diff options
author | Titus Wormer <tituswormer@gmail.com> | 2022-06-08 15:52:16 +0200 |
---|---|---|
committer | Titus Wormer <tituswormer@gmail.com> | 2022-06-08 15:52:16 +0200 |
commit | 4c06c8554c35887f8f5147783953b2b7e7c2327f (patch) | |
tree | 1b2463848a3ae4c645f7f1a325877ee829ab65c5 /src/construct/partial_whitespace.rs | |
download | markdown-rs-4c06c8554c35887f8f5147783953b2b7e7c2327f.tar.gz markdown-rs-4c06c8554c35887f8f5147783953b2b7e7c2327f.tar.bz2 markdown-rs-4c06c8554c35887f8f5147783953b2b7e7c2327f.zip |
.
Diffstat (limited to '')
-rw-r--r-- | src/construct/partial_whitespace.rs | 66 |
1 files changed, 66 insertions, 0 deletions
diff --git a/src/construct/partial_whitespace.rs b/src/construct/partial_whitespace.rs new file mode 100644 index 0000000..dd0d2b5 --- /dev/null +++ b/src/construct/partial_whitespace.rs @@ -0,0 +1,66 @@ +//! A little helper to parse `space_or_tab` +//! +//! They’re formed with the following BNF: +//! +//! ```bnf +//! space_or_tab ::= 1*(' ' '\t') +//! ``` +//! +//! Depending on where whitespace can occur, it can be optional (or not), +//! and present in the rendered result (or not). +//! +//! ## References +//! +//! * [`micromark-factory-space/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-space/dev/index.js) +//! +//! <!-- To do: link stuff --> + +use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer}; + +// To do: should `token_type` be a `Some`, with `None` defaulting to something? +// To do: should `max: Some(usize)` be added? + +/// Before whitespace. +/// +/// ```markdown +/// alpha| bravo +/// ``` +pub fn start(tokenizer: &mut Tokenizer, code: Code, token_type: TokenType) -> StateFnResult { + match code { + Code::VirtualSpace | Code::Char('\t' | ' ') => { + // To do: lifetimes. + let clone = token_type.clone(); + tokenizer.enter(token_type); + tokenizer.consume(code); + ( + State::Fn(Box::new(|tokenizer, code| inside(tokenizer, code, clone))), + None, + ) + } + _ => (State::Nok, None), + } +} + +/// In whitespace. +/// +/// ```markdown +/// alpha |bravo +/// alpha | bravo +/// ``` +fn inside(tokenizer: &mut Tokenizer, code: Code, token_type: TokenType) -> StateFnResult { + match code { + Code::VirtualSpace | Code::Char('\t' | ' ') => { + tokenizer.consume(code); + ( + State::Fn(Box::new(|tokenizer, code| { + inside(tokenizer, code, token_type) + })), + None, + ) + } + _ => { + tokenizer.exit(token_type); + (State::Ok, Some(vec![code])) + } + } +} |