beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-21 23:20:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

Everywhere: codepoint => code point

Browse source
This commit is contained in:
Andreas Kling 2021-06-01 10:01:11 +02:00
parent a8ae8b24de
commit 12a42edd13
Notes: sideshowbarker 2024-07-18 17:03:28 +09:00 
Author: https://github.com/awesomekling
Commit: https://github.com/SerenityOS/serenity/commit/12a42edd13f
18 changed files with 240 additions and 240 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
AK/Utf8View.cpp
View file

@ -71,20 +71,20 @@ Utf8View Utf8View::substring_view(size_t byte_offset, size_t byte_length) const
return Utf8View { string };
}
Utf8View Utf8View::unicode_substring_view(size_t codepoint_offset, size_t codepoint_length) const
Utf8View Utf8View::unicode_substring_view(size_t code_point_offset, size_t code_point_length) const
{
if (codepoint_length == 0)
if (code_point_length == 0)
return {};
size_t codepoint_index = 0, offset_in_bytes = 0;
size_t code_point_index = 0, offset_in_bytes = 0;
for (auto iterator = begin(); !iterator.done(); ++iterator) {
if (codepoint_index == codepoint_offset)
if (code_point_index == code_point_offset)
offset_in_bytes = byte_offset_of(iterator);
if (codepoint_index == codepoint_offset + codepoint_length - 1) {
if (code_point_index == code_point_offset + code_point_length - 1) {
size_t length_in_bytes = byte_offset_of(++iterator) - offset_in_bytes;
return substring_view(offset_in_bytes, length_in_bytes);
}
++codepoint_index;
++code_point_index;
}
VERIFY_NOT_REACHED();

4
AK/Utf8View.h
View file

@ -64,8 +64,8 @@ public:
Utf8View substring_view(size_t byte_offset, size_t byte_length) const;
Utf8View substring_view(size_t byte_offset) const { return substring_view(byte_offset, byte_length() - byte_offset); }
Utf8View unicode_substring_view(size_t codepoint_offset, size_t codepoint_length) const;
Utf8View unicode_substring_view(size_t codepoint_offset) const { return unicode_substring_view(codepoint_offset, length() - codepoint_offset); }
Utf8View unicode_substring_view(size_t code_point_offset, size_t code_point_length) const;
Utf8View unicode_substring_view(size_t code_point_offset) const { return unicode_substring_view(code_point_offset, length() - code_point_offset); }
bool is_empty() const { return m_string.is_empty(); }
bool starts_with(const Utf8View&) const;

4
Userland/Libraries/LibGUI/IconView.cpp
View file

@ -435,8 +435,8 @@ void IconView::get_item_rects(int item_index, ItemData& item_data, const Gfx::Fo
Utf8View utf8_view(item_data.text);
auto it = utf8_view.begin();
for (; it != utf8_view.end(); ++it) {
auto codepoint = *it;
auto glyph_width = font.glyph_width(codepoint);
auto code_point = *it;
auto glyph_width = font.glyph_width(code_point);
if ((current_line_width + glyph_width + font.glyph_spacing()) > available_width) {
item_data.wrapped_text_lines.append(item_data.text.substring_view(current_line_start, utf8_view.byte_offset_of(it) - current_line_start));
current_line_start = utf8_view.byte_offset_of(it);

2
Userland/Libraries/LibGUI/VimEditingEngine.h
View file

@ -84,7 +84,7 @@ public:
EndOfWord,
// End of a WORD.
EndOfWORD,
// Characters (or Unicode codepoints based on how pedantic you want to
// Characters (or Unicode code points based on how pedantic you want to
// get).
Character,
// Used for find-mode.

18
Userland/Libraries/LibJS/Runtime/GlobalObject.cpp
View file

@ -248,15 +248,15 @@ JS_DEFINE_NATIVE_FUNCTION(GlobalObject::parse_int)
}
}
auto parse_digit = [&](u32 codepoint, i32 radix) -> Optional<i32> {
auto parse_digit = [&](u32 code_point, i32 radix) -> Optional<i32> {
i32 digit = -1;
if (isdigit(codepoint))
digit = codepoint - '0';
else if (islower(codepoint))
digit = 10 + (codepoint - 'a');
else if (isupper(codepoint))
digit = 10 + (codepoint - 'A');
if (isdigit(code_point))
digit = code_point - '0';
else if (islower(code_point))
digit = 10 + (code_point - 'a');
else if (isupper(code_point))
digit = 10 + (code_point - 'A');
if (digit == -1 || digit >= radix)
return {};
@ -265,8 +265,8 @@ JS_DEFINE_NATIVE_FUNCTION(GlobalObject::parse_int)
bool had_digits = false;
double number = 0;
for (auto codepoint : Utf8View(s)) {
auto digit = parse_digit(codepoint, radix);
for (auto code_point : Utf8View(s)) {
auto digit = parse_digit(code_point, radix);
if (!digit.has_value())
break;
had_digits = true;

10
Userland/Libraries/LibPDF/Renderer.cpp
View file

@ -534,7 +534,7 @@ void Renderer::show_text(const String& string, int shift)
auto utf = Utf8View(string);
auto& font = text_state().font;
for (auto codepoint : utf) {
for (auto code_point : utf) {
// FIXME: Don't calculate this matrix for every character
auto& text_rendering_matrix = calculate_text_rendering_matrix();
@ -542,14 +542,14 @@ void Renderer::show_text(const String& string, int shift)
text_position.set_y(static_cast<float>(m_bitmap->height()) - text_position.y());
// FIXME: For some reason, the space character in LiberationSerif is drawn as an exclamation point
if (codepoint != 0x20)
m_painter.draw_glyph(text_position.to_type<int>(), codepoint, *text_state().font, state().paint_color);
if (code_point != 0x20)
m_painter.draw_glyph(text_position.to_type<int>(), code_point, *text_state().font, state().paint_color);
auto glyph_width = static_cast<float>(font->glyph_width(codepoint));
auto glyph_width = static_cast<float>(font->glyph_width(code_point));
auto tx = (glyph_width - static_cast<float>(shift) / 1000.0f);
tx += text_state().character_spacing;
if (codepoint == ' ')
if (code_point == ' ')
tx += text_state().word_spacing;
tx *= text_state().horizontal_scaling;

2
Userland/Libraries/LibRegex/RegexParser.cpp
View file

@ -1485,7 +1485,7 @@ bool ECMA262Parser::parse_nonempty_class_ranges(Vector<CompareTypeAndValuePair>&
if (try_skip("u")) {
if (auto code_point = read_digits(ReadDigitsInitialZeroState::Allow, true, 4); code_point.has_value()) {
// FIXME: While codepoint ranges are supported, codepoint matches as "Char" are not!
// FIXME: While code point ranges are supported, code point matches as "Char" are not!
return { { .code_point = code_point.value(), .is_character_class = false } };
} else if (!unicode) {
// '\u' is allowed in non-unicode mode, just matches 'u'.

36
Userland/Libraries/LibTTF/Cmap.cpp
View file

@ -75,72 +75,72 @@ Optional<Cmap::Subtable> Cmap::subtable(u32 index) const
}
// FIXME: This only handles formats 4 (SegmentToDelta) and 12 (SegmentedCoverage) for now.
u32 Cmap::Subtable::glyph_id_for_codepoint(u32 codepoint) const
u32 Cmap::Subtable::glyph_id_for_code_point(u32 code_point) const
{
switch (format()) {
case Format::SegmentToDelta:
return glyph_id_for_codepoint_table_4(codepoint);
return glyph_id_for_code_point_table_4(code_point);
case Format::SegmentedCoverage:
return glyph_id_for_codepoint_table_12(codepoint);
return glyph_id_for_code_point_table_12(code_point);
default:
return 0;
}
}
u32 Cmap::Subtable::glyph_id_for_codepoint_table_4(u32 codepoint) const
u32 Cmap::Subtable::glyph_id_for_code_point_table_4(u32 code_point) const
{
u32 segcount_x2 = be_u16(m_slice.offset_pointer((u32)Table4Offsets::SegCountX2));
if (m_slice.size() < segcount_x2 * (u32)Table4Sizes::NonConstMultiplier + (u32)Table4Sizes::Constant) {
return 0;
}
for (u32 offset = 0; offset < segcount_x2; offset += 2) {
u32 end_codepoint = be_u16(m_slice.offset_pointer((u32)Table4Offsets::EndConstBase + offset));
if (codepoint > end_codepoint) {
u32 end_code_point = be_u16(m_slice.offset_pointer((u32)Table4Offsets::EndConstBase + offset));
if (code_point > end_code_point) {
continue;
}
u32 start_codepoint = be_u16(m_slice.offset_pointer((u32)Table4Offsets::StartConstBase + segcount_x2 + offset));
if (codepoint < start_codepoint) {
u32 start_code_point = be_u16(m_slice.offset_pointer((u32)Table4Offsets::StartConstBase + segcount_x2 + offset));
if (code_point < start_code_point) {
break;
}
u32 delta = be_u16(m_slice.offset_pointer((u32)Table4Offsets::DeltaConstBase + segcount_x2 * 2 + offset));
u32 range = be_u16(m_slice.offset_pointer((u32)Table4Offsets::RangeConstBase + segcount_x2 * 3 + offset));
if (range == 0) {
return (codepoint + delta) & 0xffff;
return (code_point + delta) & 0xffff;
}
u32 glyph_offset = (u32)Table4Offsets::GlyphOffsetConstBase + segcount_x2 * 3 + offset + range + (codepoint - start_codepoint) * 2;
u32 glyph_offset = (u32)Table4Offsets::GlyphOffsetConstBase + segcount_x2 * 3 + offset + range + (code_point - start_code_point) * 2;
VERIFY(glyph_offset + 2 <= m_slice.size());
return (be_u16(m_slice.offset_pointer(glyph_offset)) + delta) & 0xffff;
}
return 0;
}
u32 Cmap::Subtable::glyph_id_for_codepoint_table_12(u32 codepoint) const
u32 Cmap::Subtable::glyph_id_for_code_point_table_12(u32 code_point) const
{
u32 num_groups = be_u32(m_slice.offset_pointer((u32)Table12Offsets::NumGroups));
VERIFY(m_slice.size() >= (u32)Table12Sizes::Header + (u32)Table12Sizes::Record * num_groups);
for (u32 offset = 0; offset < num_groups * (u32)Table12Sizes::Record; offset += (u32)Table12Sizes::Record) {
u32 start_codepoint = be_u32(m_slice.offset_pointer((u32)Table12Offsets::Record_StartCode + offset));
if (codepoint < start_codepoint) {
u32 start_code_point = be_u32(m_slice.offset_pointer((u32)Table12Offsets::Record_StartCode + offset));
if (code_point < start_code_point) {
break;
}
u32 end_codepoint = be_u32(m_slice.offset_pointer((u32)Table12Offsets::Record_EndCode + offset));
if (codepoint > end_codepoint) {
u32 end_code_point = be_u32(m_slice.offset_pointer((u32)Table12Offsets::Record_EndCode + offset));
if (code_point > end_code_point) {
continue;
}
u32 glyph_offset = be_u32(m_slice.offset_pointer((u32)Table12Offsets::Record_StartGlyph + offset));
return codepoint - start_codepoint + glyph_offset;
return code_point - start_code_point + glyph_offset;
}
return 0;
}
u32 Cmap::glyph_id_for_codepoint(u32 codepoint) const
u32 Cmap::glyph_id_for_code_point(u32 code_point) const
{
auto opt_subtable = subtable(m_active_index);
if (!opt_subtable.has_value()) {
return 0;
}
auto subtable = opt_subtable.value();
return subtable.glyph_id_for_codepoint(codepoint);
return subtable.glyph_id_for_code_point(code_point);
}
Optional<Cmap> Cmap::from_slice(const ReadonlyBytes& slice)

