
         auto& realm = stream->realm();
+        HTML::TemporaryExecutionContext execution_context { realm };
         if (auto result = stream->flush_and_enqueue(); result.is_error())
             return WebIDL::create_rejected_promise_from_exception(realm, result.release_error());
         return WebIDL::create_resolved_promise(realm, JS::js_undefined());
@@ -81,11 +84,14 @@ WebIDL::ExceptionOr<GC::Ref<TextDecoderStream>> TextDecoderStream::construct_imp
     return stream;
 }
 
-TextDecoderStream::TextDecoderStream(JS::Realm& realm, GC::Ref<Streams::TransformStream> transform, TextCodec::Decoder& decoder, FlyString encoding, ErrorMode error_mode, bool ignore_bom)
+TextDecoderStream::TextDecoderStream(JS::Realm& realm, GC::Ref<Streams::TransformStream> transform, TextCodec::Decoder& decoder, FlyString encoding, TextCodec::ErrorMode error_mode, bool ignore_bom)
     : Bindings::PlatformObject(realm)
     , Streams::GenericTransformStreamMixin(transform)
     , TextDecoderCommonMixin(decoder, move(encoding), error_mode, ignore_bom)
-    , m_streaming_decoder(make<TextCodec::StreamingDecoder>(m_encoding))
+    , m_streaming_decoder(make<TextCodec::StreamingDecoder>(
+          m_encoding,
+          m_ignore_bom ? TextCodec::IgnoreBOM::Yes : TextCodec::IgnoreBOM::No,
+          m_error_mode))
 {
 }
 
@@ -119,7 +125,10 @@ WebIDL::ExceptionOr<void> TextDecoderStream::decode_and_enqueue_chunk(JS::Value
         return WebIDL::OperationError::create(realm, "Failed to copy bytes from BufferSource"_utf16);
     auto buffer = buffer_or_error.release_value();
 
-    auto decoded = TRY_OR_THROW_OOM(vm, m_streaming_decoder->to_utf8(buffer.bytes()));
+    auto decoded_or_error = m_streaming_decoder->to_utf8(buffer.bytes());
+    if (decoded_or_error.is_error() && decoded_or_error.error().code() != ENOMEM)
+        return WebIDL::SimpleException { WebIDL::SimpleExceptionType::TypeError, "Decoding failed"sv };
+    auto decoded = TRY_OR_THROW_OOM(vm, move(decoded_or_error));
 
     // 3-4. Run "processing an item" until the input is exhausted, accumulating the output, then enqueue any non-empty
     //      result. If processing returns error, throw a TypeError.
@@ -130,7 +139,10 @@ WebIDL::ExceptionOr<void> TextDecoderStream::decode_and_enqueue_chunk(JS::Value
 WebIDL::ExceptionOr<void> TextDecoderStream::flush_and_enqueue()
 {
     // 1-3. Drain decoder's I/O queue and run "processing an item" to completion.
-    auto decoded = TRY_OR_THROW_OOM(vm(), m_streaming_decoder->finish());
+    auto decoded_or_error = m_streaming_decoder->finish();
+    if (decoded_or_error.is_error() && decoded_or_error.error().code() != ENOMEM)
+        return WebIDL::SimpleException { WebIDL::SimpleExceptionType::TypeError, "Decoding failed"sv };
+    auto decoded = TRY_OR_THROW_OOM(vm(), move(decoded_or_error));
     return enqueue_decoded_output(decoded);
 }
 
@@ -139,22 +151,9 @@ WebIDL::ExceptionOr<void> TextDecoderStream::enqueue_decoded_output(String const
     auto& realm = this->realm();
     auto& vm = realm.vm();
 
-    // https://encoding.spec.whatwg.org/#concept-td-serialize
-    // FIXME: The underlying TextCodec decoders currently strip leading BOMs unconditionally for UTF-8 and UTF-16BE/LE,
-    //        so the "ignore BOM" flag is effectively ignored here. Once the decoders accept a "preserve BOM" mode,
-    //        plumb m_ignore_bom through and strip the BOM from `decoded` only when m_ignore_bom is false.
-    if (!m_bom_seen && !decoded.is_empty())
-        m_bom_seen = true;
-
     if (decoded.is_empty())
         return {};
 
-    // If decoder's error mode is "fatal" and processing produced any error, throw a TypeError.
-    // NB: We can only detect this approximately by looking for U+FFFD in the decoded output, which the underlying
-    //     decoder substitutes for invalid sequences. This matches the existing TextDecoder.decode() behavior.
-    if (fatal() && decoded.contains(0xFFFD))
-        return WebIDL::SimpleException { WebIDL::SimpleExceptionType::TypeError, "Decoding failed"sv };
-
     auto js_string = JS::PrimitiveString::create(vm, Utf16String::from_utf8(decoded));
     return Streams::transform_stream_default_controller_enqueue(*m_transform->controller(), js_string);
 }

Libraries/LibWeb/Encoding/TextDecoderStream.h

@@ -27,7 +27,7 @@ public:
     virtual ~TextDecoderStream() override;
 
 private:
-    TextDecoderStream(JS::Realm&, GC::Ref<Streams::TransformStream>, TextCodec::Decoder&, FlyString encoding, ErrorMode, bool ignore_bom);
+    TextDecoderStream(JS::Realm&, GC::Ref<Streams::TransformStream>, TextCodec::Decoder&, FlyString encoding, TextCodec::ErrorMode, bool ignore_bom);
 
     virtual void initialize(JS::Realm&) override;
     virtual void visit_edges(Cell::Visitor&) override;

Libraries/LibWeb/Encoding/TextEncoder.cpp

@@ -14,7 +14,7 @@ namespace Web::Encoding {
 
 GC_DEFINE_ALLOCATOR(TextEncoder);
 
-WebIDL::ExceptionOr<GC::Ref<TextEncoder>> TextEncoder::construct_impl(JS::Realm& realm)
+GC::Ref<TextEncoder> TextEncoder::construct_impl(JS::Realm& realm)
 {
     return realm.create<TextEncoder>(realm);
 }

