path: root/src/construct/hard_break_escape.rs

//! Hard break (escape) is a construct that occurs in the  [text][] content
//! type.
//!
//! They’re formed with the following BNF:
//!
//! ```bnf
//! ; Restriction: followed by a line ending  (that is part of the construct
//! ; instead of ending it).
//! hard_break_escape ::= '\\'
//! ```
//!
//! Hard breaks in markdown relate to the HTML element `<br>`.
//! See [*§ 4.5.27 The `br` element* in the HTML spec][html] for more info.
//!
//! It is also possible to create a hard break with a
//! [hard break (trailing)][hard_break_trailing].
//! That construct is not recommended because trailing spaces are typically
//! invisible in editors, or even automatically removed, making them hard to
//! use.
//!
//! It is also possible to escape punctuation characters with a similar
//! construct: a [character escape][character_escape] is a backslash followed
//! by an ASCII punctuation character.
//! Arbitrary characters can be escaped with
//! [character reference][character_reference]s.
//!
//! ## Tokens
//!
//! *   [`HardBreakEscape`][Name::HardBreakEscape]
//!
//! ## References
//!
//! *   [`hard-break-escape.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/hard-break-escape.js)
//! *   [*§ 6.7 Hard line breaks* in `CommonMark`](https://spec.commonmark.org/0.30/#hard-line-breaks)
//!
//! [text]: crate::construct::text
//! [character_escape]: crate::construct::character_escape
//! [character_reference]: crate::construct::character_reference
//! [hard_break_trailing]: crate::construct::partial_whitespace
//! [html]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-br-element

use crate::event::Name;
use crate::state::{Name as StateName, State};
use crate::tokenizer::Tokenizer;

/// Start of hard break (escape).
///
/// ```markdown
/// > | a\
///      ^
///   | b
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
    if tokenizer.parse_state.constructs.hard_break_escape && tokenizer.current == Some(b'\\') {
        tokenizer.enter(Name::HardBreakEscape);
        tokenizer.consume();
        State::Next(StateName::HardBreakEscapeAfter)
    } else {
        State::Nok
    }
}

/// After `\`, at eol.
///
/// ```markdown
/// > | a\
///       ^
///   | b
/// ```
pub fn after(tokenizer: &mut Tokenizer) -> State {
    match tokenizer.current {
        Some(b'\n') => {
            tokenizer.exit(Name::HardBreakEscape);
            State::Ok
        }
        _ => State::Nok,
    }
}