8
Userland/Libraries/LibTTF/Cmap.h
View file

@ -44,7 +44,7 @@ public:
{
}
// Returns 0 if glyph not found. This corresponds to the "missing glyph"
u32 glyph_id_for_codepoint(u32 codepoint) const;
u32 glyph_id_for_code_point(u32 code_point) const;
Platform platform_id() const;
u16 encoding_id() const { return m_encoding_id; }
Format format() const;
@ -73,8 +73,8 @@ public:
Record = 12,
};
u32 glyph_id_for_codepoint_table_4(u32 codepoint) const;
u32 glyph_id_for_codepoint_table_12(u32 codepoint) const;
u32 glyph_id_for_code_point_table_4(u32 code_point) const;
u32 glyph_id_for_code_point_table_12(u32 code_point) const;
ReadonlyBytes m_slice;
u16 m_raw_platform_id { 0 };
@ -86,7 +86,7 @@ public:
Optional<Subtable> subtable(u32 index) const;
void set_active_index(u32 index) { m_active_index = index; }
// Returns 0 if glyph not found. This corresponds to the "missing glyph"
u32 glyph_id_for_codepoint(u32 codepoint) const;
u32 glyph_id_for_code_point(u32 code_point) const;
private:
enum class Offsets {

16
Userland/Libraries/LibTTF/Font.cpp
View file

@ -501,7 +501,7 @@ bool Font::is_fixed_width() const
{
// FIXME: Read this information from the font file itself.
// FIXME: Although, it appears some application do similar hacks
return glyph_metrics(glyph_id_for_codepoint('.'), 1, 1).advance_width == glyph_metrics(glyph_id_for_codepoint('X'), 1, 1).advance_width;
return glyph_metrics(glyph_id_for_code_point('.'), 1, 1).advance_width == glyph_metrics(glyph_id_for_code_point('X'), 1, 1).advance_width;
}
int ScaledFont::width(const StringView& string) const
@ -513,8 +513,8 @@ int ScaledFont::width(const StringView& string) const
int ScaledFont::width(const Utf8View& utf8) const
{
int width = 0;
for (u32 codepoint : utf8) {
u32 glyph_id = glyph_id_for_codepoint(codepoint);
for (u32 code_point : utf8) {
u32 glyph_id = glyph_id_for_code_point(code_point);
auto metrics = glyph_metrics(glyph_id);
width += metrics.advance_width;
}
@ -525,7 +525,7 @@ int ScaledFont::width(const Utf32View& utf32) const
{
int width = 0;
for (size_t i = 0; i < utf32.length(); i++) {
u32 glyph_id = glyph_id_for_codepoint(utf32.code_points()[i]);
u32 glyph_id = glyph_id_for_code_point(utf32.code_points()[i]);
auto metrics = glyph_metrics(glyph_id);
width += metrics.advance_width;
}
@ -545,7 +545,7 @@ RefPtr<Gfx::Bitmap> ScaledFont::raster_glyph(u32 glyph_id) const
Gfx::Glyph ScaledFont::glyph(u32 code_point) const
{
auto id = glyph_id_for_codepoint(code_point);
auto id = glyph_id_for_code_point(code_point);
auto bitmap = raster_glyph(id);
auto metrics = glyph_metrics(id);
return Gfx::Glyph(bitmap, metrics.left_side_bearing, metrics.advance_width, metrics.ascender);
@ -553,21 +553,21 @@ Gfx::Glyph ScaledFont::glyph(u32 code_point) const
u8 ScaledFont::glyph_width(size_t code_point) const
{
auto id = glyph_id_for_codepoint(code_point);
auto id = glyph_id_for_code_point(code_point);
auto metrics = glyph_metrics(id);
return metrics.advance_width;
}
int ScaledFont::glyph_or_emoji_width(u32 code_point) const
{
auto id = glyph_id_for_codepoint(code_point);
auto id = glyph_id_for_code_point(code_point);
auto metrics = glyph_metrics(id);
return metrics.advance_width;
}
u8 ScaledFont::glyph_fixed_width() const
{
return glyph_metrics(glyph_id_for_codepoint(' ')).advance_width;
return glyph_metrics(glyph_id_for_code_point(' ')).advance_width;
}
}

