Refactor to work on `char`s

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.

1 files changed, 3 insertions, 3 deletions

diff --git a/src/content/string.rs b/src/content/string.rs
index c6c0094..8bc2b91 100644
--- a/src/content/string.rs
+++ b/src/content/string.rs
@@ -16,9 +16,9 @@ use crate::construct::{
     character_escape::start as character_escape, character_reference::start as character_reference,
     partial_data::start as data, partial_whitespace::create_resolve_whitespace,
 };
-use crate::tokenizer::{Code, State, Tokenizer};
+use crate::tokenizer::{State, Tokenizer};
 
-const MARKERS: [Code; 2] = [Code::Char('&'), Code::Char('\\')];
+const MARKERS: [char; 2] = ['&', '\\'];
 
 /// Start of string.
 pub fn start(tokenizer: &mut Tokenizer) -> State {
@@ -32,7 +32,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State {
 /// Before string.
 fn before(tokenizer: &mut Tokenizer) -> State {
     match tokenizer.current {
-        Code::None => State::Ok,
+        None => State::Ok,
         _ => tokenizer.attempt_n(
             vec![Box::new(character_reference), Box::new(character_escape)],
             |ok| Box::new(if ok { before } else { before_data }),