mirrors/ladybird
0
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-05-01 00:38:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

LibWeb: Set consistent positions for the start and end of HTML tags

Browse source 
To illustrate the previous behavior, consider these tags and their start
and end positions (shown inclusively below):

    Start tag:    End tag:
    <span>        </span>
     ^ start       ^ start
         ^end           ^end

The start position of a tag is the first ASCII-alpha code point after
the opening brace. The start position of a close tag is the slash just
before the first ASCII-alpha code point. And the end position of both
is the closing brace. So the opening brace is not included in the
emitted tag, but the closing brace is. And the end tag including the
slash is an oddity that had to be worked around in its only use case
(syntax highlighting).

We now consistently exclude the braces from the emitted tag, and also
exclude the slash from the end tag, so that it does not need to be
accounted for in syntax highlighting. That is, we now have:

    Start tag:    End tag:
    <span>        </span>
     ^ start        ^ start
        ^end           ^end

The tokenizer unit test has been extended to test these positions.
This commit is contained in:
Timothy Flynn 2023-08-24 17:01:19 -04:00 • committed by Andreas Kling
parent 70a87795e4
commit 5b2bc90b50
Notes: sideshowbarker 2024-07-17 07:48:42 +09:00
3 changed files with 39 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
View file

@ -347,7 +347,6 @@ _StartOfFunction:
ON('>')
{
m_current_token.set_tag_name(consume_current_builder());
m_current_token.set_end_position({}, nth_last_position(1));
SWITCH_TO_AND_EMIT_CURRENT_TOKEN(Data);
}
ON_ASCII_UPPER_ALPHA
@ -366,7 +365,6 @@ _StartOfFunction:
ON_EOF
{
log_parse_error();
m_current_token.set_end_position({}, nth_last_position(0));
EMIT_EOF;
}
ANYTHING_ELSE
@ -2773,19 +2771,9 @@ bool HTMLTokenizer::consume_next_if_match(StringView string, CaseSensitivity cas
void HTMLTokenizer::create_new_token(HTMLToken::Type type)
{
m_current_token = { type };
size_t offset = 0;
switch (type) {
case HTMLToken::Type::StartTag:
offset = 1;
break;
case HTMLToken::Type::EndTag:
offset = 2;
break;
default:
break;
}
m_current_token.set_start_position({}, nth_last_position(offset));
auto is_start_or_end_tag = type == HTMLToken::Type::StartTag || type == HTMLToken::Type::EndTag;
m_current_token.set_start_position({}, nth_last_position(is_start_or_end_tag ? 1 : 0));
}
HTMLTokenizer::HTMLTokenizer()
@ -2855,7 +2843,9 @@ void HTMLTokenizer::will_emit(HTMLToken& token)
{
if (token.is_start_tag())
m_last_emitted_start_tag_name = token.tag_name();
token.set_end_position({}, nth_last_position(0));
auto is_start_or_end_tag = token.type() == HTMLToken::Type::StartTag || token.type() == HTMLToken::Type::EndTag;
token.set_end_position({}, nth_last_position(is_start_or_end_tag ? 1 : 0));
}
bool HTMLTokenizer::current_end_tag_token_is_appropriate() const