6
Userland/Libraries/LibTTF/Font.h
View file

@ -54,7 +54,7 @@ public:
RefPtr<Gfx::Bitmap> raster_glyph(u32 glyph_id, float x_scale, float y_scale) const;
u32 glyph_count() const;
u16 units_per_em() const;
u32 glyph_id_for_codepoint(u32 codepoint) const { return m_cmap.glyph_id_for_codepoint(codepoint); }
u32 glyph_id_for_code_point(u32 code_point) const { return m_cmap.glyph_id_for_code_point(code_point); }
String family() const;
String variant() const;
u16 weight() const;
@ -110,7 +110,7 @@ public:
m_x_scale = (point_width * dpi_x) / (POINTS_PER_INCH * units_per_em);
m_y_scale = (point_height * dpi_y) / (POINTS_PER_INCH * units_per_em);
}
u32 glyph_id_for_codepoint(u32 codepoint) const { return m_font->glyph_id_for_codepoint(codepoint); }
u32 glyph_id_for_code_point(u32 code_point) const { return m_font->glyph_id_for_code_point(code_point); }
ScaledFontMetrics metrics() const { return m_font->metrics(m_x_scale, m_y_scale); }
ScaledGlyphMetrics glyph_metrics(u32 glyph_id) const { return m_font->glyph_metrics(glyph_id, m_x_scale, m_y_scale); }
RefPtr<Gfx::Bitmap> raster_glyph(u32 glyph_id) const;
@ -120,7 +120,7 @@ public:
virtual u8 presentation_size() const override { return m_point_height; }
virtual u16 weight() const override { return m_font->weight(); }
virtual Gfx::Glyph glyph(u32 code_point) const override;
virtual bool contains_glyph(u32 code_point) const override { return m_font->glyph_id_for_codepoint(code_point) > 0; }
virtual bool contains_glyph(u32 code_point) const override { return m_font->glyph_id_for_code_point(code_point) > 0; }
virtual u8 glyph_width(size_t ch) const override;
virtual int glyph_or_emoji_width(u32 code_point) const override;
virtual u8 glyph_height() const override { return m_point_height; }

8
Userland/Libraries/LibVT/EscapeSequenceParser.cpp
View file

@ -39,10 +39,10 @@ Vector<EscapeSequenceParser::OscParameter> EscapeSequenceParser::osc_parameters(
void EscapeSequenceParser::perform_action(EscapeSequenceStateMachine::Action action, u8 byte)
{
auto advance_utf8 = [&](u8 byte) {
u32 new_codepoint = m_code_point;
new_codepoint <<= 6;
new_codepoint |= byte & 0x3f;
return new_codepoint;
u32 new_code_point = m_code_point;
new_code_point <<= 6;
new_code_point |= byte & 0x3f;
return new_code_point;
};
switch (action) {

