beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 07:30:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

Unicode: Try s/codepoint/code_point/g again

Browse source 
This time, without trailing 's'. Ran:

    git grep -l 'codepoint' | xargs sed -ie 's/codepoint/code_point/g
This commit is contained in:
Nico Weber 2020-08-05 16:31:20 -04:00 committed by Andreas Kling
parent 19ac1f6368
commit ce95628b7f
Notes: sideshowbarker 2024-07-19 04:15:29 +09:00 
Author: https://github.com/nico
Commit: https://github.com/SerenityOS/serenity/commit/ce95628b7f9
Pull-request: https://github.com/SerenityOS/serenity/pull/3018
45 changed files with 441 additions and 441 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
AK/JsonParser.cpp
View file

@ -126,9 +126,9 @@ String JsonParser::consume_quoted_string()
sb.append(consume()); sb.append(consume());
sb.append(consume()); sb.append(consume());
auto codepoint = AK::StringUtils::convert_to_uint_from_hex(sb.to_string()); auto code_point = AK::StringUtils::convert_to_uint_from_hex(sb.to_string());
if (codepoint.has_value()) { if (code_point.has_value()) {
final_sb.append_codepoint(codepoint.value()); final_sb.append_code_point(code_point.value());
} else { } else {
final_sb.append('?'); final_sb.append('?');
} }

34
AK/StringBuilder.cpp
View file

@ -113,22 +113,22 @@ void StringBuilder::clear()
m_length = 0; m_length = 0;
} }
void StringBuilder::append_codepoint(u32 codepoint) void StringBuilder::append_code_point(u32 code_point)
{ {
if (codepoint <= 0x7f) { if (code_point <= 0x7f) {
append((char)codepoint); append((char)code_point);
} else if (codepoint <= 0x07ff) { } else if (code_point <= 0x07ff) {
append((char)(((codepoint >> 6) & 0x1f) | 0xc0)); append((char)(((code_point >> 6) & 0x1f) | 0xc0));
append((char)(((codepoint >> 0) & 0x3f) | 0x80)); append((char)(((code_point >> 0) & 0x3f) | 0x80));
} else if (codepoint <= 0xffff) { } else if (code_point <= 0xffff) {
append((char)(((codepoint >> 12) & 0x0f) | 0xe0)); append((char)(((code_point >> 12) & 0x0f) | 0xe0));
append((char)(((codepoint >> 6) & 0x3f) | 0x80)); append((char)(((code_point >> 6) & 0x3f) | 0x80));
append((char)(((codepoint >> 0) & 0x3f) | 0x80)); append((char)(((code_point >> 0) & 0x3f) | 0x80));
} else if (codepoint <= 0x10ffff) { } else if (code_point <= 0x10ffff) {
append((char)(((codepoint >> 18) & 0x07) | 0xf0)); append((char)(((code_point >> 18) & 0x07) | 0xf0));
append((char)(((codepoint >> 12) & 0x3f) | 0x80)); append((char)(((code_point >> 12) & 0x3f) | 0x80));
append((char)(((codepoint >> 6) & 0x3f) | 0x80)); append((char)(((code_point >> 6) & 0x3f) | 0x80));
append((char)(((codepoint >> 0) & 0x3f) | 0x80)); append((char)(((code_point >> 0) & 0x3f) | 0x80));
} else { } else {
append(0xef); append(0xef);
append(0xbf); append(0xbf);
@ -139,8 +139,8 @@ void StringBuilder::append_codepoint(u32 codepoint)
void StringBuilder::append(const Utf32View& utf32_view) void StringBuilder::append(const Utf32View& utf32_view)
{ {
for (size_t i = 0; i < utf32_view.length(); ++i) { for (size_t i = 0; i < utf32_view.length(); ++i) {
auto codepoint = utf32_view.codepoints()[i]; auto code_point = utf32_view.code_points()[i];
append_codepoint(codepoint); append_code_point(code_point);
} }
} }

2
AK/StringBuilder.h
View file

@ -42,7 +42,7 @@ public:
void append(const StringView&); void append(const StringView&);
void append(const Utf32View&); void append(const Utf32View&);
void append(char); void append(char);
void append_codepoint(u32); void append_code_point(u32);
void append(const char*, size_t); void append(const char*, size_t);
void appendf(const char*, ...); void appendf(const char*, ...);
void appendvf(const char*, va_list); void appendvf(const char*, va_list);

8
AK/Tests/TestUtf8.cpp
View file

@ -37,9 +37,9 @@ TEST_CASE(decode_ascii)
size_t expected_size = sizeof(expected) / sizeof(expected[0]); size_t expected_size = sizeof(expected) / sizeof(expected[0]);
size_t i = 0; size_t i = 0;
for (u32 codepoint : utf8) { for (u32 code_point : utf8) {
ASSERT(i < expected_size); ASSERT(i < expected_size);
EXPECT_EQ(codepoint, expected[i]); EXPECT_EQ(code_point, expected[i]);
i++; i++;
} }
EXPECT_EQ(i, expected_size); EXPECT_EQ(i, expected_size);
@ -56,9 +56,9 @@ TEST_CASE(decode_utf8)
size_t expected_size = sizeof(expected) / sizeof(expected[0]); size_t expected_size = sizeof(expected) / sizeof(expected[0]);
size_t i = 0; size_t i = 0;
for (u32 codepoint : utf8) { for (u32 code_point : utf8) {
ASSERT(i < expected_size); ASSERT(i < expected_size);
EXPECT_EQ(codepoint, expected[i]); EXPECT_EQ(code_point, expected[i]);
i++; i++;
} }
EXPECT_EQ(i, expected_size); EXPECT_EQ(i, expected_size);

12
AK/Utf32View.h
View file

@ -35,14 +35,14 @@ namespace AK {
class Utf32View { class Utf32View {
public: public:
Utf32View() { } Utf32View() { }
Utf32View(const u32* codepoints, size_t length) Utf32View(const u32* code_points, size_t length)
: m_codepoints(codepoints) : m_code_points(code_points)
, m_length(length) , m_length(length)
{ {
ASSERT(codepoints || length == 0); ASSERT(code_points || length == 0);
} }
const u32* codepoints() const { return m_codepoints; } const u32* code_points() const { return m_code_points; }
bool is_empty() const { return m_length == 0; } bool is_empty() const { return m_length == 0; }
size_t length() const { return m_length; } size_t length() const { return m_length; }
@ -53,11 +53,11 @@ public:
ASSERT(offset < m_length); ASSERT(offset < m_length);
ASSERT(!Checked<size_t>::addition_would_overflow(offset, length)); ASSERT(!Checked<size_t>::addition_would_overflow(offset, length));
ASSERT((offset + length) <= m_length); ASSERT((offset + length) <= m_length);
return Utf32View(m_codepoints + offset, length); return Utf32View(m_code_points + offset, length);
} }
private: private:
const u32* m_codepoints { nullptr }; const u32* m_code_points { nullptr };
size_t m_length { 0 }; size_t m_length { 0 };
}; };

62
AK/Utf8View.cpp
View file

@ -81,12 +81,12 @@ Utf8View Utf8View::substring_view(int byte_offset, int byte_length) const
static inline bool decode_first_byte( static inline bool decode_first_byte(
unsigned char byte, unsigned char byte,
int& out_codepoint_length_in_bytes, int& out_code_point_length_in_bytes,
u32& out_value) u32& out_value)
{ {
if ((byte & 128) == 0) { if ((byte & 128) == 0) {
out_value = byte; out_value = byte;
out_codepoint_length_in_bytes = 1; out_code_point_length_in_bytes = 1;
return true; return true;
} }
if ((byte & 64) == 0) { if ((byte & 64) == 0) {
@ -94,17 +94,17 @@ static inline bool decode_first_byte(
} }
if ((byte & 32) == 0) { if ((byte & 32) == 0) {
out_value = byte & 31; out_value = byte & 31;
out_codepoint_length_in_bytes = 2; out_code_point_length_in_bytes = 2;
return true; return true;
} }
if ((byte & 16) == 0) { if ((byte & 16) == 0) {
out_value = byte & 15; out_value = byte & 15;
out_codepoint_length_in_bytes = 3; out_code_point_length_in_bytes = 3;
return true; return true;
} }
if ((byte & 8) == 0) { if ((byte & 8) == 0) {
out_value = byte & 7; out_value = byte & 7;
out_codepoint_length_in_bytes = 4; out_code_point_length_in_bytes = 4;
return true; return true;
} }
@ -115,13 +115,13 @@ bool Utf8View::validate(size_t& valid_bytes) const
{ {
valid_bytes = 0; valid_bytes = 0;
for (auto ptr = begin_ptr(); ptr < end_ptr(); ptr++) { for (auto ptr = begin_ptr(); ptr < end_ptr(); ptr++) {
int codepoint_length_in_bytes; int code_point_length_in_bytes;
u32 value; u32 value;
bool first_byte_makes_sense = decode_first_byte(*ptr, codepoint_length_in_bytes, value); bool first_byte_makes_sense = decode_first_byte(*ptr, code_point_length_in_bytes, value);
if (!first_byte_makes_sense) if (!first_byte_makes_sense)
return false; return false;
for (int i = 1; i < codepoint_length_in_bytes; i++) { for (int i = 1; i < code_point_length_in_bytes; i++) {
ptr++; ptr++;
if (ptr >= end_ptr()) if (ptr >= end_ptr())
return false; return false;
@ -129,17 +129,17 @@ bool Utf8View::validate(size_t& valid_bytes) const
return false; return false;
} }
valid_bytes += codepoint_length_in_bytes; valid_bytes += code_point_length_in_bytes;
} }
return true; return true;
} }
size_t Utf8View::length_in_codepoints() const size_t Utf8View::length_in_code_points() const
{ {
size_t length = 0; size_t length = 0;
for (auto codepoint : *this) { for (auto code_point : *this) {
(void)codepoint; (void)code_point;
++length; ++length;
} }
return length; return length;
@ -165,54 +165,54 @@ Utf8CodepointIterator& Utf8CodepointIterator::operator++()
{ {
ASSERT(m_length > 0); ASSERT(m_length > 0);
int codepoint_length_in_bytes = 0; int code_point_length_in_bytes = 0;
u32 value; u32 value;
bool first_byte_makes_sense = decode_first_byte(*m_ptr, codepoint_length_in_bytes, value); bool first_byte_makes_sense = decode_first_byte(*m_ptr, code_point_length_in_bytes, value);
ASSERT(first_byte_makes_sense); ASSERT(first_byte_makes_sense);
(void)value; (void)value;
ASSERT(codepoint_length_in_bytes <= m_length); ASSERT(code_point_length_in_bytes <= m_length);
m_ptr += codepoint_length_in_bytes; m_ptr += code_point_length_in_bytes;
m_length -= codepoint_length_in_bytes; m_length -= code_point_length_in_bytes;
return *this; return *this;
} }
int Utf8CodepointIterator::codepoint_length_in_bytes() const int Utf8CodepointIterator::code_point_length_in_bytes() const
{ {
ASSERT(m_length > 0); ASSERT(m_length > 0);
int codepoint_length_in_bytes = 0; int code_point_length_in_bytes = 0;
u32 value; u32 value;
bool first_byte_makes_sense = decode_first_byte(*m_ptr, codepoint_length_in_bytes, value); bool first_byte_makes_sense = decode_first_byte(*m_ptr, code_point_length_in_bytes, value);
ASSERT(first_byte_makes_sense); ASSERT(first_byte_makes_sense);
return codepoint_length_in_bytes; return code_point_length_in_bytes;
} }
u32 Utf8CodepointIterator::operator*() const u32 Utf8CodepointIterator::operator*() const
{ {
ASSERT(m_length > 0); ASSERT(m_length > 0);
u32 codepoint_value_so_far = 0; u32 code_point_value_so_far = 0;
int codepoint_length_in_bytes = 0; int code_point_length_in_bytes = 0;
bool first_byte_makes_sense = decode_first_byte(m_ptr[0], codepoint_length_in_bytes, codepoint_value_so_far); bool first_byte_makes_sense = decode_first_byte(m_ptr[0], code_point_length_in_bytes, code_point_value_so_far);
if (!first_byte_makes_sense) { if (!first_byte_makes_sense) {
dbg() << "First byte doesn't make sense, bytes: " << StringView((const char*)m_ptr, m_length); dbg() << "First byte doesn't make sense, bytes: " << StringView((const char*)m_ptr, m_length);
} }
ASSERT(first_byte_makes_sense); ASSERT(first_byte_makes_sense);
if (codepoint_length_in_bytes > m_length) { if (code_point_length_in_bytes > m_length) {
dbg() << "Not enough bytes (need " << codepoint_length_in_bytes << ", have " << m_length << "), first byte is: " << m_ptr[0] << " " << (const char*)m_ptr; dbg() << "Not enough bytes (need " << code_point_length_in_bytes << ", have " << m_length << "), first byte is: " << m_ptr[0] << " " << (const char*)m_ptr;
} }
ASSERT(codepoint_length_in_bytes <= m_length); ASSERT(code_point_length_in_bytes <= m_length);
for (int offset = 1; offset < codepoint_length_in_bytes; offset++) { for (int offset = 1; offset < code_point_length_in_bytes; offset++) {
ASSERT(m_ptr[offset] >> 6 == 2); ASSERT(m_ptr[offset] >> 6 == 2);
codepoint_value_so_far <<= 6; code_point_value_so_far <<= 6;
codepoint_value_so_far |= m_ptr[offset] & 63; code_point_value_so_far |= m_ptr[offset] & 63;
} }
return codepoint_value_so_far; return code_point_value_so_far;
} }
} }

4
AK/Utf8View.h
View file

@ -45,7 +45,7 @@ public:
Utf8CodepointIterator& operator++(); Utf8CodepointIterator& operator++();
u32 operator*() const; u32 operator*() const;
int codepoint_length_in_bytes() const; int code_point_length_in_bytes() const;
bool done() const { return !m_length; } bool done() const { return !m_length; }
private: private:
@ -80,7 +80,7 @@ public:
return validate(valid_bytes); return validate(valid_bytes);
} }
size_t length_in_codepoints() const; size_t length_in_code_points() const;
private: private:
const unsigned char* begin_ptr() const; const unsigned char* begin_ptr() const;

2
Applications/KeyboardMapper/KeyboardMapperWidget.cpp
View file

@ -267,7 +267,7 @@ void KeyboardMapperWidget::set_current_map(const String current_map)
continue; continue;
AK::StringBuilder sb; AK::StringBuilder sb;
sb.append_codepoint(map[index]); sb.append_code_point(map[index]);
m_keys.at(k)->set_text(sb.to_string()); m_keys.at(k)->set_text(sb.to_string());
} }

4
Kernel/TTY/VirtualConsole.cpp
View file

@ -287,10 +287,10 @@ void VirtualConsole::flush_dirty_lines()
if (!line.is_dirty() && !m_terminal.m_need_full_flush) if (!line.is_dirty() && !m_terminal.m_need_full_flush)
continue; continue;
for (size_t column = 0; column < line.length(); ++column) { for (size_t column = 0; column < line.length(); ++column) {
u32 codepoint = line.codepoint(column); u32 code_point = line.code_point(column);
auto attribute = line.attributes()[column]; auto attribute = line.attributes()[column];
u16 vga_index = (visual_row * 160) + (column * 2); u16 vga_index = (visual_row * 160) + (column * 2);
m_current_vga_window[vga_index] = codepoint < 128 ? codepoint : '?'; m_current_vga_window[vga_index] = code_point < 128 ? code_point : '?';
m_current_vga_window[vga_index + 1] = attribute_to_vga(attribute); m_current_vga_window[vga_index + 1] = attribute_to_vga(attribute);
} }
line.set_dirty(false); line.set_dirty(false);