Libraries/LibWeb/Encoding/TextEncoder.h

@@ -27,7 +27,7 @@ class TextEncoder final
     GC_DECLARE_ALLOCATOR(TextEncoder);
 
 public:
-    static WebIDL::ExceptionOr<GC::Ref<TextEncoder>> construct_impl(JS::Realm&);
+    static GC::Ref<TextEncoder> construct_impl(JS::Realm&);
 
     virtual ~TextEncoder() override;
 

Libraries/LibWeb/Encoding/TextEncoderStream.cpp

@@ -12,6 +12,7 @@
 #include <LibWeb/Bindings/Intrinsics.h>
 #include <LibWeb/Bindings/TextEncoderStream.h>
 #include <LibWeb/Encoding/TextEncoderStream.h>
+#include <LibWeb/HTML/Scripting/TemporaryExecutionContext.h>
 #include <LibWeb/Streams/TransformStream.h>
 #include <LibWeb/Streams/TransformStreamOperations.h>
 #include <LibWeb/WebIDL/Promise.h>
@@ -21,7 +22,7 @@ namespace Web::Encoding {
 GC_DEFINE_ALLOCATOR(TextEncoderStream);
 
 // https://encoding.spec.whatwg.org/#dom-textencoderstream
-WebIDL::ExceptionOr<GC::Ref<TextEncoderStream>> TextEncoderStream::construct_impl(JS::Realm& realm)
+GC::Ref<TextEncoderStream> TextEncoderStream::construct_impl(JS::Realm& realm)
 {
     // 1. Set this’s encoder to an instance of the UTF-8 encoder.
     // NOTE: No-op, as AK::String is already in UTF-8 format.
@@ -38,6 +39,7 @@ WebIDL::ExceptionOr<GC::Ref<TextEncoderStream>> TextEncoderStream::construct_imp
     auto transform_algorithm = GC::create_function(realm.heap(), [stream](JS::Value chunk) -> GC::Ref<WebIDL::Promise> {
         auto& realm = stream->realm();
         auto& vm = realm.vm();
+        HTML::TemporaryExecutionContext execution_context { realm };
 
         if (auto result = stream->encode_and_enqueue_chunk(chunk); result.is_error()) {
             auto throw_completion = Bindings::exception_to_throw_completion(vm, result.exception());
@@ -51,6 +53,7 @@ WebIDL::ExceptionOr<GC::Ref<TextEncoderStream>> TextEncoderStream::construct_imp
     auto flush_algorithm = GC::create_function(realm.heap(), [stream]() -> GC::Ref<WebIDL::Promise> {
         auto& realm = stream->realm();
         auto& vm = realm.vm();
+        HTML::TemporaryExecutionContext execution_context { realm };
 
         if (auto result = stream->encode_and_flush(); result.is_error()) {
             auto throw_completion = Bindings::exception_to_throw_completion(vm, result.exception());

Libraries/LibWeb/Encoding/TextEncoderStream.h

@@ -20,7 +20,7 @@ class TextEncoderStream final
     GC_DECLARE_ALLOCATOR(TextEncoderStream);
 
 public:
-    static WebIDL::ExceptionOr<GC::Ref<TextEncoderStream>> construct_impl(JS::Realm&);
+    static GC::Ref<TextEncoderStream> construct_impl(JS::Realm&);
     virtual ~TextEncoderStream() override;
 
 private:

Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp

@@ -108,7 +108,7 @@ HTMLTokenizer::HTMLTokenizer(StringView input, ByteString const& encoding, Input
     if (input_type == InputType::EncodedBytes) {
         auto decoder = TextCodec::decoder_for(encoding);
         VERIFY(decoder.has_value());
-        m_source = MUST(decoder->to_utf8(input));
+        m_source = MUST(decoder->to_utf8(input, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement));
     } else {
         m_source = decoded_string_for_utf8_tokenizer(input);
     }

Libraries/LibWeb/HTML/Parser/IncrementalDocumentParser.cpp

@@ -68,7 +68,7 @@ void IncrementalDocumentParser::initialize_parser(ReadonlyBytes sniff_bytes)
 
     auto standardized_encoding = TextCodec::get_standardized_encoding(encoding);
     VERIFY(standardized_encoding.has_value());
-    m_decoder = make<TextCodec::StreamingDecoder>(standardized_encoding.value());
+    m_decoder = make<TextCodec::StreamingDecoder>(standardized_encoding.value(), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement);
 
     // https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
     // The document's character encoding must immediately be set to the value returned from this

Libraries/LibWeb/WebAssembly/Instance.cpp

@@ -54,7 +54,7 @@ void Instance::initialize(JS::Realm& realm)
             [&](Wasm::FunctionAddress const& address) {
                 Optional<GC::Ptr<JS::FunctionObject>> object = m_function_instances.get(address);
                 if (!object.has_value()) {
-                    object = Detail::create_native_function(vm, address, name, this);
+                    object = Detail::create_native_function(vm, address, this);
                     m_function_instances.set(address, *object);
                 }
 

Libraries/LibWeb/WebAssembly/WebAssembly.cpp

@@ -289,6 +289,7 @@ JS::ThrowCompletionOr<NonnullRefPtr<Wasm::ModuleInstance>> instantiate_module(JS
 
     // 2. Let imports be « ».
     HashMap<Wasm::Linker::Name, Wasm::ExternValue> resolved_imports;
+    size_t imported_function_count = 0;
     if (import_object) {
         dbgln_if(LIBWEB_WASM_DEBUG, "Trying to resolve stuff because import object was specified");
 
@@ -330,7 +331,7 @@ JS::ThrowCompletionOr<NonnullRefPtr<Wasm::ModuleInstance>> instantiate_module(JS
                     else {
                         // 3.4.3.1. Create a host function from v and functype, and let funcaddr be the result.
                         cache.add_imported_object(function);
-                        auto host_function = create_host_function(vm, function, function_type, ByteString::formatted("func{}", resolved_imports.size()));
+                        auto host_function = create_host_function(vm, function, function_type, ByteString::number(imported_function_count));
                         address = cache.abstract_machine().store().allocate(move(host_function));
                         // FIXME: 3.4.3.2. Let index be the number of external functions in imports. This value index is known as the index of the host function funcaddr.
                         //        'index' doesn't seem to be used anywhere?
@@ -342,6 +343,7 @@ JS::ThrowCompletionOr<NonnullRefPtr<Wasm::ModuleInstance>> instantiate_module(JS
                     // 3.4.4. Let externfunc be the external value func funcaddr.
                     // 3.4.5. Append externfunc to imports.
                     resolved_imports.set(import_name, Wasm::ExternValue { Wasm::FunctionAddress { *address } });
+                    ++imported_function_count;
                     return {};
                 },
                 // 3.5. If externtype is of the form global mut valtype,
@@ -647,14 +649,20 @@ JS::ThrowCompletionOr<JS::HandledByHost> host_grow_shared_array_buffer(JS::VM& v
 