328
Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.cpp
View file

@ -20,179 +20,179 @@ static inline void log_parse_error(const SourceLocation& location = SourceLocati
dbgln_if(CSS_TOKENIZER_TRACE, "Parse error (css tokenization) {} ", location);
}
static inline bool is_surrogate(u32 codepoint)
static inline bool is_surrogate(u32 code_point)
{
return (codepoint & 0xfffff800) == 0xd800;
return (code_point & 0xfffff800) == 0xd800;
}
static inline bool is_quotation_mark(u32 codepoint)
static inline bool is_quotation_mark(u32 code_point)
{
return codepoint == 0x22;
return code_point == 0x22;
}
static inline bool is_greater_than_maximum_allowed_codepoint(u32 codepoint)
static inline bool is_greater_than_maximum_allowed_code_point(u32 code_point)
{
return codepoint > 0x10FFFF;
return code_point > 0x10FFFF;
}
static inline bool is_hex_digit(u32 codepoint)
static inline bool is_hex_digit(u32 code_point)
{
return isxdigit(codepoint);
return isxdigit(code_point);
}
static inline bool is_low_line(u32 codepoint)
static inline bool is_low_line(u32 code_point)
{
return codepoint == 0x5F;
return code_point == 0x5F;
}
static inline bool is_non_ascii(u32 codepoint)
static inline bool is_non_ascii(u32 code_point)
{
return codepoint >= 0x80;
return code_point >= 0x80;
}
static inline bool is_name_start_codepoint(u32 codepoint)
static inline bool is_name_start_code_point(u32 code_point)
{
return isalpha(codepoint) || is_non_ascii(codepoint) || is_low_line(codepoint);
return isalpha(code_point) || is_non_ascii(code_point) || is_low_line(code_point);
}
static inline bool is_hyphen_minus(u32 codepoint)
static inline bool is_hyphen_minus(u32 code_point)
{
return codepoint == 0x2D;
return code_point == 0x2D;
}
static inline bool is_name_codepoint(u32 codepoint)
static inline bool is_name_code_point(u32 code_point)
{
return is_name_start_codepoint(codepoint) || isdigit(codepoint) || is_hyphen_minus(codepoint);
return is_name_start_code_point(code_point) || isdigit(code_point) || is_hyphen_minus(code_point);
}
static inline bool is_non_printable(u32 codepoint)
static inline bool is_non_printable(u32 code_point)
{
return codepoint <= 0x8 || codepoint == 0xB || (codepoint >= 0xE && codepoint <= 0x1F) || codepoint == 0x7F;
return code_point <= 0x8 || code_point == 0xB || (code_point >= 0xE && code_point <= 0x1F) || code_point == 0x7F;
}
static inline bool is_number_sign(u32 codepoint)
static inline bool is_number_sign(u32 code_point)
{
return codepoint == 0x23;
return code_point == 0x23;
}
static inline bool is_reverse_solidus(u32 codepoint)
static inline bool is_reverse_solidus(u32 code_point)
{
return codepoint == 0x5C;
return code_point == 0x5C;
}
static inline bool is_apostrophe(u32 codepoint)
static inline bool is_apostrophe(u32 code_point)
{
return codepoint == 0x27;
return code_point == 0x27;
}
static inline bool is_left_paren(u32 codepoint)
static inline bool is_left_paren(u32 code_point)
{
return codepoint == 0x28;
return code_point == 0x28;
}
static inline bool is_right_paren(u32 codepoint)
static inline bool is_right_paren(u32 code_point)
{
return codepoint == 0x29;
return code_point == 0x29;
}
static inline bool is_plus_sign(u32 codepoint)
static inline bool is_plus_sign(u32 code_point)
{
return codepoint == 0x2B;
return code_point == 0x2B;
}
static inline bool is_comma(u32 codepoint)
static inline bool is_comma(u32 code_point)
{
return codepoint == 0x2C;
return code_point == 0x2C;
}
static inline bool is_full_stop(u32 codepoint)
static inline bool is_full_stop(u32 code_point)
{
return codepoint == 0x2E;
return code_point == 0x2E;
}
static inline bool is_newline(u32 codepoint)
static inline bool is_newline(u32 code_point)
{
return codepoint == 0xA;
return code_point == 0xA;
}
static inline bool is_asterisk(u32 codepoint)
static inline bool is_asterisk(u32 code_point)
{
return codepoint == 0x2A;
return code_point == 0x2A;
}
static inline bool is_solidus(u32 codepoint)
static inline bool is_solidus(u32 code_point)
{
return codepoint == 0x2F;
return code_point == 0x2F;
}
static inline bool is_colon(u32 codepoint)
static inline bool is_colon(u32 code_point)
{
return codepoint == 0x3A;
return code_point == 0x3A;
}
static inline bool is_semicolon(u32 codepoint)
static inline bool is_semicolon(u32 code_point)
{
return codepoint == 0x3B;
return code_point == 0x3B;
}
static inline bool is_less_than_sign(u32 codepoint)
static inline bool is_less_than_sign(u32 code_point)
{
return codepoint == 0x3C;
return code_point == 0x3C;
}
static inline bool is_greater_than_sign(u32 codepoint)
static inline bool is_greater_than_sign(u32 code_point)
{
return codepoint == 0x3E;
return code_point == 0x3E;
}
static inline bool is_at(u32 codepoint)
static inline bool is_at(u32 code_point)
{
return codepoint == 0x40;
return code_point == 0x40;
}
static inline bool is_open_square_bracket(u32 codepoint)
static inline bool is_open_square_bracket(u32 code_point)
{
return codepoint == 0x5B;
return code_point == 0x5B;
}
static inline bool is_closed_square_bracket(u32 codepoint)
static inline bool is_closed_square_bracket(u32 code_point)
{
return codepoint == 0x5D;
return code_point == 0x5D;
}
static inline bool is_open_curly_bracket(u32 codepoint)
static inline bool is_open_curly_bracket(u32 code_point)
{
return codepoint == 0x7B;
return code_point == 0x7B;
}
static inline bool is_closed_curly_bracket(u32 codepoint)
static inline bool is_closed_curly_bracket(u32 code_point)
{
return codepoint == 0x7D;
return code_point == 0x7D;
}
static inline bool is_whitespace(u32 codepoint)
static inline bool is_whitespace(u32 code_point)
{
return codepoint == 0x9 || codepoint == 0xA || codepoint == 0x20;
return code_point == 0x9 || code_point == 0xA || code_point == 0x20;
}
static inline bool is_percent(u32 codepoint)
static inline bool is_percent(u32 code_point)
{
return codepoint == 0x25;
return code_point == 0x25;
}
static inline bool is_exclamation_mark(u32 codepoint)
static inline bool is_exclamation_mark(u32 code_point)
{
return codepoint == 0x21;
return code_point == 0x21;
}
static inline bool is_e(u32 codepoint)
static inline bool is_e(u32 code_point)
{
return codepoint == 0x65;
return code_point == 0x65;
}
static inline bool is_E(u32 codepoint)
static inline bool is_E(u32 code_point)
{
return codepoint == 0x45;
return code_point == 0x45;
}
namespace Web::CSS {
@ -222,17 +222,17 @@ Vector<Token> Tokenizer::parse()
}
}
Optional<u32> Tokenizer::next_codepoint()
Optional<u32> Tokenizer::next_code_point()
{
if (m_utf8_iterator == m_utf8_view.end())
return {};
m_prev_utf8_iterator = m_utf8_iterator;
++m_utf8_iterator;
