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/definition.rs | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'src/construct/definition.rs') diff --git a/src/construct/definition.rs b/src/construct/definition.rs index ffaaa98..f2b5ae0 100644 --- a/src/construct/definition.rs +++ b/src/construct/definition.rs @@ -100,7 +100,7 @@ use crate::construct::{ partial_title::{start as title, Options as TitleOptions}, }; use crate::token::Token; -use crate::tokenizer::{Code, State, Tokenizer}; +use crate::tokenizer::{State, Tokenizer}; use crate::util::skip::opt_back as skip_opt_back; /// At the start of a definition. @@ -137,7 +137,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { /// ``` fn before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Code::Char('[') => tokenizer.go( + Some('[') => tokenizer.go( |t| { label( t, @@ -162,7 +162,7 @@ fn before(tokenizer: &mut Tokenizer) -> State { /// ``` fn label_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Code::Char(':') => { + Some(':') => { tokenizer.enter(Token::DefinitionMarker); tokenizer.consume(); tokenizer.exit(Token::DefinitionMarker); @@ -231,7 +231,7 @@ fn after(tokenizer: &mut Tokenizer) -> State { /// ``` fn after_whitespace(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => { + None | Some('\n') => { tokenizer.exit(Token::Definition); // You’d be interrupting. tokenizer.interrupt = true; @@ -294,7 +294,7 @@ fn title_after(tokenizer: &mut Tokenizer) -> State { /// ``` fn title_after_after_optional_whitespace(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => State::Ok, + None | Some('\n') => State::Ok, _ => State::Nok, } } -- cgit