 GC_DEFINE_ALLOCATOR(ExportedWasmFunction);
 
-GC::Ref<ExportedWasmFunction> ExportedWasmFunction::create(JS::Realm& realm, Utf16FlyString name, Function<JS::ThrowCompletionOr<JS::Value>(JS::VM&)> behavior, Wasm::FunctionAddress exported_address)
+GC::Ref<ExportedWasmFunction> ExportedWasmFunction::create(JS::Realm& realm, Utf16FlyString name, size_t length, Function<JS::ThrowCompletionOr<JS::Value>(JS::VM&)> behavior, Wasm::FunctionAddress exported_address)
 {
+    auto& vm = realm.vm();
+
     auto prototype = realm.intrinsics().function_prototype();
-    return realm.create<ExportedWasmFunction>(
+    auto function = realm.create<ExportedWasmFunction>(
         move(name),
         move(behavior),
         exported_address,
         prototype);
+    function->define_direct_property(vm.names.length, JS::Value { static_cast<double>(length) }, JS::Attribute::Configurable);
+    function->define_direct_property(vm.names.name, JS::PrimitiveString::create(vm, function->name()), JS::Attribute::Configurable);
+
+    return function;
 }
 
 ExportedWasmFunction::ExportedWasmFunction(Utf16FlyString name, AK::Function<JS::ThrowCompletionOr<JS::Value>(JS::VM&)> behavior, Wasm::FunctionAddress exported_address, JS::Object& prototype)
@@ -676,19 +684,57 @@ JS::ThrowCompletionOr<JS::Value> ExportedWasmFunction::call()
     return m_behavior(vm());
 }
 
-JS::NativeFunction* create_native_function(JS::VM& vm, Wasm::FunctionAddress address, Utf16FlyString name, Instance* instance)
+// https://www.w3.org/TR/wasm-js-api-2/#name-of-the-webassembly-function
+static Utf16FlyString name_of_webassembly_function(Wasm::Store& store, Wasm::FunctionAddress function_address)
+{
+    // 1. Let store be the surrounding agent’s associated store.
+
+    // 2. Let funcinst be store.funcs[funcaddr].
+    auto* function_instance = store.get(function_address);
+    VERIFY(function_instance);
+
+    auto index = function_instance->visit(
+        // 3. If funcinst is of the form {type functype, hostcode hostfunc},
+        [&](Wasm::HostFunction const& host_function) {
+            // 1. Assert: hostfunc is a JavaScript object and IsCallable(hostfunc) is true.
+            // 2. Let index be the index of the host function funcaddr.
+            auto index = host_function.name().to_number<size_t>(TrimWhitespace::No);
+            VERIFY(index.has_value());
+            return *index;
+        },
+        // 4. Otherwise,
+        [&](Wasm::WasmFunction const& wasm_function) {
+            // 1. Let moduleinst be funcinst.module.
+            auto const& module_instance = wasm_function.module();
+
+            // 2. Assert: funcaddr is contained in moduleinst.funcaddrs.
+            // 3. Let index be the index of moduleinst.funcaddrs where funcaddr is found.
+            auto index = module_instance.functions().find_first_index(function_address);
+            VERIFY(index.has_value());
+            return *index;
+        });
+
+    // 5. Return ! ToString(index).
+    return Utf16String::number(index);
+}
+
+JS::NativeFunction* create_native_function(JS::VM& vm, Wasm::FunctionAddress address, Instance* instance)
 {
     auto& realm = *vm.current_realm();
-    Optional<Wasm::FunctionType> type;
     auto& cache = get_cache(realm);
-    cache.abstract_machine().store().get(address)->visit([&](auto const& value) { type = value.type(); });
+
     if (auto entry = cache.get_function_instance(address); entry.has_value())
         return *entry;
 
+    auto& store = cache.abstract_machine().store();
+    auto type = store.get(address)->visit([&](auto const& value) { return value.type(); });
+    auto length = type.parameters().size();
+
     auto function = ExportedWasmFunction::create(
         realm,
-        move(name),
+        name_of_webassembly_function(store, address),
-        [address, type = type.release_value(), instance](JS::VM& vm) -> JS::ThrowCompletionOr<JS::Value> {
+        length,
+        [address, type = move(type), instance](JS::VM& vm) -> JS::ThrowCompletionOr<JS::Value> {
             (void)instance;
             auto& realm = *vm.current_realm();
             Vector<Wasm::Value> values;
@@ -861,17 +907,7 @@ JS::Value to_js_value(JS::VM& vm, Wasm::Value& wasm_value, Wasm::ValueType type)
         if (ref_.ref().has<Wasm::Reference::Null>())
             return JS::js_null();
         auto address = ref_.ref().get<Wasm::Reference::Func>().address;
-        auto& cache = get_cache(realm);
+        return create_native_function(vm, address);
-        auto* function = cache.abstract_machine().store().get(address);
-        auto name = function->visit(
-            [&](Wasm::WasmFunction& wasm_function) {
-                auto index = *wasm_function.module().functions().find_first_index(address);
-                return ByteString::formatted("func{}", index);
-            },
-            [](Wasm::HostFunction& host_function) {
-                return host_function.name();
-            });
-        return create_native_function(vm, address, Utf16FlyString::from_utf8(name));
     }
     case Wasm::ValueType::ExternReference: {
         auto ref_ = wasm_value.to<Wasm::Reference>();