dbgln_if(CSS_TOKENIZER_TRACE, "(Tokenizer) Next codepoint: {:c}", (char)*m_prev_utf8_iterator);
dbgln_if(CSS_TOKENIZER_TRACE, "(Tokenizer) Next code_point: {:c}", (char)*m_prev_utf8_iterator);
return *m_prev_utf8_iterator;
}
Optional<u32> Tokenizer::peek_codepoint(size_t offset) const
Optional<u32> Tokenizer::peek_code_point(size_t offset) const
{
auto it = m_utf8_iterator;
for (size_t i = 0; i < offset && it != m_utf8_view.end(); ++i)
@ -292,32 +292,32 @@ Token Tokenizer::create_value_token(Token::TokenType type, u32 value)
return token;
}
u32 Tokenizer::consume_escaped_codepoint()
u32 Tokenizer::consume_escaped_code_point()
{
auto codepoint = next_codepoint();
auto code_point = next_code_point();
if (!codepoint.has_value()) {
if (!code_point.has_value()) {
log_parse_error();
return REPLACEMENT_CHARACTER;
}
auto input = codepoint.value();
auto input = code_point.value();
if (is_hex_digit(input)) {
StringBuilder builder;
builder.append_code_point(input);
size_t counter = 0;
while (is_hex_digit(peek_codepoint().value()) && counter++ < 5) {
builder.append_code_point(next_codepoint().value());
while (is_hex_digit(peek_code_point().value()) && counter++ < 5) {
builder.append_code_point(next_code_point().value());
}
if (is_whitespace(peek_codepoint().value())) {
(void)next_codepoint();
if (is_whitespace(peek_code_point().value())) {
(void)next_code_point();
}
auto unhexed = strtoul(builder.to_string().characters(), nullptr, 16);
if (unhexed == 0 || is_surrogate(unhexed) || is_greater_than_maximum_allowed_codepoint(unhexed)) {
if (unhexed == 0 || is_surrogate(unhexed) || is_greater_than_maximum_allowed_code_point(unhexed)) {
return REPLACEMENT_CHARACTER;
}
@ -336,8 +336,8 @@ Token Tokenizer::consume_an_ident_like_token()
{
auto string = consume_a_name();
if (string.equals_ignoring_case("url") && is_left_paren(peek_codepoint().value())) {
(void)next_codepoint();
if (string.equals_ignoring_case("url") && is_left_paren(peek_code_point().value())) {
(void)next_code_point();
for (;;) {
auto maybe_whitespace = peek_twin().value();
@ -345,7 +345,7 @@ Token Tokenizer::consume_an_ident_like_token()
break;
}
(void)next_codepoint();
(void)next_code_point();
}
auto next_two = peek_twin().value();
@ -357,8 +357,8 @@ Token Tokenizer::consume_an_ident_like_token()
return consume_a_url_token();
}
if (is_left_paren(peek_codepoint().value())) {
(void)next_codepoint();
if (is_left_paren(peek_code_point().value())) {
(void)next_code_point();
return create_value_token(Token::TokenType::Function, string);
}
@ -371,32 +371,32 @@ CSSNumber Tokenizer::consume_a_number()
StringBuilder repr;
Token::NumberType type = Token::NumberType::Integer;
auto next_input = peek_codepoint().value();
auto next_input = peek_code_point().value();
if (is_plus_sign(next_input) || is_hyphen_minus(next_input)) {
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
}
for (;;) {
auto digits = peek_codepoint().value();
auto digits = peek_code_point().value();
if (!isdigit(digits))
break;
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
}
auto maybe_number = peek_twin().value();
if (is_full_stop(maybe_number.first) && isdigit(maybe_number.second)) {
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
repr.append_code_point(next_code_point().value());
type = Token::NumberType::Number;
for (;;) {
auto digits = peek_codepoint();
auto digits = peek_code_point();
if (digits.has_value() && !isdigit(digits.value()))
break;
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
}
}
@ -404,23 +404,23 @@ CSSNumber Tokenizer::consume_a_number()
if (is_E(maybe_exp.first) || is_e(maybe_exp.first)) {
if (is_plus_sign(maybe_exp.second) || is_hyphen_minus(maybe_exp.second)) {
if (isdigit(maybe_exp.third)) {
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
repr.append_code_point(next_code_point().value());
repr.append_code_point(next_code_point().value());
}
} else if (isdigit(maybe_exp.second)) {
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
repr.append_code_point(next_code_point().value());
}
type = Token::NumberType::Number;
for (;;) {
auto digits = peek_codepoint().value();
auto digits = peek_code_point().value();
if (!isdigit(digits))
break;
repr.append_code_point(next_codepoint().value());
repr.append_code_point(next_code_point().value());
}
}
@ -432,66 +432,66 @@ String Tokenizer::consume_a_name()
StringBuilder result;
for (;;) {
auto input = next_codepoint().value();
auto input = next_code_point().value();
if (is_name_codepoint(input)) {
if (is_name_code_point(input)) {
result.append_code_point(input);
continue;
}
auto next = peek_codepoint();
auto next = peek_code_point();
if (next.has_value() && is_valid_escape_sequence({ input, next.value() })) {
result.append_code_point(consume_escaped_codepoint());
result.append_code_point(consume_escaped_code_point());
continue;
}
break;
}
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return result.to_string();
}
Token Tokenizer::consume_a_url_token()
{
auto token = create_new_token(Token::TokenType::Url);
for (;;) {
if (!is_whitespace(peek_codepoint().value())) {
if (!is_whitespace(peek_code_point().value())) {
break;
}
(void)next_codepoint();
(void)next_code_point();
}
for (;;) {
auto codepoint = peek_codepoint();
if (!codepoint.has_value()) {
auto code_point = peek_code_point();
if (!code_point.has_value()) {
log_parse_error();
return token;
}
auto input = codepoint.value();
auto input = code_point.value();
if (is_right_paren(input)) {
(void)next_codepoint();
(void)next_code_point();
return token;
}
if (is_whitespace(input)) {
for (;;) {
if (!is_whitespace(peek_codepoint().value())) {
if (!is_whitespace(peek_code_point().value())) {
break;
}
codepoint = next_codepoint();
code_point = next_code_point();
}
if (!codepoint.has_value()) {
if (!code_point.has_value()) {
log_parse_error();
return token;
}
input = codepoint.value();
input = code_point.value();
if (is_right_paren(input)) {
return token;
@ -503,30 +503,30 @@ Token Tokenizer::consume_a_url_token()
if (is_quotation_mark(input) || is_apostrophe(input) || is_left_paren(input) || is_non_printable(input)) {
log_parse_error();
(void)next_codepoint();
(void)next_code_point();
consume_the_remnants_of_a_bad_url();
return create_new_token(Token::TokenType::BadUrl);
}
if (is_reverse_solidus(input)) {
if (is_valid_escape_sequence()) {
token.m_value.append_code_point(consume_escaped_codepoint());
token.m_value.append_code_point(consume_escaped_code_point());
} else {
log_parse_error();
(void)next_codepoint();
(void)next_code_point();
consume_the_remnants_of_a_bad_url();
return create_new_token(Token::TokenType::BadUrl);
}
}
token.m_value.append_code_point(next_codepoint().value());
