LadybirdBrowser/ladybird
1
1
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-13 11:42:38 +03:00
Code Issues Packages Projects Releases Wiki Activity

AK: Skip UTF-8 validation inside URL parser

Browse Source 
Since we're already building up a percent-encoded ASCII-only string
in the internal parser buffer, there's no need to do a second UTF-8
validation pass before assigning each part of the parsed URL.

This makes URL parsing signficantly faster.
This commit is contained in:
Andreas Kling 2023-12-29 17:35:01 +01:00
parent f045a877b4
commit 75cecd19a5
Notes: sideshowbarker 2024-07-17 03:35:24 +09:00 
Author: https://github.com/awesomekling
Commit: https://github.com/SerenityOS/serenity/commit/75cecd19a5
Pull-request: https://github.com/SerenityOS/serenity/pull/22496
Reviewed-by: https://github.com/LucasChollet
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
AK/URLParser.cpp
View File

@ -891,7 +891,7 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
}
// 2. Set url’s scheme to buffer.
url->m_scheme = buffer.to_string().release_value_but_fixme_should_propagate_errors();
url->m_scheme = buffer.to_string_without_validation();
// 3. If state override is given, then:
if (state_override.has_value()) {
@ -1554,7 +1554,7 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
buffer.append(':');
}
// 2. Append buffer to url’s path.
url->m_paths.append(buffer.to_string().release_value_but_fixme_should_propagate_errors());
url->m_paths.append(buffer.to_string_without_validation());
}
// 5. Set buffer to the empty string.
@ -1592,7 +1592,7 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
// 1. If c is U+003F (?), then set url’s query to the empty string and state to query state.
if (code_point == '?') {
url->m_paths[0] = buffer.to_string().release_value_but_fixme_should_propagate_errors();
url->m_paths[0] = buffer.to_string_without_validation();
url->m_query = String {};
buffer.clear();
state = State::Query;
@ -1600,7 +1600,7 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
// 2. Otherwise, if c is U+0023 (#), then set url’s fragment to the empty string and state to fragment state.
else if (code_point == '#') {
// NOTE: This needs to be percent decoded since the member variables contain decoded data.
url->m_paths[0] = buffer.to_string().release_value_but_fixme_should_propagate_errors();
url->m_paths[0] = buffer.to_string_without_validation();
url->m_fragment = String {};
buffer.clear();
state = State::Fragment;
@ -1619,7 +1619,7 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
if (code_point != end_of_file) {
URL::append_percent_encoded_if_necessary(buffer, code_point, URL::PercentEncodeSet::C0Control);
} else {
url->m_paths[0] = buffer.to_string().release_value_but_fixme_should_propagate_errors();
url->m_paths[0] = buffer.to_string_without_validation();
buffer.clear();
}
}