Libraries/LibWeb/WebAssembly/WebAssembly.h

@@ -101,7 +101,7 @@ class ExportedWasmFunction final : public JS::NativeFunction {
     GC_DECLARE_ALLOCATOR(ExportedWasmFunction);
 
 public:
-    static GC::Ref<ExportedWasmFunction> create(JS::Realm&, Utf16FlyString name, ESCAPING Function<JS::ThrowCompletionOr<JS::Value>(JS::VM&)>, Wasm::FunctionAddress);
+    static GC::Ref<ExportedWasmFunction> create(JS::Realm&, Utf16FlyString name, size_t length, ESCAPING Function<JS::ThrowCompletionOr<JS::Value>(JS::VM&)>, Wasm::FunctionAddress);
     virtual ~ExportedWasmFunction() override = default;
 
     Wasm::FunctionAddress exported_address() const { return m_exported_address; }
@@ -122,7 +122,7 @@ WebAssemblyCache& get_cache(JS::Realm&);
 
 JS::ThrowCompletionOr<NonnullRefPtr<Wasm::ModuleInstance>> instantiate_module(JS::VM&, Wasm::Module const&, GC::Ptr<JS::Object> import_object);
 JS::ThrowCompletionOr<NonnullRefPtr<CompiledWebAssemblyModule>> compile_a_webassembly_module(JS::VM&, ByteBuffer);
-JS::NativeFunction* create_native_function(JS::VM&, Wasm::FunctionAddress address, Utf16FlyString name, Instance* instance = nullptr);
+JS::NativeFunction* create_native_function(JS::VM&, Wasm::FunctionAddress address, Instance* instance = nullptr);
 JS::ThrowCompletionOr<Wasm::Value> to_webassembly_value(JS::VM&, JS::Value value, Wasm::ValueType const& type);
 Wasm::Value default_webassembly_value(JS::VM&, Wasm::ValueType type);
 JS::Value to_js_value(JS::VM&, Wasm::Value& wasm_value, Wasm::ValueType type);

Libraries/LibWeb/XPath/XPath.cpp

@@ -92,7 +92,10 @@ static xmlNodePtr mirror_node(xmlDocPtr doc, DOM::Node const& node)
     }
     case DOM::NodeType::DOCUMENT_NODE: {
         auto const& document = static_cast<DOM::Document const&>(node);
-        return mirror_node(doc, *document.document_element());
+        auto const* document_element = document.document_element();
+        if (!document_element)
+            return nullptr;
+        return mirror_node(doc, *document_element);
     }
     case DOM::NodeType::DOCUMENT_TYPE_NODE: {
         return nullptr; // Unused in libxml2

Libraries/LibWebView/Autocomplete.cpp

@@ -438,7 +438,7 @@ ErrorOr<Vector<String>> Autocomplete::received_autocomplete_respsonse(Autocomple
     if (!decoder.has_value())
         decoder = TextCodec::decoder_for_exact_name("UTF-8"sv);
 
-    auto decoded_response = TRY(decoder->to_utf8(response));
+    auto decoded_response = TRY(decoder->to_utf8(response, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement));
     auto json = TRY(JsonValue::from_string(decoded_response));
 
     if (engine.name == "DuckDuckGo")

Meta/Fuzzers/FuzzTextDecoder.cpp

@@ -24,6 +24,6 @@ extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
     if (!decoder.has_value())
         return 0;
 
-    (void)decoder->to_utf8(encoded_data);
+    (void)decoder->to_utf8(encoded_data, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement);
     return 0;
 }

Services/RequestServer/Request.cpp

@@ -1085,7 +1085,7 @@ size_t Request::on_header_received(void* buffer, size_t size, size_t nmemb, void
                 auto decoder = TextCodec::decoder_for_exact_name("ISO-8859-1"sv);
                 VERIFY(decoder.has_value());
 
-                request.m_reason_phrase = MUST(decoder->to_utf8(reason_phrase));
+                request.m_reason_phrase = MUST(decoder->to_utf8(reason_phrase, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement));
                 return total_size;
             }
         }

Tests/LibTextCodec/TestTextDecoders.cpp

@@ -37,13 +37,13 @@ TEST_CASE(test_utf8_decode)
     // Bytes for U+1F600 GRINNING FACE
     auto test_string = "\xf0\x9f\x98\x80"sv;
 
-    EXPECT(decoder.validate(test_string));
+    EXPECT(!decoder.to_utf8(test_string, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
 
     auto processed_code_points = process_code_points(decoder, test_string);
     EXPECT(processed_code_points.size() == 1);
     EXPECT(processed_code_points[0] == 0x1F600);
 
-    EXPECT(MUST(decoder.to_utf8(test_string)) == test_string);
+    EXPECT(MUST(decoder.to_utf8(test_string, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)) == test_string);
 }
 
 TEST_CASE(test_utf8_process_code_points)
@@ -60,8 +60,8 @@ TEST_CASE(test_utf8_process_code_points_replaces_surrogates)
     auto utf8_encoded_surrogate_bytes = Vector<u8> { 0xed, 0xa0, 0x80 };
     auto utf8_encoded_surrogate = StringView(bytes(utf8_encoded_surrogate_bytes));
 
-    EXPECT(!decoder.validate(utf8_encoded_surrogate));
+    EXPECT(decoder.to_utf8(utf8_encoded_surrogate, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
-    EXPECT_EQ(MUST(decoder.to_utf8(utf8_encoded_surrogate)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(utf8_encoded_surrogate, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(process_code_points(decoder, utf8_encoded_surrogate), (Vector<u32> { 0xfffd, 0xfffd, 0xfffd }));
 }
 
@@ -71,8 +71,8 @@ TEST_CASE(test_utf8_process_code_points_replaces_truncated_tail_as_single_error)
     auto truncated_tail_bytes = Vector<u8> { 0xf0, 0x9f, 0x98 };
     auto truncated_tail = StringView(bytes(truncated_tail_bytes));
 
-    EXPECT(!decoder.validate(truncated_tail));
+    EXPECT(decoder.to_utf8(truncated_tail, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
-    EXPECT_EQ(MUST(decoder.to_utf8(truncated_tail)), "\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(truncated_tail, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "\xef\xbf\xbd"sv);
     EXPECT_EQ(process_code_points(decoder, truncated_tail), (Vector<u32> { 0xfffd }));
 }
 
@@ -82,8 +82,8 @@ TEST_CASE(test_utf8_process_code_points_replaces_overlong_sequences)
     auto overlong_null_bytes = Vector<u8> { 0xc0, 0x80 };
     auto overlong_null = StringView(bytes(overlong_null_bytes));
 
