fergalmoran/ladybird
1
0
Fork 0
mirror of https://github.com/fergalmoran/ladybird.git synced 2025-12-25 10:48:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

LibWeb: Fix utf16-be check in HTMLEncodingDetection

Browse Source 
The utf-16be check mistakenly skipped index 3, so was not checking the
correct bytes. This meant UTF16-BE files could fail to decode.
This commit is contained in:
MacDue
2024-01-05 00:49:08 +00:00
committed by Andreas Kling
parent 5e973fca0b
commit fc41c282ec
3 changed files with 24 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Userland/Libraries/LibWeb/HTML/Parser/HTMLEncodingDetection.cpp
View File

@@ -251,10 +251,12 @@ Optional<ByteString> run_prescan_byte_stream_algorithm(DOM::Document& document,
// https://html.spec.whatwg.org/multipage/parsing.html#prescan-a-byte-stream-to-determine-its-encoding
// Detects '<?x'
if (!prescan_should_abort(input, 6)) {
if (!prescan_should_abort(input, 5)) {
// A sequence of bytes starting with: 0x3C, 0x0, 0x3F, 0x0, 0x78, 0x0
if (input[0] == 0x3C && input[1] == 0x00 && input[2] == 0x3F && input[3] == 0x00 && input[4] == 0x78 && input[5] == 0x00)
return "utf-16le";
if (input[0] == 0x00 && input[1] == 0x3C && input[2] == 0x00 && input[4] == 0x3F && input[5] == 0x00 && input[6] == 0x78)
// A sequence of bytes starting with: 0x0, 0x3C, 0x0, 0x3F, 0x0, 0x78
if (input[0] == 0x00 && input[1] == 0x3C && input[2] == 0x00 && input[3] == 0x3F && input[4] == 0x00 && input[5] == 0x78)
return "utf-16be";
}