eliott/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird synced 2026-04-26 01:35:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

LibURL: Percent decode over byte sequence

Browse Source 
Instead of going over UTF-8 code points. This better follows the spec,
and is also more performant.
This commit is contained in:
Shannon Booth
2024-12-01 21:37:29 +13:00
committed by Alexander Kalenik
parent fd25fea3ab
commit 0b4670fb7c
Notes: github-actions[bot] 2024-12-05 16:31:03 +00:00 
Author: https://github.com/shannonbooth
Commit: https://github.com/LadybirdBrowser/ladybird/commit/0b4670fb7cb
Pull-request: https://github.com/LadybirdBrowser/ladybird/pull/2675
1 changed files with 25 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
Libraries/LibURL/URL.cpp
View File

@@ -475,23 +475,36 @@ String percent_encode(StringView input, PercentEncodeSet set, SpaceAsPlus space_
return MUST(builder.to_string());
}
// https://url.spec.whatwg.org/#percent-decode
ByteString percent_decode(StringView input)
{
if (!input.contains('%'))
return input;
// 1. Let output be an empty byte sequence.
StringBuilder builder;
Utf8View utf8_view(input);
for (auto it = utf8_view.begin(); !it.done(); ++it) {
if (*it != '%') {
builder.append_code_point(*it);
} else if (!is_ascii_hex_digit(it.peek(1).value_or(0)) || !is_ascii_hex_digit(it.peek(2).value_or(0))) {
builder.append_code_point(*it);
} else {
++it;
u8 byte = parse_ascii_hex_digit(*it) << 4;
++it;
byte += parse_ascii_hex_digit(*it);
builder.append(byte);
// 2. For each byte byte in input:
for (size_t i = 0; i < input.length(); ++i) {
// 1. If byte is not 0x25 (%), then append byte to output.
if (input[i] != '%') {
builder.append(input[i]);
}
// 2. Otherwise, if byte is 0x25 (%) and the next two bytes after byte in input are not in the ranges 0x30 (0)
// to 0x39 (9), 0x41 (A) to 0x46 (F), and 0x61 (a) to 0x66 (f), all inclusive, append byte to output.
else if (i + 2 >= input.length() || !is_ascii_hex_digit(input[i + 1]) || !is_ascii_hex_digit(input[i + 2])) {
builder.append(input[i]);
}
// 3. Otherwise:
else {
// 1. Let bytePoint be the two bytes after byte in input, decoded, and then interpreted as hexadecimal number.
u8 byte_point = (parse_ascii_hex_digit(input[i + 1]) << 4) | parse_ascii_hex_digit(input[i + 2]);
// 2. Append a byte whose value is bytePoint to output.
builder.append(byte_point);
// 3. Skip the next two bytes in input.
i += 2;
}
}
return builder.to_byte_string();