-    EXPECT(!decoder.validate(overlong_null));
+    EXPECT(decoder.to_utf8(overlong_null, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
-    EXPECT_EQ(MUST(decoder.to_utf8(overlong_null)), "\xef\xbf\xbd\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(overlong_null, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(process_code_points(decoder, overlong_null), (Vector<u32> { 0xfffd, 0xfffd }));
 }
 
@@ -95,12 +95,12 @@ TEST_CASE(test_utf8_process_code_points_restores_invalid_second_byte)
     auto out_of_range_four_byte_sequence_bytes = Vector<u8> { 0xf4, 0x90, 0x80, 0x80 };
     auto out_of_range_four_byte_sequence = StringView(bytes(out_of_range_four_byte_sequence_bytes));
 
-    EXPECT(!decoder.validate(overlong_three_byte_sequence));
+    EXPECT(decoder.to_utf8(overlong_three_byte_sequence, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
-    EXPECT_EQ(MUST(decoder.to_utf8(overlong_three_byte_sequence)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(overlong_three_byte_sequence, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(process_code_points(decoder, overlong_three_byte_sequence), (Vector<u32> { 0xfffd, 0xfffd, 0xfffd }));
 
-    EXPECT(!decoder.validate(out_of_range_four_byte_sequence));
+    EXPECT(decoder.to_utf8(out_of_range_four_byte_sequence, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal).is_error());
-    EXPECT_EQ(MUST(decoder.to_utf8(out_of_range_four_byte_sequence)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(out_of_range_four_byte_sequence, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(process_code_points(decoder, out_of_range_four_byte_sequence), (Vector<u32> { 0xfffd, 0xfffd, 0xfffd, 0xfffd }));
 }
 
@@ -110,8 +110,7 @@ TEST_CASE(test_utf16be_decode)
     // This is the output of `python3 -c "print('säk😀'.encode('utf-16be'))"`.
     auto test_string = "\x00s\x00\xe4\x00k\xd8=\xde\x00"sv;
 
-    EXPECT(decoder.validate(test_string));
+    auto utf8 = MUST(decoder.to_utf8(test_string, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal));
-    auto utf8 = MUST(decoder.to_utf8(test_string));
     EXPECT_EQ(utf8, "säk😀"sv);
 }
 
@@ -122,12 +121,12 @@ TEST_CASE(test_utf16be_process_code_points)
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 0xfe, 0xff, 0x00, 'A', 0xd8, 0x3d, 0xde, 0x00 }))), (Vector<u32> { 0x41, 0x1F600 }));
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 0xd8, 0x3d, 0x00, 'A', 0xde, 0x00 }))), (Vector<u32> { 0xfffd, 0x41, 0xfffd }));
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 0x00, 'A', 0xff }))), (Vector<u32> { 0x41, 0xfffd }));
-    EXPECT_EQ(MUST(decoder.to_utf8(StringView(bytes({ 0x00, 'A', 0xff })))), "A\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(StringView(bytes({ 0x00, 'A', 0xff })), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "A\xef\xbf\xbd"sv);
 }
 
 TEST_CASE(test_streaming_decoder_utf8_mid_sequence)
 {
-    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 'a', 0xc3 }))), "a"sv);
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xa9, 'b' }))), "éb"sv);
@@ -137,27 +136,27 @@ TEST_CASE(test_streaming_decoder_utf8_mid_sequence)
 TEST_CASE(test_streaming_decoder_finishes_incomplete_sequence)
 {
     auto& decoder = decoder_for("UTF-8"sv);
-    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
 
     auto incomplete_sequence = Vector<u8> { 0xc3 };
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes(incomplete_sequence))), ""sv);
-    EXPECT_EQ(MUST(streaming_decoder.finish()), MUST(decoder.to_utf8(StringView(bytes(incomplete_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder.finish()), MUST(decoder.to_utf8(StringView(bytes(incomplete_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
 }
 
 TEST_CASE(test_streaming_decoder_utf8_invalid_second_byte_tail)
 {
-    auto streaming_decoder_for_overlong_three_byte_sequence = TextCodec::StreamingDecoder { "UTF-8"sv };
+    auto streaming_decoder_for_overlong_three_byte_sequence = TextCodec::StreamingDecoder { "UTF-8"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     EXPECT_EQ(MUST(streaming_decoder_for_overlong_three_byte_sequence.to_utf8(bytes({ 0xe0, 0x80 }))), "\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(MUST(streaming_decoder_for_overlong_three_byte_sequence.finish()), ""sv);
 
-    auto streaming_decoder_for_out_of_range_four_byte_sequence = TextCodec::StreamingDecoder { "UTF-8"sv };
+    auto streaming_decoder_for_out_of_range_four_byte_sequence = TextCodec::StreamingDecoder { "UTF-8"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     EXPECT_EQ(MUST(streaming_decoder_for_out_of_range_four_byte_sequence.to_utf8(bytes({ 0xf4, 0x90 }))), "\xef\xbf\xbd\xef\xbf\xbd"sv);
     EXPECT_EQ(MUST(streaming_decoder_for_out_of_range_four_byte_sequence.finish()), ""sv);
 }
 
 TEST_CASE(test_streaming_decoder_utf8_valid_second_byte_tail)
 {
-    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-8"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xe0, 0xa0 }))), ""sv);
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x80 }))), "\xe0\xa0\x80"sv);
@@ -166,7 +165,7 @@ TEST_CASE(test_streaming_decoder_utf8_valid_second_byte_tail)
 
 TEST_CASE(test_streaming_decoder_utf16_odd_byte)
 {
-    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-16LE"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-16LE"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x41, 0x00, 0x42 }))), "A"sv);
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x00 }))), "B"sv);
@@ -175,7 +174,7 @@ TEST_CASE(test_streaming_decoder_utf16_odd_byte)
 
