RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 02:37:42 +00:00
Code Issues Activity Actions

LibWeb: Parser should prefer the longest matchable HTML entity

Browse source 
If we can match both "&copy" and "©" we should prefer the latter.

Also remove invalid FIXME's about case insensitive entities.
This commit is contained in:
Andreas Kling 2020-05-30 11:01:01 +02:00
parent 1ef5d609d9
commit c8e0426ab9
1 changed files with 13 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

23
Libraries/LibWeb/Parser/Entities.cpp
View file

@ -2276,20 +2276,23 @@ Optional<EntityMatch> codepoints_from_entity(const StringView& entity)
{ "vsupne;", 0x0228B, 0x0FE00 }, { "vsupne;", 0x0228B, 0x0FE00 },
}; };
// FIXME: Make case-insensitive EntityMatch match;
for (auto& single_codepoint_entity : single_codepoint_entities) {
if (entity.starts_with(single_codepoint_entity.entity))
return EntityMatch { { single_codepoint_entity.codepoint }, StringView(single_codepoint_entity.entity) };
}
// FIXME: Make case-insensitive for (auto& single_codepoint_entity : single_codepoint_entities) {
for (auto& double_codepoint_entity : double_codepoint_entities) { if (entity.starts_with(single_codepoint_entity.entity)) {
if (entity.starts_with(double_codepoint_entity.entity)) { if (match.entity.is_null() || entity.length() > match.entity.length())
return EntityMatch { { double_codepoint_entity.codepoint1, double_codepoint_entity.codepoint2 }, StringView(double_codepoint_entity.entity) }; match = { { single_codepoint_entity.codepoint }, StringView(single_codepoint_entity.entity) };
} }
} }
return {}; for (auto& double_codepoint_entity : double_codepoint_entities) {
if (entity.starts_with(double_codepoint_entity.entity)) {
if (match.entity.is_null() || entity.length() > match.entity.length())
match = EntityMatch { { double_codepoint_entity.codepoint1, double_codepoint_entity.codepoint2 }, StringView(double_codepoint_entity.entity) };
}
}
return match;
} }
} }