From f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456 Mon Sep 17 00:00:00 2001 From: Titus Wormer Date: Thu, 28 Jul 2022 16:48:00 +0200 Subject: Refactor to work on `char`s MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously, a custom char implementation was used. This was easier to work with, as sometimes “virtual” characters are injected, or characters are ignored. This replaces that with working on actual `char`s. In the hope of in the future working on `u8`s, even. This simplifies the state machine somewhat, as only `\n` is fed, regardless of whether it was a CRLF, CR, or LF. It also feeds `' '` instead of virtual spaces. The BOM, if present, is now available as a `ByteOrderMark` event. --- src/construct/partial_non_lazy_continuation.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/construct/partial_non_lazy_continuation.rs') diff --git a/src/construct/partial_non_lazy_continuation.rs b/src/construct/partial_non_lazy_continuation.rs index bdc22e4..068e30f 100644 --- a/src/construct/partial_non_lazy_continuation.rs +++ b/src/construct/partial_non_lazy_continuation.rs @@ -11,7 +11,7 @@ //! [html_flow]: crate::construct::html_flow use crate::token::Token; -use crate::tokenizer::{Code, State, Tokenizer}; +use crate::tokenizer::{State, Tokenizer}; /// Start of continuation. /// @@ -22,7 +22,7 @@ use crate::tokenizer::{Code, State, Tokenizer}; /// ``` pub fn start(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => { + Some('\n') => { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); -- cgit