aboutsummaryrefslogtreecommitdiffstats
path: root/src/construct/partial_space_or_tab.rs
diff options
context:
space:
mode:
authorLibravatar Titus Wormer <tituswormer@gmail.com>2022-07-28 16:48:00 +0200
committerLibravatar Titus Wormer <tituswormer@gmail.com>2022-07-28 16:48:00 +0200
commitf7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456 (patch)
treec1ac3f22473bd79566d835b2474d2ae9e00d6c55 /src/construct/partial_space_or_tab.rs
parentd729b07712ca9cc91e68af1776dac9d7008a90cb (diff)
downloadmarkdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.tar.gz
markdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.tar.bz2
markdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.zip
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.
Diffstat (limited to 'src/construct/partial_space_or_tab.rs')
-rw-r--r--src/construct/partial_space_or_tab.rs13
1 files changed, 5 insertions, 8 deletions
diff --git a/src/construct/partial_space_or_tab.rs b/src/construct/partial_space_or_tab.rs
index 5f1a917..6070ffe 100644
--- a/src/construct/partial_space_or_tab.rs
+++ b/src/construct/partial_space_or_tab.rs
@@ -6,7 +6,7 @@
use crate::subtokenize::link;
use crate::token::Token;
-use crate::tokenizer::{Code, ContentType, State, StateFn, Tokenizer};
+use crate::tokenizer::{ContentType, State, StateFn, Tokenizer};
/// Options to parse `space_or_tab`.
#[derive(Debug)]
@@ -134,7 +134,7 @@ pub fn space_or_tab_eol_with_options(options: EolOptions) -> Box<StateFn> {
/// ```
fn start(tokenizer: &mut Tokenizer, mut info: Info) -> State {
match tokenizer.current {
- Code::VirtualSpace | Code::Char('\t' | ' ') if info.options.max > 0 => {
+ Some('\t' | ' ') if info.options.max > 0 => {
tokenizer
.enter_with_content(info.options.kind.clone(), info.options.content_type.clone());
@@ -165,7 +165,7 @@ fn start(tokenizer: &mut Tokenizer, mut info: Info) -> State {
/// ```
fn inside(tokenizer: &mut Tokenizer, mut info: Info) -> State {
match tokenizer.current {
- Code::VirtualSpace | Code::Char('\t' | ' ') if info.size < info.options.max => {
+ Some('\t' | ' ') if info.size < info.options.max => {
tokenizer.consume();
info.size += 1;
State::Fn(Box::new(|t| inside(t, info)))
@@ -190,7 +190,7 @@ fn inside(tokenizer: &mut Tokenizer, mut info: Info) -> State {
/// ```
fn after_space_or_tab(tokenizer: &mut Tokenizer, mut info: EolInfo) -> State {
match tokenizer.current {
- Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
+ Some('\n') => {
tokenizer.enter_with_content(Token::LineEnding, info.options.content_type.clone());
if info.connect {
@@ -239,10 +239,7 @@ fn after_eol(tokenizer: &mut Tokenizer, info: EolInfo) -> State {
/// ```
fn after_more_space_or_tab(tokenizer: &mut Tokenizer) -> State {
// Blank line not allowed.
- if matches!(
- tokenizer.current,
- Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r')
- ) {
+ if matches!(tokenizer.current, None | Some('\n')) {
State::Nok
} else {
State::Ok