//! Thematic breaks, sometimes called horizontal rules, are a construct that
//! occurs in the [flow][] content type.
//!
//! They’re formed with the following BNF:
//!
//! ```bnf
//! ; Restriction: all markers must be identical.
//! ; Restriction: at least 3 markers must be used.
//! thematic_break ::= *space_or_tab 1*(1*marker *space_or_tab)
//!
//! space_or_tab ::= ' ' | '\t'
//! marker ::= '*' | '-' | '_'
//! ```
//!
//! Thematic breaks in markdown typically relate to the HTML element `
`.
//! See [*§ 4.4.2 The `hr` element* in the HTML spec][html] for more info.
//!
//! It is recommended to use exactly three asterisks without whitespace when
//! writing markdown.
//! As using more than three markers has no effect other than wasting space,
//! it is recommended to use exactly three markers.
//! Thematic breaks formed with asterisks or dashes can interfere with
//! [list][]s if there is whitespace between them: `* * *` and `- - -`.
//! For these reasons, it is recommend to not use spaces or tabs between the
//! markers.
//! Thematic breaks formed with dashes (without whitespace) can also form
//! [heading (setext)][heading_setext].
//! As dashes and underscores frequently occur in natural language and URLs, it
//! is recommended to use asterisks for thematic breaks to distinguish from
//! such use.
//! Because asterisks can be used to form the most markdown constructs, using
//! them has the added benefit of making it easier to gloss over markdown: you
//! can look for asterisks to find syntax while not worrying about other
//! characters.
//!
//! ## Tokens
//!
//! * [`ThematicBreak`][Name::ThematicBreak]
//! * [`ThematicBreakSequence`][Name::ThematicBreakSequence]
//!
//! ## References
//!
//! * [`thematic-break.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/thematic-break.js)
//! * [*§ 4.1 Thematic breaks* in `CommonMark`](https://spec.commonmark.org/0.30/#thematic-breaks)
//!
//! [flow]: crate::content::flow
//! [heading_setext]: crate::construct::heading_setext
//! [list]: crate::construct::list
//! [html]: https://html.spec.whatwg.org/multipage/grouping-content.html#the-hr-element
use super::partial_space_or_tab::{space_or_tab, space_or_tab_min_max};
use crate::constant::{TAB_SIZE, THEMATIC_BREAK_MARKER_COUNT_MIN};
use crate::event::Name;
use crate::state::{Name as StateName, State};
use crate::tokenizer::Tokenizer;
/// Start of thematic break.
///
/// ```markdown
/// > | ***
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
if tokenizer.parse_state.constructs.thematic_break {
tokenizer.enter(Name::ThematicBreak);
tokenizer.attempt(State::Next(StateName::ThematicBreakBefore), State::Nok);
State::Retry(space_or_tab_min_max(
tokenizer,
0,
if tokenizer.parse_state.constructs.code_indented {
TAB_SIZE - 1
} else {
usize::MAX
},
))
} else {
State::Nok
}
}
/// After optional whitespace, at marker.
///
/// ```markdown
/// > | ***
/// ^
/// ```
pub fn before(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'*' | b'-' | b'_') => {
tokenizer.tokenize_state.marker = tokenizer.current.unwrap();
State::Retry(StateName::ThematicBreakAtBreak)
}
_ => State::Nok,
}
}
/// After something, before something else.
///
/// ```markdown
/// > | ***
/// ^
/// ```
pub fn at_break(tokenizer: &mut Tokenizer) -> State {
if tokenizer.current == Some(tokenizer.tokenize_state.marker) {
tokenizer.enter(Name::ThematicBreakSequence);
State::Retry(StateName::ThematicBreakSequence)
} else if tokenizer.tokenize_state.size >= THEMATIC_BREAK_MARKER_COUNT_MIN
&& matches!(tokenizer.current, None | Some(b'\n'))
{
tokenizer.tokenize_state.marker = 0;
tokenizer.tokenize_state.size = 0;
tokenizer.exit(Name::ThematicBreak);
// Feel free to interrupt.
tokenizer.interrupt = false;
State::Ok
} else {
tokenizer.tokenize_state.marker = 0;
tokenizer.tokenize_state.size = 0;
State::Nok
}
}
/// In sequence.
///
/// ```markdown
/// > | ***
/// ^
/// ```
pub fn sequence(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'*' | b'-' | b'_')
if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker =>
{
tokenizer.consume();
tokenizer.tokenize_state.size += 1;
State::Next(StateName::ThematicBreakSequence)
}
_ => {
tokenizer.exit(Name::ThematicBreakSequence);
tokenizer.attempt(
State::Next(StateName::ThematicBreakAtBreak),
State::Next(StateName::ThematicBreakAtBreak),
);
State::Retry(space_or_tab(tokenizer))
}
}
}