 TEST_CASE(test_streaming_decoder_utf16_surrogate_pair_split)
 {
-    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-16BE"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "UTF-16BE"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x00, 0x41, 0xd8, 0x3d }))), "A"sv);
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xde, 0x00 }))), "😀"sv);
@@ -185,48 +184,48 @@ TEST_CASE(test_streaming_decoder_utf16_surrogate_pair_split)
 TEST_CASE(test_streaming_decoder_gb18030_four_byte_tail)
 {
     auto& decoder = decoder_for("gb18030"sv);
-    auto streaming_decoder = TextCodec::StreamingDecoder { "gb18030"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "gb18030"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     auto gb18030_sequence = Vector<u8> { 0x81, 0x30, 0x81, 0x30 };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 'a', 0x81, 0x30, 0x81 }))), "a"sv);
-    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x30 }))), MUST(decoder.to_utf8(StringView(bytes(gb18030_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x30 }))), MUST(decoder.to_utf8(StringView(bytes(gb18030_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
     EXPECT_EQ(MUST(streaming_decoder.finish()), ""sv);
 }
 
 TEST_CASE(test_streaming_decoder_big5_overlapping_trail)
 {
     auto& decoder = decoder_for("Big5"sv);
-    auto streaming_decoder = TextCodec::StreamingDecoder { "Big5"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "Big5"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     auto big5_sequence = Vector<u8> { 0xa4, 0xa4 };
 
-    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes(big5_sequence))), MUST(decoder.to_utf8(StringView(bytes(big5_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes(big5_sequence))), MUST(decoder.to_utf8(StringView(bytes(big5_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
     EXPECT_EQ(MUST(streaming_decoder.finish()), ""sv);
 
-    auto streaming_decoder_for_split_input = TextCodec::StreamingDecoder { "Big5"sv };
+    auto streaming_decoder_for_split_input = TextCodec::StreamingDecoder { "Big5"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     EXPECT_EQ(MUST(streaming_decoder_for_split_input.to_utf8(bytes({ 0xa4 }))), ""sv);
-    EXPECT_EQ(MUST(streaming_decoder_for_split_input.to_utf8(bytes({ 0xa4 }))), MUST(decoder.to_utf8(StringView(bytes(big5_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder_for_split_input.to_utf8(bytes({ 0xa4 }))), MUST(decoder.to_utf8(StringView(bytes(big5_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
     EXPECT_EQ(MUST(streaming_decoder_for_split_input.finish()), ""sv);
 }
 
 TEST_CASE(test_streaming_decoder_euc_jp_three_byte_tail)
 {
     auto& decoder = decoder_for("EUC-JP"sv);
-    auto streaming_decoder = TextCodec::StreamingDecoder { "EUC-JP"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "EUC-JP"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     auto euc_jp_sequence = Vector<u8> { 0x8f, 0xa2, 0xaf };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x8f, 0xa2 }))), ""sv);
-    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xaf }))), MUST(decoder.to_utf8(StringView(bytes(euc_jp_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xaf }))), MUST(decoder.to_utf8(StringView(bytes(euc_jp_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
     EXPECT_EQ(MUST(streaming_decoder.finish()), ""sv);
 }
 
 TEST_CASE(test_streaming_decoder_shift_jis_tail)
 {
     auto& decoder = decoder_for("Shift_JIS"sv);
-    auto streaming_decoder = TextCodec::StreamingDecoder { "Shift_JIS"sv };
+    auto streaming_decoder = TextCodec::StreamingDecoder { "Shift_JIS"sv, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement };
     auto shift_jis_sequence = Vector<u8> { 0x82, 0xa0 };
 
     EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0x82 }))), ""sv);
-    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xa0 }))), MUST(decoder.to_utf8(StringView(bytes(shift_jis_sequence)))));
+    EXPECT_EQ(MUST(streaming_decoder.to_utf8(bytes({ 0xa0 }))), MUST(decoder.to_utf8(StringView(bytes(shift_jis_sequence)), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)));
     EXPECT_EQ(MUST(streaming_decoder.finish()), ""sv);
 }
 
@@ -236,8 +235,7 @@ TEST_CASE(test_utf16le_decode)
     // This is the output of `python3 -c "print('säk😀'.encode('utf-16le'))"`.
     auto test_string = "s\x00\xe4\x00k\x00=\xd8\x00\xde"sv;
 
-    EXPECT(decoder.validate(test_string));
+    auto utf8 = MUST(decoder.to_utf8(test_string, TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Fatal));
-    auto utf8 = MUST(decoder.to_utf8(test_string));
     EXPECT_EQ(utf8, "säk😀"sv);
 }
 
@@ -248,5 +246,5 @@ TEST_CASE(test_utf16le_process_code_points)
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 0xff, 0xfe, 'A', 0x00, 0x3d, 0xd8, 0x00, 0xde }))), (Vector<u32> { 0x41, 0x1F600 }));
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 0x3d, 0xd8, 'A', 0x00, 0x00, 0xde }))), (Vector<u32> { 0xfffd, 0x41, 0xfffd }));
     EXPECT_EQ(process_code_points(decoder, StringView(bytes({ 'A', 0x00, 0xff }))), (Vector<u32> { 0x41, 0xfffd }));
-    EXPECT_EQ(MUST(decoder.to_utf8(StringView(bytes({ 'A', 0x00, 0xff })))), "A\xef\xbf\xbd"sv);
+    EXPECT_EQ(MUST(decoder.to_utf8(StringView(bytes({ 'A', 0x00, 0xff })), TextCodec::IgnoreBOM::No, TextCodec::ErrorMode::Replacement)), "A\xef\xbf\xbd"sv);
 }

Tests/LibWeb/Crash/DOM/xpath-evaluate-rootless-document.html

@@ -0,0 +1,6 @@
+<!DOCTYPE html>
+<script>
+    // createDocument with an empty qualified name yields a document with no root element.
+    const doc = document.implementation.createDocument(null, "", null);
+    document.evaluate("/", doc, null, XPathResult.ANY_TYPE, null);
+</script>

Tests/LibWeb/Text/expected/Wasm/WebAssembly-exported-function-metadata.txt

@@ -0,0 +1,6 @@
+length: 2
+name: 0
+export name: sqlite3_aggregate_context
+length descriptor: writable=false, enumerable=false, configurable=true
+name descriptor: writable=false, enumerable=false, configurable=true
+call result: 42