20
Libraries/LibGUI/EmojiInputDialog.cpp
View file

@ -37,9 +37,9 @@
namespace GUI { namespace GUI {
static Vector<u32> supported_emoji_codepoints() static Vector<u32> supported_emoji_code_points()
{ {
Vector<u32> codepoints; Vector<u32> code_points;
Core::DirIterator dt("/res/emoji", Core::DirIterator::SkipDots); Core::DirIterator dt("/res/emoji", Core::DirIterator::SkipDots);
while (dt.has_next()) { while (dt.has_next()) {
auto filename = dt.next_path(); auto filename = dt.next_path();
@ -49,10 +49,10 @@ static Vector<u32> supported_emoji_codepoints()
auto basename = lexical_path.basename(); auto basename = lexical_path.basename();
if (!basename.starts_with("U+")) if (!basename.starts_with("U+"))
continue; continue;
u32 codepoint = strtoul(basename.characters() + 2, nullptr, 16); u32 code_point = strtoul(basename.characters() + 2, nullptr, 16);
codepoints.append(codepoint); code_points.append(code_point);
} }
return codepoints; return code_points;
} }
EmojiInputDialog::EmojiInputDialog(Window* parent_window) EmojiInputDialog::EmojiInputDialog(Window* parent_window)
@ -67,20 +67,20 @@ EmojiInputDialog::EmojiInputDialog(Window* parent_window)
auto& main_layout = main_widget.set_layout<VerticalBoxLayout>(); auto& main_layout = main_widget.set_layout<VerticalBoxLayout>();
main_layout.set_spacing(0); main_layout.set_spacing(0);
auto codepoints = supported_emoji_codepoints(); auto code_points = supported_emoji_code_points();
size_t index = 0; size_t index = 0;
size_t columns = 6; size_t columns = 6;
size_t rows = ceil_div(codepoints.size(), columns); size_t rows = ceil_div(code_points.size(), columns);
for (size_t row = 0; row < rows && index < codepoints.size(); ++row) { for (size_t row = 0; row < rows && index < code_points.size(); ++row) {
auto& horizontal_container = main_widget.add<Widget>(); auto& horizontal_container = main_widget.add<Widget>();
auto& horizontal_layout = horizontal_container.set_layout<HorizontalBoxLayout>(); auto& horizontal_layout = horizontal_container.set_layout<HorizontalBoxLayout>();
horizontal_layout.set_spacing(0); horizontal_layout.set_spacing(0);
for (size_t column = 0; column < columns; ++column) { for (size_t column = 0; column < columns; ++column) {
if (index < codepoints.size()) { if (index < code_points.size()) {
StringBuilder builder; StringBuilder builder;
builder.append(Utf32View(&codepoints[index++], 1)); builder.append(Utf32View(&code_points[index++], 1));
auto emoji_text = builder.to_string(); auto emoji_text = builder.to_string();
auto& button = horizontal_container.add<Button>(emoji_text); auto& button = horizontal_container.add<Button>(emoji_text);
button.set_button_style(Gfx::ButtonStyle::CoolBar); button.set_button_style(Gfx::ButtonStyle::CoolBar);

2
Libraries/LibGUI/Event.h
View file

@ -298,7 +298,7 @@ public:
String text() const String text() const
{ {
StringBuilder sb; StringBuilder sb;
sb.append_codepoint(m_code_point); sb.append_code_point(m_code_point);
return sb.to_string(); return sb.to_string();
} }
u32 scancode() const { return m_scancode; } u32 scancode() const { return m_scancode; }

76
Libraries/LibGUI/TextDocument.cpp
View file

@ -87,8 +87,8 @@ void TextDocument::set_text(const StringView& text)
size_t TextDocumentLine::first_non_whitespace_column() const size_t TextDocumentLine::first_non_whitespace_column() const
{ {
for (size_t i = 0; i < length(); ++i) { for (size_t i = 0; i < length(); ++i) {
auto codepoint = codepoints()[i]; auto code_point = code_points()[i];
if (!isspace(codepoint)) if (!isspace(code_point))
return i; return i;
} }
return length(); return length();
@ -131,35 +131,35 @@ void TextDocumentLine::set_text(TextDocument& document, const StringView& text)
} }
m_text.clear(); m_text.clear();
Utf8View utf8_view(text); Utf8View utf8_view(text);
for (auto codepoint : utf8_view) for (auto code_point : utf8_view)
m_text.append(codepoint); m_text.append(code_point);
document.update_views({}); document.update_views({});
} }
void TextDocumentLine::append(TextDocument& document, const u32* codepoints, size_t length) void TextDocumentLine::append(TextDocument& document, const u32* code_points, size_t length)
{ {
if (length == 0) if (length == 0)
return; return;
m_text.append(codepoints, length); m_text.append(code_points, length);
document.update_views({}); document.update_views({});
} }
void TextDocumentLine::append(TextDocument& document, u32 codepoint) void TextDocumentLine::append(TextDocument& document, u32 code_point)
{ {
insert(document, length(), codepoint); insert(document, length(), code_point);
} }
void TextDocumentLine::prepend(TextDocument& document, u32 codepoint) void TextDocumentLine::prepend(TextDocument& document, u32 code_point)
{ {
insert(document, 0, codepoint); insert(document, 0, code_point);
} }
void TextDocumentLine::insert(TextDocument& document, size_t index, u32 codepoint) void TextDocumentLine::insert(TextDocument& document, size_t index, u32 code_point)
{ {
if (index == length()) { if (index == length()) {
m_text.append(codepoint); m_text.append(code_point);
} else { } else {
m_text.insert(index, codepoint); m_text.insert(index, code_point);
} }
document.update_views({}); document.update_views({});
} }
@ -274,7 +274,7 @@ String TextDocument::text_in_range(const TextRange& a_range) const
auto& line = this->line(i); auto& line = this->line(i);
size_t selection_start_column_on_line = range.start().line() == i ? range.start().column() : 0; size_t selection_start_column_on_line = range.start().line() == i ? range.start().column() : 0;
size_t selection_end_column_on_line = range.end().line() == i ? range.end().column() : line.length(); size_t selection_end_column_on_line = range.end().line() == i ? range.end().column() : line.length();
builder.append(Utf32View(line.codepoints() + selection_start_column_on_line, selection_end_column_on_line - selection_start_column_on_line)); builder.append(Utf32View(line.code_points() + selection_start_column_on_line, selection_end_column_on_line - selection_start_column_on_line));
if (i != range.end().line()) if (i != range.end().line())
builder.append('\n'); builder.append('\n');
} }
@ -282,13 +282,13 @@ String TextDocument::text_in_range(const TextRange& a_range) const
return builder.to_string(); return builder.to_string();
} }
u32 TextDocument::codepoint_at(const TextPosition& position) const u32 TextDocument::code_point_at(const TextPosition& position) const
{ {
ASSERT(position.line() < line_count()); ASSERT(position.line() < line_count());
auto& line = this->line(position.line()); auto& line = this->line(position.line());
if (position.column() == line.length()) if (position.column() == line.length())
return '\n'; return '\n';
return line.codepoints()[position.column()]; return line.code_points()[position.column()];
} }
TextPosition TextDocument::next_position_after(const TextPosition& position, SearchShouldWrap should_wrap) const TextPosition TextDocument::next_position_after(const TextPosition& position, SearchShouldWrap should_wrap) const
@ -333,7 +333,7 @@ TextRange TextDocument::find_next(const StringView& needle, const TextPosition&
size_t needle_index = 0; size_t needle_index = 0;
do { do {
auto ch = codepoint_at(position); auto ch = code_point_at(position);
// FIXME: This is not the right way to use a Unicode needle! // FIXME: This is not the right way to use a Unicode needle!
if (ch == (u32)needle[needle_index]) { if (ch == (u32)needle[needle_index]) {
if (needle_index == 0) if (needle_index == 0)
@ -365,7 +365,7 @@ TextRange TextDocument::find_previous(const StringView& needle, const TextPositi
size_t needle_index = needle.length() - 1; size_t needle_index = needle.length() - 1;
do { do {
auto ch = codepoint_at(position); auto ch = code_point_at(position);
// FIXME: This is not the right way to use a Unicode needle! // FIXME: This is not the right way to use a Unicode needle!
if (ch == (u32)needle[needle_index]) { if (ch == (u32)needle[needle_index]) {
if (needle_index == needle.length() - 1) if (needle_index == needle.length() - 1)
@ -439,11 +439,11 @@ TextPosition TextDocument::first_word_break_before(const TextPosition& position,
auto target = position; auto target = position;
auto line = this->line(target.line()); auto line = this->line(target.line());
auto is_start_alphanumeric = isalnum(line.codepoints()[target.column() - (start_at_column_before ? 1 : 0)]); auto is_start_alphanumeric = isalnum(line.code_points()[target.column() - (start_at_column_before ? 1 : 0)]);
while (target.column() > 0) { while (target.column() > 0) {
auto prev_codepoint = line.codepoints()[target.column() - 1]; auto prev_code_point = line.code_points()[target.column() - 1];
if ((is_start_alphanumeric && !isalnum(prev_codepoint)) || (!is_start_alphanumeric && isalnum(prev_codepoint))) if ((is_start_alphanumeric && !isalnum(prev_code_point)) || (!is_start_alphanumeric && isalnum(prev_code_point)))
break; break;
target.set_column(target.column() - 1); target.set_column(target.column() - 1);
} }
@ -463,11 +463,11 @@ TextPosition TextDocument::first_word_break_after(const TextPosition& position)
return TextPosition(position.line() + 1, 0); return TextPosition(position.line() + 1, 0);
} }
auto is_start_alphanumeric = isalnum(line.codepoints()[target.column()]); auto is_start_alphanumeric = isalnum(line.code_points()[target.column()]);
while (target.column() < line.length()) { while (target.column() < line.length()) {
auto next_codepoint = line.codepoints()[target.column()]; auto next_code_point = line.code_points()[target.column()];
if ((is_start_alphanumeric && !isalnum(next_codepoint)) || (!is_start_alphanumeric && isalnum(next_codepoint))) if ((is_start_alphanumeric && !isalnum(next_code_point)) || (!is_start_alphanumeric && isalnum(next_code_point)))
break; break;
target.set_column(target.column() + 1); target.set_column(target.column() + 1);
} }
@ -555,26 +555,26 @@ TextPosition TextDocument::insert_at(const TextPosition& position, const StringV
{ {
TextPosition cursor = position; TextPosition cursor = position;
Utf8View utf8_view(text); Utf8View utf8_view(text);
for (auto codepoint : utf8_view) for (auto code_point : utf8_view)
cursor = insert_at(cursor, codepoint, client); cursor = insert_at(cursor, code_point, client);
return cursor; return cursor;
} }
TextPosition TextDocument::insert_at(const TextPosition& position, u32 codepoint, const Client* client) TextPosition TextDocument::insert_at(const TextPosition& position, u32 code_point, const Client* client)
{ {
bool automatic_indentation_enabled = client ? client->is_automatic_indentation_enabled() : false; bool automatic_indentation_enabled = client ? client->is_automatic_indentation_enabled() : false;
size_t m_soft_tab_width = client ? client->soft_tab_width() : 4; size_t m_soft_tab_width = client ? client->soft_tab_width() : 4;
bool at_head = position.column() == 0; bool at_head = position.column() == 0;
bool at_tail = position.column() == line(position.line()).length(); bool at_tail = position.column() == line(position.line()).length();
if (codepoint == '\n') { if (code_point == '\n') {
if (at_tail || at_head) { if (at_tail || at_head) {
String new_line_contents; String new_line_contents;
if (automatic_indentation_enabled && at_tail) { if (automatic_indentation_enabled && at_tail) {
size_t leading_spaces = 0; size_t leading_spaces = 0;
auto& old_line = lines()[position.line()]; auto& old_line = lines()[position.line()];
for (size_t i = 0; i < old_line.length(); ++i) { for (size_t i = 0; i < old_line.length(); ++i) {
if (old_line.codepoints()[i] == ' ') if (old_line.code_points()[i] == ' ')
++leading_spaces; ++leading_spaces;
else else
break; break;
@ -586,23 +586,23 @@ TextPosition TextDocument::insert_at(const TextPosition& position, u32 codepoint
size_t row = position.line(); size_t row = position.line();
Vector<u32> line_content; Vector<u32> line_content;
for (size_t i = position.column(); i < line(row).length(); i++) for (size_t i = position.column(); i < line(row).length(); i++)
line_content.append(line(row).codepoints()[i]); line_content.append(line(row).code_points()[i]);
insert_line(position.line() + (at_tail ? 1 : 0), make<TextDocumentLine>(*this, new_line_contents)); insert_line(position.line() + (at_tail ? 1 : 0), make<TextDocumentLine>(*this, new_line_contents));
notify_did_change(); notify_did_change();
return { position.line() + 1, line(position.line() + 1).length() }; return { position.line() + 1, line(position.line() + 1).length() };
} }
auto new_line = make<TextDocumentLine>(*this); auto new_line = make<TextDocumentLine>(*this);
new_line->append(*this, line(position.line()).codepoints() + position.column(), line(position.line()).length() - position.column()); new_line->append(*this, line(position.line()).code_points() + position.column(), line(position.line()).length() - position.column());
Vector<u32> line_content; Vector<u32> line_content;
for (size_t i = 0; i < new_line->length(); i++) for (size_t i = 0; i < new_line->length(); i++)
line_content.append(new_line->codepoints()[i]); line_content.append(new_line->code_points()[i]);
line(position.line()).truncate(*this, position.column()); line(position.line()).truncate(*this, position.column());
insert_line(position.line() + 1, move(new_line)); insert_line(position.line() + 1, move(new_line));
notify_did_change(); notify_did_change();
return { position.line() + 1, 0 }; return { position.line() + 1, 0 };
} }
if (codepoint == '\t') { if (code_point == '\t') {
size_t next_soft_tab_stop = ((position.column() + m_soft_tab_width) / m_soft_tab_width) * m_soft_tab_width; size_t next_soft_tab_stop = ((position.column() + m_soft_tab_width) / m_soft_tab_width) * m_soft_tab_width;
size_t spaces_to_insert = next_soft_tab_stop - position.column(); size_t spaces_to_insert = next_soft_tab_stop - position.column();
for (size_t i = 0; i < spaces_to_insert; ++i) { for (size_t i = 0; i < spaces_to_insert; ++i) {
@ -611,7 +611,7 @@ TextPosition TextDocument::insert_at(const TextPosition& position, u32 codepoint
notify_did_change(); notify_did_change();
return { position.line(), next_soft_tab_stop }; return { position.line(), next_soft_tab_stop };
} }
line(position.line()).insert(*this, position.column(), codepoint); line(position.line()).insert(*this, position.column(), code_point);
notify_did_change(); notify_did_change();
return { position.line(), position.column() + 1 }; return { position.line(), position.column() + 1 };
} }
@ -644,10 +644,10 @@ void TextDocument::remove(const TextRange& unnormalized_range)
ASSERT(range.start().line() == range.end().line() - 1); ASSERT(range.start().line() == range.end().line() - 1);
auto& first_line = line(range.start().line()); auto& first_line = line(range.start().line());
auto& second_line = line(range.end().line()); auto& second_line = line(range.end().line());
Vector<u32> codepoints; Vector<u32> code_points;
codepoints.append(first_line.codepoints(), range.start().column()); code_points.append(first_line.code_points(), range.start().column());
codepoints.append(second_line.codepoints() + range.end().column(), second_line.length() - range.end().column()); code_points.append(second_line.code_points() + range.end().column(), second_line.length() - range.end().column());
first_line.set_text(*this, move(codepoints)); first_line.set_text(*this, move(code_points));
remove_line(range.end().line()); remove_line(range.end().line());
} }

6
Libraries/LibGUI/TextDocument.h
View file

@ -113,7 +113,7 @@ public:
TextPosition next_position_after(const TextPosition&, SearchShouldWrap = SearchShouldWrap::Yes) const; TextPosition next_position_after(const TextPosition&, SearchShouldWrap = SearchShouldWrap::Yes) const;
TextPosition previous_position_before(const TextPosition&, SearchShouldWrap = SearchShouldWrap::Yes) const; TextPosition previous_position_before(const TextPosition&, SearchShouldWrap = SearchShouldWrap::Yes) const;
u32 codepoint_at(const TextPosition&) const; u32 code_point_at(const TextPosition&) const;
TextRange range_for_entire_line(size_t line_index) const; TextRange range_for_entire_line(size_t line_index) const;
@ -159,8 +159,8 @@ public:
String to_utf8() const; String to_utf8() const;
Utf32View view() const { return { codepoints(), length() }; } Utf32View view() const { return { code_points(), length() }; }
const u32* codepoints() const { return m_text.data(); } const u32* code_points() const { return m_text.data(); }
size_t length() const { return m_text.size(); } size_t length() const { return m_text.size(); }
void set_text(TextDocument&, const StringView&); void set_text(TextDocument&, const StringView&);
void set_text(TextDocument&, Vector<u32>); void set_text(TextDocument&, Vector<u32>);

