From ee8ab781672e7ab608e74a5b605eb189828f0afe Mon Sep 17 00:00:00 2001
From: Martin Fischer <martin@push-f.com>
Date: Tue, 26 Sep 2023 08:22:21 +0200
Subject: fix(tokenizer): don't lowercase temp chars in ScriptDataEndTagName
This bug resulted in e.g. "<script></SCRI" being wrongly tokenized as:
StartTag(StartTag { name: "script", self_closing: false, attributes: {} })
Char('<')
Char('/')
Char('s')
Char('c')
Char('r')
Char('i')
EndOfFile
Note that the Char tokens should be uppercase. (This bug could only be
observed when properly doing state switching via tree construction.)
---
src/tokenizer/machine.rs | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'src/tokenizer')
diff --git a/src/tokenizer/machine.rs b/src/tokenizer/machine.rs
index 944eb01..100f645 100644
--- a/src/tokenizer/machine.rs
+++ b/src/tokenizer/machine.rs
@@ -428,7 +428,7 @@ where
}
Some(x) if x.is_ascii_alphabetic() => {
slf.push_tag_name(ctostr!(x.to_ascii_lowercase()));
- slf.temporary_buffer.push(x.to_ascii_lowercase());
+ slf.temporary_buffer.push(x);
Ok(ControlToken::Continue)
}
c => {
--
cgit v1.2.3