Tests/LibWeb/Text/expected/wpt-import/encoding/streams/decode-ignore-bom.any.txt

@@ -0,0 +1,17 @@
+Harness status: OK
+
+Found 12 tests
+
+12 Pass
+Pass	ignoreBOM should work for encoding utf-8, split at character 0
+Pass	ignoreBOM should work for encoding utf-8, split at character 1
+Pass	ignoreBOM should work for encoding utf-8, split at character 2
+Pass	ignoreBOM should work for encoding utf-8, split at character 3
+Pass	ignoreBOM should work for encoding utf-16le, split at character 0
+Pass	ignoreBOM should work for encoding utf-16le, split at character 1
+Pass	ignoreBOM should work for encoding utf-16le, split at character 2
+Pass	ignoreBOM should work for encoding utf-16le, split at character 3
+Pass	ignoreBOM should work for encoding utf-16be, split at character 0
+Pass	ignoreBOM should work for encoding utf-16be, split at character 1
+Pass	ignoreBOM should work for encoding utf-16be, split at character 2
+Pass	ignoreBOM should work for encoding utf-16be, split at character 3

Tests/LibWeb/Text/expected/wpt-import/encoding/streams/realms.window.txt

@@ -2,17 +2,16 @@ Harness status: OK
 
 Found 12 tests
 
-4 Pass
+12 Pass
-8 Fail
 Pass	a TextEncoderStream object should be associated with the realm the constructor came from
 Pass	TextEncoderStream's readable and writable attributes should come from the same realm as the constructor definition
-Fail	the output chunks when read is called after write should come from the same realm as the constructor of TextEncoderStream
+Pass	the output chunks when read is called after write should come from the same realm as the constructor of TextEncoderStream
-Fail	the output chunks when write is called with a pending read should come from the same realm as the constructor of TextEncoderStream
+Pass	the output chunks when write is called with a pending read should come from the same realm as the constructor of TextEncoderStream
-Fail	TypeError for unconvertable chunk should come from constructor realm of TextEncoderStream
+Pass	TypeError for unconvertable chunk should come from constructor realm of TextEncoderStream
 Pass	a TextDecoderStream object should be associated with the realm the constructor came from
 Pass	TextDecoderStream's readable and writable attributes should come from the same realm as the constructor definition
-Fail	the result object when read is called after write should come from the same realm as the constructor of TextDecoderStream
+Pass	the result object when read is called after write should come from the same realm as the constructor of TextDecoderStream
-Fail	the result object when write is called with a pending read should come from the same realm as the constructor of TextDecoderStream
+Pass	the result object when write is called with a pending read should come from the same realm as the constructor of TextDecoderStream
-Fail	TypeError for chunk with the wrong type should come from constructor realm of TextDecoderStream
+Pass	TypeError for chunk with the wrong type should come from constructor realm of TextDecoderStream
-Fail	TypeError for invalid chunk should come from constructor realm of TextDecoderStream
+Pass	TypeError for invalid chunk should come from constructor realm of TextDecoderStream
-Fail	TypeError for incomplete input should come from constructor realm of TextDecoderStream
+Pass	TypeError for incomplete input should come from constructor realm of TextDecoderStream

Tests/LibWeb/Text/expected/wpt-import/encoding/textdecoder-fatal-streaming.any.txt

@@ -0,0 +1,8 @@
+Harness status: OK
+
+Found 2 tests
+
+1 Pass
+1 Fail
+Pass	Fatal flag, non-streaming cases
+Fail	Fatal flag, streaming cases

Tests/LibWeb/Text/expected/wpt-import/encoding/textdecoder-ignorebom.any.txt

@@ -2,9 +2,8 @@ Harness status: OK
 
 Found 4 tests
 
-1 Pass
+4 Pass
-3 Fail
+Pass	BOM is ignored if ignoreBOM option is specified: utf-8
-Fail	BOM is ignored if ignoreBOM option is specified: utf-8
+Pass	BOM is ignored if ignoreBOM option is specified: utf-16le
-Fail	BOM is ignored if ignoreBOM option is specified: utf-16le
+Pass	BOM is ignored if ignoreBOM option is specified: utf-16be
-Fail	BOM is ignored if ignoreBOM option is specified: utf-16be
 Pass	The ignoreBOM attribute of TextDecoder

Tests/LibWeb/Text/expected/wpt-import/encoding/textdecoder-mistakes.any.txt

@@ -2,8 +2,8 @@ Harness status: OK
 
 Found 87 tests
 
-72 Pass
+74 Pass
-15 Fail
+13 Fail
 Pass	Invalid Unicode input is replaced: utf-8
 Pass	Invalid Unicode input is replaced: utf-16le
 Pass	Invalid Unicode input is replaced: utf-16be
@@ -51,8 +51,8 @@ Pass	selected single-byte: iso-8859-8-i
 Pass	selected single-byte: iso-8859-16
 Pass	selected single-byte: x-mac-cyrillic
 Pass	Concatenating two ISO-2022-JP outputs is not always valid
-Fail	gb18030 version and ranges
+Pass	gb18030 version and ranges
-Fail	gbk version and ranges
+Pass	gbk version and ranges
 Pass	gbk decoder is gb18030 decoder
 Pass	Replacement, push back ASCII characters: big5
 Pass	Replacement, push back ASCII characters: iso-2022-jp

Tests/LibWeb/Text/input/Wasm/WebAssembly-exported-function-metadata.html

@@ -0,0 +1,32 @@
+<!DOCTYPE html>
+<script src="../include.js"></script>
+<script>
+    asyncTest(async (done) => {
+        const wasmBytes = new Uint8Array([
+            0x00, 0x61, 0x73, 0x6d, 0x01, 0x00, 0x00, 0x00,
+            0x01, 0x07, 0x01, 0x60, 0x02, 0x7f, 0x7f, 0x01, 0x7f,
+            0x03, 0x02, 0x01, 0x00,
+            0x07, 0x1d, 0x01, 0x19,
+            0x73, 0x71, 0x6c, 0x69, 0x74, 0x65, 0x33, 0x5f,
+            0x61, 0x67, 0x67, 0x72, 0x65, 0x67, 0x61, 0x74,
+            0x65, 0x5f, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74,
+            0x00, 0x00,
+            0x0a, 0x06, 0x01, 0x04, 0x00, 0x20, 0x00, 0x0b,
+        ]);
+
+        const { instance } = await WebAssembly.instantiate(wasmBytes);
+        const fn = instance.exports.sqlite3_aggregate_context;
+        const exportName = Object.getOwnPropertyNames(instance.exports)[0];
+        const lengthDescriptor = Object.getOwnPropertyDescriptor(fn, "length");
+        const nameDescriptor = Object.getOwnPropertyDescriptor(fn, "name");
+
+        println(`length: ${fn.length}`);
+        println(`name: ${fn.name}`);
+        println(`export name: ${exportName}`);
+        println(`length descriptor: writable=${lengthDescriptor.writable}, enumerable=${lengthDescriptor.enumerable}, configurable=${lengthDescriptor.configurable}`);
+        println(`name descriptor: writable=${nameDescriptor.writable}, enumerable=${nameDescriptor.enumerable}, configurable=${nameDescriptor.configurable}`);
+        println(`call result: ${fn(42, 7)}`);
+
+        done();
+    });
+</script>

