0ct0pu5/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-12-03 04:50:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

AK: Report validation error for URLs with invalid percent encodings

Browse source 
This part of the spec is mostly useful for our debugging for now, but
could eventually be hooked up so that the user can see any reported
validation errors.
This commit is contained in:
Shannon Booth 2023-08-13 11:17:02 +12:00 committed by Andrew Kaster
parent f53dfdd6ac
commit e233de1e48
Notes: sideshowbarker 2024-07-16 23:55:09 +09:00 
Author: https://github.com/shannonbooth
Commit: https://github.com/SerenityOS/serenity/commit/e233de1e48
Pull-request: https://github.com/SerenityOS/serenity/pull/20567
Reviewed-by: https://github.com/ADKaster
1 changed files with 16 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
AK/URLParser.cpp
View file

@ -786,6 +786,10 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
return input.substring_view(iterator - input.begin() + iterator.underlying_code_point_length_in_bytes()).as_string();
};
auto remaining_starts_with_two_ascii_hex_digits = [&]() {
return is_ascii_hex_digit(iterator.peek(1).value_or(end_of_file)) && is_ascii_hex_digit(iterator.peek(2).value_or(end_of_file));
};
// 9. Keep running the following state machine by switching on state. If after a run pointer points to the EOF code point, go to the next step. Otherwise, increase pointer by 1 and continue with the state machine.
// NOTE: "continue" should only be used to prevent incrementing the iterator, as this is done at the end of the loop.
// ++iterator : "increase pointer by 1"
@ -1528,7 +1532,9 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
if (!is_url_code_point(code_point) && code_point != '%')
report_validation_error();
// FIXME: 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
// 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
if (code_point == '%' && !remaining_starts_with_two_ascii_hex_digits())
report_validation_error();
// 3. UTF-8 percent-encode c using the path percent-encode set and append the result to buffer.
URL::append_percent_encoded_if_necessary(buffer, code_point, URL::PercentEncodeSet::Path);
@ -1560,7 +1566,9 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
if (code_point != end_of_file && !is_url_code_point(code_point) && code_point != '%')
report_validation_error();
// FIXME: 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
// 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
if (code_point == '%' && !remaining_starts_with_two_ascii_hex_digits())
report_validation_error();
// 3. If c is not the EOF code point, UTF-8 percent-encode c using the C0 control percent-encode set and append the result to url’s path.
if (code_point != end_of_file) {
@ -1606,7 +1614,9 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
if (!is_url_code_point(code_point) && code_point != '%')
report_validation_error();
// FIXME: 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
// 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
if (code_point == '%' && !remaining_starts_with_two_ascii_hex_digits())
report_validation_error();
// 3. Append c to buffer.
buffer.append_code_point(code_point);
@ -1621,7 +1631,9 @@ URL URLParser::basic_parse(StringView raw_input, Optional<URL> const& base_url,
if (!is_url_code_point(code_point) && code_point != '%')
report_validation_error();
// FIXME: 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
// 2. If c is U+0025 (%) and remaining does not start with two ASCII hex digits, validation error.
if (code_point == '%' && !remaining_starts_with_two_ascii_hex_digits())
report_validation_error();
// FIXME: 3. UTF-8 percent-encode c using the fragment percent-encode set and append the result to url’s fragment.
buffer.append_code_point(code_point);