diff options
Diffstat (limited to 'src/construct/blank_line.rs')
-rw-r--r-- | src/construct/blank_line.rs | 61 |
1 files changed, 61 insertions, 0 deletions
diff --git a/src/construct/blank_line.rs b/src/construct/blank_line.rs new file mode 100644 index 0000000..7b7962b --- /dev/null +++ b/src/construct/blank_line.rs @@ -0,0 +1,61 @@ +//! Blank lines are a construct that occurs in the flow content type. +//! +//! They’re formed with the following BNF: +//! +//! ```bnf +//! blank_line ::= *(' ' '\t') +//! ``` +//! +//! Blank lines are sometimes needed, such as to differentiate a paragraph +//! from another paragraph. +//! In several cases, blank lines are not needed between flow constructs, +//! such as between two headings. +//! Sometimes, whether blank lines are present, changes the behavior of how +//! HTML is rendered, such as whether blank lines are present between list +//! items in a list. +//! More than one blank line is never needed in `CommonMark`. +//! +//! Because blank lines can be empty (line endings are not considered part of +//! it), and events cannot be empty, blank lines are not present as a token. +//! +//! ## References +//! +//! * [`blank-line.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/blank-line.js) +//! * [*§ 4.9 Blank lines* in `CommonMark`](https://spec.commonmark.org/0.30/#blank-lines) +//! +//! <!-- To do: link `flow`, `heading`, `list`, `paragraph` --> + +use crate::construct::partial_whitespace::start as whitespace; +use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer}; + +/// Start of a blank line. +/// +/// Note: `␠` represents a space character. +/// +/// ```markdown +/// |␠␠ +/// | +/// ``` +pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult { + tokenizer.attempt( + |tokenizer, code| whitespace(tokenizer, code, TokenType::BlankLineWhitespace), + |_ok| Box::new(after), + )(tokenizer, code) +} + +/// After zero or more spaces or tabs, before a line ending or EOF. +/// +/// Note: `␠` represents a space character. +/// +/// ```markdown +/// |␠␠ +/// | +/// ``` +fn after(_tokenizer: &mut Tokenizer, code: Code) -> StateFnResult { + match code { + Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => { + (State::Ok, Some(vec![code])) + } + _ => (State::Nok, None), + } +} |