LibTextCodec+Everywhere: Port Decoders to new Strings

8 files changed, 41 insertions, 39 deletions

diff --git a/Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.cpp b/Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.cpp
index 8cb69ab0c7..f808bbaea7 100644
--- a/Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.cpp
+++ b/Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.cpp
@@ -206,37 +206,39 @@ Tokenizer::Tokenizer(StringView input, StringView encoding)
         bool last_was_carriage_return = false;
 
         // To filter code points from a stream of (unfiltered) code points input:
-        decoder->process(input, [&builder, &last_was_carriage_return](u32 code_point) {
-            // Replace any U+000D CARRIAGE RETURN (CR) code points,
-            // U+000C FORM FEED (FF) code points,
-            // or pairs of U+000D CARRIAGE RETURN (CR) followed by U+000A LINE FEED (LF)
-            // in input by a single U+000A LINE FEED (LF) code point.
-            if (code_point == '\r') {
-                if (last_was_carriage_return) {
-                    builder.append('\n');
-                } else {
-                    last_was_carriage_return = true;
-                }
-            } else {
-                if (last_was_carriage_return)
-                    builder.append('\n');
-
-                if (code_point == '\n') {
-                    if (!last_was_carriage_return)
-                        builder.append('\n');
-
-                } else if (code_point == '\f') {
-                    builder.append('\n');
-                    // Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (�).
-                } else if (code_point == 0x00 || (code_point >= 0xD800 && code_point <= 0xDFFF)) {
-                    builder.append_code_point(REPLACEMENT_CHARACTER);
-                } else {
-                    builder.append_code_point(code_point);
-                }
-
-                last_was_carriage_return = false;
-            }
-        });
+        decoder->process(input, [&builder, &last_was_carriage_return](u32 code_point) -> ErrorOr<void> {
+                   // Replace any U+000D CARRIAGE RETURN (CR) code points,
+                   // U+000C FORM FEED (FF) code points,
+                   // or pairs of U+000D CARRIAGE RETURN (CR) followed by U+000A LINE FEED (LF)
+                   // in input by a single U+000A LINE FEED (LF) code point.
+                   if (code_point == '\r') {
+                       if (last_was_carriage_return) {
+                           TRY(builder.try_append('\n'));
+                       } else {
+                           last_was_carriage_return = true;
+                       }
+                   } else {
+                       if (last_was_carriage_return)
+                           TRY(builder.try_append('\n'));
+
+                       if (code_point == '\n') {
+                           if (!last_was_carriage_return)
+                               TRY(builder.try_append('\n'));
+
+                       } else if (code_point == '\f') {
+                           TRY(builder.try_append('\n'));
+                           // Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (�).
+                       } else if (code_point == 0x00 || (code_point >= 0xD800 && code_point <= 0xDFFF)) {
+                           TRY(builder.try_append_code_point(REPLACEMENT_CHARACTER));
+                       } else {
+                           TRY(builder.try_append_code_point(code_point));
+                       }
+
+                       last_was_carriage_return = false;
+                   }
+                   return {};
+               })
+            .release_value_but_fixme_should_propagate_errors();
         return builder.to_string();
     };
 
diff --git a/Userland/Libraries/LibWeb/Encoding/TextDecoder.cpp b/Userland/Libraries/LibWeb/Encoding/TextDecoder.cpp
index af2cce78aa..1420352dbc 100644
--- a/Userland/Libraries/LibWeb/Encoding/TextDecoder.cpp
+++ b/Userland/Libraries/LibWeb/Encoding/TextDecoder.cpp
@@ -50,7 +50,7 @@ WebIDL::ExceptionOr<DeprecatedString> TextDecoder::decode(JS::Handle<JS::Object>
     if (data_buffer_or_error.is_error())
         return WebIDL::OperationError::create(realm(), "Failed to copy bytes from ArrayBuffer");
     auto& data_buffer = data_buffer_or_error.value();
-    return m_decoder.to_utf8({ data_buffer.data(), data_buffer.size() });
+    return TRY_OR_THROW_OOM(vm(), m_decoder.to_utf8({ data_buffer.data(), data_buffer.size() }));
 }
 
 }
diff --git a/Userland/Libraries/LibWeb/HTML/HTMLScriptElement.cpp b/Userland/Libraries/LibWeb/HTML/HTMLScriptElement.cpp
index b3904a5d84..8b9943944c 100644
--- a/Userland/Libraries/LibWeb/HTML/HTMLScriptElement.cpp
+++ b/Userland/Libraries/LibWeb/HTML/HTMLScriptElement.cpp
@@ -515,7 +515,7 @@ void HTMLScriptElement::resource_did_load()
     // we have to re-encode it to UTF-8.
     if (resource()->has_encoding()) {
         if (auto codec = TextCodec::decoder_for(resource()->encoding().value()); codec.has_value()) {
-            data = codec->to_utf8(data).to_byte_buffer();
+            data = codec->to_utf8(data).release_value_but_fixme_should_propagate_errors().to_deprecated_string().to_byte_buffer();
         }
     }
 