20
Libraries/LibGUI/TextEditor.cpp
View file

@ -172,7 +172,7 @@ TextPosition TextEditor::text_position_at(const Gfx::IntPoint& a_position) const
int glyph_x = 0; int glyph_x = 0;
size_t i = 0; size_t i = 0;
for (; i < view.length(); ++i) { for (; i < view.length(); ++i) {
int advance = font().glyph_width(view.codepoints()[i]) + font().glyph_spacing(); int advance = font().glyph_width(view.code_points()[i]) + font().glyph_spacing();
if ((glyph_x + (advance / 2)) >= position.x()) if ((glyph_x + (advance / 2)) >= position.x())
break; break;
glyph_x += advance; glyph_x += advance;
@ -465,7 +465,7 @@ void TextEditor::paint_event(PaintEvent& event)
} else { } else {
Gfx::IntRect character_rect = { visual_line_rect.location(), { 0, line_height() } }; Gfx::IntRect character_rect = { visual_line_rect.location(), { 0, line_height() } };
for (size_t i = 0; i < visual_line_text.length(); ++i) { for (size_t i = 0; i < visual_line_text.length(); ++i) {
u32 codepoint = visual_line_text.substring_view(i, 1).codepoints()[0]; u32 code_point = visual_line_text.substring_view(i, 1).code_points()[0];
const Gfx::Font* font = &this->font(); const Gfx::Font* font = &this->font();
Color color; Color color;
Optional<Color> background_color; Optional<Color> background_color;
@ -482,7 +482,7 @@ void TextEditor::paint_event(PaintEvent& event)
underline = span.is_underlined; underline = span.is_underlined;
break; break;
} }
character_rect.set_width(font->glyph_width(codepoint) + font->glyph_spacing()); character_rect.set_width(font->glyph_width(code_point) + font->glyph_spacing());
if (background_color.has_value()) if (background_color.has_value())
painter.fill_rect(character_rect, background_color.value()); painter.fill_rect(character_rect, background_color.value());
painter.draw_text(character_rect, visual_line_text.substring_view(i, 1), *font, m_text_alignment, color); painter.draw_text(character_rect, visual_line_text.substring_view(i, 1), *font, m_text_alignment, color);
@ -524,9 +524,9 @@ void TextEditor::paint_event(PaintEvent& event)
painter.fill_rect(selection_rect, background_color); painter.fill_rect(selection_rect, background_color);
if (visual_line_text.codepoints()) { if (visual_line_text.code_points()) {
Utf32View visual_selected_text { Utf32View visual_selected_text {
visual_line_text.codepoints() + start_of_selection_within_visual_line, visual_line_text.code_points() + start_of_selection_within_visual_line,
end_of_selection_within_visual_line - start_of_selection_within_visual_line end_of_selection_within_visual_line - start_of_selection_within_visual_line
}; };
@ -660,7 +660,7 @@ void TextEditor::sort_selected_lines()
auto end = lines.begin() + (int)last_line + 1; auto end = lines.begin() + (int)last_line + 1;
quick_sort(start, end, [](auto& a, auto& b) { quick_sort(start, end, [](auto& a, auto& b) {
return strcmp_utf32(a.codepoints(), b.codepoints(), min(a.length(), b.length())) < 0; return strcmp_utf32(a.code_points(), b.code_points(), min(a.length(), b.length())) < 0;
}); });
did_change(); did_change();
@ -939,7 +939,7 @@ void TextEditor::keydown_event(KeyEvent& event)
if (is_editable() && !event.ctrl() && !event.alt() && event.code_point() != 0) { if (is_editable() && !event.ctrl() && !event.alt() && event.code_point() != 0) {
StringBuilder sb; StringBuilder sb;
sb.append_codepoint(event.code_point()); sb.append_code_point(event.code_point());
insert_at_cursor_or_replace_selection(sb.to_string()); insert_at_cursor_or_replace_selection(sb.to_string());
return; return;
@ -1525,8 +1525,8 @@ void TextEditor::recompute_visual_lines(size_t line_index)
auto glyph_spacing = font().glyph_spacing(); auto glyph_spacing = font().glyph_spacing();
for (size_t i = 0; i < line.length(); ++i) { for (size_t i = 0; i < line.length(); ++i) {
auto codepoint = line.codepoints()[i]; auto code_point = line.code_points()[i];
auto glyph_width = font().glyph_or_emoji_width(codepoint); auto glyph_width = font().glyph_or_emoji_width(code_point);
if ((line_width_so_far + glyph_width + glyph_spacing) > available_width) { if ((line_width_so_far + glyph_width + glyph_spacing) > available_width) {
visual_data.visual_line_breaks.append(i); visual_data.visual_line_breaks.append(i);
line_width_so_far = glyph_width + glyph_spacing; line_width_so_far = glyph_width + glyph_spacing;
@ -1555,7 +1555,7 @@ void TextEditor::for_each_visual_line(size_t line_index, Callback callback) cons
auto& visual_data = m_line_visual_data[line_index]; auto& visual_data = m_line_visual_data[line_index];
for (auto visual_line_break : visual_data.visual_line_breaks) { for (auto visual_line_break : visual_data.visual_line_breaks) {
auto visual_line_view = Utf32View(line.codepoints() + start_of_line, visual_line_break - start_of_line); auto visual_line_view = Utf32View(line.code_points() + start_of_line, visual_line_break - start_of_line);
Gfx::IntRect visual_line_rect { Gfx::IntRect visual_line_rect {
visual_data.visual_rect.x(), visual_data.visual_rect.x(),
visual_data.visual_rect.y() + ((int)visual_line_index * line_height()), visual_data.visual_rect.y() + ((int)visual_line_index * line_height()),

10
Libraries/LibGfx/Emoji.cpp
View file

@ -33,21 +33,21 @@ namespace Gfx {
static HashMap<u32, RefPtr<Gfx::Bitmap>> s_emojis; static HashMap<u32, RefPtr<Gfx::Bitmap>> s_emojis;
const Bitmap* Emoji::emoji_for_codepoint(u32 codepoint) const Bitmap* Emoji::emoji_for_code_point(u32 code_point)
{ {
auto it = s_emojis.find(codepoint); auto it = s_emojis.find(code_point);
if (it != s_emojis.end()) if (it != s_emojis.end())
return (*it).value.ptr(); return (*it).value.ptr();
String path = String::format("/res/emoji/U+%X.png", codepoint); String path = String::format("/res/emoji/U+%X.png", code_point);
auto bitmap = Bitmap::load_from_file(path); auto bitmap = Bitmap::load_from_file(path);
if (!bitmap) { if (!bitmap) {
s_emojis.set(codepoint, nullptr); s_emojis.set(code_point, nullptr);
return nullptr; return nullptr;
} }
s_emojis.set(codepoint, bitmap); s_emojis.set(code_point, bitmap);
return bitmap.ptr(); return bitmap.ptr();
} }

2
Libraries/LibGfx/Emoji.h
View file

@ -34,7 +34,7 @@ class Bitmap;
class Emoji { class Emoji {
public: public:
static const Gfx::Bitmap* emoji_for_codepoint(u32 codepoint); static const Gfx::Bitmap* emoji_for_code_point(u32 code_point);
}; };
} }

18
Libraries/LibGfx/Font.cpp
View file

@ -255,20 +255,20 @@ bool Font::write_to_file(const StringView& path)
return true; return true;
} }
GlyphBitmap Font::glyph_bitmap(u32 codepoint) const GlyphBitmap Font::glyph_bitmap(u32 code_point) const
{ {
return GlyphBitmap(&m_rows[codepoint * m_glyph_height], { glyph_width(codepoint), m_glyph_height }); return GlyphBitmap(&m_rows[code_point * m_glyph_height], { glyph_width(code_point), m_glyph_height });
} }
int Font::glyph_or_emoji_width(u32 codepoint) const int Font::glyph_or_emoji_width(u32 code_point) const
{ {
if (codepoint < m_glyph_count) if (code_point < m_glyph_count)
return glyph_width(codepoint); return glyph_width(code_point);
if (m_fixed_width) if (m_fixed_width)
return m_glyph_width; return m_glyph_width;
auto* emoji = Emoji::emoji_for_codepoint(codepoint); auto* emoji = Emoji::emoji_for_code_point(code_point);
if (emoji == nullptr) if (emoji == nullptr)
return glyph_width('?'); return glyph_width('?');
return emoji->size().width(); return emoji->size().width();
@ -285,11 +285,11 @@ int Font::width(const Utf8View& utf8) const
bool first = true; bool first = true;
int width = 0; int width = 0;
for (u32 codepoint : utf8) { for (u32 code_point : utf8) {
if (!first) if (!first)
width += glyph_spacing(); width += glyph_spacing();
first = false; first = false;
width += glyph_or_emoji_width(codepoint); width += glyph_or_emoji_width(code_point);
} }
return width; return width;
@ -301,7 +301,7 @@ int Font::width(const Utf32View& view) const
return 0; return 0;
int width = (view.length() - 1) * glyph_spacing(); int width = (view.length() - 1) * glyph_spacing();
for (size_t i = 0; i < view.length(); ++i) for (size_t i = 0; i < view.length(); ++i)
width += glyph_or_emoji_width(view.codepoints()[i]); width += glyph_or_emoji_width(view.code_points()[i]);
return width; return width;
} }

4
Libraries/LibGfx/Font.h
View file

@ -89,10 +89,10 @@ public:
~Font(); ~Font();
GlyphBitmap glyph_bitmap(u32 codepoint) const; GlyphBitmap glyph_bitmap(u32 code_point) const;
u8 glyph_width(size_t ch) const { return m_fixed_width ? m_glyph_width : m_glyph_widths[ch]; } u8 glyph_width(size_t ch) const { return m_fixed_width ? m_glyph_width : m_glyph_widths[ch]; }
int glyph_or_emoji_width(u32 codepoint) const; int glyph_or_emoji_width(u32 code_point) const;
u8 glyph_height() const { return m_glyph_height; } u8 glyph_height() const { return m_glyph_height; }
u8 min_glyph_width() const { return m_min_glyph_width; } u8 min_glyph_width() const { return m_min_glyph_width; }
u8 max_glyph_width() const { return m_max_glyph_width; } u8 max_glyph_width() const { return m_max_glyph_width; }

52
Libraries/LibGfx/Painter.cpp
View file

@ -803,14 +803,14 @@ void Painter::draw_scaled_bitmap(const IntRect& a_dst_rect, const Gfx::Bitmap& s
} }
} }
FLATTEN void Painter::draw_glyph(const IntPoint& point, u32 codepoint, Color color) FLATTEN void Painter::draw_glyph(const IntPoint& point, u32 code_point, Color color)
{ {
draw_glyph(point, codepoint, font(), color); draw_glyph(point, code_point, font(), color);
} }
FLATTEN void Painter::draw_glyph(const IntPoint& point, u32 codepoint, const Font& font, Color color) FLATTEN void Painter::draw_glyph(const IntPoint& point, u32 code_point, const Font& font, Color color)
{ {
draw_bitmap(point, font.glyph_bitmap(codepoint), color); draw_bitmap(point, font.glyph_bitmap(code_point), color);
} }
void Painter::draw_emoji(const IntPoint& point, const Gfx::Bitmap& emoji, const Font& font) void Painter::draw_emoji(const IntPoint& point, const Gfx::Bitmap& emoji, const Font& font)
@ -828,19 +828,19 @@ void Painter::draw_emoji(const IntPoint& point, const Gfx::Bitmap& emoji, const
} }
} }
void Painter::draw_glyph_or_emoji(const IntPoint& point, u32 codepoint, const Font& font, Color color) void Painter::draw_glyph_or_emoji(const IntPoint& point, u32 code_point, const Font& font, Color color)
{ {
if (codepoint < (u32)font.glyph_count()) { if (code_point < (u32)font.glyph_count()) {
// This looks like a regular character. // This looks like a regular character.
draw_glyph(point, (size_t)codepoint, font, color); draw_glyph(point, (size_t)code_point, font, color);
return; return;
} }
// Perhaps it's an emoji? // Perhaps it's an emoji?
auto* emoji = Emoji::emoji_for_codepoint(codepoint); auto* emoji = Emoji::emoji_for_code_point(code_point);
if (emoji == nullptr) { if (emoji == nullptr) {
#ifdef EMOJI_DEBUG #ifdef EMOJI_DEBUG
dbg() << "Failed to find an emoji for codepoint " << codepoint; dbg() << "Failed to find an emoji for code_point " << code_point;
#endif #endif
draw_glyph(point, '?', font, color); draw_glyph(point, '?', font, color);
return; return;
@ -862,8 +862,8 @@ void Painter::draw_text_line(const IntRect& a_rect, const Utf8View& text, const
int new_width = font.width("..."); int new_width = font.width("...");
if (new_width < text_width) { if (new_width < text_width) {
for (auto it = final_text.begin(); it != final_text.end(); ++it) { for (auto it = final_text.begin(); it != final_text.end(); ++it) {
u32 codepoint = *it; u32 code_point = *it;
int glyph_width = font.glyph_or_emoji_width(codepoint); int glyph_width = font.glyph_or_emoji_width(code_point);
// NOTE: Glyph spacing should not be added after the last glyph on the line, // NOTE: Glyph spacing should not be added after the last glyph on the line,
// but since we are here because the last glyph does not actually fit on the line, // but since we are here because the last glyph does not actually fit on the line,
// we don't have to worry about spacing. // we don't have to worry about spacing.
@ -904,13 +904,13 @@ void Painter::draw_text_line(const IntRect& a_rect, const Utf8View& text, const
auto point = rect.location(); auto point = rect.location();
int space_width = font.glyph_width(' ') + font.glyph_spacing(); int space_width = font.glyph_width(' ') + font.glyph_spacing();
for (u32 codepoint : final_text) { for (u32 code_point : final_text) {
if (codepoint == ' ') { if (code_point == ' ') {
point.move_by(space_width, 0); point.move_by(space_width, 0);
continue; continue;
} }
draw_glyph_or_emoji(point, codepoint, font, color); draw_glyph_or_emoji(point, code_point, font, color);
point.move_by(font.glyph_or_emoji_width(codepoint) + font.glyph_spacing(), 0); point.move_by(font.glyph_or_emoji_width(code_point) + font.glyph_spacing(), 0);
} }
} }
@ -927,8 +927,8 @@ void Painter::draw_text_line(const IntRect& a_rect, const Utf32View& text, const
if (new_width < text_width) { if (new_width < text_width) {
size_t i = 0; size_t i = 0;
for (; i < text.length(); ++i) { for (; i < text.length(); ++i) {
u32 codepoint = text.codepoints()[i]; u32 code_point = text.code_points()[i];
int glyph_width = font.glyph_or_emoji_width(codepoint); int glyph_width = font.glyph_or_emoji_width(code_point);
// NOTE: Glyph spacing should not be added after the last glyph on the line, // NOTE: Glyph spacing should not be added after the last glyph on the line,
// but since we are here because the last glyph does not actually fit on the line, // but since we are here because the last glyph does not actually fit on the line,
// we don't have to worry about spacing. // we don't have to worry about spacing.
@ -938,7 +938,7 @@ void Painter::draw_text_line(const IntRect& a_rect, const Utf32View& text, const
new_width += glyph_width + glyph_spacing; new_width += glyph_width + glyph_spacing;
} }
elided_text.clear(); elided_text.clear();
elided_text.append(final_text.codepoints(), i); elided_text.append(final_text.code_points(), i);
elided_text.append('.'); elided_text.append('.');
elided_text.append('.'); elided_text.append('.');
elided_text.append('.'); elided_text.append('.');
@ -970,13 +970,13 @@ void Painter::draw_text_line(const IntRect& a_rect, const Utf32View& text, const
int space_width = font.glyph_width(' ') + font.glyph_spacing(); int space_width = font.glyph_width(' ') + font.glyph_spacing();
for (size_t i = 0; i < final_text.length(); ++i) { for (size_t i = 0; i < final_text.length(); ++i) {
auto codepoint = final_text.codepoints()[i]; auto code_point = final_text.code_points()[i];
if (codepoint == ' ') { if (code_point == ' ') {
point.move_by(space_width, 0); point.move_by(space_width, 0);
continue; continue;
} }
draw_glyph_or_emoji(point, codepoint, font, color); draw_glyph_or_emoji(point, code_point, font, color);
point.move_by(font.glyph_or_emoji_width(codepoint) + font.glyph_spacing(), 0); point.move_by(font.glyph_or_emoji_width(code_point) + font.glyph_spacing(), 0);
} }
} }
@ -997,8 +997,8 @@ void Painter::draw_text(const IntRect& rect, const StringView& raw_text, const F
int start_of_current_line = 0; int start_of_current_line = 0;
for (auto it = text.begin(); it != text.end(); ++it) { for (auto it = text.begin(); it != text.end(); ++it) {
u32 codepoint = *it; u32 code_point = *it;
if (codepoint == '\n') { if (code_point == '\n') {
int byte_offset = text.byte_offset_of(it); int byte_offset = text.byte_offset_of(it);
Utf8View line = text.substring_view(start_of_current_line, byte_offset - start_of_current_line); Utf8View line = text.substring_view(start_of_current_line, byte_offset - start_of_current_line);
lines.append(line); lines.append(line);
@ -1055,8 +1055,8 @@ void Painter::draw_text(const IntRect& rect, const Utf32View& text, const Font&
size_t start_of_current_line = 0; size_t start_of_current_line = 0;
for (size_t i = 0; i < text.length(); ++i) { for (size_t i = 0; i < text.length(); ++i) {
u32 codepoint = text.codepoints()[i]; u32 code_point = text.code_points()[i];
if (codepoint == '\n') { if (code_point == '\n') {
Utf32View line = text.substring_view(start_of_current_line, i - start_of_current_line); Utf32View line = text.substring_view(start_of_current_line, i - start_of_current_line);
lines.append(line); lines.append(line);
start_of_current_line = i + 1; start_of_current_line = i + 1;

