summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Userland/Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp3
-rw-r--r--Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp2
-rw-r--r--Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h12
-rw-r--r--Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp37
4 files changed, 33 insertions, 21 deletions
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp
index 80aacf0905..fb3f82f5dd 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLDocumentParser.cpp
@@ -1572,8 +1572,7 @@ void HTMLDocumentParser::handle_in_body(HTMLToken& token)
if (token.is_start_tag() && token.tag_name() == HTML::TagNames::image) {
// Parse error. Change the token's tag name to HTML::TagNames::img and reprocess it. (Don't ask.)
log_parse_error();
- token.m_tag.tag_name.clear();
- token.m_tag.tag_name.append(HTML::TagNames::img);
+ token.m_tag.tag_name = "img";
process_using_the_rules_for(m_insertion_mode, token);
return;
}
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
index 10f577bd2b..eccf3c1723 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
@@ -40,7 +40,7 @@ String HTMLToken::to_string() const
if (type() == HTMLToken::Type::StartTag || type() == HTMLToken::Type::EndTag) {
builder.append(" { name: '");
- builder.append(m_tag.tag_name.to_string());
+ builder.append(m_tag.tag_name);
builder.append("', { ");
for (auto& attribute : m_tag.attributes) {
builder.append(attribute.local_name);
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h
index e3fb7fb29f..95475d8c1f 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.h
@@ -42,7 +42,7 @@ public:
{
HTMLToken token;
token.m_type = Type::StartTag;
- token.m_tag.tag_name.append(tag_name);
+ token.m_tag.tag_name = tag_name;
return token;
}
@@ -81,7 +81,7 @@ public:
String tag_name() const
{
VERIFY(is_start_tag() || is_end_tag());
- return m_tag.tag_name.to_string();
+ return m_tag.tag_name;
}
bool is_self_closing() const
@@ -120,10 +120,8 @@ public:
void adjust_tag_name(const FlyString& old_name, const FlyString& new_name)
{
VERIFY(is_start_tag() || is_end_tag());
- if (old_name == m_tag.tag_name.string_view()) {
- m_tag.tag_name.clear();
- m_tag.tag_name.append(new_name);
- }
+ if (old_name == m_tag.tag_name)
+ m_tag.tag_name = new_name;
}
void adjust_attribute_name(const FlyString& old_name, const FlyString& new_name)
@@ -202,7 +200,7 @@ private:
// Type::StartTag
// Type::EndTag
struct {
- StringBuilder tag_name;
+ String tag_name;
bool self_closing { false };
bool self_closing_acknowledged { false };
Vector<AttributeBuilder> attributes;
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
index 44c3a7ba9b..312875ece5 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
@@ -303,29 +303,32 @@ _StartOfFunction:
{
ON_WHITESPACE
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
m_current_token.m_end_position = nth_last_position(1);
SWITCH_TO(BeforeAttributeName);
}
ON('/')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
m_current_token.m_end_position = nth_last_position(0);
SWITCH_TO(SelfClosingStartTag);
}
ON('>')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
m_current_token.m_end_position = nth_last_position(1);
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
}
ON_ASCII_UPPER_ALPHA
{
- m_current_token.m_tag.tag_name.append(to_ascii_lowercase(current_input_character.value()));
+ m_current_builder.append_code_point(to_ascii_lowercase(current_input_character.value()));
m_current_token.m_end_position = nth_last_position(0);
continue;
}
ON(0)
{
log_parse_error();
- m_current_token.m_tag.tag_name.append_code_point(0xFFFD);
+ m_current_builder.append_code_point(0xFFFD);
m_current_token.m_end_position = nth_last_position(0);
continue;
}
@@ -337,7 +340,7 @@ _StartOfFunction:
}
ANYTHING_ELSE
{
- m_current_token.m_tag.tag_name.append_code_point(current_input_character.value());
+ m_current_builder.append_code_point(current_input_character.value());
m_current_token.m_end_position = nth_last_position(0);
continue;
}