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
index 3dfd4e3274..f661ee6f80 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
@@ -2800,7 +2800,7 @@ HTMLTokenizer::HTMLTokenizer(StringView input, DeprecatedString const& encoding)
 {
     auto decoder = TextCodec::decoder_for(encoding);
     VERIFY(decoder.has_value());
-    m_decoded_input = decoder->to_utf8(input);
+    m_decoded_input = decoder->to_utf8(input).release_value_but_fixme_should_propagate_errors().to_deprecated_string();
     m_utf8_view = Utf8View(m_decoded_input);
     m_utf8_iterator = m_utf8_view.begin();
     m_prev_utf8_iterator = m_utf8_view.begin();
diff --git a/Userland/Libraries/LibWeb/HTML/Window.cpp b/Userland/Libraries/LibWeb/HTML/Window.cpp
index 1edac12573..c03b9e7425 100644
--- a/Userland/Libraries/LibWeb/HTML/Window.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Window.cpp
@@ -1421,9 +1421,9 @@ JS_DEFINE_NATIVE_FUNCTION(Window::atob)
     // NOTE: Any 8-bit encoding -> utf-8 decoder will work for this
     auto text_decoder = TextCodec::decoder_for("windows-1252"sv);
     VERIFY(text_decoder.has_value());
-    auto text = text_decoder->to_utf8(decoded.release_value());
+    auto text = TRY_OR_THROW_OOM(vm, text_decoder->to_utf8(decoded.release_value()));
 
-    return JS::PrimitiveString::create(vm, DeprecatedString(text));
+    return JS::PrimitiveString::create(vm, text);
 }
 
 JS_DEFINE_NATIVE_FUNCTION(Window::btoa)
diff --git a/Userland/Libraries/LibWeb/HTML/WorkerGlobalScope.cpp b/Userland/Libraries/LibWeb/HTML/WorkerGlobalScope.cpp
index c31c8982b1..e600860285 100644
--- a/Userland/Libraries/LibWeb/HTML/WorkerGlobalScope.cpp
+++ b/Userland/Libraries/LibWeb/HTML/WorkerGlobalScope.cpp
@@ -163,7 +163,7 @@ WebIDL::ExceptionOr<DeprecatedString> WorkerGlobalScope::atob(DeprecatedString c
     // decode_base64() returns a byte string. LibJS uses UTF-8 for strings. Use Latin1Decoder to convert bytes 128-255 to UTF-8.
     auto decoder = TextCodec::decoder_for("windows-1252"sv);
     VERIFY(decoder.has_value());
-    return decoder->to_utf8(decoded_data.value());
+    return TRY_OR_THROW_OOM(vm(), decoder->to_utf8(decoded_data.value()));
 }
 
 }
diff --git a/Userland/Libraries/LibWeb/Infra/JSON.cpp b/Userland/Libraries/LibWeb/Infra/JSON.cpp
index 5bc079c626..05d73c5dfc 100644
--- a/Userland/Libraries/LibWeb/Infra/JSON.cpp
+++ b/Userland/Libraries/LibWeb/Infra/JSON.cpp
@@ -27,7 +27,7 @@ WebIDL::ExceptionOr<JS::Value> parse_json_bytes_to_javascript_value(JS::VM& vm,
 {
     // 1. Let string be the result of running UTF-8 decode on bytes.
     TextCodec::UTF8Decoder decoder;
-    auto string = decoder.to_utf8(bytes);
+    auto string = TRY_OR_THROW_OOM(vm, decoder.to_utf8(bytes));
 
     // 2. Return the result of parsing a JSON string to an Infra value given string.
     return parse_json_string_to_javascript_value(vm, string);
diff --git a/Userland/Libraries/LibWeb/XHR/XMLHttpRequest.cpp b/Userland/Libraries/LibWeb/XHR/XMLHttpRequest.cpp
index 1f8529eb91..e12d38c38e 100644
--- a/Userland/Libraries/LibWeb/XHR/XMLHttpRequest.cpp
+++ b/Userland/Libraries/LibWeb/XHR/XMLHttpRequest.cpp
@@ -224,7 +224,7 @@ DeprecatedString XMLHttpRequest::get_text_response() const
     // If we don't support the decoder yet, let's crash instead of attempting to return something, as the result would be incorrect and create obscure bugs.
     VERIFY(decoder.has_value());
 
-    return TextCodec::convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte_order_mark(*decoder, m_received_bytes);
+    return TextCodec::convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte_order_mark(*decoder, m_received_bytes).release_value_but_fixme_should_propagate_errors().to_deprecated_string();
 }
 
 // https://xhr.spec.whatwg.org/#final-mime-type