2
Libraries/LibGfx/Painter.h
View file

@ -81,7 +81,7 @@ public:
void draw_glyph(const IntPoint&, u32, Color); void draw_glyph(const IntPoint&, u32, Color);
void draw_glyph(const IntPoint&, u32, const Font&, Color); void draw_glyph(const IntPoint&, u32, const Font&, Color);
void draw_emoji(const IntPoint&, const Gfx::Bitmap&, const Font&); void draw_emoji(const IntPoint&, const Gfx::Bitmap&, const Font&);
void draw_glyph_or_emoji(const IntPoint&, u32 codepoint, const Font&, Color); void draw_glyph_or_emoji(const IntPoint&, u32 code_point, const Font&, Color);
static void for_each_line_segment_on_bezier_curve(const FloatPoint& control_point, const FloatPoint& p1, const FloatPoint& p2, Function<void(const FloatPoint&, const FloatPoint&)>&); static void for_each_line_segment_on_bezier_curve(const FloatPoint& control_point, const FloatPoint& p1, const FloatPoint& p2, Function<void(const FloatPoint&, const FloatPoint&)>&);
static void for_each_line_segment_on_bezier_curve(const FloatPoint& control_point, const FloatPoint& p1, const FloatPoint& p2, Function<void(const FloatPoint&, const FloatPoint&)>&&); static void for_each_line_segment_on_bezier_curve(const FloatPoint& control_point, const FloatPoint& p1, const FloatPoint& p2, Function<void(const FloatPoint&, const FloatPoint&)>&&);

2
Libraries/LibJS/Parser.cpp
View file

@ -834,7 +834,7 @@ NonnullRefPtr<StringLiteral> Parser::parse_string_literal(Token token)
auto type = status == Token::StringValueStatus::MalformedUnicodeEscape ? "unicode" : "hexadecimal"; auto type = status == Token::StringValueStatus::MalformedUnicodeEscape ? "unicode" : "hexadecimal";
message = String::format("Malformed %s escape sequence", type); message = String::format("Malformed %s escape sequence", type);
} else if (status == Token::StringValueStatus::UnicodeEscapeOverflow) { } else if (status == Token::StringValueStatus::UnicodeEscapeOverflow) {
message = "Unicode codepoint must not be greater than 0x10ffff in escape sequence"; message = "Unicode code_point must not be greater than 0x10ffff in escape sequence";
} }
syntax_error( syntax_error(

2
Libraries/LibJS/Runtime/StringIteratorPrototype.cpp
View file

@ -69,7 +69,7 @@ JS_DEFINE_NATIVE_FUNCTION(StringIteratorPrototype::next)
} }
StringBuilder builder; StringBuilder builder;
builder.append_codepoint(*utf8_iterator); builder.append_code_point(*utf8_iterator);
++utf8_iterator; ++utf8_iterator;
return create_iterator_result_object(global_object, js_string(interpreter, builder.to_string()), false); return create_iterator_result_object(global_object, js_string(interpreter, builder.to_string()), false);

8
Libraries/LibJS/Runtime/StringPrototype.cpp
View file

@ -321,7 +321,7 @@ JS_DEFINE_NATIVE_FUNCTION(StringPrototype::substring)
if (interpreter.argument_count() == 0) if (interpreter.argument_count() == 0)
return js_string(interpreter, string); return js_string(interpreter, string);
// FIXME: index_start and index_end should index a UTF-16 codepoint view of the string. // FIXME: index_start and index_end should index a UTF-16 code_point view of the string.
auto string_length = string.length(); auto string_length = string.length();
auto index_start = min(interpreter.argument(0).to_size_t(interpreter), string_length); auto index_start = min(interpreter.argument(0).to_size_t(interpreter), string_length);
if (interpreter.exception()) if (interpreter.exception())
@ -358,7 +358,7 @@ JS_DEFINE_NATIVE_FUNCTION(StringPrototype::includes)
if (interpreter.exception()) if (interpreter.exception())
return {}; return {};
// FIXME: position should index a UTF-16 codepoint view of the string. // FIXME: position should index a UTF-16 code_point view of the string.
size_t position = 0; size_t position = 0;
if (interpreter.argument_count() >= 2) { if (interpreter.argument_count() >= 2) {
position = interpreter.argument(1).to_size_t(interpreter); position = interpreter.argument(1).to_size_t(interpreter);
@ -385,7 +385,7 @@ JS_DEFINE_NATIVE_FUNCTION(StringPrototype::slice)
if (interpreter.argument_count() == 0) if (interpreter.argument_count() == 0)
return js_string(interpreter, string); return js_string(interpreter, string);
// FIXME: index_start and index_end should index a UTF-16 codepoint view of the string. // FIXME: index_start and index_end should index a UTF-16 code_point view of the string.
auto string_length = static_cast<i32>(string.length()); auto string_length = static_cast<i32>(string.length());
auto index_start = interpreter.argument(0).to_i32(interpreter); auto index_start = interpreter.argument(0).to_i32(interpreter);
if (interpreter.exception()) if (interpreter.exception())
@ -437,7 +437,7 @@ JS_DEFINE_NATIVE_FUNCTION(StringPrototype::last_index_of)
auto max_index = string.length() - search_string.length(); auto max_index = string.length() - search_string.length();
auto from_index = max_index; auto from_index = max_index;
if (interpreter.argument_count() >= 2) { if (interpreter.argument_count() >= 2) {
// FIXME: from_index should index a UTF-16 codepoint view of the string. // FIXME: from_index should index a UTF-16 code_point view of the string.
from_index = min(interpreter.argument(1).to_size_t(interpreter), max_index); from_index = min(interpreter.argument(1).to_size_t(interpreter), max_index);
if (interpreter.exception()) if (interpreter.exception())
return {}; return {};

8
Libraries/LibJS/Runtime/Value.cpp
View file

@ -917,10 +917,10 @@ TriState abstract_relation(Interpreter& interpreter, bool left_first, Value lhs,
if (y_string.starts_with(x_string)) if (y_string.starts_with(x_string))
return TriState::True; return TriState::True;
Utf8View x_codepoints { x_string }; Utf8View x_code_points { x_string };
Utf8View y_codepoints { y_string }; Utf8View y_code_points { y_string };
for (auto k = x_codepoints.begin(), l = y_codepoints.begin(); for (auto k = x_code_points.begin(), l = y_code_points.begin();
k != x_codepoints.end() && l != y_codepoints.end(); k != x_code_points.end() && l != y_code_points.end();
++k, ++l) { ++k, ++l) {
if (*k != *l) { if (*k != *l) {
if (*k < *l) { if (*k < *l) {

4
Libraries/LibJS/Token.cpp
View file

@ -136,7 +136,7 @@ String Token::string_value(StringValueStatus& status) const
auto digit2 = m_value[++i]; auto digit2 = m_value[++i];
if (!isxdigit(digit1) || !isxdigit(digit2)) if (!isxdigit(digit1) || !isxdigit(digit2))
return encoding_failure(StringValueStatus::MalformedHexEscape); return encoding_failure(StringValueStatus::MalformedHexEscape);
builder.append_codepoint(hex2int(digit1) * 16 + hex2int(digit2)); builder.append_code_point(hex2int(digit1) * 16 + hex2int(digit2));
break; break;
} }
case 'u': { case 'u': {
@ -174,7 +174,7 @@ String Token::string_value(StringValueStatus& status) const
} }
} }
builder.append_codepoint(code_point); builder.append_code_point(code_point);
break; break;
} }
default: default:

92
Libraries/LibLine/Editor.cpp
View file

@ -97,7 +97,7 @@ void Editor::clear_line()
void Editor::insert(const Utf32View& string) void Editor::insert(const Utf32View& string)
{ {
for (size_t i = 0; i < string.length(); ++i) for (size_t i = 0; i < string.length(); ++i)
insert(string.codepoints()[i]); insert(string.code_points()[i]);
} }
void Editor::insert(const String& string) void Editor::insert(const String& string)
@ -137,15 +137,15 @@ void Editor::register_character_input_callback(char ch, Function<bool(Editor&)>
m_key_callbacks.set(ch, make<KeyCallback>(move(callback))); m_key_callbacks.set(ch, make<KeyCallback>(move(callback)));
} }
static size_t codepoint_length_in_utf8(u32 codepoint) static size_t code_point_length_in_utf8(u32 code_point)
{ {
if (codepoint <= 0x7f) if (code_point <= 0x7f)
return 1; return 1;
if (codepoint <= 0x07ff) if (code_point <= 0x07ff)
return 2; return 2;
if (codepoint <= 0xffff) if (code_point <= 0xffff)
return 3; return 3;
if (codepoint <= 0x10ffff) if (code_point <= 0x10ffff)
return 4; return 4;
return 3; return 3;
} }
@ -156,20 +156,20 @@ static size_t codepoint_length_in_utf8(u32 codepoint)
// | | +- scan offset = M // | | +- scan offset = M
// | +- range end = M - B // | +- range end = M - B
// +- range start = M - A // +- range start = M - A
// This method converts a byte range defined by [start_byte_offset, end_byte_offset] to a codepoint range [M - A, M - B] as shown in the diagram above. // This method converts a byte range defined by [start_byte_offset, end_byte_offset] to a code_point range [M - A, M - B] as shown in the diagram above.
// If `reverse' is true, A and B are before M, if not, A and B are after M. // If `reverse' is true, A and B are before M, if not, A and B are after M.
Editor::CodepointRange Editor::byte_offset_range_to_codepoint_offset_range(size_t start_byte_offset, size_t end_byte_offset, size_t scan_codepoint_offset, bool reverse) const Editor::CodepointRange Editor::byte_offset_range_to_code_point_offset_range(size_t start_byte_offset, size_t end_byte_offset, size_t scan_code_point_offset, bool reverse) const
{ {
size_t byte_offset = 0; size_t byte_offset = 0;
size_t codepoint_offset = scan_codepoint_offset + (reverse ? 1 : 0); size_t code_point_offset = scan_code_point_offset + (reverse ? 1 : 0);
CodepointRange range; CodepointRange range;
for (;;) { for (;;) {
if (!reverse) { if (!reverse) {
if (codepoint_offset >= m_buffer.size()) if (code_point_offset >= m_buffer.size())
break; break;
} else { } else {
if (codepoint_offset == 0) if (code_point_offset == 0)
break; break;
} }
@ -182,7 +182,7 @@ Editor::CodepointRange Editor::byte_offset_range_to_codepoint_offset_range(size_
if (byte_offset < end_byte_offset) if (byte_offset < end_byte_offset)
++range.end; ++range.end;
byte_offset += codepoint_length_in_utf8(m_buffer[reverse ? --codepoint_offset : codepoint_offset++]); byte_offset += code_point_length_in_utf8(m_buffer[reverse ? --code_point_offset : code_point_offset++]);
} }
return range; return range;
@ -197,7 +197,7 @@ void Editor::stylize(const Span& span, const Style& style)
auto end = span.end(); auto end = span.end();
if (span.mode() == Span::ByteOriented) { if (span.mode() == Span::ByteOriented) {
auto offsets = byte_offset_range_to_codepoint_offset_range(start, end, 0); auto offsets = byte_offset_range_to_code_point_offset_range(start, end, 0);
start = offsets.start; start = offsets.start;
end = offsets.end; end = offsets.end;
@ -231,7 +231,7 @@ void Editor::suggest(size_t invariant_offset, size_t static_offset, Span::Mode o
if (offset_mode == Span::Mode::ByteOriented) { if (offset_mode == Span::Mode::ByteOriented) {
// FIXME: We're assuming that invariant_offset points to the end of the available data // FIXME: We're assuming that invariant_offset points to the end of the available data
// this is not necessarily true, but is true in most cases. // this is not necessarily true, but is true in most cases.
auto offsets = byte_offset_range_to_codepoint_offset_range(internal_static_offset, internal_invariant_offset + internal_static_offset, m_cursor - 1, true); auto offsets = byte_offset_range_to_code_point_offset_range(internal_static_offset, internal_invariant_offset + internal_static_offset, m_cursor - 1, true);
internal_static_offset = offsets.start; internal_static_offset = offsets.start;
internal_invariant_offset = offsets.end - offsets.start; internal_invariant_offset = offsets.end - offsets.start;
@ -445,7 +445,7 @@ void Editor::handle_read_event()
} }
Utf8View input_view { StringView { m_incomplete_data.data(), valid_bytes } }; Utf8View input_view { StringView { m_incomplete_data.data(), valid_bytes } };
size_t consumed_codepoints = 0; size_t consumed_code_points = 0;
enum Amount { enum Amount {
Character, Character,
@ -552,18 +552,18 @@ void Editor::handle_read_event()
m_refresh_needed = true; m_refresh_needed = true;
}; };
for (auto codepoint : input_view) { for (auto code_point : input_view) {
if (m_finish) if (m_finish)
break; break;
++consumed_codepoints; ++consumed_code_points;
if (codepoint == 0) if (code_point == 0)
continue; continue;
switch (m_state) { switch (m_state) {
case InputState::ExpectBracket: case InputState::ExpectBracket:
if (codepoint == '[') { if (code_point == '[') {
m_state = InputState::ExpectFinal; m_state = InputState::ExpectFinal;
continue; continue;
} else { } else {
@ -571,7 +571,7 @@ void Editor::handle_read_event()
break; break;
} }
case InputState::ExpectFinal: case InputState::ExpectFinal:
switch (codepoint) { switch (code_point) {
case 'O': // mod_ctrl case 'O': // mod_ctrl
ctrl_held = true; ctrl_held = true;
continue; continue;
@ -621,7 +621,7 @@ void Editor::handle_read_event()
ctrl_held = false; ctrl_held = false;
continue; continue;
default: default:
dbgprintf("LibLine: Unhandled final: %02x (%c)\r\n", codepoint, codepoint); dbgprintf("LibLine: Unhandled final: %02x (%c)\r\n", code_point, code_point);
m_state = InputState::Free; m_state = InputState::Free;
ctrl_held = false; ctrl_held = false;
continue; continue;
@ -631,14 +631,14 @@ void Editor::handle_read_event()
m_state = InputState::Free; m_state = InputState::Free;
continue; continue;
case InputState::Free: case InputState::Free:
if (codepoint == 27) { if (code_point == 27) {
m_state = InputState::ExpectBracket; m_state = InputState::ExpectBracket;
continue; continue;
} }
break; break;
} }
auto cb = m_key_callbacks.get(codepoint); auto cb = m_key_callbacks.get(code_point);
if (cb.has_value()) { if (cb.has_value()) {
if (!cb.value()->callback(*this)) { if (!cb.value()->callback(*this)) {
continue; continue;
@ -646,19 +646,19 @@ void Editor::handle_read_event()
} }
// ^N // ^N
if (codepoint == ctrl('N')) { if (code_point == ctrl('N')) {
do_search_forwards(); do_search_forwards();
continue; continue;
} }
// ^P // ^P
if (codepoint == ctrl('P')) { if (code_point == ctrl('P')) {
do_search_backwards(); do_search_backwards();
continue; continue;
} }
m_search_offset = 0; // reset search offset on any key m_search_offset = 0; // reset search offset on any key
if (codepoint == '\t' || reverse_tab) { if (code_point == '\t' || reverse_tab) {
if (!on_tab_complete) if (!on_tab_complete)
continue; continue;
@ -773,7 +773,7 @@ void Editor::handle_read_event()
} }
m_times_tab_pressed = 0; // Safe to say if we get here, the user didn't press TAB m_times_tab_pressed = 0; // Safe to say if we get here, the user didn't press TAB
if (codepoint == m_termios.c_cc[VWERASE]) { if (code_point == m_termios.c_cc[VWERASE]) {
bool has_seen_nonspace = false; bool has_seen_nonspace = false;
while (m_cursor > 0) { while (m_cursor > 0) {
if (isspace(m_buffer[m_cursor - 1])) { if (isspace(m_buffer[m_cursor - 1])) {
@ -786,7 +786,7 @@ void Editor::handle_read_event()
} }
continue; continue;
} }
if (codepoint == m_termios.c_cc[VKILL]) { if (code_point == m_termios.c_cc[VKILL]) {
for (size_t i = 0; i < m_cursor; ++i) for (size_t i = 0; i < m_cursor; ++i)
remove_at_index(0); remove_at_index(0);
m_cursor = 0; m_cursor = 0;
@ -795,7 +795,7 @@ void Editor::handle_read_event()
} }
// Normally ^D. `stty eof \^n` can change it to ^N (or something else), but Serenity doesn't have `stty` yet. // Normally ^D. `stty eof \^n` can change it to ^N (or something else), but Serenity doesn't have `stty` yet.
// Handle it before ctrl shortcuts below and only continue if the buffer is empty, so that the editing shortcuts can take effect else. // Handle it before ctrl shortcuts below and only continue if the buffer is empty, so that the editing shortcuts can take effect else.
if (codepoint == m_termios.c_cc[VEOF] && m_buffer.is_empty()) { if (code_point == m_termios.c_cc[VEOF] && m_buffer.is_empty()) {
printf("<EOF>\n"); printf("<EOF>\n");
if (!m_always_refresh) { if (!m_always_refresh) {
m_input_error = Error::Eof; m_input_error = Error::Eof;
@ -804,37 +804,37 @@ void Editor::handle_read_event()
continue; continue;
} }
// ^A // ^A
if (codepoint == ctrl('A')) { if (code_point == ctrl('A')) {
m_cursor = 0; m_cursor = 0;
continue; continue;
} }
// ^B // ^B
if (codepoint == ctrl('B')) { if (code_point == ctrl('B')) {
do_cursor_left(Character); do_cursor_left(Character);
continue; continue;
} }
// ^D // ^D
if (codepoint == ctrl('D')) { if (code_point == ctrl('D')) {
do_delete(); do_delete();
continue; continue;
} }
// ^E // ^E
if (codepoint == ctrl('E')) { if (code_point == ctrl('E')) {
m_cursor = m_buffer.size(); m_cursor = m_buffer.size();
continue; continue;
} }
// ^F // ^F
if (codepoint == ctrl('F')) { if (code_point == ctrl('F')) {
do_cursor_right(Character); do_cursor_right(Character);
continue; continue;
} }
// ^H: ctrl('H') == '\b' // ^H: ctrl('H') == '\b'
if (codepoint == '\b' || codepoint == m_termios.c_cc[VERASE]) { if (code_point == '\b' || code_point == m_termios.c_cc[VERASE]) {
do_backspace(); do_backspace();
continue; continue;
} }
// ^L // ^L
if (codepoint == ctrl('L')) { if (code_point == ctrl('L')) {
printf("\033[3J\033[H\033[2J"); // Clear screen. printf("\033[3J\033[H\033[2J"); // Clear screen.
VT::move_absolute(1, 1); VT::move_absolute(1, 1);
set_origin(1, 1); set_origin(1, 1);
@ -842,7 +842,7 @@ void Editor::handle_read_event()
continue; continue;
} }
// ^R // ^R
if (codepoint == ctrl('R')) { if (code_point == ctrl('R')) {
if (m_is_searching) { if (m_is_searching) {
// how did we get here? // how did we get here?
ASSERT_NOT_REACHED(); ASSERT_NOT_REACHED();
@ -850,8 +850,8 @@ void Editor::handle_read_event()
m_is_searching = true; m_is_searching = true;
m_search_offset = 0; m_search_offset = 0;
m_pre_search_buffer.clear(); m_pre_search_buffer.clear();
for (auto codepoint : m_buffer) for (auto code_point : m_buffer)
m_pre_search_buffer.append(codepoint); m_pre_search_buffer.append(code_point);
m_pre_search_cursor = m_cursor; m_pre_search_cursor = m_cursor;
// Disable our own notifier so as to avoid interfering with the search editor. // Disable our own notifier so as to avoid interfering with the search editor.
@ -958,7 +958,7 @@ void Editor::handle_read_event()
continue; continue;
} }
// ^T // ^T
if (codepoint == ctrl('T')) { if (code_point == ctrl('T')) {
if (m_cursor > 0 && m_buffer.size() >= 2) { if (m_cursor > 0 && m_buffer.size() >= 2) {
if (m_cursor < m_buffer.size()) if (m_cursor < m_buffer.size())
++m_cursor; ++m_cursor;
@ -968,18 +968,18 @@ void Editor::handle_read_event()
} }
continue; continue;
} }
if (codepoint == '\n') { if (code_point == '\n') {
finish(); finish();
continue; continue;
} }
insert(codepoint); insert(code_point);
} }
if (consumed_codepoints == m_incomplete_data.size()) { if (consumed_code_points == m_incomplete_data.size()) {
m_incomplete_data.clear(); m_incomplete_data.clear();
} else { } else {
for (size_t i = 0; i < consumed_codepoints; ++i) for (size_t i = 0; i < consumed_code_points; ++i)
m_incomplete_data.take_first(); m_incomplete_data.take_first();
} }
} }
@ -1425,8 +1425,8 @@ StringMetrics Editor::actual_rendered_string_metrics(const Utf32View& view) cons
VTState state { Free }; VTState state { Free };
for (size_t i = 0; i < view.length(); ++i) { for (size_t i = 0; i < view.length(); ++i) {
auto c = view.codepoints()[i]; auto c = view.code_points()[i];
auto next_c = i + 1 < view.length() ? view.codepoints()[i + 1] : 0; auto next_c = i + 1 < view.length() ? view.code_points()[i + 1] : 0;
state = actual_rendered_string_length_step(metrics, length, c, next_c, state); state = actual_rendered_string_length_step(metrics, length, c, next_c, state);
} }

2
Libraries/LibLine/Editor.h
View file

@ -310,7 +310,7 @@ private:
size_t start { 0 }; size_t start { 0 };
size_t end { 0 }; size_t end { 0 };
}; };
CodepointRange byte_offset_range_to_codepoint_offset_range(size_t byte_start, size_t byte_end, size_t codepoint_scan_offset, bool reverse = false) const; CodepointRange byte_offset_range_to_code_point_offset_range(size_t byte_start, size_t byte_end, size_t code_point_scan_offset, bool reverse = false) const;
void get_terminal_size(); void get_terminal_size();

6
Libraries/LibLine/SuggestionManager.cpp
View file

@ -59,16 +59,16 @@ void SuggestionManager::set_suggestions(Vector<CompletionSuggestion>&& suggestio
if (m_suggestions.size() == 1) { if (m_suggestions.size() == 1) {
m_largest_common_suggestion_prefix_length = m_suggestions[0].text_view.length(); m_largest_common_suggestion_prefix_length = m_suggestions[0].text_view.length();
} else if (m_suggestions.size()) { } else if (m_suggestions.size()) {
u32 last_valid_suggestion_codepoint; u32 last_valid_suggestion_code_point;
for (;; ++common_suggestion_prefix) { for (;; ++common_suggestion_prefix) {
if (m_suggestions[0].text_view.length() <= common_suggestion_prefix) if (m_suggestions[0].text_view.length() <= common_suggestion_prefix)
goto no_more_commons; goto no_more_commons;
last_valid_suggestion_codepoint = m_suggestions[0].text_view.codepoints()[common_suggestion_prefix]; last_valid_suggestion_code_point = m_suggestions[0].text_view.code_points()[common_suggestion_prefix];
for (auto& suggestion : m_suggestions) { for (auto& suggestion : m_suggestions) {
if (suggestion.text_view.length() <= common_suggestion_prefix || suggestion.text_view.codepoints()[common_suggestion_prefix] != last_valid_suggestion_codepoint) { if (suggestion.text_view.length() <= common_suggestion_prefix || suggestion.text_view.code_points()[common_suggestion_prefix] != last_valid_suggestion_code_point) {
goto no_more_commons; goto no_more_commons;
} }
} }

4
Libraries/LibTextCodec/Decoder.cpp
View file

@ -65,8 +65,8 @@ String Latin1Decoder::to_utf8(const StringView& input)
StringBuilder builder(input.length()); StringBuilder builder(input.length());
for (size_t i = 0; i < input.length(); ++i) { for (size_t i = 0; i < input.length(); ++i) {
u8 ch = input[i]; u8 ch = input[i];
// Latin1 is the same as the first 256 Unicode codepoints, so no mapping is needed, just utf-8 encoding. // Latin1 is the same as the first 256 Unicode code_points, so no mapping is needed, just utf-8 encoding.
builder.append_codepoint(ch); builder.append_code_point(ch);
} }
return builder.to_string(); return builder.to_string();
} }

36
Libraries/LibVT/Line.cpp
View file

@ -37,25 +37,25 @@ Line::Line(u16 length)
Line::~Line() Line::~Line()
{ {
if (m_utf32) if (m_utf32)
delete[] m_codepoints.as_u32; delete[] m_code_points.as_u32;
else else
delete[] m_codepoints.as_u8; delete[] m_code_points.as_u8;
delete[] m_attributes; delete[] m_attributes;
} }
template<typename CodepointType> template<typename CodepointType>
static CodepointType* create_new_codepoint_array(size_t new_length, const CodepointType* old_codepoints, size_t old_length) static CodepointType* create_new_code_point_array(size_t new_length, const CodepointType* old_code_points, size_t old_length)
{ {
auto* new_codepoints = new CodepointType[new_length]; auto* new_code_points = new CodepointType[new_length];
for (size_t i = 0; i < new_length; ++i) for (size_t i = 0; i < new_length; ++i)
new_codepoints[i] = ' '; new_code_points[i] = ' ';
if (old_codepoints) { if (old_code_points) {
for (size_t i = 0; i < min(old_length, new_length); ++i) { for (size_t i = 0; i < min(old_length, new_length); ++i) {
new_codepoints[i] = old_codepoints[i]; new_code_points[i] = old_code_points[i];
} }
} }
delete[] old_codepoints; delete[] old_code_points;
return new_codepoints; return new_code_points;
} }
void Line::set_length(u16 new_length) void Line::set_length(u16 new_length)
@ -64,9 +64,9 @@ void Line::set_length(u16 new_length)
return; return;
if (m_utf32) if (m_utf32)
m_codepoints.as_u32 = create_new_codepoint_array<u32>(new_length, m_codepoints.as_u32, m_length); m_code_points.as_u32 = create_new_code_point_array<u32>(new_length, m_code_points.as_u32, m_length);
else else
m_codepoints.as_u8 = create_new_codepoint_array<u8>(new_length, m_codepoints.as_u8, m_length); m_code_points.as_u8 = create_new_code_point_array<u8>(new_length, m_code_points.as_u8, m_length);
auto* new_attributes = new Attribute[new_length]; auto* new_attributes = new Attribute[new_length];
if (m_attributes) { if (m_attributes) {
@ -82,15 +82,15 @@ void Line::clear(Attribute attribute)
{ {
if (m_dirty) { if (m_dirty) {
for (u16 i = 0; i < m_length; ++i) { for (u16 i = 0; i < m_length; ++i) {
set_codepoint(i, ' '); set_code_point(i, ' ');
m_attributes[i] = attribute; m_attributes[i] = attribute;
} }
return; return;
} }
for (unsigned i = 0; i < m_length; ++i) { for (unsigned i = 0; i < m_length; ++i) {
if (codepoint(i) != ' ') if (code_point(i) != ' ')
m_dirty = true; m_dirty = true;
set_codepoint(i, ' '); set_code_point(i, ' ');
} }
for (unsigned i = 0; i < m_length; ++i) { for (unsigned i = 0; i < m_length; ++i) {
if (m_attributes[i] != attribute) if (m_attributes[i] != attribute)
@ -115,12 +115,12 @@ bool Line::has_only_one_background_color() const
void Line::convert_to_utf32() void Line::convert_to_utf32()
{ {
ASSERT(!m_utf32); ASSERT(!m_utf32);
auto* new_codepoints = new u32[m_length]; auto* new_code_points = new u32[m_length];
for (size_t i = 0; i < m_length; ++i) { for (size_t i = 0; i < m_length; ++i) {
new_codepoints[i] = m_codepoints.as_u8[i]; new_code_points[i] = m_code_points.as_u8[i];
} }
delete m_codepoints.as_u8; delete m_code_points.as_u8;
m_codepoints.as_u32 = new_codepoints; m_code_points.as_u32 = new_code_points;
m_utf32 = true; m_utf32 = true;
} }

16
Libraries/LibVT/Line.h
View file

@ -90,22 +90,22 @@ public:
u16 length() const { return m_length; } u16 length() const { return m_length; }
u32 codepoint(size_t index) const u32 code_point(size_t index) const
{ {
if (m_utf32) if (m_utf32)
return m_codepoints.as_u32[index]; return m_code_points.as_u32[index];
return m_codepoints.as_u8[index]; return m_code_points.as_u8[index];
} }
void set_codepoint(size_t index, u32 codepoint) void set_code_point(size_t index, u32 code_point)
{ {
if (!m_utf32 && codepoint & 0xffffff80u) if (!m_utf32 && code_point & 0xffffff80u)
convert_to_utf32(); convert_to_utf32();
if (m_utf32) if (m_utf32)
m_codepoints.as_u32[index] = codepoint; m_code_points.as_u32[index] = code_point;
else else
m_codepoints.as_u8[index] = codepoint; m_code_points.as_u8[index] = code_point;
} }
bool is_dirty() const { return m_dirty; } bool is_dirty() const { return m_dirty; }
@ -122,7 +122,7 @@ private:
union { union {
u8* as_u8; u8* as_u8;
u32* as_u32; u32* as_u32;
} m_codepoints { nullptr }; } m_code_points { nullptr };
Attribute* m_attributes { nullptr }; Attribute* m_attributes { nullptr };
bool m_dirty { false }; bool m_dirty { false };
bool m_utf32 { false }; bool m_utf32 { false };