Tests/LibWeb/Text/input/wpt-import/encoding/streams/decode-ignore-bom.any.html

@@ -0,0 +1,16 @@
+<!doctype html>
+<meta charset=utf-8>
+
+<script>
+self.GLOBAL = {
+  isWindow: function() { return true; },
+  isWorker: function() { return false; },
+  isShadowRealm: function() { return false; },
+};
+</script>
+<script src="../../resources/testharness.js"></script>
+<script src="../../resources/testharnessreport.js"></script>
+<script src="resources/readable-stream-from-array.js"></script>
+<script src="resources/readable-stream-to-array.js"></script>
+<div id=log></div>
+<script src="../../encoding/streams/decode-ignore-bom.any.js"></script>

Tests/LibWeb/Text/input/wpt-import/encoding/streams/decode-ignore-bom.any.js

@@ -0,0 +1,38 @@
+// META: global=window,worker
+// META: script=resources/readable-stream-from-array.js
+// META: script=resources/readable-stream-to-array.js
+
+const cases = [
+    {encoding: 'utf-8', bytes: [0xEF, 0xBB, 0xBF, 0x61, 0x62, 0x63]},
+    {encoding: 'utf-16le', bytes: [0xFF, 0xFE, 0x61, 0x00, 0x62, 0x00, 0x63, 0x00]},
+    {encoding: 'utf-16be', bytes: [0xFE, 0xFF, 0x00, 0x61, 0x00, 0x62, 0x00, 0x63]}
+];
+const BOM = '\uFEFF';
+
+// |inputChunks| is an array of chunks, each represented by an array of
+// integers. |ignoreBOM| is true or false. The result value is the output of the
+// pipe, concatenated into a single string.
+async function pipeAndAssemble(inputChunks, encoding, ignoreBOM) {
+  const chunksAsUint8 = inputChunks.map(values => new Uint8Array(values));
+  const readable = readableStreamFromArray(chunksAsUint8);
+  const outputArray = await readableStreamToArray(readable.pipeThrough(
+      new TextDecoderStream(encoding, {ignoreBOM})));
+  return outputArray.join('');
+}
+
+for (const testCase of cases) {
+  for (let splitPoint = 0; splitPoint < 4; ++splitPoint) {
+    promise_test(async () => {
+      const inputChunks = [testCase.bytes.slice(0, splitPoint),
+                           testCase.bytes.slice(splitPoint)];
+      const withIgnoreBOM =
+            await pipeAndAssemble(inputChunks, testCase.encoding, true);
+      assert_equals(withIgnoreBOM, BOM + 'abc', 'BOM should be preserved');
+
+      const withoutIgnoreBOM =
+            await pipeAndAssemble(inputChunks, testCase.encoding, false);
+      assert_equals(withoutIgnoreBOM, 'abc', 'BOM should be stripped')
+    }, `ignoreBOM should work for encoding ${testCase.encoding}, split at ` +
+       `character ${splitPoint}`);
+  }
+}

Tests/LibWeb/Text/input/wpt-import/encoding/textdecoder-fatal-streaming.any.html

@@ -0,0 +1,15 @@
+<!doctype html>
+<meta charset=utf-8>
+<title>Encoding API: End-of-file</title>
+<script>
+self.GLOBAL = {
+  isWindow: function() { return true; },
+  isWorker: function() { return false; },
+  isShadowRealm: function() { return false; },
+};
+</script>
+<script src="../resources/testharness.js"></script>
+<script src="../resources/testharnessreport.js"></script>
+
+<div id=log></div>
+<script src="../encoding/textdecoder-fatal-streaming.any.js"></script>

Tests/LibWeb/Text/input/wpt-import/encoding/textdecoder-fatal-streaming.any.js

@@ -0,0 +1,45 @@
+// META: global=window,dedicatedworker
+// META: title=Encoding API: End-of-file
+
+test(function() {
+    [
+        {encoding: 'utf-8', sequence: [0xC0]},
+        {encoding: 'utf-16le', sequence: [0x00]},
+        {encoding: 'utf-16be', sequence: [0x00]}
+    ].forEach(function(testCase) {
+
+        assert_throws_js(TypeError, function() {
+            var decoder = new TextDecoder(testCase.encoding, {fatal: true});
+            decoder.decode(new Uint8Array(testCase.sequence));
+        }, 'Unterminated ' + testCase.encoding + ' sequence should throw if fatal flag is set');
+
+        assert_equals(
+            new TextDecoder(testCase.encoding).decode(new Uint8Array([testCase.sequence])),
+            '\uFFFD',
+            'Unterminated UTF-8 sequence should emit replacement character if fatal flag is unset');
+    });
+}, 'Fatal flag, non-streaming cases');
+
+test(function() {
+
+    var decoder = new TextDecoder('utf-16le', {fatal: true});
+    var odd = new Uint8Array([0x00]);
+    var even = new Uint8Array([0x00, 0x00]);
+
+    assert_equals(decoder.decode(odd, {stream: true}), '');
+    assert_equals(decoder.decode(odd), '\u0000');
+
+    assert_throws_js(TypeError, function() {
+        decoder.decode(even, {stream: true});
+        decoder.decode(odd)
+    });
+
+    assert_throws_js(TypeError, function() {
+        decoder.decode(odd, {stream: true});
+        decoder.decode(even);
+    });
+
+    assert_equals(decoder.decode(even, {stream: true}), '\u0000');
+    assert_equals(decoder.decode(even), '\u0000');
+
+}, 'Fatal flag, streaming cases');