token.m_value.append_code_point(next_code_point().value());
}
}
void Tokenizer::consume_the_remnants_of_a_bad_url()
{
for (;;) {
auto next = peek_codepoint();
auto next = peek_code_point();
if (!next.has_value()) {
return;
@ -535,19 +535,19 @@ void Tokenizer::consume_the_remnants_of_a_bad_url()
auto input = next.value();
if (is_right_paren(input)) {
(void)next_codepoint();
(void)next_code_point();
return;
}
if (is_valid_escape_sequence()) {
[[maybe_unused]] auto cp = consume_escaped_codepoint();
[[maybe_unused]] auto cp = consume_escaped_code_point();
}
(void)next_codepoint();
(void)next_code_point();
}
}
void Tokenizer::reconsume_current_input_codepoint()
void Tokenizer::reconsume_current_input_code_point()
{
m_utf8_iterator = m_prev_utf8_iterator;
}
@ -566,8 +566,8 @@ Token Tokenizer::consume_a_numeric_token()
return token;
}
if (is_percent(peek_codepoint().value())) {
(void)next_codepoint();
if (is_percent(peek_code_point().value())) {
(void)next_code_point();
auto token = create_new_token(Token::TokenType::Percentage);
token.m_value.append(number.value);
@ -632,12 +632,12 @@ bool Tokenizer::would_start_an_identifier()
bool Tokenizer::would_start_an_identifier(U32Triplet values)
{
if (is_hyphen_minus(values.first)) {
if (is_name_start_codepoint(values.second) || is_hyphen_minus(values.second) || is_valid_escape_sequence(values.to_twin_23()))
if (is_name_start_code_point(values.second) || is_hyphen_minus(values.second) || is_valid_escape_sequence(values.to_twin_23()))
return true;
return false;
}
if (is_name_start_codepoint(values.first)) {
if (is_name_start_code_point(values.first)) {
return true;
}
@ -650,39 +650,39 @@ bool Tokenizer::would_start_an_identifier(U32Triplet values)
return false;
}
Token Tokenizer::consume_string_token(u32 ending_codepoint)
Token Tokenizer::consume_string_token(u32 ending_code_point)
{
auto token = create_new_token(Token::TokenType::String);
for (;;) {
auto codepoint = next_codepoint();
auto code_point = next_code_point();
if (!codepoint.has_value()) {
if (!code_point.has_value()) {
log_parse_error();
return token;
}
auto input = codepoint.value();
auto input = code_point.value();
if (input == ending_codepoint)
if (input == ending_code_point)
return token;
if (is_newline(input)) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return create_new_token(Token::TokenType::BadString);
}
if (is_reverse_solidus(input)) {
auto next_input = peek_codepoint();
auto next_input = peek_code_point();
if (!next_input.has_value())
continue;
if (is_newline(next_input.value())) {
(void)next_codepoint();
(void)next_code_point();
continue;
}
auto escaped = consume_escaped_codepoint();
auto escaped = consume_escaped_code_point();
token.m_value.append_code_point(escaped);
}
@ -703,8 +703,8 @@ start:
if (!(is_solidus(twin.first) && is_asterisk(twin.second)))
return;
(void)next_codepoint();
(void)next_codepoint();
(void)next_code_point();
(void)next_code_point();
for (;;) {
auto peek_inner = peek_twin();
@ -716,12 +716,12 @@ start:
auto twin_inner = peek_inner.value();
if (is_asterisk(twin_inner.first) && is_solidus(twin_inner.second)) {
(void)next_codepoint();
(void)next_codepoint();
(void)next_code_point();
(void)next_code_point();
goto start;
}
(void)next_codepoint();
(void)next_code_point();
}
}
@ -729,19 +729,19 @@ Token Tokenizer::consume_a_token()
{
consume_comments();
auto codepoint = next_codepoint();
auto code_point = next_code_point();
if (!codepoint.has_value()) {
if (!code_point.has_value()) {
return create_new_token(Token::TokenType::EndOfFile);
}
auto input = codepoint.value();
auto input = code_point.value();
if (is_whitespace(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is whitespace");
while (is_whitespace(peek_codepoint().value()))
(void)next_codepoint();
while (is_whitespace(peek_code_point().value()))
(void)next_code_point();
return create_new_token(Token::TokenType::Whitespace);
}
@ -754,10 +754,10 @@ Token Tokenizer::consume_a_token()
if (is_number_sign(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is number sign");
auto next_input = peek_codepoint().value();
auto next_input = peek_code_point().value();
auto maybe_escape = peek_twin().value();
if (is_name_codepoint(next_input) || is_valid_escape_sequence(maybe_escape)) {
if (is_name_code_point(next_input) || is_valid_escape_sequence(maybe_escape)) {
auto token = create_new_token(Token::TokenType::Hash);
if (would_start_an_identifier())
@ -790,7 +790,7 @@ Token Tokenizer::consume_a_token()
if (is_plus_sign(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is plus sign");
if (starts_with_a_number()) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_a_numeric_token();
}
@ -805,20 +805,20 @@ Token Tokenizer::consume_a_token()
if (is_hyphen_minus(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is hyphen minus");
if (starts_with_a_number()) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_a_numeric_token();
}
auto next_twin = peek_twin().value();
if (is_hyphen_minus(next_twin.first) && is_greater_than_sign(next_twin.second)) {
(void)next_codepoint();
(void)next_codepoint();
(void)next_code_point();
(void)next_code_point();
return create_new_token(Token::TokenType::CDC);
}
if (would_start_an_identifier()) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_an_ident_like_token();
}
@ -828,7 +828,7 @@ Token Tokenizer::consume_a_token()
if (is_full_stop(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is full stop");
if (starts_with_a_number()) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_a_numeric_token();
}
@ -850,9 +850,9 @@ Token Tokenizer::consume_a_token()
auto maybe_cdo = peek_triplet().value();
if (is_exclamation_mark(maybe_cdo.first) && is_hyphen_minus(maybe_cdo.second) && is_hyphen_minus(maybe_cdo.third)) {
(void)next_codepoint();
(void)next_codepoint();
(void)next_codepoint();
(void)next_code_point();
(void)next_code_point();
(void)next_code_point();
return create_new_token(Token::TokenType::CDO);
}
@ -879,7 +879,7 @@ Token Tokenizer::consume_a_token()
if (is_reverse_solidus(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is reverse solidus");
if (is_valid_escape_sequence()) {
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_an_ident_like_token();
}
@ -904,13 +904,13 @@ Token Tokenizer::consume_a_token()
if (isdigit(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is digit");
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_a_numeric_token();
}
if (is_name_start_codepoint(input)) {
if (is_name_start_code_point(input)) {
dbgln_if(CSS_TOKENIZER_TRACE, "is name start");
reconsume_current_input_codepoint();
reconsume_current_input_code_point();
return consume_an_ident_like_token();
}