38
Libraries/LibVT/Terminal.cpp
View file

@ -361,7 +361,7 @@ void Terminal::escape$b(const ParamVector& params)
return; return;
for (unsigned i = 0; i < params[0]; ++i) for (unsigned i = 0; i < params[0]; ++i)
put_character_at(m_cursor_row, m_cursor_column++, m_last_codepoint); put_character_at(m_cursor_row, m_cursor_column++, m_last_code_point);
} }
void Terminal::escape$d(const ParamVector& params) void Terminal::escape$d(const ParamVector& params)
@ -537,11 +537,11 @@ void Terminal::escape$P(const ParamVector& params)
// Move n characters of line to the left // Move n characters of line to the left
for (int i = m_cursor_column; i < line.length() - num; i++) for (int i = m_cursor_column; i < line.length() - num; i++)
line.set_codepoint(i, line.codepoint(i + num)); line.set_code_point(i, line.code_point(i + num));
// Fill remainder of line with blanks // Fill remainder of line with blanks
for (int i = line.length() - num; i < line.length(); i++) for (int i = line.length() - num; i < line.length(); i++)
line.set_codepoint(i, ' '); line.set_code_point(i, ' ');
line.set_dirty(true); line.set_dirty(true);
} }
@ -768,17 +768,17 @@ void Terminal::set_cursor(unsigned a_row, unsigned a_column)
invalidate_cursor(); invalidate_cursor();
} }
void Terminal::put_character_at(unsigned row, unsigned column, u32 codepoint) void Terminal::put_character_at(unsigned row, unsigned column, u32 code_point)
{ {
ASSERT(row < rows()); ASSERT(row < rows());
ASSERT(column < columns()); ASSERT(column < columns());
auto& line = m_lines[row]; auto& line = m_lines[row];
line.set_codepoint(column, codepoint); line.set_code_point(column, code_point);
line.attributes()[column] = m_current_attribute; line.attributes()[column] = m_current_attribute;
line.attributes()[column].flags |= Attribute::Touched; line.attributes()[column].flags |= Attribute::Touched;
line.set_dirty(true); line.set_dirty(true);
m_last_codepoint = codepoint; m_last_code_point = code_point;
} }
void Terminal::NEL() void Terminal::NEL()
@ -820,14 +820,14 @@ void Terminal::on_input(u8 ch)
auto fail_utf8_parse = [this] { auto fail_utf8_parse = [this] {
m_parser_state = Normal; m_parser_state = Normal;
on_codepoint('%'); on_code_point('%');
}; };
auto advance_utf8_parse = [this, ch] { auto advance_utf8_parse = [this, ch] {
m_parser_codepoint <<= 6; m_parser_code_point <<= 6;
m_parser_codepoint |= ch & 0x3f; m_parser_code_point |= ch & 0x3f;
if (m_parser_state == UTF8Needs1Byte) { if (m_parser_state == UTF8Needs1Byte) {
on_codepoint(m_parser_codepoint); on_code_point(m_parser_code_point);
m_parser_state = Normal; m_parser_state = Normal;
} else { } else {
m_parser_state = (ParserState)(m_parser_state + 1); m_parser_state = (ParserState)(m_parser_state + 1);
@ -928,17 +928,17 @@ void Terminal::on_input(u8 ch)
break; break;
if ((ch & 0xe0) == 0xc0) { if ((ch & 0xe0) == 0xc0) {
m_parser_state = UTF8Needs1Byte; m_parser_state = UTF8Needs1Byte;
m_parser_codepoint = ch & 0x1f; m_parser_code_point = ch & 0x1f;
return; return;
} }
if ((ch & 0xf0) == 0xe0) { if ((ch & 0xf0) == 0xe0) {
m_parser_state = UTF8Needs2Bytes; m_parser_state = UTF8Needs2Bytes;
m_parser_codepoint = ch & 0x0f; m_parser_code_point = ch & 0x0f;
return; return;
} }
if ((ch & 0xf8) == 0xf0) { if ((ch & 0xf8) == 0xf0) {
m_parser_state = UTF8Needs3Bytes; m_parser_state = UTF8Needs3Bytes;
m_parser_codepoint = ch & 0x07; m_parser_code_point = ch & 0x07;
return; return;
} }
fail_utf8_parse(); fail_utf8_parse();
@ -978,26 +978,26 @@ void Terminal::on_input(u8 ch)
return; return;
} }
on_codepoint(ch); on_code_point(ch);
} }
void Terminal::on_codepoint(u32 codepoint) void Terminal::on_code_point(u32 code_point)
{ {
auto new_column = m_cursor_column + 1; auto new_column = m_cursor_column + 1;
if (new_column < columns()) { if (new_column < columns()) {
put_character_at(m_cursor_row, m_cursor_column, codepoint); put_character_at(m_cursor_row, m_cursor_column, code_point);
set_cursor(m_cursor_row, new_column); set_cursor(m_cursor_row, new_column);
return; return;
} }
if (m_stomp) { if (m_stomp) {
m_stomp = false; m_stomp = false;
newline(); newline();
put_character_at(m_cursor_row, m_cursor_column, codepoint); put_character_at(m_cursor_row, m_cursor_column, code_point);
set_cursor(m_cursor_row, 1); set_cursor(m_cursor_row, 1);
} else { } else {
// Curious: We wait once on the right-hand side // Curious: We wait once on the right-hand side
m_stomp = true; m_stomp = true;
put_character_at(m_cursor_row, m_cursor_column, codepoint); put_character_at(m_cursor_row, m_cursor_column, code_point);
} }
} }
@ -1078,7 +1078,7 @@ void Terminal::handle_key_press(KeyCode key, u32 code_point, u8 flags)
emit_string("\033"); emit_string("\033");
StringBuilder sb; StringBuilder sb;
sb.append_codepoint(code_point); sb.append_code_point(code_point);
emit_string(sb.to_string()); emit_string(sb.to_string());
} }

6
Libraries/LibVT/Terminal.h
View file

@ -106,7 +106,7 @@ public:
private: private:
typedef Vector<unsigned, 4> ParamVector; typedef Vector<unsigned, 4> ParamVector;
void on_codepoint(u32); void on_code_point(u32);
void scroll_up(); void scroll_up();
void scroll_down(); void scroll_down();
@ -193,13 +193,13 @@ private:
}; };
ParserState m_parser_state { Normal }; ParserState m_parser_state { Normal };
u32 m_parser_codepoint { 0 }; u32 m_parser_code_point { 0 };
Vector<u8> m_parameters; Vector<u8> m_parameters;
Vector<u8> m_intermediates; Vector<u8> m_intermediates;
Vector<u8> m_xterm_parameters; Vector<u8> m_xterm_parameters;
Vector<bool> m_horizontal_tabs; Vector<bool> m_horizontal_tabs;
u8 m_final { 0 }; u8 m_final { 0 };
u32 m_last_codepoint { 0 }; u32 m_last_code_point { 0 };
}; };
} }

18
Libraries/LibVT/TerminalWidget.cpp
View file

@ -294,7 +294,7 @@ void TerminalWidget::paint_event(GUI::PaintEvent& event)
painter.clear_rect(row_rect, color_from_rgb(line.attributes()[0].background_color).with_alpha(m_opacity)); painter.clear_rect(row_rect, color_from_rgb(line.attributes()[0].background_color).with_alpha(m_opacity));
for (size_t column = 0; column < line.length(); ++column) { for (size_t column = 0; column < line.length(); ++column) {
u32 codepoint = line.codepoint(column); u32 code_point = line.code_point(column);
bool should_reverse_fill_for_cursor_or_selection = m_cursor_blink_state bool should_reverse_fill_for_cursor_or_selection = m_cursor_blink_state
&& m_has_logical_focus && m_has_logical_focus
&& visual_row == row_with_cursor && visual_row == row_with_cursor
@ -342,12 +342,12 @@ void TerminalWidget::paint_event(GUI::PaintEvent& event)
} }
} }
if (codepoint == ' ') if (code_point == ' ')
continue; continue;
painter.draw_glyph_or_emoji( painter.draw_glyph_or_emoji(
character_rect.location(), character_rect.location(),
codepoint, code_point,
attribute.flags & VT::Attribute::Bold ? bold_font() : font(), attribute.flags & VT::Attribute::Bold ? bold_font() : font(),
text_color); text_color);
} }
@ -524,16 +524,16 @@ void TerminalWidget::doubleclick_event(GUI::MouseEvent& event)
auto position = buffer_position_at(event.position()); auto position = buffer_position_at(event.position());
auto& line = m_terminal.line(position.row()); auto& line = m_terminal.line(position.row());
bool want_whitespace = line.codepoint(position.column()) == ' '; bool want_whitespace = line.code_point(position.column()) == ' ';
int start_column = 0; int start_column = 0;
int end_column = 0; int end_column = 0;
for (int column = position.column(); column >= 0 && (line.codepoint(column) == ' ') == want_whitespace; --column) { for (int column = position.column(); column >= 0 && (line.code_point(column) == ' ') == want_whitespace; --column) {
start_column = column; start_column = column;
} }
for (int column = position.column(); column < m_terminal.columns() && (line.codepoint(column) == ' ') == want_whitespace; ++column) { for (int column = position.column(); column < m_terminal.columns() && (line.code_point(column) == ' ') == want_whitespace; ++column) {
end_column = column; end_column = column;
} }
@ -715,10 +715,10 @@ String TerminalWidget::selected_text() const
} }
// FIXME: This is a bit hackish. // FIXME: This is a bit hackish.
if (line.is_utf32()) { if (line.is_utf32()) {
u32 codepoint = line.codepoint(column); u32 code_point = line.code_point(column);
builder.append(Utf32View(&codepoint, 1)); builder.append(Utf32View(&code_point, 1));
} else { } else {
builder.append(line.codepoint(column)); builder.append(line.code_point(column));
} }
if (column == line.length() - 1 || (m_rectangle_selection && column == last_column)) { if (column == line.length() - 1 || (m_rectangle_selection && column == last_column)) {
builder.append('\n'); builder.append('\n');

6
Libraries/LibWeb/Bindings/WindowObject.cpp
View file

@ -272,10 +272,10 @@ JS_DEFINE_NATIVE_FUNCTION(WindowObject::btoa)
Vector<u8> byte_string; Vector<u8> byte_string;
byte_string.ensure_capacity(string.length()); byte_string.ensure_capacity(string.length());
for (u32 codepoint : Utf8View(string)) { for (u32 code_point : Utf8View(string)) {
if (codepoint > 0xff) if (code_point > 0xff)
return interpreter.throw_exception<JS::InvalidCharacterError>(JS::ErrorType::NotAByteString, "btoa"); return interpreter.throw_exception<JS::InvalidCharacterError>(JS::ErrorType::NotAByteString, "btoa");
byte_string.append(codepoint); byte_string.append(code_point);
} }
auto encoded = encode_base64(byte_string.span()); auto encoded = encode_base64(byte_string.span());

28
Libraries/LibWeb/HTML/Parser/Entities.cpp
View file

@ -31,12 +31,12 @@
namespace Web { namespace Web {
namespace HTML { namespace HTML {
Optional<EntityMatch> codepoints_from_entity(const StringView& entity) Optional<EntityMatch> code_points_from_entity(const StringView& entity)
{ {
constexpr struct { constexpr struct {
StringView entity; StringView entity;
u32 codepoint; u32 code_point;
} single_codepoint_entities[] = { } single_code_point_entities[] = {
{ "AElig;", 0x000C6 }, { "AElig;", 0x000C6 },
{ "AElig", 0x000C6 }, { "AElig", 0x000C6 },
{ "AMP;", 0x00026 }, { "AMP;", 0x00026 },
@ -2179,9 +2179,9 @@ Optional<EntityMatch> codepoints_from_entity(const StringView& entity)
constexpr struct { constexpr struct {
StringView entity; StringView entity;
u32 codepoint1; u32 code_point1;
u32 codepoint2; u32 code_point2;
} double_codepoint_entities[] = { } double_code_point_entities[] = {
{ "NotEqualTilde;", 0x02242, 0x00338 }, { "NotEqualTilde;", 0x02242, 0x00338 },
{ "NotGreaterFullEqual;", 0x02267, 0x00338 }, { "NotGreaterFullEqual;", 0x02267, 0x00338 },
{ "NotGreaterGreater;", 0x0226B, 0x00338 }, { "NotGreaterGreater;", 0x0226B, 0x00338 },
@ -2279,17 +2279,17 @@ Optional<EntityMatch> codepoints_from_entity(const StringView& entity)
EntityMatch match; EntityMatch match;
for (auto& single_codepoint_entity : single_codepoint_entities) { for (auto& single_code_point_entity : single_code_point_entities) {
if (entity.starts_with(single_codepoint_entity.entity)) { if (entity.starts_with(single_code_point_entity.entity)) {
if (match.entity.is_null() || single_codepoint_entity.entity.length() > match.entity.length()) if (match.entity.is_null() || single_code_point_entity.entity.length() > match.entity.length())
match = { { single_codepoint_entity.codepoint }, single_codepoint_entity.entity }; match = { { single_code_point_entity.code_point }, single_code_point_entity.entity };
} }
} }
for (auto& double_codepoint_entity : double_codepoint_entities) { for (auto& double_code_point_entity : double_code_point_entities) {
if (entity.starts_with(double_codepoint_entity.entity)) { if (entity.starts_with(double_code_point_entity.entity)) {
if (match.entity.is_null() || double_codepoint_entity.entity.length() > match.entity.length()) if (match.entity.is_null() || double_code_point_entity.entity.length() > match.entity.length())
match = EntityMatch { { double_codepoint_entity.codepoint1, double_codepoint_entity.codepoint2 }, StringView(double_codepoint_entity.entity) }; match = EntityMatch { { double_code_point_entity.code_point1, double_code_point_entity.code_point2 }, StringView(double_code_point_entity.entity) };
} }
} }

4
Libraries/LibWeb/HTML/Parser/Entities.h
View file

@ -33,11 +33,11 @@ namespace Web {
namespace HTML { namespace HTML {
struct EntityMatch { struct EntityMatch {
Vector<u32, 2> codepoints; Vector<u32, 2> code_points;
StringView entity; StringView entity;
}; };
Optional<EntityMatch> codepoints_from_entity(const StringView&); Optional<EntityMatch> code_points_from_entity(const StringView&);
} }
} }

