0ct0pu5/ladybird
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2

LibWeb: Use getter and setter for Character type HTMLTokens

Browse source 
While storing the code point in a UTF-8 encoded String in horrendously
inefficient, this problem will be addressed at a later stage.
This commit is contained in:
Max Wipfli 2021-07-14 23:33:12 +02:00 • committed by Ali Mohammad Pur
parent e8e9426b4f
commit 1aeafcc58b
Notes: sideshowbarker 2024-07-18 08:53:02 +09:00
2 changed files with 26 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h
View file

@ -50,10 +50,7 @@ public:
{ {
HTMLToken token; HTMLToken token;
token.m_type = Type::Character; token.m_type = Type::Character;
StringBuilder builder; token.set_code_point(code_point);
// FIXME: This narrows code_point to char, should this be append_code_point() instead?
builder.append(code_point);
token.m_comment_or_character.data = builder.to_string();
return token; return token;
} }
@ -97,6 +94,14 @@ public:
} }
} }
void set_code_point(u32 code_point)
{
VERIFY(is_character());
StringBuilder builder;
builder.append_code_point(code_point);
m_comment_or_character.data = builder.to_string();
}
String const& comment() const String const& comment() const
{ {
VERIFY(is_comment()); VERIFY(is_comment());

36
Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View file

@ -75,18 +75,17 @@ namespace Web::HTML {
goto new_state; \ goto new_state; \
} while (0) } while (0)
#define FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE \ #define FLUSH_CODEPOINTS_CONSUMED_AS_A_CHARACTER_REFERENCE \
do { \ do { \
for (auto code_point : 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_builder.append_code_point(code_point); \ m_current_builder.append_code_point(code_point); \
} else { \ } else { \
create_new_token(HTMLToken::Type::Character); \ create_new_token(HTMLToken::Type::Character); \
m_current_builder.append_code_point(code_point); \ m_current_token.set_code_point(code_point); \
m_current_token.m_comment_or_character.data = consume_current_builder(); \ m_queued_tokens.enqueue(move(m_current_token)); \
m_queued_tokens.enqueue(move(m_current_token)); \ } \
} \ } \
} \
} while (0) } while (0)
#define DONT_CONSUME_NEXT_INPUT_CHARACTER \ #define DONT_CONSUME_NEXT_INPUT_CHARACTER \
@ -142,13 +141,12 @@ namespace Web::HTML {
return m_queued_tokens.dequeue(); \ return m_queued_tokens.dequeue(); \
} while (0) } while (0)
#define EMIT_CHARACTER(code_point) \ #define EMIT_CHARACTER(code_point) \
do { \ do { \
create_new_token(HTMLToken::Type::Character); \ create_new_token(HTMLToken::Type::Character); \
m_current_builder.append_code_point(code_point); \ m_current_token.set_code_point(code_point); \
m_current_token.m_comment_or_character.data = consume_current_builder(); \ m_queued_tokens.enqueue(move(m_current_token)); \
m_queued_tokens.enqueue(move(m_current_token)); \ return m_queued_tokens.dequeue(); \
return m_queued_tokens.dequeue(); \
} while (0) } while (0)
#define EMIT_CURRENT_CHARACTER \ #define EMIT_CURRENT_CHARACTER \