@@ -1846,6 +1849,7 @@ _StartOfFunction:
{
ON_WHITESPACE
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1857,6 +1861,7 @@ _StartOfFunction:
}
ON('/')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1868,6 +1873,7 @@ _StartOfFunction:
}
ON('>')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1879,13 +1885,13 @@ _StartOfFunction:
}
ON_ASCII_UPPER_ALPHA
{
- m_current_token.m_tag.tag_name.append(to_ascii_lowercase(current_input_character.value()));
+ m_current_builder.append_code_point(to_ascii_lowercase(current_input_character.value()));
m_temporary_buffer.append(current_input_character.value());
continue;
}
ON_ASCII_LOWER_ALPHA
{
- m_current_token.m_tag.tag_name.append_code_point(current_input_character.value());
+ m_current_builder.append_code_point(current_input_character.value());
m_temporary_buffer.append(current_input_character.value());
continue;
}
@@ -1956,6 +1962,7 @@ _StartOfFunction:
{
ON_WHITESPACE
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1967,6 +1974,7 @@ _StartOfFunction:
}
ON('/')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1978,6 +1986,7 @@ _StartOfFunction:
}
ON('>')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (!current_end_tag_token_is_appropriate()) {
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
m_queued_tokens.enqueue(HTMLToken::make_character('/'));
@@ -1989,13 +1998,13 @@ _StartOfFunction:
}
ON_ASCII_UPPER_ALPHA
{
- m_current_token.m_tag.tag_name.append(to_ascii_lowercase(current_input_character.value()));
+ m_current_builder.append_code_point(to_ascii_lowercase(current_input_character.value()));
m_temporary_buffer.append(current_input_character.value());
continue;
}
ON_ASCII_LOWER_ALPHA
{
- m_current_token.m_tag.tag_name.append(current_input_character.value());
+ m_current_builder.append(current_input_character.value());
m_temporary_buffer.append(current_input_character.value());
continue;
}
@@ -2166,6 +2175,7 @@ _StartOfFunction:
{
ON_WHITESPACE
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO(BeforeAttributeName);
@@ -2178,6 +2188,7 @@ _StartOfFunction:
}
ON('/')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO(SelfClosingStartTag);
@@ -2190,6 +2201,7 @@ _StartOfFunction:
}
ON('>')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
@@ -2202,13 +2214,13 @@ _StartOfFunction:
}
ON_ASCII_UPPER_ALPHA
{
- m_current_token.m_tag.tag_name.append(to_ascii_lowercase(current_input_character.value()));
+ m_current_builder.append_code_point(to_ascii_lowercase(current_input_character.value()));
m_temporary_buffer.append(current_input_character.value());
continue;
}
ON_ASCII_LOWER_ALPHA
{
- m_current_token.m_tag.tag_name.append(current_input_character.value());
+ m_current_builder.append(current_input_character.value());
m_temporary_buffer.append(current_input_character.value());
continue;
}
@@ -2491,6 +2503,7 @@ _StartOfFunction:
{
ON_WHITESPACE
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO(BeforeAttributeName);
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
@@ -2501,6 +2514,7 @@ _StartOfFunction:
}
ON('/')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO(SelfClosingStartTag);
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
@@ -2511,6 +2525,7 @@ _StartOfFunction:
}
ON('>')
{
+ m_current_token.m_tag.tag_name = consume_current_builder();
if (current_end_tag_token_is_appropriate())
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
m_queued_tokens.enqueue(HTMLToken::make_character('<'));
@@ -2521,13 +2536,13 @@ _StartOfFunction:
}
ON_ASCII_UPPER_ALPHA
{
- m_current_token.m_tag.tag_name.append(to_ascii_lowercase(current_input_character.value()));
+ m_current_builder.append_code_point(to_ascii_lowercase(current_input_character.value()));
m_temporary_buffer.append(current_input_character.value());
continue;
}
ON_ASCII_LOWER_ALPHA
{
- m_current_token.m_tag.tag_name.append(current_input_character.value());
+ m_current_builder.append(current_input_character.value());
m_temporary_buffer.append(current_input_character.value());
continue;
}