30
Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp
View file

@ -472,7 +472,7 @@ void HTMLDocumentParser::insert_comment(HTMLToken& token)
void HTMLDocumentParser::handle_in_head(HTMLToken& token) void HTMLDocumentParser::handle_in_head(HTMLToken& token)
{ {
if (token.is_parser_whitespace()) { if (token.is_parser_whitespace()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
@ -671,7 +671,7 @@ void HTMLDocumentParser::insert_character(u32 data)
void HTMLDocumentParser::handle_after_head(HTMLToken& token) void HTMLDocumentParser::handle_after_head(HTMLToken& token)
{ {
if (token.is_character() && token.is_parser_whitespace()) { if (token.is_character() && token.is_parser_whitespace()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
@ -1004,17 +1004,17 @@ bool HTMLDocumentParser::is_special_tag(const FlyString& tag_name)
void HTMLDocumentParser::handle_in_body(HTMLToken& token) void HTMLDocumentParser::handle_in_body(HTMLToken& token)
{ {
if (token.is_character()) { if (token.is_character()) {
if (token.codepoint() == 0) { if (token.code_point() == 0) {
PARSE_ERROR(); PARSE_ERROR();
return; return;
} }
if (token.is_parser_whitespace()) { if (token.is_parser_whitespace()) {
reconstruct_the_active_formatting_elements(); reconstruct_the_active_formatting_elements();
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
reconstruct_the_active_formatting_elements(); reconstruct_the_active_formatting_elements();
insert_character(token.codepoint()); insert_character(token.code_point());
m_frameset_ok = false; m_frameset_ok = false;
return; return;
} }
@ -1162,7 +1162,7 @@ void HTMLDocumentParser::handle_in_body(HTMLToken& token)
// then ignore that token and move on to the next one. // then ignore that token and move on to the next one.
// (Newlines at the start of pre blocks are ignored as an authoring convenience.) // (Newlines at the start of pre blocks are ignored as an authoring convenience.)
auto next_token = m_tokenizer.next_token(); auto next_token = m_tokenizer.next_token();
if (next_token.has_value() && next_token.value().is_character() && next_token.value().codepoint() == '\n') { if (next_token.has_value() && next_token.value().is_character() && next_token.value().code_point() == '\n') {
// Ignore it. // Ignore it.
} else { } else {
process_using_the_rules_for(m_insertion_mode, next_token.value()); process_using_the_rules_for(m_insertion_mode, next_token.value());
@ -1503,7 +1503,7 @@ void HTMLDocumentParser::handle_in_body(HTMLToken& token)
m_frameset_ok = false; m_frameset_ok = false;
m_insertion_mode = InsertionMode::Text; m_insertion_mode = InsertionMode::Text;
if (next_token.has_value() && next_token.value().is_character() && next_token.value().codepoint() == '\n') { if (next_token.has_value() && next_token.value().is_character() && next_token.value().code_point() == '\n') {
// Ignore it. // Ignore it.
} else { } else {
process_using_the_rules_for(m_insertion_mode, next_token.value()); process_using_the_rules_for(m_insertion_mode, next_token.value());
@ -1750,7 +1750,7 @@ void HTMLDocumentParser::decrement_script_nesting_level()
void HTMLDocumentParser::handle_text(HTMLToken& token) void HTMLDocumentParser::handle_text(HTMLToken& token)
{ {
if (token.is_character()) { if (token.is_character()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
if (token.is_end_of_file()) { if (token.is_end_of_file()) {
@ -1979,7 +1979,7 @@ void HTMLDocumentParser::handle_in_cell(HTMLToken& token)
void HTMLDocumentParser::handle_in_table_text(HTMLToken& token) void HTMLDocumentParser::handle_in_table_text(HTMLToken& token)
{ {
if (token.is_character()) { if (token.is_character()) {
if (token.codepoint() == 0) { if (token.code_point() == 0) {
PARSE_ERROR(); PARSE_ERROR();
return; return;
} }
@ -2000,7 +2000,7 @@ void HTMLDocumentParser::handle_in_table_text(HTMLToken& token)
} }
for (auto& pending_token : m_pending_table_character_tokens) { for (auto& pending_token : m_pending_table_character_tokens) {
insert_character(pending_token.codepoint()); insert_character(pending_token.code_point());
} }
m_insertion_mode = m_original_insertion_mode; m_insertion_mode = m_original_insertion_mode;
@ -2210,11 +2210,11 @@ void HTMLDocumentParser::handle_in_select_in_table(HTMLToken& token)
void HTMLDocumentParser::handle_in_select(HTMLToken& token) void HTMLDocumentParser::handle_in_select(HTMLToken& token)
{ {
if (token.is_character()) { if (token.is_character()) {
if (token.codepoint() == 0) { if (token.code_point() == 0) {
PARSE_ERROR(); PARSE_ERROR();
return; return;
} }
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
@ -2384,7 +2384,7 @@ void HTMLDocumentParser::handle_in_caption(HTMLToken& token)
void HTMLDocumentParser::handle_in_column_group(HTMLToken& token) void HTMLDocumentParser::handle_in_column_group(HTMLToken& token)
{ {
if (token.is_character() && token.is_parser_whitespace()) { if (token.is_character() && token.is_parser_whitespace()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
@ -2527,7 +2527,7 @@ void HTMLDocumentParser::handle_in_template(HTMLToken& token)
void HTMLDocumentParser::handle_in_frameset(HTMLToken& token) void HTMLDocumentParser::handle_in_frameset(HTMLToken& token)
{ {
if (token.is_character() && token.is_parser_whitespace()) { if (token.is_character() && token.is_parser_whitespace()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }
@ -2587,7 +2587,7 @@ void HTMLDocumentParser::handle_in_frameset(HTMLToken& token)
void HTMLDocumentParser::handle_after_frameset(HTMLToken& token) void HTMLDocumentParser::handle_after_frameset(HTMLToken& token)
{ {
if (token.is_character() && token.is_parser_whitespace()) { if (token.is_character() && token.is_parser_whitespace()) {
insert_character(token.codepoint()); insert_character(token.code_point());
return; return;
} }

10
Libraries/LibWeb/HTML/Parser/HTMLToken.h
View file

@ -50,11 +50,11 @@ public:
EndOfFile, EndOfFile,
}; };
static HTMLToken make_character(u32 codepoint) static HTMLToken make_character(u32 code_point)
{ {
HTMLToken token; HTMLToken token;
token.m_type = Type::Character; token.m_type = Type::Character;
token.m_comment_or_character.data.append(codepoint); token.m_comment_or_character.data.append(code_point);
return token; return token;
} }
@ -73,11 +73,11 @@ public:
bool is_character() const { return m_type == Type::Character; } bool is_character() const { return m_type == Type::Character; }
bool is_end_of_file() const { return m_type == Type::EndOfFile; } bool is_end_of_file() const { return m_type == Type::EndOfFile; }
u32 codepoint() const u32 code_point() const
{ {
ASSERT(is_character()); ASSERT(is_character());
Utf8View view(m_comment_or_character.data.string_view()); Utf8View view(m_comment_or_character.data.string_view());
ASSERT(view.length_in_codepoints() == 1); ASSERT(view.length_in_code_points() == 1);
return *view.begin(); return *view.begin();
} }
@ -86,7 +86,7 @@ public:
// NOTE: The parser considers '\r' to be whitespace, while the tokenizer does not. // NOTE: The parser considers '\r' to be whitespace, while the tokenizer does not.
if (!is_character()) if (!is_character())
return false; return false;
switch (codepoint()) { switch (code_point()) {
case '\t': case '\t':
case '\n': case '\n':
case '\f': case '\f':

