system/serenity
system/serenity
1
0
Fork 0
mirror of https://github.com/SerenityOS/serenity synced 2024-10-14 20:03:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

LibTextCodec+Everywhere: Make TextCodec::decoder_for() take a StringView

Browse source 
We don't need a full String/DeprecatedString inside this function, so we
might as well not force users to create one.
This commit is contained in:
Sam Atkins 2023-02-13 17:23:31 +00:00 committed by Tim Flynn
parent 3c8bfa4662
commit d6075ef5b5
14 changed files with 16 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Meta/Lagom/Fuzzers/FuzzCyrillicDecoder.cpp
View file

@ -11,7 +11,7 @@
extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
{
auto* decoder = TextCodec::decoder_for("windows-1251");
auto* decoder = TextCodec::decoder_for("windows-1251"sv);
VERIFY(decoder);
decoder->to_utf8({ data, size });
return 0;

2
Meta/Lagom/Fuzzers/FuzzHebrewDecoder.cpp
View file

@ -11,7 +11,7 @@
extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
{
auto* decoder = TextCodec::decoder_for("windows-1255");
auto* decoder = TextCodec::decoder_for("windows-1255"sv);
VERIFY(decoder);
decoder->to_utf8({ data, size });
return 0;

2
Meta/Lagom/Fuzzers/FuzzLatin1Decoder.cpp
View file

@ -11,7 +11,7 @@
extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
{
auto* decoder = TextCodec::decoder_for("windows-1252");
auto* decoder = TextCodec::decoder_for("windows-1252"sv);
VERIFY(decoder);
decoder->to_utf8({ data, size });
return 0;

2
Meta/Lagom/Fuzzers/FuzzLatin2Decoder.cpp
View file

@ -11,7 +11,7 @@
extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
{
auto* decoder = TextCodec::decoder_for("iso-8859-2");
auto* decoder = TextCodec::decoder_for("iso-8859-2"sv);
VERIFY(decoder);
decoder->to_utf8({ data, size });
return 0;

2
Meta/Lagom/Fuzzers/FuzzUTF16BEDecoder.cpp
View file

@ -11,7 +11,7 @@
extern "C" int LLVMFuzzerTestOneInput(uint8_t const* data, size_t size)
{
auto* decoder = TextCodec::decoder_for("utf-16be");
auto* decoder = TextCodec::decoder_for("utf-16be"sv);
VERIFY(decoder);
decoder->to_utf8({ data, size });
return 0;

2
Userland/Libraries/LibGfx/Font/OpenType/Font.cpp
View file

@ -321,7 +321,7 @@ DeprecatedString Name::string_for_id(NameId id) const
auto const offset = name_record.string_offset;
if (platform_id == to_underlying(Platform::Windows)) {
static auto& decoder = *TextCodec::decoder_for("utf-16be");
static auto& decoder = *TextCodec::decoder_for("utf-16be"sv);
return decoder.to_utf8(StringView { (char const*)m_slice.offset_pointer(storage_offset + offset), length });
}

6
Userland/Libraries/LibGfx/ICC/TagTypes.cpp
View file

@ -747,7 +747,7 @@ ErrorOr<NonnullRefPtr<MultiLocalizedUnicodeTagData>> MultiLocalizedUnicodeTagDat
// "For the definition of language codes and country codes, see respectively
// ISO 639-1 and ISO 3166-1. The Unicode strings in storage should be encoded as 16-bit big-endian, UTF-16BE,
// and should not be NULL terminated."
auto& utf_16be_decoder = *TextCodec::decoder_for("utf-16be");
auto& utf_16be_decoder = *TextCodec::decoder_for("utf-16be"sv);
struct RawRecord {
BigEndian<u16> language_code;
@ -1023,7 +1023,7 @@ ErrorOr<NonnullRefPtr<TextDescriptionTagData>> TextDescriptionTagData::from_byte
return Error::from_string_literal("ICC::Profile: textDescriptionType Unicode description not \\0-terminated");
StringView utf_16be_data { unicode_description_data, byte_size_without_nul };
unicode_description = TRY(String::from_deprecated_string(TextCodec::decoder_for("utf-16be")->to_utf8(utf_16be_data)));
unicode_description = TRY(String::from_deprecated_string(TextCodec::decoder_for("utf-16be"sv)->to_utf8(utf_16be_data)));
}
// ScriptCode
@ -1069,7 +1069,7 @@ ErrorOr<NonnullRefPtr<TextDescriptionTagData>> TextDescriptionTagData::from_byte
if (macintosh_description_data[macintosh_description_length - 1] != '\0')
return Error::from_string_literal("ICC::Profile: textDescriptionType ScriptCode not \\0-terminated");
macintosh_description = TRY(String::from_deprecated_string(TextCodec::decoder_for("x-mac-roman")->to_utf8({ macintosh_description_data, (size_t)macintosh_description_length - 1 })));
macintosh_description = TRY(String::from_deprecated_string(TextCodec::decoder_for("x-mac-roman"sv)->to_utf8({ macintosh_description_data, (size_t)macintosh_description_length - 1 })));
} else {
dbgln("TODO: ICCProfile textDescriptionType ScriptCode {}, length {}", scriptcode_code, macintosh_description_length);
}