10
Userland/Libraries/LibWeb/CSS/Parser/Tokenizer.h
View file

@ -71,8 +71,8 @@ public:
[[nodiscard]] Vector<Token> parse();
private:
[[nodiscard]] Optional<u32> next_codepoint();
[[nodiscard]] Optional<u32> peek_codepoint(size_t offset = 0) const;
[[nodiscard]] Optional<u32> next_code_point();
[[nodiscard]] Optional<u32> peek_code_point(size_t offset = 0) const;
[[nodiscard]] Optional<U32Twin> peek_twin() const;
[[nodiscard]] Optional<U32Triplet> peek_triplet() const;
@ -80,16 +80,16 @@ private:
[[nodiscard]] static Token create_value_token(Token::TokenType, String value);
[[nodiscard]] static Token create_value_token(Token::TokenType, u32 value);
[[nodiscard]] Token consume_a_token();
[[nodiscard]] Token consume_string_token(u32 ending_codepoint);
[[nodiscard]] Token consume_string_token(u32 ending_code_point);
[[nodiscard]] Token consume_a_numeric_token();
[[nodiscard]] Token consume_an_ident_like_token();
[[nodiscard]] CSSNumber consume_a_number();
[[nodiscard]] String consume_a_name();
[[nodiscard]] u32 consume_escaped_codepoint();
[[nodiscard]] u32 consume_escaped_code_point();
[[nodiscard]] Token consume_a_url_token();
void consume_the_remnants_of_a_bad_url();
void consume_comments();
void reconsume_current_input_codepoint();
void reconsume_current_input_code_point();
[[nodiscard]] bool is_valid_escape_sequence();
[[nodiscard]] static bool is_valid_escape_sequence(U32Twin);
[[nodiscard]] bool would_start_an_identifier();

4
Userland/Libraries/LibWeb/DOM/Position.cpp
View file

@ -39,7 +39,7 @@ bool Position::increment_offset()
for (auto iterator = text.begin(); !iterator.done(); ++iterator) {
if (text.byte_offset_of(iterator) >= m_offset) {
// NOTE: If the current offset is inside a multi-byte codepoint, it will be moved to the start of the next codepoint.
// NOTE: If the current offset is inside a multi-byte code point, it will be moved to the start of the next code point.
m_offset = text.byte_offset_of(++iterator);
return true;
}
@ -66,7 +66,7 @@ bool Position::decrement_offset()
last_smaller_offset = text.byte_offset_of(iterator);
}
// NOTE: If the current offset is inside a multi-byte codepoint, it will be moved to the start of that codepoint.
// NOTE: If the current offset is inside a multi-byte code point, it will be moved to the start of that code point.
m_offset = last_smaller_offset;
return true;
}

4
Userland/Libraries/LibWeb/Page/EditEventHandler.cpp
View file

@ -26,11 +26,11 @@ void EditEventHandler::handle_delete_character_after(const DOM::Position& cursor
auto& node = *static_cast<DOM::Text*>(const_cast<DOM::Node*>(cursor_position.node()));
auto& text = node.data();
auto codepoint_length = Utf8View(text).iterator_at_byte_offset(cursor_position.offset()).code_point_length_in_bytes();
auto code_point_length = Utf8View(text).iterator_at_byte_offset(cursor_position.offset()).code_point_length_in_bytes();
StringBuilder builder;
builder.append(text.substring_view(0, cursor_position.offset()));
builder.append(text.substring_view(cursor_position.offset() + codepoint_length));
builder.append(text.substring_view(cursor_position.offset() + code_point_length));
node.set_data(builder.to_string());
m_frame.did_edit({});

6
Userland/Libraries/LibWeb/Page/EventHandler.cpp
View file

@ -379,10 +379,10 @@ bool EventHandler::focus_previous_element()
return false;
}
constexpr bool should_ignore_keydown_event(u32 codepoint)
constexpr bool should_ignore_keydown_event(u32 code_point)
{
// FIXME: There are probably also keys with non-zero codepoints that should be filtered out.
return codepoint == 0;
// FIXME: There are probably also keys with non-zero code points that should be filtered out.
return code_point == 0;
}
bool EventHandler::handle_keydown(KeyCode key, unsigned modifiers, u32 code_point)

2
Userland/Shell/Tests/brace-exp.sh
View file

@ -11,7 +11,7 @@ if not test "$(echo {a,b,,})" = "a b " { fail normal brace expansion with two
if not test "$(echo {a..c})" = "a b c" { fail range brace expansion, alpha }
if not test "$(echo {0..3})" = "0 1 2 3" { fail range brace expansion, number }
if not test "$(echo {😂..😄})" = "😂 😃 😄" { fail range brace expansion, unicode codepoint }
if not test "$(echo {😂..😄})" = "😂 😃 😄" { fail range brace expansion, unicode code point }
# Make sure that didn't mess with dots and commas in normal barewords
if not test .. = ".." { fail range brace expansion delimiter affects normal barewords }