204
Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View file

@ -46,7 +46,7 @@ namespace Web::HTML {
#endif #endif
#define CONSUME_NEXT_INPUT_CHARACTER \ #define CONSUME_NEXT_INPUT_CHARACTER \
current_input_character = next_codepoint(); current_input_character = next_code_point();
#define SWITCH_TO(new_state) \ #define SWITCH_TO(new_state) \
do { \ do { \
@ -86,9 +86,9 @@ namespace Web::HTML {
return m_queued_tokens.dequeue(); \ return m_queued_tokens.dequeue(); \
} while (0) } while (0)
#define EMIT_CHARACTER_AND_RECONSUME_IN(codepoint, new_state) \ #define EMIT_CHARACTER_AND_RECONSUME_IN(code_point, new_state) \
do { \ do { \
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); \ m_queued_tokens.enqueue(HTMLToken::make_character(code_point)); \
will_reconsume_in(State::new_state); \ will_reconsume_in(State::new_state); \
m_state = State::new_state; \ m_state = State::new_state; \
goto new_state; \ goto new_state; \
@ -96,12 +96,12 @@ namespace Web::HTML {
#define FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE \ #define FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE \
do { \ do { \
for (auto codepoint : m_temporary_buffer) { \ for (auto code_point : m_temporary_buffer) { \
if (consumed_as_part_of_an_attribute()) { \ if (consumed_as_part_of_an_attribute()) { \
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(codepoint); \ m_current_token.m_tag.attributes.last().value_builder.append_code_point(code_point); \
} else { \ } else { \
create_new_token(HTMLToken::Type::Character); \ create_new_token(HTMLToken::Type::Character); \
m_current_token.m_comment_or_character.data.append_codepoint(codepoint); \ m_current_token.m_comment_or_character.data.append_code_point(code_point); \
m_queued_tokens.enqueue(m_current_token); \ m_queued_tokens.enqueue(m_current_token); \
} \ } \
} \ } \
@ -112,8 +112,8 @@ namespace Web::HTML {
m_utf8_iterator = m_prev_utf8_iterator; \ m_utf8_iterator = m_prev_utf8_iterator; \
} while (0) } while (0)
#define ON(codepoint) \ #define ON(code_point) \
if (current_input_character.has_value() && current_input_character.value() == codepoint) if (current_input_character.has_value() && current_input_character.value() == code_point)
#define ON_EOF \ #define ON_EOF \
if (!current_input_character.has_value()) if (!current_input_character.has_value())
@ -159,10 +159,10 @@ namespace Web::HTML {
return m_queued_tokens.dequeue(); \ return m_queued_tokens.dequeue(); \
} while (0) } while (0)
#define EMIT_CHARACTER(codepoint) \ #define EMIT_CHARACTER(code_point) \
do { \ do { \
create_new_token(HTMLToken::Type::Character); \ create_new_token(HTMLToken::Type::Character); \
m_current_token.m_comment_or_character.data.append_codepoint(codepoint); \ m_current_token.m_comment_or_character.data.append_code_point(code_point); \
m_queued_tokens.enqueue(m_current_token); \ m_queued_tokens.enqueue(m_current_token); \
return m_queued_tokens.dequeue(); \ return m_queued_tokens.dequeue(); \
} while (0) } while (0)
@ -170,11 +170,11 @@ namespace Web::HTML {
#define EMIT_CURRENT_CHARACTER \ #define EMIT_CURRENT_CHARACTER \
EMIT_CHARACTER(current_input_character.value()); EMIT_CHARACTER(current_input_character.value());
#define SWITCH_TO_AND_EMIT_CHARACTER(codepoint, new_state) \ #define SWITCH_TO_AND_EMIT_CHARACTER(code_point, new_state) \
do { \ do { \
will_switch_to(State::new_state); \ will_switch_to(State::new_state); \
m_state = State::new_state; \ m_state = State::new_state; \
EMIT_CHARACTER(codepoint); \ EMIT_CHARACTER(code_point); \
} while (0) } while (0)
#define SWITCH_TO_AND_EMIT_CURRENT_CHARACTER(new_state) \ #define SWITCH_TO_AND_EMIT_CURRENT_CHARACTER(new_state) \
@ -193,39 +193,39 @@ namespace Web::HTML {
} \ } \
} }
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_noncharacter(u32 codepoint) static inline bool is_noncharacter(u32 code_point)
{ {
return codepoint >= 0xfdd0 && (codepoint <= 0xfdef || (codepoint & 0xfffe) == 0xfffe) && codepoint <= 0x10ffff; return code_point >= 0xfdd0 && (code_point <= 0xfdef || (code_point & 0xfffe) == 0xfffe) && code_point <= 0x10ffff;
} }
static inline bool is_c0_control(u32 codepoint) static inline bool is_c0_control(u32 code_point)
{ {
return codepoint <= 0x1f; return code_point <= 0x1f;
} }
static inline bool is_control(u32 codepoint) static inline bool is_control(u32 code_point)
{ {
return is_c0_control(codepoint) || (codepoint >= 0x7f && codepoint <= 0x9f); return is_c0_control(code_point) || (code_point >= 0x7f && code_point <= 0x9f);
} }
Optional<u32> HTMLTokenizer::next_codepoint() Optional<u32> HTMLTokenizer::next_code_point()
{ {
if (m_utf8_iterator == m_utf8_view.end()) if (m_utf8_iterator == m_utf8_view.end())
return {}; return {};
m_prev_utf8_iterator = m_utf8_iterator; m_prev_utf8_iterator = m_utf8_iterator;
++m_utf8_iterator; ++m_utf8_iterator;
#ifdef TOKENIZER_TRACE #ifdef TOKENIZER_TRACE
dbg() << "(Tokenizer) Next codepoint: " << (char)*m_prev_utf8_iterator; dbg() << "(Tokenizer) Next code_point: " << (char)*m_prev_utf8_iterator;
#endif #endif
return *m_prev_utf8_iterator; return *m_prev_utf8_iterator;
} }
Optional<u32> HTMLTokenizer::peek_codepoint(size_t offset) const Optional<u32> HTMLTokenizer::peek_code_point(size_t offset) const
{ {
auto it = m_utf8_iterator; auto it = m_utf8_iterator;
for (size_t i = 0; i < offset && it != m_utf8_view.end(); ++i) for (size_t i = 0; i < offset && it != m_utf8_view.end(); ++i)
@ -242,7 +242,7 @@ _StartOfFunction:
return m_queued_tokens.dequeue(); return m_queued_tokens.dequeue();
for (;;) { for (;;) {
auto current_input_character = next_codepoint(); auto current_input_character = next_code_point();
switch (m_state) { switch (m_state) {
BEGIN_STATE(Data) BEGIN_STATE(Data)
{ {
@ -328,7 +328,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_tag.tag_name.append_codepoint(0xFFFD); m_current_token.m_tag.tag_name.append_code_point(0xFFFD);
continue; continue;
} }
ON_EOF ON_EOF
@ -338,7 +338,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_tag.tag_name.append_codepoint(current_input_character.value()); m_current_token.m_tag.tag_name.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -408,12 +408,12 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_comment_or_character.data.append_codepoint(0xFFFD); m_current_token.m_comment_or_character.data.append_code_point(0xFFFD);
continue; continue;
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_comment_or_character.data.append_codepoint(current_input_character.value()); m_current_token.m_comment_or_character.data.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -462,7 +462,7 @@ _StartOfFunction:
{ {
PARSE_ERROR(); PARSE_ERROR();
create_new_token(HTMLToken::Type::DOCTYPE); create_new_token(HTMLToken::Type::DOCTYPE);
m_current_token.m_doctype.name.append_codepoint(0xFFFD); m_current_token.m_doctype.name.append_code_point(0xFFFD);
m_current_token.m_doctype.missing_name = false; m_current_token.m_doctype.missing_name = false;
SWITCH_TO(DOCTYPEName); SWITCH_TO(DOCTYPEName);
} }
@ -484,7 +484,7 @@ _StartOfFunction:
ANYTHING_ELSE ANYTHING_ELSE
{ {
create_new_token(HTMLToken::Type::DOCTYPE); create_new_token(HTMLToken::Type::DOCTYPE);
m_current_token.m_doctype.name.append_codepoint(current_input_character.value()); m_current_token.m_doctype.name.append_code_point(current_input_character.value());
m_current_token.m_doctype.missing_name = false; m_current_token.m_doctype.missing_name = false;
SWITCH_TO(DOCTYPEName); SWITCH_TO(DOCTYPEName);
} }
@ -509,7 +509,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_doctype.name.append_codepoint(0xFFFD); m_current_token.m_doctype.name.append_code_point(0xFFFD);
continue; continue;
} }
ON_EOF ON_EOF
@ -521,7 +521,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.name.append_codepoint(current_input_character.value()); m_current_token.m_doctype.name.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -732,7 +732,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_doctype.public_identifier.append_codepoint(0xFFFD); m_current_token.m_doctype.public_identifier.append_code_point(0xFFFD);
continue; continue;
} }
ON('>') ON('>')
@ -750,7 +750,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.public_identifier.append_codepoint(current_input_character.value()); m_current_token.m_doctype.public_identifier.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -765,7 +765,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_doctype.public_identifier.append_codepoint(0xFFFD); m_current_token.m_doctype.public_identifier.append_code_point(0xFFFD);
continue; continue;
} }
ON('>') ON('>')
@ -783,7 +783,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.public_identifier.append_codepoint(current_input_character.value()); m_current_token.m_doctype.public_identifier.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -798,7 +798,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_doctype.system_identifier.append_codepoint(0xFFFD); m_current_token.m_doctype.system_identifier.append_code_point(0xFFFD);
continue; continue;
} }
ON('>') ON('>')
@ -816,7 +816,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.system_identifier.append_codepoint(current_input_character.value()); m_current_token.m_doctype.system_identifier.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -831,7 +831,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_doctype.system_identifier.append_codepoint(0xFFFD); m_current_token.m_doctype.system_identifier.append_code_point(0xFFFD);
continue; continue;
} }
ON('>') ON('>')
@ -849,7 +849,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_doctype.system_identifier.append_codepoint(current_input_character.value()); m_current_token.m_doctype.system_identifier.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1003,7 +1003,7 @@ _StartOfFunction:
{ {
PARSE_ERROR(); PARSE_ERROR();
auto new_attribute = HTMLToken::AttributeBuilder(); auto new_attribute = HTMLToken::AttributeBuilder();
new_attribute.local_name_builder.append_codepoint(current_input_character.value()); new_attribute.local_name_builder.append_code_point(current_input_character.value());
m_current_token.m_tag.attributes.append(new_attribute); m_current_token.m_tag.attributes.append(new_attribute);
SWITCH_TO(AttributeName); SWITCH_TO(AttributeName);
} }
@ -1059,13 +1059,13 @@ _StartOfFunction:
} }
ON_ASCII_UPPER_ALPHA ON_ASCII_UPPER_ALPHA
{ {
m_current_token.m_tag.attributes.last().local_name_builder.append_codepoint(tolower(current_input_character.value())); m_current_token.m_tag.attributes.last().local_name_builder.append_code_point(tolower(current_input_character.value()));
continue; continue;
} }
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_tag.attributes.last().local_name_builder.append_codepoint(0xFFFD); m_current_token.m_tag.attributes.last().local_name_builder.append_code_point(0xFFFD);
continue; continue;
} }
ON('"') ON('"')
@ -1086,7 +1086,7 @@ _StartOfFunction:
ANYTHING_ELSE ANYTHING_ELSE
{ {
AnythingElseAttributeName: AnythingElseAttributeName:
m_current_token.m_tag.attributes.last().local_name_builder.append_codepoint(current_input_character.value()); m_current_token.m_tag.attributes.last().local_name_builder.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1163,7 +1163,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(0xFFFD); m_current_token.m_tag.attributes.last().value_builder.append_code_point(0xFFFD);
continue; continue;
} }
ON_EOF ON_EOF
@ -1173,7 +1173,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(current_input_character.value()); m_current_token.m_tag.attributes.last().value_builder.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1193,7 +1193,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(0xFFFD); m_current_token.m_tag.attributes.last().value_builder.append_code_point(0xFFFD);
continue; continue;
} }
ON_EOF ON_EOF
@ -1203,7 +1203,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(current_input_character.value()); m_current_token.m_tag.attributes.last().value_builder.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1227,7 +1227,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(0xFFFD); m_current_token.m_tag.attributes.last().value_builder.append_code_point(0xFFFD);
continue; continue;
} }
ON('"') ON('"')
@ -1263,7 +1263,7 @@ _StartOfFunction:
ANYTHING_ELSE ANYTHING_ELSE
{ {
AnythingElseAttributeValueUnquoted: AnythingElseAttributeValueUnquoted:
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(current_input_character.value()); m_current_token.m_tag.attributes.last().value_builder.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1343,7 +1343,7 @@ _StartOfFunction:
{ {
ON('<') ON('<')
{ {
m_current_token.m_comment_or_character.data.append_codepoint(current_input_character.value()); m_current_token.m_comment_or_character.data.append_code_point(current_input_character.value());
SWITCH_TO(CommentLessThanSign); SWITCH_TO(CommentLessThanSign);
} }
ON('-') ON('-')
@ -1353,7 +1353,7 @@ _StartOfFunction:
ON(0) ON(0)
{ {
PARSE_ERROR(); PARSE_ERROR();
m_current_token.m_comment_or_character.data.append_codepoint(0xFFFD); m_current_token.m_comment_or_character.data.append_code_point(0xFFFD);
continue; continue;
} }
ON_EOF ON_EOF
@ -1364,7 +1364,7 @@ _StartOfFunction:
} }
ANYTHING_ELSE ANYTHING_ELSE
{ {
m_current_token.m_comment_or_character.data.append_codepoint(current_input_character.value()); m_current_token.m_comment_or_character.data.append_code_point(current_input_character.value());
continue; continue;
} }
} }
@ -1449,12 +1449,12 @@ _StartOfFunction:
{ {
ON('!') ON('!')
{ {
m_current_token.m_comment_or_character.data.append_codepoint(current_input_character.value()); m_current_token.m_comment_or_character.data.append_code_point(current_input_character.value());
SWITCH_TO(CommentLessThanSignBang); SWITCH_TO(CommentLessThanSignBang);
} }
ON('<') ON('<')
{ {
m_current_token.m_comment_or_character.data.append_codepoint(current_input_character.value()); m_current_token.m_comment_or_character.data.append_code_point(current_input_character.value());
continue; continue;
} }
ANYTHING_ELSE ANYTHING_ELSE
@ -1533,7 +1533,7 @@ _StartOfFunction:
{ {
size_t byte_offset = m_utf8_view.byte_offset_of(m_prev_utf8_iterator); size_t byte_offset = m_utf8_view.byte_offset_of(m_prev_utf8_iterator);
auto match = HTML::codepoints_from_entity(m_decoded_input.substring_view(byte_offset, m_decoded_input.length() - byte_offset - 1)); auto match = HTML::code_points_from_entity(m_decoded_input.substring_view(byte_offset, m_decoded_input.length() - byte_offset - 1));
if (match.has_value()) { if (match.has_value()) {
for (size_t i = 0; i < match.value().entity.length() - 1; ++i) { for (size_t i = 0; i < match.value().entity.length() - 1; ++i) {
@ -1543,8 +1543,8 @@ _StartOfFunction:
for (auto ch : match.value().entity) for (auto ch : match.value().entity)
m_temporary_buffer.append(ch); m_temporary_buffer.append(ch);
if (consumed_as_part_of_an_attribute() && match.value().codepoints.last() != ';') { if (consumed_as_part_of_an_attribute() && match.value().code_points.last() != ';') {
auto next = peek_codepoint(0); auto next = peek_code_point(0);
if (next.has_value() && (next.value() == '=' || isalnum(next.value()))) { if (next.has_value() && (next.value() == '=' || isalnum(next.value()))) {
FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE; FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE;
SWITCH_TO_RETURN_STATE; SWITCH_TO_RETURN_STATE;
@ -1552,8 +1552,8 @@ _StartOfFunction:
} }
if (consumed_as_part_of_an_attribute() && match.value().entity.ends_with(';')) { if (consumed_as_part_of_an_attribute() && match.value().entity.ends_with(';')) {
auto next_codepoint = peek_codepoint(0); auto next_code_point = peek_code_point(0);
if (next_codepoint.has_value() && next_codepoint.value() == '=') { if (next_code_point.has_value() && next_code_point.value() == '=') {
FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE; FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE;
SWITCH_TO_RETURN_STATE; SWITCH_TO_RETURN_STATE;
} }
@ -1564,7 +1564,7 @@ _StartOfFunction:
} }
m_temporary_buffer.clear(); m_temporary_buffer.clear();
m_temporary_buffer.append(match.value().codepoints); m_temporary_buffer.append(match.value().code_points);
FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE; FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE;
SWITCH_TO_RETURN_STATE; SWITCH_TO_RETURN_STATE;
@ -1580,7 +1580,7 @@ _StartOfFunction:
ON_ASCII_ALPHANUMERIC ON_ASCII_ALPHANUMERIC
{ {
if (consumed_as_part_of_an_attribute()) { if (consumed_as_part_of_an_attribute()) {
m_current_token.m_tag.attributes.last().value_builder.append_codepoint(current_input_character.value()); m_current_token.m_tag.attributes.last().value_builder.append_code_point(current_input_character.value());
continue; continue;
} else { } else {
EMIT_CURRENT_CHARACTER; EMIT_CURRENT_CHARACTER;
@ -1724,7 +1724,7 @@ _StartOfFunction:
PARSE_ERROR(); PARSE_ERROR();
constexpr struct { constexpr struct {
u32 number; u32 number;
u32 codepoint; u32 code_point;
} conversion_table[] = { } conversion_table[] = {
{ 0x80, 0x20AC }, { 0x80, 0x20AC },
{ 0x82, 0x201A }, { 0x82, 0x201A },
@ -1756,7 +1756,7 @@ _StartOfFunction:
}; };
for (auto& entry : conversion_table) { for (auto& entry : conversion_table) {
if (m_character_reference_code == entry.number) { if (m_character_reference_code == entry.number) {
m_character_reference_code = entry.codepoint; m_character_reference_code = entry.code_point;
break; break;
} }
} }
@ -1833,8 +1833,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RCDATA); RECONSUME_IN(RCDATA);
} }
SWITCH_TO(BeforeAttributeName); SWITCH_TO(BeforeAttributeName);
@ -1844,8 +1844,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RCDATA); RECONSUME_IN(RCDATA);
} }
SWITCH_TO(SelfClosingStartTag); SWITCH_TO(SelfClosingStartTag);
@ -1855,8 +1855,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RCDATA); RECONSUME_IN(RCDATA);
} }
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data); SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
@ -1869,7 +1869,7 @@ _StartOfFunction:
} }
ON_ASCII_LOWER_ALPHA ON_ASCII_LOWER_ALPHA
{ {
m_current_token.m_tag.tag_name.append_codepoint(current_input_character.value()); m_current_token.m_tag.tag_name.append_code_point(current_input_character.value());
m_temporary_buffer.append(current_input_character.value()); m_temporary_buffer.append(current_input_character.value());
continue; continue;
} }
@ -1877,8 +1877,8 @@ _StartOfFunction:
{ {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RCDATA); RECONSUME_IN(RCDATA);
} }
} }
@ -1943,8 +1943,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RAWTEXT); RECONSUME_IN(RAWTEXT);
} }
SWITCH_TO(BeforeAttributeName); SWITCH_TO(BeforeAttributeName);
@ -1954,8 +1954,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RAWTEXT); RECONSUME_IN(RAWTEXT);
} }
SWITCH_TO(SelfClosingStartTag); SWITCH_TO(SelfClosingStartTag);
@ -1965,8 +1965,8 @@ _StartOfFunction:
if (!current_end_tag_token_is_appropriate()) { if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RAWTEXT); RECONSUME_IN(RAWTEXT);
} }
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data); SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
@ -1987,8 +1987,8 @@ _StartOfFunction:
{ {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(RAWTEXT); RECONSUME_IN(RAWTEXT);
} }
} }
@ -2155,8 +2155,8 @@ _StartOfFunction:
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) { for (auto code_point : m_temporary_buffer) {
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
} }
RECONSUME_IN(ScriptDataEscaped); RECONSUME_IN(ScriptDataEscaped);
} }
@ -2167,8 +2167,8 @@ _StartOfFunction:
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) { for (auto code_point : m_temporary_buffer) {
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
} }
RECONSUME_IN(ScriptDataEscaped); RECONSUME_IN(ScriptDataEscaped);
} }
@ -2179,8 +2179,8 @@ _StartOfFunction:
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) { for (auto code_point : m_temporary_buffer) {
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
} }
RECONSUME_IN(ScriptDataEscaped); RECONSUME_IN(ScriptDataEscaped);
} }
@ -2200,8 +2200,8 @@ _StartOfFunction:
{ {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) { for (auto code_point : m_temporary_buffer) {
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
} }
RECONSUME_IN(ScriptDataEscaped); RECONSUME_IN(ScriptDataEscaped);
} }
@ -2479,8 +2479,8 @@ _StartOfFunction:
SWITCH_TO(BeforeAttributeName); SWITCH_TO(BeforeAttributeName);
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(ScriptData); RECONSUME_IN(ScriptData);
} }
ON('/') ON('/')
@ -2489,8 +2489,8 @@ _StartOfFunction:
SWITCH_TO(SelfClosingStartTag); SWITCH_TO(SelfClosingStartTag);
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(ScriptData); RECONSUME_IN(ScriptData);
} }
ON('>') ON('>')
@ -2499,8 +2499,8 @@ _StartOfFunction:
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data); SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(ScriptData); RECONSUME_IN(ScriptData);
} }
ON_ASCII_UPPER_ALPHA ON_ASCII_UPPER_ALPHA
@ -2519,8 +2519,8 @@ _StartOfFunction:
{ {
m_queued_tokens.enqueue(HTMLToken::make_character('<')); m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/')); m_queued_tokens.enqueue(HTMLToken::make_character('/'));
for (auto codepoint : m_temporary_buffer) for (auto code_point : m_temporary_buffer)
m_queued_tokens.enqueue(HTMLToken::make_character(codepoint)); m_queued_tokens.enqueue(HTMLToken::make_character(code_point));
RECONSUME_IN(ScriptData); RECONSUME_IN(ScriptData);
} }
} }
@ -2585,18 +2585,18 @@ _StartOfFunction:
bool HTMLTokenizer::consume_next_if_match(const StringView& string, CaseSensitivity case_sensitivity) bool HTMLTokenizer::consume_next_if_match(const StringView& string, CaseSensitivity case_sensitivity)
{ {
for (size_t i = 0; i < string.length(); ++i) { for (size_t i = 0; i < string.length(); ++i) {
auto codepoint = peek_codepoint(i); auto code_point = peek_code_point(i);
if (!codepoint.has_value()) if (!code_point.has_value())
return false; return false;
// FIXME: This should be more Unicode-aware. // FIXME: This should be more Unicode-aware.
if (case_sensitivity == CaseSensitivity::CaseInsensitive) { if (case_sensitivity == CaseSensitivity::CaseInsensitive) {
if (codepoint.value() < 0x80) { if (code_point.value() < 0x80) {
if (tolower(codepoint.value()) != tolower(string[i])) if (tolower(code_point.value()) != tolower(string[i]))
return false; return false;
continue; continue;
} }
} }
if (codepoint.value() != (u32)string[i]) if (code_point.value() != (u32)string[i])
return false; return false;
} }
for (size_t i = 0; i < string.length(); ++i) { for (size_t i = 0; i < string.length(); ++i) {

4
Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
View file

@ -137,8 +137,8 @@ public:
String source() const { return m_decoded_input; } String source() const { return m_decoded_input; }
private: private:
Optional<u32> next_codepoint(); Optional<u32> next_code_point();
Optional<u32> peek_codepoint(size_t offset) const; Optional<u32> peek_code_point(size_t offset) const;
bool consume_next_if_match(const StringView&, CaseSensitivity = CaseSensitivity::CaseSensitive); bool consume_next_if_match(const StringView&, CaseSensitivity = CaseSensitivity::CaseSensitive);
void create_new_token(HTMLToken::Type); void create_new_token(HTMLToken::Type);
bool current_end_tag_token_is_appropriate() const; bool current_end_tag_token_is_appropriate() const;

2
Libraries/LibWeb/Layout/LayoutText.cpp
View file

@ -209,7 +209,7 @@ void LayoutText::split_into_lines_by_rules(LayoutBlock& container, LayoutMode la
skip_over_whitespace(); skip_over_whitespace();
for (; it != utf8_view.end(); ++it) { for (; it != utf8_view.end(); ++it) {
if (!isspace(*it)) { if (!isspace(*it)) {
builder.append(utf8_view.as_string().characters_without_null_termination() + utf8_view.byte_offset_of(it), it.codepoint_length_in_bytes()); builder.append(utf8_view.as_string().characters_without_null_termination() + utf8_view.byte_offset_of(it), it.code_point_length_in_bytes());
} else { } else {
builder.append(' '); builder.append(' ');
skip_over_whitespace(); skip_over_whitespace();

2
Libraries/LibWeb/Page/EventHandler.cpp
View file

@ -255,7 +255,7 @@ bool EventHandler::handle_keydown(KeyCode key, unsigned, u32 code_point)
auto& text_node = downcast<DOM::Text>(*m_frame.cursor_position().node()); auto& text_node = downcast<DOM::Text>(*m_frame.cursor_position().node());
StringBuilder builder; StringBuilder builder;
builder.append(text_node.data().substring_view(0, m_frame.cursor_position().offset())); builder.append(text_node.data().substring_view(0, m_frame.cursor_position().offset()));
builder.append_codepoint(code_point); builder.append_code_point(code_point);
builder.append(text_node.data().substring_view(m_frame.cursor_position().offset(), text_node.data().length() - m_frame.cursor_position().offset())); builder.append(text_node.data().substring_view(m_frame.cursor_position().offset(), text_node.data().length() - m_frame.cursor_position().offset()));
text_node.set_data(builder.to_string()); text_node.set_data(builder.to_string());
// FIXME: This will advance the cursor incorrectly when inserting multiple whitespaces (DOM vs layout whitespace collapse difference.) // FIXME: This will advance the cursor incorrectly when inserting multiple whitespaces (DOM vs layout whitespace collapse difference.)

2
Services/WindowServer/MenuManager.cpp
View file

@ -146,7 +146,7 @@ void MenuManager::event(Core::Event& event)
if (m_current_menu && event.type() == Event::KeyDown if (m_current_menu && event.type() == Event::KeyDown
&& ((key_event.key() >= Key_A && key_event.key() <= Key_Z) && ((key_event.key() >= Key_A && key_event.key() <= Key_Z)
|| (key_event.key() >= Key_0 && key_event.key() <= Key_9))) { || (key_event.key() >= Key_0 && key_event.key() <= Key_9))) {
m_current_search.append_codepoint(key_event.code_point()); m_current_search.append_code_point(key_event.code_point());
m_search_timer->restart(s_search_timeout); m_search_timer->restart(s_search_timeout);
for (int i = 0; i < m_current_menu->item_count(); ++i) { for (int i = 0; i < m_current_menu->item_count(); ++i) {
auto text = m_current_menu->item(i).text(); auto text = m_current_menu->item(i).text();

2
Userland/ls.cpp
View file

@ -144,7 +144,7 @@ int print_escaped(const char* name)
Utf8View utf8_name(name); Utf8View utf8_name(name);
if (utf8_name.validate()) { if (utf8_name.validate()) {
printf("%s", name); printf("%s", name);
return utf8_name.length_in_codepoints(); return utf8_name.length_in_code_points();
} }
for (int i = 0; name[i] != '\0'; i++) { for (int i = 0; name[i] != '\0'; i++) {