2
Userland/Libraries/LibPDF/Parser.cpp
View file

@ -267,7 +267,7 @@ NonnullRefPtr<StringObject> Parser::parse_string()
if (unencrypted_string.bytes().starts_with(Array<u8, 2> { 0xfe, 0xff })) {
// The string is encoded in UTF16-BE
string_object->set_string(TextCodec::decoder_for("utf-16be")->to_utf8(unencrypted_string));
string_object->set_string(TextCodec::decoder_for("utf-16be"sv)->to_utf8(unencrypted_string));
} else if (unencrypted_string.bytes().starts_with(Array<u8, 3> { 239, 187, 191 })) {
// The string is encoded in UTF-8. This is the default anyways, but if these bytes
// are explicitly included, we have to trim them

2
Userland/Libraries/LibTextCodec/Decoder.cpp
View file

@ -30,7 +30,7 @@ TurkishDecoder s_turkish_decoder;
XUserDefinedDecoder s_x_user_defined_decoder;
}
Decoder* decoder_for(DeprecatedString const& a_encoding)
Decoder* decoder_for(StringView a_encoding)
{
auto encoding = get_standardized_encoding(a_encoding);
if (encoding.has_value()) {

2
Userland/Libraries/LibTextCodec/Decoder.h
View file

@ -84,7 +84,7 @@ public:
virtual void process(StringView, Function<void(u32)> on_code_point) override;
};
Decoder* decoder_for(DeprecatedString const& encoding);
Decoder* decoder_for(StringView encoding);
Optional<StringView> get_standardized_encoding(StringView encoding);
// This returns the appropriate Unicode decoder for the sniffed BOM or nullptr if there is no appropriate decoder.

2
Userland/Libraries/LibWeb/HTML/Window.cpp
View file

@ -1419,7 +1419,7 @@ JS_DEFINE_NATIVE_FUNCTION(Window::atob)
// The bytes object might contain bytes greater than 128, encode them in UTF8
// NOTE: Any 8-bit encoding -> utf-8 decoder will work for this
auto text_decoder = TextCodec::decoder_for("windows-1252");
auto text_decoder = TextCodec::decoder_for("windows-1252"sv);
VERIFY(text_decoder);
auto text = text_decoder->to_utf8(decoded.release_value());

2
Userland/Libraries/LibWeb/HTML/WorkerGlobalScope.cpp
View file

@ -158,7 +158,7 @@ WebIDL::ExceptionOr<DeprecatedString> WorkerGlobalScope::atob(DeprecatedString c
// 3. Return decodedData.
// 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");
auto* decoder = TextCodec::decoder_for("windows-1252"sv);
VERIFY(decoder);
return decoder->to_utf8(decoded_data.value());
}

2
Userland/Libraries/LibWeb/Loader/Resource.cpp
View file

@ -81,7 +81,7 @@ static DeprecatedString mime_type_from_content_type(DeprecatedString const& cont
return content_type;
}
static bool is_valid_encoding(DeprecatedString const& encoding)
static bool is_valid_encoding(StringView encoding)
{
return TextCodec::decoder_for(encoding);
}

2
Userland/Utilities/js.cpp
View file

@ -877,7 +877,7 @@ ErrorOr<int> serenity_main(Main::Arguments arguments)
if (Utf8View { file_contents }.validate()) {
builder.append(source);
} else {
auto* decoder = TextCodec::decoder_for("windows-1252");
auto* decoder = TextCodec::decoder_for("windows-1252"sv);
VERIFY(decoder);
auto utf8_source = TextCodec::convert_input_to_utf8_using_given_decoder_unless_there_is_a_byte_order_mark(*decoder, source);