Last active
November 29, 2023 02:21
-
-
Save emwalker/572811acb8ab1e5d5cb9a8219233bf2b to your computer and use it in GitHub Desktop.
Nom parser for CSS3 tokens
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use super::{ast::Node, new_tokenizer::Token}; | |
use nom::{ | |
branch::alt, bytes::complete::tag, combinator::map, sequence::tuple, Compare, IResult, | |
InputIter, InputLength, InputTake, | |
}; | |
impl InputLength for Token { | |
fn input_len(&self) -> usize { | |
1 | |
} | |
} | |
#[derive(Clone, Debug)] | |
struct Span<'t>(&'t [Token]); | |
impl InputTake for Span<'_> { | |
fn take(&self, count: usize) -> Self { | |
todo!() | |
} | |
fn take_split(&self, count: usize) -> (Self, Self) { | |
todo!() | |
} | |
} | |
impl Compare<Token> for Span<'_> { | |
fn compare(&self, t: Token) -> nom::CompareResult { | |
todo!() | |
} | |
fn compare_no_case(&self, t: Token) -> nom::CompareResult { | |
todo!() | |
} | |
} | |
impl InputLength for Span<'_> { | |
fn input_len(&self) -> usize { | |
self.0.len() | |
} | |
} | |
struct SpanIter; | |
impl Iterator for SpanIter { | |
type Item = (usize, Token); | |
fn next(&mut self) -> Option<Self::Item> { | |
todo!() | |
} | |
} | |
struct TokenIter; | |
impl Iterator for TokenIter { | |
type Item = Token; | |
fn next(&mut self) -> Option<Self::Item> { | |
todo!() | |
} | |
} | |
impl InputIter for Span<'_> { | |
type Item = Token; | |
type Iter = SpanIter; | |
type IterElem = TokenIter; | |
fn iter_indices(&self) -> Self::Iter { | |
todo!() | |
} | |
fn iter_elements(&self) -> Self::IterElem { | |
todo!() | |
} | |
fn position<P>(&self, predicate: P) -> Option<usize> | |
where | |
P: Fn(Self::Item) -> bool, | |
{ | |
todo!() | |
} | |
fn slice_index(&self, count: usize) -> Result<usize, nom::Needed> { | |
todo!() | |
} | |
} | |
fn ident(i: Span) -> IResult<Span, Node> { | |
todo!() | |
} | |
fn child_combinator(i: Span) -> IResult<Span, Node> { | |
map( | |
tuple((ident, tag(Token::Delim('>')), ident)), | |
|(a, _, b)| Node { | |
name: "ChildCombinator".into(), | |
children: vec![a, b], | |
..Default::default() | |
}, | |
)(i) | |
} | |
fn adjecent_sibling_combinator(i: Span) -> IResult<Span, Node> { | |
todo!() | |
} | |
fn general_sibling_combinator(i: Span) -> IResult<Span, Node> { | |
todo!() | |
} | |
fn column_combinator(i: Span) -> IResult<Span, Node> { | |
todo!() | |
} | |
fn parse_combinator(i: Span) -> IResult<Span, Node> { | |
alt(( | |
child_combinator, | |
adjecent_sibling_combinator, | |
general_sibling_combinator, | |
column_combinator, | |
))(i) | |
} | |
#[cfg(test)] | |
mod tests { | |
use super::*; | |
use crate::{ | |
bytes::{CharIterator, Encoding}, | |
css3::new_tokenizer::{TokenStreamer, Tokenizer}, | |
}; | |
fn input(s: &str) -> Vec<Token> { | |
let mut iter = CharIterator::new(); | |
iter.read_from_str(s, Some(Encoding::UTF8)); | |
let mut tokenizer = Tokenizer::new(&mut iter); | |
let mut res = vec![]; | |
while tokenizer.current() != Token::Eof { | |
res.push(tokenizer.consume()); | |
} | |
res | |
} | |
#[test] | |
fn good() { | |
let input = input("a > b"); | |
let span = Span(&input); | |
let (_, node) = parse_combinator(span).unwrap(); | |
assert_eq!(node.name, "ChildCombinator"); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment